Electrical Engineering & Computer Science Project Postings

Improving and assessing the CiteFair tool to foster citation diversity in the reference lists of papers published in computing venues 

Professor: Alvine Boaye Belle 
Contact Info: alvine.belle@lassonde.yorku.ca 
Lab Website: https://lassonde.yorku.ca/users/alvinebelle 
Position Type: Lassonde Undergraduate Research Award (LURA); NSERC Undergraduate Student Research Award (USRA) 
Open Positions: 2 
Project Description: The number of citations of scientific articles has a huge impact on recommendations for funding allocations, recruitment decisions, promotion decisions and awards, just to name a few. Recent studies conducted in different scientific disciplines (e.g., physics and neuroscience) have concluded that researchers belonging to some socio-cultural groups (e.g., women, Black, Hispanic) are usually less cited than other researchers belonging to dominating groups. This is usually due to the presence of citation biases in reference lists. These citation biases towards researchers from some socio-cultural groups may inevitably cause unfairness and inaccuracy in the assessment of articles impact. These citation biases may therefore translate to significant disparities in salaries, promotion, retention, grant funding, awards, collaborative opportunities, and publications. To tackle citation gaps, a new tool called CiteFair has been developed. CiteFair relies on Machine Learning techniques to increase the citation diversity in the reference list of each computing conference/journal manuscript it analyzes. CiteFair is meant to run on the cloud. CiteFair currently focuses on improving gendered citation practices. CiteFair still needs to be further developed to address additional socio-cultural groups among others. CiteFair also needs to be assessed. 
Duties and Responsibilities:  
1. Explore the literature on citation biases identification and mitigation in STEM fields 
2. Extend the features of the CiteFair tool by relying on various web-based technologies 
3. Help run experiments to assess the CiteFair tool 
4. Help write a scientific paper focusing on CiteFair description and assessment. 
Desired Technical Skills:  
1. Good oral and written skills in English 
2. Good knowledge of web-based technologies (e.g., React JS, Spring, HTML, CSS, Ajax, JavaScript, Netlify, AWS)  
3. Familiarity with git (e.g., GitHub)  
4. Familiarity with Large Language Models. 
Desired Course(s):  
• The student should be enrolled in the fourth year of a computer science undergraduate program.  
• The student should have completed the EECS 4413 course (Building E-commerce systems course), or a similar course, or should have industrial experience (e.g., internship) on web-based development.  

XTune: Reliable and eXplainable Data Systems Tuning via Deep Learning 

Professor:  Jarek Szlichta  
Contact Info: szlichta@yorku.ca 
Lab Website: https://www.yorku.ca/lassonde/lab/data-and-ai/ 
Position Type: Lassonde Undergraduate Research Award (LURA); NSERC Undergraduate Student Research Award (USRA) 
Open Positions: 2 
Project Description:  Modern data systems, such as IBM Db2, have dozens of system configuration parameters, commonly referred to as knobs. These parameters wield significant influence over the performance of business queries. Knobs are responsible for configuring various aspects, including the allocation of working memory, such as the number of pages allocated to the buffer pool and sort heap, the degree of parallelism to be used, and even toggle specific features by setting an optimization level. 
Duties and Responsibilities:  Students’ duties and responsibilities will include: reviewing related work in automatic knobs tuning for data systems, designing large-scale machine learning-driven approaches to the tuning of configuration parameters, implementing the solution with the deep reinforcement learning model, conducting comprehensive experimental evaluation over synthetic and real-world query workloads, and writing a research paper to be submitted to one of the top-tier conferences in data science, such as VLDB, ACM SIGMOD, IEEE ICDE and EDBT. 
Desired Technical Skills:  The student should possess algorithmic design and development knowledge, as well as demonstrated strong programming skills. 
Desired Course(s):  It is recommended to have completed some of the data science courses such as LE/EECS 4415 3.00 – Big Data Systems, LE/EECS 4411 3.00 – Database Management Systems, LE/EECS 4412 3.00 – Data Mining, LE/EECS 4404 3.00 – Introduction to Machine Learning and Pattern Recognition, LE/EECS 3421 3.00 – Introduction to Database Systems, etc.  
Other Desired Qualifications:  Other qualifications include good communication skills. 

LLM fairness analysis 

Professor:  Laleh Seyyed-Kalantari  
Contact Info: lsk@yorku.ca 
Lab Website: https://responsibleai.eecs.yorku.ca/ 
Position Type: Lassonde Undergraduate Research Award (LURA); NSERC Undergraduate Student Research Award (USRA) 
Open Positions: 2 
Project Description:  Large Language Models (LLMs) are increasingly deployed for public use, particularly in developing conversational applications like chatbots. However, their limitations and risks, especially those related to bias, remain significantly under-explored. This paper presents a comprehensive evaluation of LLMs using twelve distinct evaluation metrics, introducing augmentations and improvements to these metrics for more accurate and meaningful assessments. We would like to evaluate recent and widely used LLMs such as Phi2, Phi3, Llama3, Llama3.1, Gemma, and Mistral. 
Duties and Responsibilities:  Training and finetuning LLMs, writing research paper. 
Desired Technical Skills:  Familiarity with transformer-based models, and former experience with training and fine-tuning small-size and medium-size language models. 
Desired Course(s):  Python, Pytorci, Deep leaning, transformers  
Other Desired Qualifications:  Any former experience with LLMs is an asset. knowledge on fairness metrics and AI fairness is asset. 

Human Computer Interaction in Virtual Reality 

Professor:  Robert Allison  
Contact Info: rallison@yorku.ca 
Position Type: Lassonde Undergraduate Research Award (LURA); NSERC Undergraduate Student Research Award (USRA) 
Open Positions: 2 
Project Description:  Students will help design, develop and conduct experiments related to human-computer interaction in virtual environments and digital media. In our lab we have a wide range of apparatus to study human perception in computer-mediated worlds including a new and unique fully immersive virtual environment display. The student would develop interactive 3D virtual worlds and conduct experiments to study self-motion perception, visual perception and human computer interaction in these virtual worlds. In particular, working with a senior graduate student or postdoctoral fellow, the successful applicant would model 3D environments, render them in a virtual reality or other digital media display, develop/implement interaction methods to control and interact with the simulation, and/or develop and run experimental scenarios to investigate these issues with human participants. 
Duties and Responsibilities:  
Depending on skills and preparation the student would be responsible for:  
• Literature reviews and research  
• Design of virtual environments  
• Computer programming  
• Testing  
• Recruiting participants  
• Conducting user studies  
• Modeling and Data analysis  
• Preparation of reports, graphics and presentations  
Desired Technical Skills:  Good programming skills, previous work with computer graphics or virtual reality would be helpful, as would basic mechanical skills. Students with background in Psychology and interest in Experimental Psychology are also welcome to apply. Artistic background or skill would be an asset but is not required. 
Desired Course(s):  Digital Media, Electrical Engineering, Computer Engineering, Computer Science, Psychology, or Vision Science  
Other Desired Qualifications:  Students should be self-directed and work well in a team environment. 

LLM4SE (Large Language Models for Software Engineering) 

Professor:  Zhen Ming (Jack) Jiang  
Contact Info: zmjiang@yorku.ca 
Lab Website: https://www.cse.yorku.ca/~zmjiang/ 
Position Type: Lassonde Undergraduate Research Award (LURA); NSERC Undergraduate Student Research Award (USRA) 
Open Positions: 2 
Project Description:  Software engineering data (e.g., source code repositories and bug databases) contain a wealth of information about a project’s status and history. With the recent advances of large language models (e.g., GPT and BERT) as well as their applications (e.g., ChatGPT or GitHub Copilot), many software engineering tasks can be automated or optimized. In this project, the student(s) will explore and investigate various software engineering applications which can benefit from the use of LLMs. 
Duties and Responsibilities:  The student will be directly supervised by the professor. There will also be one graduate student as a mentor to manage the student in a day-to-day basis. We will work together to design the experiments, analyze the data, and articulate the findings. The goal for the student is to submit one technical paper at the end of their internship based on their research work done in the summer around this topic. 
Desired Technical Skills:  Proficient in Python and Java-based programming. 
Desired Course(s): 
– Major in Computer Science/Software Engineering/Computer Engineering 
– Third year and up 
– At least B+ for EECS 3311  

FMOps 

Professor:  Zhen Ming (Jack) Jiang  
Contact Info: zmjiang@yorku.ca 
Lab Website: https://www.cse.yorku.ca/~zmjiang/ 
Position Type: Lassonde Undergraduate Research Award (LURA); NSERC Undergraduate Student Research Award (USRA) 
Open Positions: 1 
Project Description:  Artificial Intelligence is gaining rapid popularity in both research and practice, due to the recent advances in machine learning (ML) research and development. Many ML applications (e.g., Tesla’s autonomous vehicle and Apple’s Siri) are already being used widely in people’s everyday lives. McKinsey recently estimated that ML applications have the potential to create between $3.5 and $5.8 trillion in value annually. Foundation models are large AI models trained on a vast quantity of data at scale. FMs can be used to power a wide range of downstream tasks (e.g., chat bots, code assistants, tutors, etc.). However, there remain many challenges in efficiently training, deploying and monitoring such FM infrastructure. In addition, there is a lack of tools and processes to further develop applications or services on top of such FMs. The goal of this project is to develop engineering tools and best practices to support effectively operationalizing FMs. 
Duties and Responsibilities:  The student will be directly supervised by the professor. There will also be one graduate student as a mentor to manage the student in a day-to-day basis. We will work together to design the experiments, analyze the data, and articulate the findings. The goal for the student is to submit one technical paper at the end of their internship based on their research work done in the summer around this topic. 
Desired Technical Skills:  Proficient in Python and Java-based programming. 
Desired Course(s): 
– Major in Computer Science/Software Engineering/Computer Engineering 
– Third year and up 
– At least B+ for EECS 3311 

Privacy Analysis of Large Language Models (LLM) 

Professor:  Yan Shvartzshnaider  
Contact Info: rhythm.lab@yorku.ca 
Lab Website: https://www.yorku.ca/lassonde/privacy/ 
Position Type: Lassonde Undergraduate Research Award (LURA); NSERC Undergraduate Student Research Award (USRA) 
Open Positions: 2 
Project Description:  The rapid shift toward digital platforms has introduced new privacy and security challenges across various sectors, including workplaces, healthcare, and education. These technologies collect and share vast amounts of data about users and their environments. However, our collective understanding of privacy expectations often lags the rapid advancements in technology and information-handling practices. Researchers worldwide are working to develop new methods to systematically analyze the ethical and privacy implications of these tools, aiming to prevent potential societal harm. 
These issues are particularly pressing with the emergence of Large Language Models (LLMs), which require training on enormous datasets, raising significant concerns about data privacy. 
To address this, the project will explore the ability of LLMs to adhere to context-specific privacy norms, using the theory of Contextual Integrity. 
Duties and Responsibilities:   
Students will assist in analyzing various LLM models. 
Specific tasks include: 
1) conducting a comprehensive literature review of existing privacy-related LLM methodologies  
2) investigating the model’s properties, such as capacity, alignment, few-shot prompting, and chain-of-thought prompting, with a focus on aligning these models with privacy norms and expectations; 
3) contributing to the development of a framework aimed at improving LLM alignment by fine-tuning the models to better align with existing policies and expectations. 
See this paper for reference: https://arxiv.org/abs/2409.03735. 
Desired Technical Skills:  
* Proven programming and data analysis skills 
* Experience working with ML and LLM models. 
Desired Course(s):  Course on ML and LLM, Data analysis.  
Other Desired Qualifications:   
*   Experience with data analysis using Jupyter and/or R 
*  Interest in usable privacy, critical analysis of systems, and of privacy-related regulations 
*   Ability to work independently 

Privacy in Sociotechnical Systems 

Professor:  Yan Shvartzshnaider  
Contact Info: rhythm.lab@yorku.ca 
Lab Website: https://www.yorku.ca/lassonde/privacy/ 
Position Type: Lassonde Undergraduate Research Award (LURA); NSERC Undergraduate Student Research Award (USRA) 
Open Positions: 2 
Project Description:  Modern sociotechnical systems share and collect vast amounts of information. These systems violate users’ privacy by ignoring the context in which the information is shared and by implementing privacy models that fail to incorporate contextual information norms. Using techniques in natural language processing, machine learning, network, and data analysis, this project is set to explore the privacy implications of mobile apps, online platforms, and other systems in different social contexts/settings. 
To tackle this challenge, the project will operationalize a cutting-edge privacy theory and methodologies to conduct an analysis of existing technologies and design privacy-enhancing tools used in the educational context. 
Duties and Responsibilities:  Students will develop privacy-enhancing mechanisms that ensure that information flows in accordance with users’ expectations and established societal norms and design. Specific tasks include: comprehensive literature review of existing methodologies and tools, analysis of privacy policies and regulations, visualization of information collection practices, and design of a web-based interface for analyzing extracted privacy statements to identify vague, misleading, or incomplete privacy statements. 
Desired Technical Skills:  Experience with machine learning, natural language processing techniques, Good programming skills overall, and experience in using Jupyter and/or R for data analysis. 
Desired Course(s):  Software engineering, computer science, and information science students. Note: students with diverse backgrounds, including in technical fields, social sciences and humanities are encouraged to apply.  
Other Desired Qualifications:  HCI design and web development. interest in usable privacy, critical analysis of privacy policies and privacy related regulation. 

A model-driven software development platform for Climate-Sensitive Infectious Disease Modelling 

Professor:  Marios Fokaefs  
Contact Info: fokaefs@yorku.ca 
Lab Website: https://fokaefs.github.io/research/projects.html 
Position Type: Lassonde Undergraduate Research Award (LURA); NSERC Undergraduate Student Research Award (USRA) 
Open Positions: 1 
Project Description:  The COVID-19 pandemic demonstrated the value of epidemiological models in battling against the disease. However, modelling is not a trivial task. It requires time, effort, and continuous maintenance to address the evolution of the disease and of the countermeasures. On one hand, this requires a systematic and robust development process to ensure the effectiveness and the quality of the produced models. On the other hand, it also implies the need for a change management process that will handle the maintenance and the evolution of the models. Furthermore, infectious diseases have to be studied in conjunction with other affecting parameters, include climate and sociodemographics. Therefore, modellers need to be able to consider multidimensional and hybrid models to better study the phenomenon. In this project, we propose the application of software engineering and model-driven engineering principles to aid the design, development, and simulation of climate-sensitive infectious disease models. More specifically, we propose a integrated development platform that will support (a) the definition and design of models, (b) the simulation of scenarios based on these models, (c) the automatic validation and verification of models and code generation, (d) the control of model versions, and (e) the merging of models from different domains. 
Duties and Responsibilities:  The hired student will work towards the development of a prototype platform for developing climate and disease models. The student will develop the theoretical foundation as well as the implementation for such a platform and leverage principles of Software Engineering and Model-Driven Engineering. The student will aim to publish in top-tier journals, including IEEE/ACM Transactions on Computational Biology and Bioinformatics, IEEE Transaction on Big Data, IEEE Transactions on Knowledge and Data Engineering, IEEE Transactions on Software Engineering, IEEE Journal of Biomedical and Health Informatics, and conferences, such as MODELS, ICSE, and others. 
Desired Technical Skills:  The student will be asked to demonstrate adequate understanding or expertise in the following topics through relevant courses (on undergraduate or graduate level) or through relevant publications in international conferences or journals. The student should consider applying if they have the expert-level skills and at least 50% of the good-level skills.

Expert programming skills, preferably in Java.
Good knowledge on model-driven engineering and technologies such as EMF (Eclipse Modeling Framework), ecore and others similar.
Good knowledge on python.
Adequate knowledge on statistical methods and tests 
Desired Course(s):  EECS3311 Software Design.  
 

Exploring the applicability of Generative AI and LLM on Software Architecture 

Professor:  Marios Fokaefs  
Contact Info: fokaefs@yorku.ca 
Lab Website: https://fokaefs.github.io/research/projects.html 
Position Type: Lassonde Undergraduate Research Award (LURA); NSERC Undergraduate Student Research Award (USRA) 
Open Positions: 2 
Project Description:  Generative AI has attracted a lot of attention recently from the research community. Its ability to generate complex solution from similar examples has made it an interesting solution for problems that require a certain degree of creativity. Design processes that are necessary in software architecture require similarly creative solutions. In addition, the problem of translating natural text requirements into design and architecture artifacts is non-linear and in most cases unstructured. In this sense, design processes can also benefit from the use of large language models (LLM), known for their ability to understand and generate natural language. The objective of this project is to explore the ability of LLMs and generative AI to produce functional and performant software architectures given free-text requirement descriptions. The developed models will need to parse these descriptions, extract functional and non-functional requirements, and produce architectural and high-level designs, as UML diagrams, following proper design principles and patterns, and architectural styles. Explainability and justifiability are of utmost importance for the produced designs. 
Duties and Responsibilities:  The hired student will work towards the review of relevant technologies and its applications on Software Engineering so far, as well as on the use of current technologies for the generation of software architecture examples. The student will develop the theoretical foundation as well as practical experience on the use of generative AI and LLM tools and methods on Software Engineering. 
Desired Technical Skills:  The student will be asked to demonstrate adequate understanding or expertise in the following topics through relevant courses (on undergraduate or graduate level) or through relevant publications in international conferences or journals. The student should consider applying if they have the expert-level skills and at least 50% of the good-level skills. 
 
Expert programming skills, preferably in Java or Python. 
Good knowledge on software architecture, software design, distributed and cloud systems. 
Adequate knowledge on AI, machine learning, deep learning, and relevant technologies. 
Desired Course(s):  At least B+ in Software Design, Machine Learning and Data Structures.  

Exploring the applicability of Generative AI and LLM on Software Performance and Self-Adaptive Systems 

Professor:  Marios Fokaefs  
Contact Info: fokaefs@yorku.ca 
Lab Website: https://fokaefs.github.io/research/projects.html 
Position Type: Lassonde Undergraduate Research Award (LURA); NSERC Undergraduate Student Research Award (USRA) 
Open Positions: 1 
Project Description:  Generative AI has attracted a lot of attention recently from the research community. Its ability to generate complex solution from similar examples has made it an interesting solution for problems that require a certain degree of creativity. Runtime adaptation to maintain software quality and performance may require similarly creative solutions. In addition, software quality assurance is a multidimensional problem, which necessitates a proper human-system interface to facilitate the work of system administrators. In this sense, runtime adaptation design can also benefit from the use of large language models (LLM), known for their ability to understand and generate natural language. The objective of this project is to explore the ability of LLMs and generative AI to produce self-adaptive strategies for complex distributed systems at runtime. The developed models will need to extract functional and non-functional requirements and produce automatically deployable adaptation strategies, using infrastructure-as-code (IaC) following proper software performance engineering principles. Explainability and justifiability are of utmost importance for the produced strategies. 
Duties and Responsibilities:  The hired student will work towards the review of relevant technologies and its applications on Software Performance so far, as well as on the use of current technologies for the generation of self-adaptive systems. The student will develop the theoretical foundation as well as practical experience on the use of generative AI and LLM tools and methods on Software Performance. 
Desired Technical Skills:  The student will be asked to demonstrate adequate understanding or expertise in the following topics through relevant courses (on undergraduate or graduate level) or through relevant publications in international conferences or journals. The student should consider applying if they have the expert-level skills and at least 50% of the good-level skills. 
 
Expert programming skills, preferably in Java or Python. 
Good knowledge on software performance engineering, self-adaptive systems, and DevOps. 
Adequate knowledge on AI, machine learning, deep learning, and relevant technologies. 
Desired Course(s):  At least B+ in Software Design, Machine Learning and Data Structures.  
 

Optimize the size and performance of AI models for low capacity devices 

Professor:  Marios Fokaefs  
Contact Info: fokaefs@yorku.ca 
Lab Website: https://fokaefs.github.io/research/projects.html 
Position Type: Lassonde Undergraduate Research Award (LURA); NSERC Undergraduate Student Research Award (USRA) 
Open Positions: 2 
Project Description:  Machine Learning and Artificial Intelligence in general slowly become an integral part in the majority of software systems and applications. In combination with the advancements in pervasive and ubiquitous computing, it is now implied that AI models need to be deployable on any device. However, it is not clear yet what the implications are of low capacity devices, such as mobile phones, on the deployment, performance, and accuracy of AI models. In this project, we aim to firstly explore these implications and quantify them, in order to guide the optimization of AI models in terms of resource consumption and constrained by requirements on their performance and accuracy. Next, we will integrate these considerations in MLOps pipelines to automate the optimization and make it an integral part of the model’s lifecycle. The expected outcome of the project is the development of models to simultaneously capture the aspect of the AI models as software artifacts (performance and resource consumption) and as AI artifacts (accuracy). Based on these models, we will also develop tools for the optimal and adaptive deployment of AI models on low capacity devices. 
Duties and Responsibilities:  The hired student will work towards the review of MLOps technologies and tools with a focus on the deployment of AI models on IoT and other low capacity devices, as well as a review of the state-of-practice on adaptive AI model deployment and operations. The student will develop the theoretical foundation as well as practical experience on the optimization of MLOps pipelines. 
Desired Technical Skills:  The student will be asked to demonstrate adequate understanding or expertise in the following topics through relevant courses (on undergraduate or graduate level) or through relevant publications in international conferences or journals. The student should consider applying if they have the expert-level skills and at least 50% of the good-level skills. 
 
Expert programming skills, preferably in Java or Python. 
Good knowledge on software performance engineering, self-adaptive systems, and DevOps. 
Adequate knowledge on AI, machine learning, deep learning, and relevant technologies. 
Desired Course(s):  At least B+ in Software Design, Software Testing, Mobile User Interfaces, Machine Learning.  
 

Using Graphene as a Material for Tritium and Deuterium Separation in Water 

Professor:  Simone Pisana  
Contact Info: pisana@yorku.ca 
Lab Website: https://pisana.lab.yorku.ca/ 
Position Type: Lassonde Undergraduate Research Award (LURA); NSERC Undergraduate Student Research Award (USRA) 
Open Positions: 2 
Project Description:  Students will help our group’s effort to devise a way to efficiently separate deuterium and tritium in water. Deuterium is a heavy form of hydrogen, it is naturally occurring and is an important resource used in the nuclear, medical, and chemical industries. Tritium is a rare radioactive isotope of hydrogen and is considered a waste product from nuclear generation stations but an element of strategic importance for future fusion power generation programs. Therefore, devising ways to economically separate deuterium and tritium-containing water molecules from water mixtures is of important for clean and economical power generation, among other applications. 
Duties and Responsibilities:  Depending on the student’s aptitudes and interest, the responsibilities include: isotopic testing of water samples, fabrication of graphene-based water filters, characterization of filter samples, assisting graduate students with their projects, conducting studies and analyzing the results. 
Desired Technical Skills:  Familiarity with material structure, basic chemistry techniques. 
Desired Course(s):  Introductory courses in materials science, chemistry, solid state physics.  
Other Desired Qualifications:  Great organizational skill, great hands-on skill, ability to work well both alone or as part of a team, resourcefulness, creativity, and problem-solving skills. 

Federated Learning in Edge Computing 

Professor:  Ping Wang  
Contact Info: pingw@yorku.ca 
Lab Website: https://www.eecs.yorku.ca/~pingw/ 
Position Type: NSERC Undergraduate Student Research Award (USRA) 
Open Positions: 1 
Project Description:  In the traditional machine learning (ML) approach, data collected by local nodes is uploaded to the data center and processed centrally, where formidable computational resources can be exploited. However, this approach is no longer suitable for edge computing networks. Firstly, users’ data is more privacy-sensitive than ever. Secondly, transferring data generated by many nodes for processing burdens the network and becomes the bottleneck of overall performance. Thirdly, the centric fashion involves a long propagation delay and incurs unacceptable latency, which is unbearable for many applications with instantaneous decision-making. Therefore, a natural question arises with the abovementioned concerns: how can an ML model from decentralized data at a resource-constrained edge node be trained? Federated Learning (FL) is a technique that fulfills this purpose. FL is an ML setting where many nodes collaboratively train a model under the orchestration of a central server (e.g. service provider) while keeping training data decentralized. However, FL also faces challenges. One major challenge is system heterogeneity. FL involves the heterogeneous participants whose local dataset, computational ability, channel condition, power level and willingness to participate may vary. Given the system heterogeneity, an optimal strategy for resource allocation needs to be developed to maximize the efficiency of FL. Another challenge is communication costs during global model training. Compared with traditional distributed machine learning, where several computational centers are involved, the FL framework is usually related to many edge nodes, incurring an extremely high communication cost. Therefore, reducing communication costs (e.g., model compression) is needed to improve efficiency. This project will focus on developing cutting-edge FL techniques to address these challenges. 
Duties and Responsibilities:  Students will gain sufficient knowledge of federated learning and gain hands-on experience in implementing federated learning algorithms. Students will research the relevant field, with mentoring from senior graduate students. 
Desired Technical Skills:  Good at coding (especially Python). Have basic knowledge of machine learning. 
Desired Course(s):  Students from computer science are preferred. 
Other Desired Qualifications:  Good GPA; Self-motivated. 

Development of Mnemonics Mobile Games to Promote Long-Term Learning 

Professor:  Kiemute Oyibo  
Contact Info: koyibo@yorku.ca 
Lab Website: https://www.linkedin.com/in/kiemute-oyibo/?originalSubdomain=ca 
Position Type: Lassonde Undergraduate Research Award (LURA); NSERC Undergraduate Student Research Award (USRA) 
Open Positions: 2 
Project Description:  The RADAR project is a part of a bigger project called the SANKOFA (Save All New Knowledge Optimally and Fetch Accurately) project, which aims to “re-member” students’ fragmented knowledge by helping them go back in an “edutaining” way to fetch all “lost knowledge.” The RADAR project aims to implement mnemonics-based serious mobile games that will help students keep learned materials within their radar to foster long-term memory and learning. The game will connect to another system (an interactive mnemonics-creation tool) in which the mnemonics are created, and the retrieved data will be used to populate the game to enable students practice retrieval of encoded knowledge. The game will implement four components collectively known as the RADAR: Recollection, Association, Decoding and Acronym/Acrostics Review. Recollection tests the player’s ability to recall or recognize their created mnemonics. Association tests the player’s ability to link each mnemonic to its corresponding topic. Decoding tests the player’s ability to decipher the meaning of their mnemonics letter by letter or word by word. Finally, Acronym/Acrostics Review enables the player to review and reflect on the list of mnemonics and meanings to reinforce learned content as well as to track their progress. The game will be used by professors and students to support long-term learning in memory-intensive courses such as biology, psychology, and user interface, to mention but a few. 
Duties and Responsibilities:  Implement a prototype of mnemonics-based mobile game, document the implementation, report progress in weekly meetings, produce a final report detailing the implementation.. 
Desired Technical Skills:  User experience, programming, version control system usage, documentation. 
Desired Course(s):  User Interface, Programming, Software Engineering.  
Other Desired Qualifications:  Communication and collaborative skills. 

Exploring Software Controlled Hardware Cache Coherence Mechanisms 

Professor:  Anirudh Kaushik  
Contact Info: kaushika@yorku.ca 
Lab Website: https://anikau31.github.io/ 
Position Type: Lassonde Undergraduate Research Award (LURA); NSERC Undergraduate Student Research Award (USRA) 
Open Positions: 1 
Project Description:  Hardware cache coherence is a standard mechanism to facilitate coherent data communication between cores on modern multi-core computing systems. Hardware cache coherence mechanisms operate transparently to the software and allow applications running simultaneously on different cores to communicate data correctly without imposing constraints on the application execution or data management. However, supporting emerging application domains that feature intensive data communication (for example, AI/ML workloads, graph analytics) and new hardware models of computation that allow data communication between heterogeneous compute agents (for example, heterogeneous multi-processor system-on-chips, processing-in-memory accelerators) requires rethinking the design of hardware cache coherence mechanisms to better serve these requirements. In this project, we will explore novel hardware cache coherence designs that address these emerging data communication patterns and demands by reevaluating the transparency to software design criteria, which is a traditional design criterion in existing hardware cache coherence mechanisms. Specifically, we will design and evaluate hardware cache coherence mechanisms that expose some details of their implementations to software and design appropriate hardware-software interfaces for software to control the operations of hardware cache coherence mechanisms. This project involves reasoning about design across multiple components of the computer systems stack: hardware cache coherence micro-architecture, instruction set architecture, compiler design, and programming languages. 
Duties and Responsibilities:   
The student will work closely with the professor/supervisor. The student will be responsible for: 
(1) Literature survey – reading relevant research on the topic of hardware cache coherence and discuss observations and findings with the professor 
(2) Benchmark analyses – identify data sharing patterns in benchmarks and workloads to consider and optimize for in the proposed cache coherence mechanisms 
(3) Design modelling and evaluation – Model the proposed cache coherence mechanism in a micro-architectural simulator or hardware prototyping platform 
(4) Good oral and written skills in English – Submit a technical paper describing this work to a workshop or conference. 
Desired Technical Skills:   
(1) Strong background in computer architecture and must have completed EECS 4201 Computer architecture 
(2) Excellent programming skills in C/C++ in order to model and evaluate cache coherence mechanisms in a C/C++-based micro-architectural simulator 
(3) Good system skills — Familiarity with revision control, Linux, build packages. 
Desired Course(s):  EECS 4201 Computer architecture, EECS 4302 Compilers, EECS 3201 Digital logic design in RTL.  
Other Desired Qualifications:  Strong interest in computer systems design, hacking and contributing to open-source projects. 

UI/UX Design for On-site Water Electrolysis Hydrogen Production and Storage

Professor:  Hany Farag 
Contact Info:hefarag@yorku.ca 
Lab Website: https://smartgrid.eecs.yorku.ca
Position Type: NSERC Undergraduate Student Research Award (USRA) 
Open Positions: 1 
Project Description:  Designing UI/UX for On-Site Water Electrolysis Hydrogen Hubs.
Designing the User Interface (UI) and User Experience (UX) for on-site water electrolysis hydrogen hubs serving hydrogen refueling stations, bus depots, and steelmaking plants requires a user-centric, scalable, and safety-focused approach. The goal is to provide operators with intuitive tools to monitor and control hydrogen production efficiently.
Core Design Principles:
1. User-Centric Design: Tailor the interface to meet the specific needs of different users. Refueling station operators need real-time data on hydrogen dispensing, while bus depot managers focus on scheduling and fleet management. Steelmaking plant operators require control over large-scale production.
2. Scalability: Ensure the UI accommodates future expansion by using modular dashboards. Adding new electrolyzers or dispensers should involve minimal configuration.
3. Cross-Application Consistency: Maintain a consistent UI layout across applications to reduce the learning curve for operators managing multiple sites.
4. Safety-Critical Design: Prioritize safety with clear visual and auditory alerts, emergency controls, and color-coded status indicators to guide operators in handling critical events.
Key UI Components:
1. Dashboard Overview: Present key performance indicators (KPIs) such as hydrogen output (kg/hr), efficiency (%), power consumption (kWh/kg), storage levels (%), and system health.
2. Detailed Monitoring Panels: Provide advanced users with data on electrolyzer performance (voltage, current density), water input quality, renewable energy integration, and historical trends.
3. Control Interfaces: Enable operators to start/stop production, adjust output, schedule maintenance, and configure operating parameters.
4. Mobile and Remote Access: Design a responsive interface for remote monitoring and control via mobile devices, especially useful for refueling station operators.
Application-Specific Features:
1. Hydrogen Refueling Stations: Include real-time queue management, automatic hydrogen dispensing logs, and integration with payment systems.
2. Bus Depots: Offer scheduling tools for bus refueling, dispatch readiness notifications, and detailed consumption reports for fleet optimization.
3. Steelmaking Plants: Support industrial operations with process control, SCADA integration, and energy optimization reports.
UX Enhancements:
1. Data Visualization: Use intuitive graphs, heatmaps, and flow diagrams to help users quickly identify trends and anomalies.
2. Customizable Layouts: Allow users to prioritize specific metrics and customize their dashboard to improve workflow efficiency.
3. Guided Workflows: Provide step-by-step workflows and checklists for common tasks, such as startup, maintenance, and alarm handling.
4. Multilingual Support: Ensure the UI is accessible to a global audience by offering support for multiple languages.
Conclusion:
Effective UI/UX design for on-site hydrogen hubs enhances usability, safety, and operational efficiency. By focusing on user needs, scalability, and cross-application consistency, the interface can support diverse applications such as refueling stations, bus depots, and steelmaking plants. A well-designed system ensures operators can manage hydrogen production reliably, fostering broader adoption of clean hydrogen technologies.
Duties and Responsibilities: The undergraduate student will play a crucial role in designing the UI/UX for the on-site hydrogen hubs. Their responsibilities include the following: 
UI/UX Design Development:
-Design user-friendly dashboards and interfaces for hydrogen production monitoring and control.
-Create layouts that present real-time KPIs, detailed monitoring panels, and control interfaces effectively.
Collaboration with PhD Students:
-Work closely with the PhD students to understand backend calculations, system behavior, and data flow.
-Incorporate backend data into the UI through appropriate visualizations and controls.
Data Visualization:
-Develop intuitive visual elements such as graphs, heatmaps, and flow diagrams to display trends and system performance.
-Ensure visual clarity and ease of interpretation for both basic and advanced users.
Customization and Responsiveness:
-Enable customizable dashboard layouts, allowing users to prioritize specific metrics.
-Design a responsive UI for both desktop and mobile devices to ensure accessibility.
Safety and Alert Features:
-Implement safety-critical UI components, including alerts, emergency controls, and status indicators.
-Ensure that alerts are visually prominent and easy to understand.
User Testing and Feedback:
-Conduct usability testing sessions with potential users and gather feedback.
-Refine the UI based on user feedback to improve usability and functionality.
Documentation:
-Prepare detailed documentation on UI/UX design decisions, workflows, and user guides.
-Ensure that the documentation is clear and accessible for future developers and operators.
By fulfilling these duties, the undergraduate student will gain valuable experience in UI/UX design for industrial applications while contributing to a critical clean energy project.
Required Technical Skills:
UI/UX Design Fundamentals:
-Strong understanding of UI/UX principles, including user-centric design, usability, and responsive layouts.
-Experience with wireframing and prototyping tools (e.g., Figma, Adobe XD, or Sketch).
Front-end Development:
-Proficiency in HTML, CSS, and JavaScript to create functional user interfaces.
-Familiarity with front-end frameworks such as React, Angular, or Vue.js for scalable and dynamic UIs.
Data Visualization:
-Ability to use libraries such as D3.js, Chart.js, or Plotly to create interactive graphs, heatmaps, and flow diagrams.
Collaboration Tools and Version Control:
-Experience with version control systems like Git for collaborative development with PhD students.
-Familiarity with collaborative platforms (e.g., GitHub, GitLab) for issue tracking and project management.
API Integration:
-Basic knowledge of RESTful APIs and how to fetch and display backend data in the UI.
-Ability to handle real-time data updates and asynchronous operations.
Mobile-Responsive Design:
-Experience in designing interfaces that work seamlessly on both desktop and mobile devices.
-Knowledge of responsive design techniques using frameworks like Bootstrap or CSS media queries.
Testing and Debugging:
-Skills in UI/UX testing, including usability testing and gathering user feedback.
-Experience in identifying and resolving UI bugs and ensuring cross-browser compatibility.
Basic Understanding of Industrial Systems:
-Familiarity with industrial processes (optional but beneficial) to design relevant and intuitive interfaces for hydrogen hubs.
-Willingness to learn about hydrogen production and energy systems to better understand the project context.
Documentation and Communication:
-Strong documentation skills to create user guides and technical documentation for the UI.
-Effective communication skills to collaborate with PhD students and present design decisions.
By combining these skills, the student will be well-prepared to take on the UI/UX design challenges and contribute meaningfully to the project.
Desired Course(s): 
-UI/UX Design: Courses on interface design, user-centered design, and usability testing.
-Frontend Development: Courses on web development covering HTML, CSS, JavaScript, and frameworks (React, Angular, or Vue.js).
-Data Visualization: Courses on data visualization techniques and libraries (D3.js, Chart.js).
-Human-Computer Interaction (HCI): Focused on creating intuitive user experiences.
-Software Development and Testing: Courses that include software design principles, debugging, and testing methodologies.
-Responsive Web Design: Training in mobile-first design and responsive frameworks like Bootstrap.
-Energy Systems (Optional): A basic course on energy systems  can help with context understanding.
Other Desired Qualifications: 
-Currently enrolled in a Bachelor’s program in Computer Science, Software Engineering, Information Technology, or Interaction Design.
-Students from Electrical or Industrial Engineering with strong UI/UX development experience will also be considered.
Desired Technical Skills:
-Experience with UI/UX design tools such as Figma, Adobe XD, or Sketch.
-Proficiency in web development technologies (HTML, CSS, JavaScript).
-Familiarity with frontend frameworks like React, Angular, or Vue.js.
-Knowledge of data visualization libraries (D3.js, Chart.js, or Plotly).
-Basic understanding of API integration and handling real-time data.
-Experience with responsive design for mobile and desktop platforms.
Additional Skills:
-Strong problem-solving and analytical thinking.
-Ability to work collaboratively in a team environment and communicate effectively with PhD students.
-Prior experience or coursework in human-computer interaction (HCI) and industrial systems is a plus.
-Familiarity with version control systems (Git/GitHub) and project management tools.
Soft Skills:
-Strong attention to detail, especially for UI/UX consistency and safety-critical elements.
-Willingness to learn and adapt to the technical requirements of hydrogen production systems.
-Excellent documentation and presentation skills to clearly communicate design decisions and progress.

Efficient Power System Management Through Precise Data Center Energy Modeling and Optimized Load Traffic Control and Sharing

Professor:  Hany Farag 
Contact Info: hefarag@yorku.ca 
Lab Website: https://smartgrid.eecs.yorku.ca
Position Type: Lassonde Undergraduate Research Award (LURA); NSERC Undergraduate Student Research Award (USRA) 
Open Positions: 1 
Project Description:  The exponential growth of data consumption and the proliferation of digital services have significantly increased energy consumption in data centers worldwide. Data centers, which house critical infrastructure for cloud computing, data storage, and web services, have become one of the largest consumers of electricity globally. This energy demand is expected to rise even further due to the growing use of artificial intelligence (AI) and machine learning (ML) technologies, particularly the training of large-scale models, such as Large Language Models. The energy-intensive process of model training, which often involves large amounts of data processing, computation, and storage, exacerbates the strain on energy resources. As AI applications become more widespread, energy consumption at data centers is projected to increase at an alarming rate, contributing to higher operational costs and environmental concerns. One effective solution to mitigate the rising energy consumption in data centers is optimal load traffic control and sharing. By implementing intelligent traffic management strategies, data centers can optimize the distribution of workloads across their infrastructure, ensuring that energy usage is more efficient. Load traffic control involves dynamically adjusting the flow of data and computing tasks to minimize power consumption while maintaining the performance and availability of services. This can be achieved through techniques such as load balancing, where computing tasks are distributed across servers based on their processing capabilities and energy efficiency. By ensuring that servers are not underutilized or overburdened, data centers can reduce unnecessary energy consumption and improve overall system performance. Additionally, optimal traffic sharing between data centers can help balance the demand for computational resources and energy across multiple facilities. By leveraging advanced algorithms and real-time monitoring systems, data centers can share workloads between geographically distributed sites. This strategy not only helps in load balancing but also allows for the efficient use of renewable energy sources, which are often intermittent and location-specific. For instance, data centers in areas with high solar or wind energy availability can absorb more workloads during peak renewable energy generation periods, while other facilities can scale down their operations when renewable energy availability is low. This sharing mechanism can reduce the reliance on fossil fuels, lower carbon emissions, and enhance the overall sustainability of data centers. Optimal load traffic control and sharing also contribute to improved power system efficiency by enhancing demand-side management. By better coordinating data center operations, energy consumption can be aligned with the availability of power, especially during periods of peak demand or when the power grid is under stress. The ability to shift computing tasks to times or locations with abundant renewable energy resources helps to smooth out energy consumption patterns and reduces the need for additional power generation. This can lead to a more reliable and resilient power system, as it reduces the risk of grid congestion and ensures that energy resources are used efficiently.
Duties and Responsibilities: In this project, the selected student will begin by conducting a survey on current energy consumption trends in data centers, particularly the impact of AI model training. This will involve reviewing existing literature, including academic papers and industry reports, to understand the main factors contributing to high energy use, such as server, serve loads including computational resources, and cooling systems.
Next, the selected student will develop energy consumption models to simulate various operational factors, such as server load and cooling requirements, within a data center. These models will account for the energy demands of AI workloads and help identify how load traffic control strategies can reduce energy usage without compromising performance. By analyzing these models, the selected student will explore ways to improve system efficiency and minimize energy consumption. This includes applying different management methods and sensitivity analysis to understand the importance of each factor in Datacenter energy consumption and flexibility each element can provide and maximum load shift, load sharing and adjustable demand. Data collection and analysis will be another key responsibility. In this regard, the selected student will gather data from their models and, if possible, from real-world data centers to validate the energy consumption models.
Desired Technical Skills:
1. Students should have strong skills in programming languages such as MATLAB, Python, or R for developing energy consumption models, simulating different scenarios, and analyzing data. MATLAB will be especially useful for numerical analysis, data visualization, and optimization tasks.
2. Experience with energy management software and other simulation tools will be important for modeling and refining energy consumption strategies in data centers.
3. Students must be able to design and execute surveys targeting industry professionals to gather insights on current energy practices in data centers.
4. Knowledge of server architectures, workload distribution, and energy management systems will be critical. Students need to understand the internal workings of data centers and computational tasks to develop accurate models and propose effective energy-saving strategies.
5. Students should be able to process large datasets, identify patterns, and perform statistical analysis to interpret results from simulations and real-world data, which will guide the development of energy optimization strategies.
Desired Programs: 
-Electrical Engineering – A program that covers energy systems, power distribution, and energy optimization.
-Computer Science/Engineering – With a focus on AI, data analysis, and software modeling.
Key Courses/Background:
-Data Center Design and Operations – Focuses on the energy use and operational dynamics within data centers.
-Machine Learning and AI Algorithms – For modeling AI workload impacts on energy consumption.
-Advanced Topics in AI and Computing Infrastructure – Focuses on the computational resource requirements for training AI models.
-Data Analytics and Big Data Processing – For analyzing large sets of energy consumption data and AI workload patterns.
-Energy Modeling and Simulation (optional) – To build and simulate models of energy systems, including data centers.
Additional Skills: 
-Programming Languages: Python, MATLAB, or R (for modeling, simulation, and data analysis).
-Energy Simulation Tools: Familiarity with energy modeling software such as EnergyPlus, HOMER, or MATLAB/Simulink for system modeling.
-Statistical Analysis and Sensitivity Analysis: Understanding statistical techniques to analyze data and determine the impact of various factors on energy consumption.

Power Interface and Control of High Voltage Battery Storage in Microgrid or EV Application

Professor:  John Lam
Contact Info: johnlam@yorku.ca
Lab Website: https://pelser.lab.yorku.ca/
Position Type: Lassonde Undergraduate Research Award (LURA); NSERC Undergraduate Student Research Award (USRA) 
Open Positions: 1 
Project Description:  Microgrid with high voltage DC distribution provides an attractive power architecture for applications such as small-scale renewable energy systems, commercial buildings, and data centers with storage due to: (1) fewer number of power conversion stages, (2) higher overall efficiency, (3) the ease of inter-connecting with back-up storage. The dynamic performance and control of the energy storage system are critical.  This research project is to investigate and develop an energy storage power interface system for use in high voltage (500-800V) battery storage application (also applicable to EV storage).  A power interface topology and an appropriate control scheme will be investigated.   The developed energy storage power interface and its control will be analyzed.  The performance of the devised system will be verified using power electronics simulation software, such as PowerSIM or Simetrix.  Preliminary hardware validation on a proof-of-concept prototype will also be performed.   This research project will be conducted at the Advanced Power Electronics Laboratory for Sustainable Energy Research. 
Duties and Responsibilities:
– Weekly meeting with project supervisor/mentor (post-doc researcher).
– Perform theoretical analysis (details).
– Perform and evaluate simulation studies.
– Perform preliminary hardware validation of the developed research idea.
Desired Technical Skills (Good Knowledge in):
– Electrical circuits
– Electronics
– Basic hardware circuit testing skills
– Power electronics
Desired Course(s):
– Electrical Circuits
– Electronics
– Digital Logic
– Power Electronics
– Introduction to Energy Systems
Other Desired Qualifications:
– Hardworking
– Strong analytical skill
– Highly motivated
– Strong written and oral communication skills

The Sim Game: Developing a Game to Facilitate the Adjustment of First-Year Students to University Life!

Professor: Meiying Qin
Contact Info: mqin@yorku.ca
Lab Website: https://lassonde.yorku.ca/users/mqin
Position Type: NSERC Undergraduate Student Research Award (USRA)
Open Positions: 1
Project Description: The project aims to help first-year students transition from high school to university and understand university expectations by developing a simulation game. This game provides incoming students with a comprehensive preview of life as a computer science student, allowing them to experience university life before classes begin. The goal is to replace traditional advice with experiential learning, helping students internalize important insights. Understanding these expectations is intended to facilitate a smoother transition, contributing to a less stressful first year and supporting overall well-being. In the project, you will have the opportunity to contribute to the creative design of the game, refining your soft engineering skills and gaining experience in game development.
Duties and Responsibilities: Game Design; Implementing the Game; Game Testing.
Desired Technical Skills: If you are a CS student, you should be strong in programming and you are not required to have game development experience; If you are a student in digital media, you should have strong skills in game development.
Desired Course(s): Students in the EECS program and digital media are all welcome to apply. If you are a CS student, you should complete a course in object-oriented programming. Having experience in the industry as a software engineer is preferred but not required (e.g., internship). If you are a digital media student, you should complete the courses in game design I and II. Having completed the game mechanics course and/or a project course is preferred but not required.

Using Mixed Reality or Augmented Reality to Visualize Python Code Execution

Professor: Meiying Qin
Contact Info: mqin@yorku.ca
Lab Website: https://lassonde.yorku.ca/users/mqin
Position Type: NSERC Undergraduate Student Research Award (USRA)
Open Positions: 1
Project Description: Debugging is one of the most important skills for computer science students. However, first-year students are usually not comfortable with working with a debugger. In order to help ease the process for first-year students, we plan to write an application that can visualize the process by animating the variable manipulated using mixed/augmented reality. In this project, you will have the opportunity to gain hands-on experience in both designing and implementing a software application. You will gain experience in mixed/augmented reality.
Duties and Responsibilities: Design the application; Implement the application; Test the application.
Desired Technical Skills: Strong programming skills or experience in developing MR/AR applications. While possessing both skills is not mandatory, it is considered advantageous.
Desired Course(s): At least one course in object-oriented programming.

Building a Physical Tutor Robot

Professor:  Meiying Qin
Contact Info: mqin@yorku.ca
Lab Website: https://lassonde.yorku.ca/users/mqin
Position Type: NSERC Undergraduate Student Research Award (USRA) 
Open Positions: 1 
Project Description:  Robot tutors have demonstrated efficacy in aiding students, yet their widespread adoption faces hurdles due to high costs and limited scalability. Current robot tutors are often impractical for widespread use in universities or personal adoption due to their expense. This project seeks to overcome these limitations by developing an affordable physical robot tutor. The objective is to create a solution that meets the educational needs of students without imposing financial constraints. By focusing on cost-effectiveness, this initiative aims to make advanced tutoring technology accessible on a broader scale, fostering inclusive and impactful learning experiences.
Duties and Responsibilities: Build a physical robot.
Desired Technical Skills: Experience working with hardware such as motors, sensors, and mechatronics. Knowledge of ROS (e.g., robot operating system), and 3D printing/CAD modeling, is recommended but not required.
Desired Course(s): Introduction to robotics or similar courses. If you have experience building robots, the course requirement can be waived.

‘Ellipti-linear’ representations for estimation of the 3D rim of an object from its 2D occluding contour

Professor:  James H. Elder
Contact Info: helio@yorku.ca
Lab Website: https://www.elderlab.yorku.ca/
Position Type: Lassonde Undergraduate Research Award (LURA); NSERC Undergraduate Student Research Award (USRA)
Open Positions: 1
Project Description:  The local shape of the occluding contour of an object is known to constrain the local shape of the object surface, however these constraints are qualitative. While strict quantitative constraints relating the occluding contour to solid shape are unlikely, we posit here that typical regularities of common objects and rules of projection induce dependencies that can be used to derive statistical estimates of quantitative solid shape from the occluding contour. To explore this conjecture, we partition the problem into two parts: 1) Estimation of the 3D rim from the 2D occluding contour, and 2) Estimation of the visible surface shape from the estimated 3D rim. We train and evaluate statistical models on two distinct 3D object datasets and evaluate their ability to capture statistical regularities that enable 3D estimation of the object shape.

Line and ellipses are invariant under projection, making them convenient contour representations for the estimation of the 3D rim from the occluding contour. In this project we will therefore focus specifically on “elliptilinear” representations of the occluding contour and rim, i.e., piecewise elliptical curves, with linear intervals occurring with non-vanishing probability.
Duties and Responsibilities:  The student will inherit 3D object datasets and software designed to recover optimal ellipti-linear representations of occluding contours. The student will validate the software and then analyze how these occluding contour representations relate to ellipti-linear approximations of the rim. Based on this analysis, the student will develop an algorithm to estimate the 3D shape of the rim from the 2D shape of the occluding contour. The student will have regular meetings with collaborator Yiming Qian (A*Star Singapore) as well as tri-weekly meetings with principal investigator Prof. James Elder.
Desired Technical Skills:  At the end of the summer the student will deliver code and labelled data in the form of a GitHub repository, and an engineering report in LaTeX that documents the objectives, methods, results, and conclusions of this project, and will present results at the Lassonde Annual Undergraduate Summer Student Research Conference.
Desired Course(s):  Computer Vision and Machine Learning courses would be good preparation.
Other Desired Qualifications: 
* MATLAB
* Aptitude in mathematics and statistics

Improving configural processing in deep neural networks

Professor:  James H. Elder
Contact Info: helio@yorku.ca
Lab Website: https://www.elderlab.yorku.ca/
Position Type: Lassonde Undergraduate Research Award (LURA); NSERC Undergraduate Student Research Award (USRA)
Open Positions: 1
Project Description:  ImageNet-trained networks fail to develop a configural representation of object shape. A main reason for this failure may be the impoverished nature of the image labelling task. While the human brain of course supports object recognition, humans form much richer representations of objects that allow us to appreciate many diverse qualities of objects and their spatial relationships to each other and the rest of the visual scene. To support this diverse experience of objects, we hypothesize that the brain establishes useful intermediate representations that can subserve multiple tasks. In this project, we explore this hypothesis computationally by modifying existing deep network architectures to expand the task from object labelling to also include object localization, segmentation, and monocular depth estimation. Critically, losses will be applied not only at the outputs of each respective head, but also at intermediate stages of computation. These intermediate losses will take the form of regional forms of their respective tasks, with spatial extent matched to the nominal receptive field size.

We hypothesize that this will lead to more holistic processing as the network takes advantage of synergies between the tasks, and local shortcuts that might be useful for recognition are disfavoured since they do not contribute to other tasks.
Duties and Responsibilities:  The student will work closely with the supervisors to develop and test algorithms for video-based highway traffic analytics. The student will have regular meetings with principal investigator Prof. James Elder.
Desired Technical Skills:  Software skills, Python, PyTorch, deep learning.
Desired Course(s):  Computer Vision and Machine Learning courses would be good preparation.

Using semantics and geometry to improve the generalization of monocular 3D perception systems

Professor:  James H. Elder
Contact Info: helio@yorku.ca
Lab Website: https://www.elderlab.yorku.ca/
Position Type: Lassonde Undergraduate Research Award (LURA); NSERC Undergraduate Student Research Award (USRA)
Open Positions: 1
Project Description:  Our pilot studies suggest that both humans and networks rely strongly on elevation in the image as a cue to depth, consistent with the dominance of ground plane surfaces. Moreover, our recent work on scene classification has suggested that human awareness of scene semantics can precede and inform awareness of 3D spatial layout. These findings motivate a novel approach to monocular depth estimation in which depth is inferred directly from semantic surface labels and the statistics of 3D spatial relationships between surfaces.

To explore this novel approach, we will again employ a dataset of planar projections generated from the SYNS dataset. State-of-the-art deep semantic and instance segmentation systems will be applied to estimate the semantic surface labels and individuate objects. In the first stage of inference, known view geometry will be used to assign depths to all ground-plane semantic categories (e.g., road, sidewalk, field). In a second stage of inference, semantic regions adjacent to ground-plane regions will be assigned depths based upon vertical propagation from assigned ground-plane depths. In a third stage, for regions not adjacent to ground-plane regions, depths will be estimated based upon adjacent regions already assigned depths and a learned table of expected relative depth for pairs of adjacent semantic categories. Our goal is to carefully refine the algorithm by also incorporating instance segmentation and more carefully encoding 3D spatial relationships between semantic categories. Results will be compared against state-of-the-art deep network systems.
Duties and Responsibilities:  The student will work closely with the supervisors to develop and test algorithms for monocular estimation of absolute and relative depth on held-out datasets. The student will have daily meetings with postdoctoral fellows Amin Alizadeh and David White to discuss progress, as well as tri-weekly meetings with principal investigator Prof. James Elder.
Desired Technical Skills:  Software skills, 3D geometry, machine learning.
Desired Course(s):  Computer Vision and Machine Learning courses would be good preparation.
Other Desired Qualifications:  At the end of the summer the student will deliver documented software in the form of a GitHub repository and an engineering report in LaTeX that documents the objectives, methods, results, and conclusions of this project, and will present results at the Lassonde Annual Undergraduate Summer Student Research Conference

Monocular mechanisms for surface attitude estimation in natural scenes

Professor:  James H. Elder
Contact Info: helio@yorku.ca
Lab Website: https://www.elderlab.yorku.ca/
Position Type: Lassonde Undergraduate Research Award (LURA); NSERC Undergraduate Student Research Award (USRA)
Open Positions: 1
Project Description:  Current deep network models are remarkably able to estimate depth from a single image. What are the underlying computational principles? Recent research in our lab has shown that for the built environment, fusion of semantic segmentation, projective geometry and linear perspective cues provides surprisingly accurate estimates of 3D scene layout, competitive with some recent deep learning approaches. However, these methods break down for natural scenes such as forests, where semantic and linear perspective cues are weak.

For such scenes, we hypothesize that approximating the texture process within each semantic image region as stationary will allow a local Fourier analysis to generate reasonable estimates of surface attitude. Furthermore, when integrated with projective geometry constraints, we predict that these local surface estimates can be propagated to recover approximate 3D scene layout.

In this project, the student will assist the team in testing this theory, implementing it as an image-computable computational model and measuring its performance on standard public datasets. In parallel, we will conduct psychophysical experiments in which human observers estimate local surface attitudes on these same datasets. Decision variable correlation of model judgements with human and deep network estimates will allow us to assess the extent to which the model accounts for human and deep learning estimation of 3D surface structure in natural scenes. This research will thus provide valuable insights into both the computational neuroscience of human 3D perception and into the principles underlying monocular depth perception in recent deep network models.
Duties and Responsibilities:  The student will work closely with the supervisors to develop and test algorithms for video-based highway traffic analytics. The student will have daily meetings with postdoctoral Fellow David White to discuss progress, as well as tri-weekly meetings with principal investigator Prof. James Elder.
Desired Technical Skills: 
* Mathematical skills, including Fourier transforms, linear algebra, probability, and statistics
* Coding skills (Matlab and/or Python)
* An interest in science
Desired Course(s):  Computer Vision and Machine Learning courses would be good preparation.
Other Desired Qualifications:  The planned outcome of this research project is a study is a new Fourier-based algorithm for estimating surface orientation from projected texture, an evaluation of this algorithm on ground truth datasets, and a comparison against human judgements of surface orientation for the same scenes.

At the end of the summer the student will deliver documented software in the form of a Github repository and an engineering report in LaTeX that documents the objectives, methods, results, and conclusions of this project, and will present results at the Lassonde Annual Undergraduate Summer Student Research Conference.

Computer vision systems for highway traffic analytics

Professor:  James H. Elder
Contact Info: helio@yorku.ca
Lab Website: https://www.elderlab.yorku.ca/
Position Type: Lassonde Undergraduate Research Award (LURA); NSERC Undergraduate Student Research Award (USRA)
Open Positions: 1
Project Description:  Traffic congestion is a major challenge throughout the world. It affects commute time, mobility, and accessibility and is a driving factor in increasing the harmful gasses that are the main culprits of the greenhouse effect. Congestion can potentially be mitigated over short time scales through improvements to signal timing and rapid detection and resolution of traffic incidents, and over longer time scales through strategic roadway improvements and optimization of public transit systems. However, all these mitigations depend critically on an accurate understanding of lane-by-lane traffic density and speed distributions. Historically, these data are obtained from embedded inductive loops, but these are expensive to maintain. This motivates the development of fully automated AI-based video analytics systems to accurately measure traffic density and speed and to detect anomalous traffic incidents.

In the proposed research we will focus specifically on highways, which in large metropolitan areas are typically the key pinch points that determine overall congestion. One challenge to achieving our objective is the volume of video data required to densely sample these highways and to react to measurements in a timely way. Distributing this quantity of data to the cloud or a central control centre for processing entails an enormous investment in communication and storage and, despite advances in low-latency communication protocols, will inevitably lead to delays in response. It also raises privacy and data security issues. These challenges motivate an edge solution, where video is processed by embedded systems located on-site, and only low-bandwidth and anonymized derived analytics products are communicated centrally. In the proposed research, we plan to design such an embedded system, optimized for highway deployment.

The system will be designed for mounting at 10m height on either meridian or side poles and will incorporate multiple cameras that together provide a field of view covering all lanes of traffic in both directions. These will be paired with an advanced embedded AI device such as an NVIDIA Jetson AGX Orin. Deep networks will be pruned and quantized (INT8, FP16, Mixed Precision) to meet throughput requirements. Provided functionality will include: 1) Automatic camera calibration and highway understanding that allows events localized in the image to be precisely back-projected to highway ground coordinates. 2) Detection, classification, and segmentation of motor vehicles. 3). Vehicle speed estimation. 4) Detection of anomalies, including accidents and stopped vehicles. 5) Reporting of anomalous vehicles through automatic number plate recognition.
Duties and Responsibilities:  The student will work closely with the supervisors to develop and test algorithms for video-based highway traffic analytics. The student will have daily meetings with senior engineer Helio Perroni Filho to discuss progress, as well as tri-weekly meetings with principal investigator Prof. James Elder and with project partners at the Ministry of Transportation Ontario.
Desired Technical Skills:  Software skills, systems hardware skills.
Desired Course(s):  Computer Vision and Machine Learning courses would be good preparation.
Other Desired Qualifications:  The planned outcome of this research project is a prototype embedded traffic analytics products optimized for highway deployment. We hope to ultimately commercialize this device through licensing or a start-up company. We believe this device will ultimately replace costly inductive loop systems and contribute to better traffic analytics, thus ultimately reducing congestion and greenhouse gas emissions.

At the end of the summer the student will deliver documented software in the form of a Github repository and an engineering report in LaTeX that documents the objectives, methods, results and conclusions of this project, and will present results at the Lassonde Annual Undergraduate Summer Student Research Conference.

LiDAR-free 3D ground-truthing of motor vehicles

Professor:  James H. Elder
Contact Info: helio@yorku.ca
Lab Website: https://www.elderlab.yorku.ca/
Position Type: Lassonde Undergraduate Research Award (LURA); NSERC Undergraduate Student Research Award (USRA)
Open Positions: 1
Project Description:  This is a novel symmetry-based framework for single-view 3D ground-truthing of motor vehicles. LiDAR-based 3D ground-truthing is expensive, requires joint calibration of LiDARs and cameras, and may be inaccurate in the far field where LiDAR returns are sparse. We are developing a tool to annotate and ground truth 3D location, pose and shape of motor vehicles from a 2D image based on 3D symmetry cues and a generalized cylinder model of motor vehicles. The annotation and ground truth will be used to train a deep learning network for 3D object detection and estimation of motor vehicles.
Duties and Responsibilities:  The student will work on statistical integration of the annotations with an online database of vehicle dimensions as well as OpenGL code to visualize estimated generalized cylinder models of the annotated vehicles. The student will have regular meetings with principal investigator Prof. James Elder.
Desired Technical Skills: 
* Software – Python, OpenGL.
* Concepts – Familiarity with computer vision and 3D geometry skills preferred.
Desired Course(s):  Computer Vision and Machine Learning courses would be good preparation.
Other Desired Qualifications:  At the end of the summer the student will deliver code and labelled data in the form of a GitHub repository as well as an engineering report in LaTeX that documents the objectives, methods, results and conclusions of this project, and will present results at the Lassonde Annual Undergraduate Summer Student Research Conference.

Improved control of a robot attentive sensor

Professor:  James H. Elder
Contact Info: helio@yorku.ca
Lab Website: https://www.elderlab.yorku.ca/
Position Type: Lassonde Undergraduate Research Award (LURA); NSERC Undergraduate Student Research Award (USRA)
Open Positions: 1
Project Description:  To be effective, a social robot must reliably detect and recognize people in all visual directions and in both near and far fields. A major challenge is the resolution/field-of-view trade-off, for which we have developed a novel attentive sensing solution. Panoramic low-resolution pre-attentive sensing is provided by an array of wide-angle cameras, while attentive sensing is achieved with a high-resolution, narrow field-of-view camera and a mirror-based gaze deflection system. Quantitative evaluation on a novel dataset shows that this attentive sensing strategy can yield good panoramic face recognition performance in the wild out to distances of ~35m.

Currently the system operates at about 0.3 fixations per second, far slower than the human fixation rate of 2-3 fixations per second. In this project we will redesign our system to come closer to human performance. This will involve lightening the payload, updating the motor, improving the control system and updating the attentive camera to allow manual control of focus so that the camera can change focus while making a saccade.
Duties and Responsibilities:  The student will work closely with the supervisors to develop and test the improved robot attentive sensor. The student will have daily meetings with Senior Robotics Engineer Helio Perroni-Filho to discuss progress, as well as tri-weekly meetings with principal investigator Prof. James Elder.
Desired Technical Skills:  Software skills, control theory and algorithms, systems design.
Desired Course(s):  Computer Vision and Machine Learning courses would be good preparation.
Other Desired Qualifications:  At the end of the summer the student will demonstrate the redesigned attentive sensor system, deliver documented software in the form of a Github repository and deliver an engineering report in LaTeX that documents the objectives, methods, results and conclusions of this project, and will present results at the Lassonde Annual Undergraduate Summer Student Research Conference.

Optimal path planning for of an attentive social robot

Professor:  James H. Elder
Contact Info: helio@yorku.ca
Lab Website: https://www.elderlab.yorku.ca/
Position Type: Lassonde Undergraduate Research Award (LURA); NSERC Undergraduate Student Research Award (USRA)
Open Positions: 1
Project Description:  When you walk into a party, one of the first things you will probably do is look around to see who is there. We have developed an attentive social robot called the SnapBot that is capable of attentively searching for people in a room, acquiring high-resolution snapshots of their faces and recognizing their identities. In this project, the student will explore how the path of the robot can be optimized to maximize the rate at which new information about the people in the environment is obtained.
Duties and Responsibilities:  The student will work closely with the supervisors to test long-term operation of the robot hardware and software. Problems will be logged, solutions proposed, designed, implemented and evaluated. The student will have daily meetings with PhD student Nizwa Javed and Senior Robotics Engineer Helio Perroni-Filho to discuss progress, as well as tri-weekly meetings with principal investigator Prof. James Elder.
Desired Technical Skills:  Software skills, systems design.
Desired Course(s):  Computer Vision and Machine Learning and Robotics courses would be good preparation.
Other Desired Qualifications:  The planned outcome of this research project is a prototype embedded traffic analytics products optimized for highway deployment. We hope to ultimately commercialize this device through licensing or a start-up company. We believe this device will ultimately replace costly inductive loop systems and contribute to better traffic analytics, thus ultimately reducing congestion and greenhouse gas emissions.

At the end of the summer the student will deliver documented software in the form of a Github repository and an engineering report in LaTeX that documents the objectives, methods, results and conclusions of this project, and will present results at the Lassonde Annual Undergraduate Summer Student Research Conference.

Eliminating occlusion artifacts in a robot attentive sensor

Professor:  James H. Elder
Contact Info: helio@yorku.ca
Lab Website: https://www.elderlab.yorku.ca/
Position Type: Lassonde Undergraduate Research Award (LURA); NSERC Undergraduate Student Research Award (USRA)
Open Positions: 1
Project Description:  We have developed an attentive social robot that is capable of attentively searching for specific individuals, recognizing them at a distance using facial recognition software, and approaching them for more information. One limitation of our attentive sensor is that the field of view is partially occluded in four directions by the aluminum posts that support the motorized mirror. Fortunately, due to focal blur the occlusion is only partial, which suggests that it could potentially be calibrated out. The goal of this project is to develop and evaluate algorithms for minimizing this artifact.
Duties and Responsibilities:  The student will work closely with the supervisors to develop and test algorithms for removing the occlusion artifact. The student will have daily meetings with Senior Robotics Engineer Helio Perroni-Filho to discuss progress, as well as tri-weekly meetings with principal investigator Prof. James Elder.
Desired Technical Skills:  Software skills, systems design.
Desired Course(s):  Computer Vision and Machine Learning and Robotics courses would be good preparation.
Other Desired Qualifications:  At the end of the summer the student will demonstrate the occlusion removal method as implemented in the robot and deliver an engineering report in LaTeX that documents the objectives, methods, results and conclusions of this project, and will present results at the Lassonde Annual Undergraduate Summer Student Research Conference.

The AirChair: Improving Mobility Assistance at Airports

Professor:  James H. Elder
Contact Info: helio@yorku.ca
Lab Website: https://www.elderlab.yorku.ca/
Position Type: Lassonde Undergraduate Research Award (LURA); NSERC Undergraduate Student Research Award (USRA)
Open Positions: 1
Project Description:  The AirChair is a semi-autonomous AI wheelchair designed at York that operates semi-automatically in platoon formation, following a human guide. The technology reduces labour and physical stress required to provide timely mobility assistance at airports. In this project, the student will assist the team in improvements to tracking and obstacle avoidance components.
Duties and Responsibilities:  The student will work closely with the supervisors to develop and test the improved tracking and obstacle avoidance algorithms. The student will have daily meetings with Senior Robotics Engineer Helio Perroni-Filho to discuss progress, as well as tri-weekly meetings with principal investigator Prof. James Elder.
Desired Technical Skills:  Software skills, control theory and algorithms, systems design.
Desired Course(s):  Computer Vision and Machine Learning and Robotics courses would be good preparation.
Other Desired Qualifications:  At the end of the summer the student will demonstrate the improved tracking and obstacle avoidance algorithms, deliver documented software in the form of a Github repository and deliver an engineering report in LaTeX that documents the objectives, methods, results and conclusions of this project, and will present results at the Lassonde Annual Undergraduate Summer Student Research Conference.

Development of Machine Learning Algorithms for Motion Artifact Detection and Removal in Brain EEG Signals

Professor:  Hossein Kassiri
Contact Info: kassiri@yorku.ca
Lab Website: https://electronics.eecs.yorku.ca/
Position Type: Lassonde Undergraduate Research Award (LURA); NSERC Undergraduate Student Research Award (USRA)
Open Positions: 2
Project Description:  Electroencephalography (EEG) is a widely used technique for monitoring brain activity in both clinical and research settings. However, EEG recordings are often contaminated by motion artifacts, which can significantly degrade the quality of the data and interfere with accurate interpretation. These artifacts arise from movements such as blinking, muscle contractions, or head motion. Removing motion artifacts effectively without losing valuable neural information is a critical challenge in EEG signal processing. This project focuses on developing machine learning (ML) algorithms to detect and remove motion artifacts from EEG data. You will leverage publicly available EEG datasets with annotated artifacts to explore different approaches, including supervised learning, unsupervised learning, and generative AI models such as autoencoders or GANs. Your goal will be to design models that can robustly distinguish artifacts from true neural signals and either remove or correct the artifacts in an automated, computationally efficient manner. The project involves several phases:
-Reviewing and understanding EEG signal processing basics and neurophysiology concepts related to motion artifacts.
-Exploring and preprocessing EEG datasets for training and evaluation.
-Developing and implementing ML algorithms for artifact detection and removal.
-Evaluating the algorithms for accuracy, robustness, and computational efficiency.
You will work closely with a graduate student mentor who will provide guidance and support throughout the project. This experience will allow you to deepen your understanding of EEG, machine learning, and biomedical signal processing, while contributing to a cutting-edge area in neurotechnology.
Duties and Responsibilities:
1. Data Exploration and Preprocessing: Search for and review publicly available EEG datasets. Preprocess EEG data (e.g., filtering, normalization, and artifact labeling).
2. Algorithm Development: Develop and implement ML models for motion artifact detection and removal. Explore generative models (e.g., autoencoders, GANs) for reconstructing clean EEG signals. Compare the performance of various approaches and optimize for accuracy and speed.
3. Model Training and Testing: Train models on labeled EEG datasets and evaluate their performance. Perform cross-validation to ensure robustness.
4. Documentation and Reporting: Maintain clear documentation of code, methodologies, and results. Present findings regularly to the project mentor and team.
5. Collaboration: Work closely with a graduate student mentor to refine project goals and methods. Contribute to brainstorming and troubleshooting sessions.
Required Skills:
-Strong foundation in machine learning, with familiarity in supervised and unsupervised learning techniques.
-Programming proficiency in Python and experience with ML libraries (e.g., TensorFlow, PyTorch, or scikit-learn).
-Basic knowledge of signal processing concepts, such as filtering and Fourier transforms.
Desired Skills:
-Familiarity with generative AI models, such as autoencoders, VAEs, or GANs.
-Understanding of EEG signal characteristics and neurophysiology, including common motion artifacts.
-Experience with biomedical signal processing tools or libraries (e.g., MNE-Python).
-Strong problem-solving and analytical skills, with attention to computational efficiency.
Desired Course(s): Students from any discipline or year of study are welcome to apply, provided they have the required technical skills and an interest in brain signal processing and machine learning.
Other Desired Qualifications:
-Strong communication and teamwork skills.
-Willingness to learn and take feedback.
-Dependable and proactive work ethic.
-Respectful and professional attitude.
-Ability to manage time and meet deadlines.

Wearable Smart Camera for Post-Surgery Monitoring

Professor:  Hossein Kassiri
Contact Info: kassiri@yorku.ca

Wab Website: https://electronics.eecs.yorku.ca/
Position Type: Lassonde Undergraduate Research Award (LURA); NSERC Undergraduate Student Research Award (USRA)
Open Positions: 2
Project Description:Post-surgical neurological care often necessitates close monitoring to identify complications such as swelling, discoloration, or abnormalities around the surgical site. These conditions can indicate severe issues like infection, hematoma, or poor wound healing, requiring immediate intervention. Traditional monitoring methods, such as frequent clinical visits or inpatient observation, are inconvenient for patients and resource-intensive for healthcare providers. This project focuses on developing a wearable smart camera module for post-surgery monitoring. The device will capture images of the surgical site every 30 minutes, process the data locally to detect signs of complications, and wirelessly transmit summaries to a base station or secure application for review by healthcare professionals. In cases of detected abnormalities, the system will send alerts to prompt immediate medical attention. The project involves two students working collaboratively, focusing on complementary aspects of the device’s development. One student will specialize in hardware integration and embedded programming, while the other will handle algorithm development, local data processing, and wireless communication. Together, they will create a lightweight, efficient, and reliable system to enhance patient care and recovery outcomes.
Duties and Responsibilities:
Student 1– Embedded Systems Developer:
1. Hardware Integration:
– Design and integrate the wearable device using a microcontroller (e.g., ESP32, STM32) and camera module.
– Ensure low-power operation for extended battery life.
2. Firmware Development:
– Write efficient firmware for scheduled image capture and device operation.
– Develop hardware interfaces for the camera and Bluetooth communication module.
3. System Testing:
– Test the hardware for reliability, durability, and patient comfort.
– Debug and troubleshoot hardware-related issues.
Student 2– Software and Communication Developer:
1. Data Processing and Algorithms:
– Develop algorithms to process captured images locally for feature detection (e.g., swelling or discoloration).
– Optimize the algorithms for low-power processing on the embedded system.
2. Wireless Communication:
– Implement Bluetooth communication to transmit processed data to a base station or mobile app.
– Ensure reliable and secure data transfer.
3. Integration and Testing:
– Collaborate with Student 1 to test end-to-end functionality of the system.
– Debug and troubleshoot software-related issues.
Shared Responsibilities:
– Document system design, implementation, and testing results.
– Present progress updates to project stakeholders.
– Conduct user comfort and usability evaluations.
Desired Technical Skills:
Student 1-Embedded Systems Developer:
– Experience in embedded programming (e.g., Arduino, STM32, or ESP32).
– Knowledge of low-power IoT hardware design.
– Familiarity with sensor integration and hardware debugging.
Student 2-Software and Communication Developer:
– Proficiency in developing algorithms for image processing and feature detection.
– Experience with wireless communication protocols (e.g., Bluetooth).
– Strong skills in optimizing software for embedded platforms.
Desired Course(s): Students from Electrical Engineering, Computer Engineering, Software Engineering, or Computer Science are ideal, but applicants with relevant technical skills and interest in biomedical applications are encouraged to apply, regardless of program or year of study.
Other Desired Qualifications:
– Ability to work collaboratively and independently.
– Strong critical-thinking and time-management skills.
– Interest in healthcare technology and innovation.

Electrophysiology of Plants: Testbed construction and data collection

Professor: Andrew Eckford
Contact Info: aeckford@yorku.ca
Lab Website: http://eckfordlab.org/
Position Type: Lassonde Undergraduate Research Award (LURA);NSERC Undergraduate Student Research Award (USRA)
Open Positions: 1
Project Description: Greenhouse agriculture is a highly valuable business in Canada, generating billions of dollars in annual revenue and providing fresh vegetables such as tomatoes, lettuce, peppers, and strawberries throughout the cold winter. Researchers and companies are increasingly interested in using data to grow healthier plants and optimize the yields of their crops. Remarkably, it may be possible to monitor the health of a plant in real time using electrophysiology: plants are known to generate action potentials, i.e., voltage spikes which are readily detectable by instrumentation, and which may indicate stress or other issues with the plant. In this project, you will construct a testbed that will grow plants in a controlled environment, subject them to various kinds of stress (e.g., drought stress), and collect electrophysiological data on the plant’s response. The goal is to intervene as early as possible to alleviate stress, or to anticipate and prevent the plant from entering a stressed state.
Duties and Responsibilities: You will construct a plant-growing testbed according to plans provided by a research collaborator. You will also gather and analyze data from this testbed, and potentially data from research collaborators.
Essential Skills: Python programming, including familiarity with Jupyter notebook or Google Colab.
Desired Course(s): EECS 3201 Digital Logic Design.
Other Desired Qualifications: Small-scale construction skills would be desirable, e.g., you should be handy with basic tools.

Electromagnetic Exposure Time-Series Forecasting with Out-of-Distribution Generalization

Professor: Hina Tabassum
Contact Info: hinat@yorku.ca
Lab Website: https://sites.google.com/view/ngwn-research-lab/home?authuser=0
Position Type: Lassonde Undergraduate Research Award (LURA);NSERC Undergraduate Student Research Award (USRA)
Open Positions: 2
Project Description: With the recent advancements in wireless technologies, forecasting electromagnetic field (EMF) exposure is becoming essential to ensure regulatory compliance, enable efficient network deployment and resource management, address public health concerns, and monitor environmental risks. In this project, we will develop a deep learning (DL)-empowered time series forecasting framework. The dynamic nature of EMF data introduces significant challenges. Historical training data and future test data often differ in distribution, necessitating models capable of out-of-distribution (OOD) generalization. To address this, our project focuses on enhancing OOD performance in EMF TSF using invariant learning principles. We identify two core challenges in applying invariant learning to EMF TSF. First, target variables in EMF data may be influenced by unobserved core variables, violating conventional assumptions of invariant learning. Second, EMF time-series datasets typically lack environment labels, rendering existing environmental inference methods ineffective. To overcome these challenges, this project aims to develop a model-agnostic framework specifically designed for EMF TSF. A novel surrogate loss function will be employed to address the impact of unobserved variables. Additionally, it incorporates a multi-head network for effective environment inference while preserving temporal adjacency, enabling the learning of invariant representations across inferred environments.
Duties and Responsibilities:
-Literature review of the relevant research works.
-Regeneration of results from existing research works.
-Develop a new model for OOD forecasting.
-Perform experiments and comparative analysis with the existing works.
-Write-up of a technical report.
Desired Technical Skills: Pytorch, Tensorflow.
Desired Course(s)/Qualification(s): Any course(s) related to machine learning and wireless communication should suffice.

Deep Learning-Based Radio Occupancy Map Estimation 

Professor: Hina Tabassum 
Contact Info: hinat@yorku.ca  
Lab Website: https://sites.google.com/view/ngwn-research-lab/home?authuser=0 
Position Type: Lassonde Undergraduate Research Award (LURA); NSERC Undergraduate Student Research Award (USRA) 
Open Positions: 1 
Project Description: Radio maps, which provide metrics like power spectral density across geographic areas, have numerous applications, including interference control, spectrum management, resource allocation, and network planning. These maps are traditionally constructed using measurements from spatially distributed spectrum sensors. However, the complex nature of electromagnetic wave propagation makes radio maps highly intricate functions of spatial coordinates, necessitating model-free approaches for accurate estimation. This project introduces a novel methodology for radio occupancy map estimation that moves beyond conventional interpolation-based techniques, which fail to learn from prior data. Instead, our approach leverages deep learning to capture the spatial structure of propagation phenomena, such as shadowing, by pretraining on datasets collected from different environments. This significantly reduces the number of measurements needed to achieve a desired level of accuracy. As a key innovation, this is the first work to utilize deep neural networks for radio occupancy map estimation. We developed a fully convolutional deep completion autoencoder architecture that effectively exploits the manifold structure inherent in this class of maps, enabling efficient and accurate map estimation. This approach marks a significant step forward in leveraging deep learning for advanced spectrum management and network optimization.
Duties and Responsibilities:  
-Literature review of the relevant research works. 
-Regeneration of results from existing research works. 
-Develop a new generative model for map estimation. 
-Perform experiments and comparative analysis with the existing works. 
-Write-up of a technical report. 
Desired Technical Skills: Pytorch, Tensorflow. 
Desired Course(s)/Qualifications: Any courses related to machine learning and wireless communication should suffice. 

Concurrent data structures

Professor: Eric Ruppert
Contact Info: eruppert@yorku.ca
Lab Website: www.eecs.yorku.ca/~eruppert
Position Type: Lassonde Undergraduate Research Award (LURA);NSERC Undergraduate Student Research Award (USRA)
Open Positions: 1
Project Description: This project is concerned with the development of concurrent data structures, which can be accessed simultaneously by multiple processes. These data structures are essential for harnessing the full power of modern multicore architectures. Processes must carefully coordinate their accesses to the data structures to ensure that simultaneous updates do not cause shared data to become corrupted. The goal of the project is to develop new concurrent data structures with good time and space complexity.
Duties and Responsibilities: Some background reading will be required, followed by work on the development of a new data structure and a proof of correctness and complexity analysis for it.
Desired Technical Skills: Ability to prove correctness of algorithms and analyse their complexity.
Desired Course(s): Computer science or software engineering students who have excelled in courses in theoretical computer science (e.g., data structures, algorithms, automata theory, complexity).
Other Desired Qualifications: Strong math background.

Investigating the Use of Language Models to Generate Control Knowledge for Hierarchical Planning

Professor: Yves Lesperance
Contact Info: lesperan@yorku.ca
Lab Website: http://www.cse.yorku.ca/~lesperan/
Position Type: Lassonde Undergraduate Research Award (LURA);NSERC Undergraduate Student Research Award (USRA)
Open Positions: 1
Project Description: AI Planning Systems can handle more complex problems when domain-specific control knowledge is provided.  In Hierarchical Task Network (HTN) planning, one specifies high-level tasks and methods to help the planner find a plan to complete the goal task.  Another approach is to specify search control knowledge in Linear Temporal Logic (LTL).  However, such control knowledge is expensive to obtain from human experts.  In this project, the student will investigate whether Large Language Models (LLM) can help in generating such control knowledge.  The student will define benchmark problems, specify prompts, and perform experiments to see if the LLM generated control knowledge is sound and can be used by the hierarchical planner to find plans.
Duties and Responsibilities:
-Complete some background reading. Select LLM and hierarchical planner to be used.
-Develop a number of benchmarks for the control knowledge generation problem with solutions, these having a range of difficulty from very easy to somewhat hard.
-Develop zero-shot and one-shot prompts for the control knowledge generation problem. 
-Run experiments and analyse and present the results.
Desired Technical Skills: Python programming skills. Previous exposure to machine learning, automated planning, and first-order logic, is desirable.
Desired Course(s): Enrolled in CS/CE/SE program. Has taken LE/EECS 3401 3.00 – Introduction to Artificial Intelligence and Logic Programming.
Other Desired Qualifications: Familiarity with Large Language Models or Natural Language Processing and relevant technologies / tools is an asset.

Cancer Survivorship Care Panel: Enhanced Surveillance of Early Signs of Iatrogenic Diseases Raising Upon Cancer Treatment

Professor: Razieh (Neda) Salahandish
Contact Info: raziehs@yorku.ca
Lab Website: https://lab-ha.eecs.yorku.ca/pages/team.html
Position Type: Lassonde Undergraduate Research Award (LURA);NSERC Undergraduate Student Research Award (USRA)
Open Positions: 2
Project Description: The rising rates of cancer survival are leading to a growing population in need of healthcare services and ongoing post-cancer monitoring. Secondary health complications emerging as the side effects of the therapeutic interventions for cancer treatment, including chemotherapy, are seen as the main source of concern causing continual burdens for patients and healthcare systems in the realm of cancer care. The management of the adverse events subsequent to the cancer treatment, through vigilant monitoring of the symptoms for proper clinical response, is one of the crucial measures throughout the care phase of cancer therapy. A major source of complications arising as a consequence of cancer treatment regimens, whether it be through chemotherapy or immunotherapy, is immunosuppression and prolonged immunodeficiency. Such conditions increase susceptibility to infections for cancer survivors, which leads to other pressing health problems subsequently. Furthermore, cancer pathogenesis and subsequent therapeutic interventions can elevate inflammation levels in patients, now acknowledged as a leading contributor to secondary health complications in affected individuals. Scientific evidence indicates that a major health concern following chemotherapy is the development of heart failure and cardiomyopathy. Anthracyclines, for instance, have been demonstrated to be associated with a higher risk of cardiotoxicity during and subsequent to the implementation of therapeutic regimens. The continuing phase of cancer care is often accompanied by considerable financial hardship, psychological and mental distress for patients and their families, as well as excess pressure on the health systems. Therefore, it is imperative to foster the development of solutions that can offer profound relief and provide affordable, reliable, and accessible health monitoring alternatives. This can be achieved through the advancement of technologies that minimize the need for multiple physician visits, centralized lab testing, long wait times, and costly examinations. A “care panel”, composed of cutting-edge smart systems designed for precise detection of biomarkers indicating the potential emergence of secondary diseases, would be then an invaluable solution for monitoring cancer survivors. This will warn the onset of the most prevalent secondary complications including cardiovascular conditions, infections, and underlying prolonged inflammation. If these conditions are examined on a regular basis, through low-cost near-patient testing modalities, it will provide patients with the mental relief that any arising condition can be managed early on, considerably reducing the burdens of disease.
Duties and Responsibilities:
– Develop and fabricate the wearable microfluidic sweat collection patch.
– Integrate lateral flow immunoassays (LFIAs).
– Literature review on AI methods for biomarker discovery.
– Develop AI-based data analysis strategy.
Desired Technical Skills: Familiar with Eng software like Solid Works and AutoCAD.

Deep Learning Models for Spectrogram Analysis in 6G Wireless Networks 

Professor:  Sunila Akbar  
Contact Info: sunila@yorku.ca 
Lab Website: https://lassonde.yorku.ca/users/sunila 
Position Type: Lassonde Undergraduate Research Award (LURA); NSERC Undergraduate Student Research Award (USRA) 
Open Positions: 1 
Project Description:  This project explores the application of machine learning models for spectrogram-based wireless signal analysis, focusing on Channel State Information (CSI)-based human activity recognition and spectrogram segmentation. A model, leveraging Generative AI, Transformers, or Recurrent Neural Networks (RNNs), will be developed to extract meaningful patterns from spectrograms. The study aims to evaluate its accuracy, generalization, and computational efficiency. By adopting a data-driven approach, this work seeks to enhance wireless sensing and communication systems, contributing to advancements in AI-driven 6G networks. 
Duties and Responsibilities:  
1)  Literature review of the relevant research works 
2)  Regeneration of results from existing research works 
3)  Develop a new model for Spectrogram Analysis in 6G Wireless Networks 
4)  Perform experiments and comparative analysis with the existing works 
5)  Write-up of a technical report  
Desired Technical Skills:  
1)  Analytical skills 
2)  Machine Learning 
3)  Coding Skills preferably in Python and Pytorch 
Desired Courses:  
1)  Advanced Object-Oriented Programming 
2)  Any Math/ Calculus Course 
Other Desired Qualifications: 
1)  Wireless Communications/ Digital Communications/ Signals and Systems background is preferred 
2)  Machine Learning background is preferred 
 

Monitoring and Predictive Tools to Enhance Resilience of Power Systems and Electrified Transportation Against Extreme Weather 

Professor:  Afshin Rezaei-Zare  
Contact Info: rezaei@yorku.ca 
Position Type: Lassonde Undergraduate Research Award (LURA); NSERC Undergraduate Student Research Award (USRA) 
Open Positions: 2 
Project Description:  This research project focuses on developing advanced monitoring and predictive tools to enhance the resilience of power systems and electrified transportation networks against natural disasters, including solar storms, wildfires, and ice storms. These events pose significant risks to grid stability and electric vehicle infrastructure, leading to potential power disruptions and mobility constraints. 
The project aims to design an interactive user interface that integrates real-time data from power system sensors, weather monitoring services, and disaster tracking sources. This system will provide grid operators and transportation planners with actionable insights by visualizing grid health, transformer conditions, and EV charging network stability. Predictive analytics will be incorporated to assess vulnerabilities and forecast potential disruptions, enabling proactive decision-making. 
Students will develop an intuitive UI/UX framework for seamless data visualization and analysis. The system’s effectiveness will be tested using historical disaster data and simulations, ensuring its capability to improve situational awareness and disaster preparedness. This interdisciplinary project will bridge power systems engineering, data science, and software development to support resilient energy and mobility infrastructure. 
Duties and Responsibilities:  Students will be responsible for designing and implementing a real-time monitoring dashboard that integrates data from power grids, electrified transportation networks, and environmental monitoring sources. They will develop predictive analytics features to assess vulnerabilities and provide early warnings. Tasks include UI/UX development, real-time data integration, predictive modeling, and system validation through simulations. The team will also document their work and prepare a final report summarizing findings and recommendations. 
Desired Technical Skills:  This project offers an opportunity to work on an interdisciplinary challenge that bridges power systems, electrified transportation, and disaster resilience through innovative monitoring solutions. 
Mandatory skills: at least two of the following: 
-Software Development & UI/UX: Proficiency in web development frameworks (e.g., React, Angular, or Vue.js) and UI/UX design principles. 
-Power Systems Knowledge: Basic understanding of electrical circuits, power grids, renewable energy integration, and electrified transportation. 
-Programming: Strong knowledge of Python and C++ for developing power system algorithms. 
Additional Skills:   
In addition to mandatory skills, priority will be given to the candidates with any of the following skills:   
-Data Visualization: Experience with tools such as D3.js, Plotly, or Power BI for real-time analytics. 
-Geospatial & Disaster Monitoring Tools: Familiarity with APIs for real-time data. 
-Machine Learning: Interest in applying AI techniques for predictive modeling of system resilience. 
Desired Course(s):  Any course(s) related to Electrical Circuits, Software Development, Introduction to Power Systems, or Machine Learning. 

LLM-based avatar for human-robot interaction 

Professor:  Michael Jenkin  
Contact Info: jenkin@yorku.ca 
Lab Website: https://michaeljenkin.info.yorku.ca/ 
Position Type: Lassonde Undergraduate Research Award (LURA); NSERC Undergraduate Student Research Award (USRA) 
Open Positions: 1 
Project Description:  Avatars have been found to provide an engaging and effective mechanism for human-robot interaction. Interacting through voice, they can literally be used to put a face on a robot or some computer-based interaction technology. This project involves enhancing our existing avatar-based interaction technology. Projects include 
– enhancing the current LLM-based interaction infrastructure, so as to provide tailored interactions for different individuals when they are engaged with the robot.  
– enhancing the current Avatar-based display to include better eye contact models and adding gestures to the avatar to improve its interaction with the user 
– deploying avatars in one or more external environments. 
Duties and Responsibilities:  
– software development in python and unity 
– enhancing the application-specific structure of information available to the LLM 
Desired Technical Skills:   
– good Python skills 
– interest in developing end-to-end LLM-based interaction technology 
– ability to work as a member of a team as well as independently  
Other Desired Qualifications:   
– CS/SE/CE background 
– good C# skills 
– knowledge of message passing protocols (e.g., ROS) is an asset 

Autonomous surface vessels for material transport in remote locations 

Professor:  Michael Jenkin  
Contact Info: jenkin@yorku.ca 
Lab Website: https://michaeljenkin.info.yorku.ca/ 
Position Type: Lassonde Undergraduate Research Award (LURA); NSERC Undergraduate Student Research Award (USRA) 
Open Positions: 1 
Project Description:  Transporting material to/from remote locations, especially the far north, is complicated by poor GPS coverage and the lack of good harbours to dock the vessel. This project will enhance the lab’s existing fleet of uncrewed surface vessels (USVs) to support simulated materials transport between the vessel to a drone to an individual on shore. Much of the project will involve existing robot hardware in the lab and additional hardware is expected to be delivered during the summer. Planed tasks include 
– GPS-based navigation on bodies of water (e.g., Stong Pond)  
– materials transport between the robot platform and UAV in indoor simulation prior to on the water deployment 
– exploring gesture-based interaction from the shore to direct the UAV to a landing site 
Duties and Responsibilities:  
– python programming (ROS) for the robot(s) 
– electro-mechanical work on the robots (minor, but some skills in electronics would be helpful) 
– deployment of robots on water bodies in the GTA 
Desired Technical Skills:   
– good Python skills 
– interest in autonomous systems 
– ability to work as a member of a team as well as independently  
Other Desired Qualifications:   
– CS/SE/CE background 
– electronics skills would be an asset 
– knowledge of ROS would be an asset