Please join the Computer Science Department for the upcoming thesis defense:

Presenter: Pronab Ghosh

Thesis title: Intelligent Vehicle-to-Vehicle Communications with Importance of Fairness and Information Freshness

Abstract: Intelligent Transportation Systems (ITS) showcase cutting-edge services designed to revolutionize transportation and mobility, especially within future smart cities. These services play a pivotal role in bolstering traffic safety, traffic flow management, infotainment, and the dependability of edge-assisted autonomous driving. Consequently, ITS introduces the Vehicle-to-Vehicle (V2V) communication paradigm, facilitating continuous connectivity between moving vehicles and their surroundings. Real-time data exchange regarding acceleration, position, speed, and braking status enables collision avoidance and congestion mitigation. V2V communication streamlines communication pathways, resulting in safer and more comfortable driving experiences, particularly in high-risk scenarios. This thesis investigates two distinct challenges within V2V communications:
1. Multi-Group V2V Communications: This study addresses the establishment and scheduling of data streams and packets between vehicles within a multi-group communication setup. In scenarios involving police cars, ambulances, buses, or city fleets, each group of vehicles communicates within itself. The objective is to establish communication links between all vehicle pairs within a group, utilizing WiFi technology to alleviate the load on cellular networks. Since not all pairs have direct communication capabilities, the problem extends to relaying and scheduling data packets through multi-hop transmissions. Resource blocks, including designated channels and time slots, are allocated. The study aims to maximize communication efficiency among vehicle groups while ensuring fairness and allowing resource block reuse under the SINR constraint.
2. Age of Information (AoI) Minimization: Traditional metrics like throughput and latency do not sufficiently capture data stream timeliness and freshness, critical for autonomous driving and accident prevention. This study targets the minimization of AoI across all data streams in autonomous vehicular networks. The goal is to reduce the total or average AoI over a specified timeframe. Unlike the first study, direct data stream connections between vehicle pairs are absent. Instead, a vehicle broadcasts data to nearby vehicles based on data importance. Minimizing AoI requires optimizing relaying decisions, transmission timing, and data packet dropping. Complexity arises from optimizing nodes for data relaying, transmission timing, and prioritizing newer data packets.
In both studies, mathematical formulations employing mixed-integer linear programming (MILP) are initially employed for optimal solutions. Due to optimization model complexity, scalable heuristic methods are proposed for larger networks. To capture dynamic environmental dynamics, both problems are modeled as Markov Decision Processes (MDP) and tackled using reinforcement learning (RL) techniques such as Q-learning and Double Deep Q-Networks (DDQN). Additionally, hybrid heuristic-based RL methods are introduced to enhance learning behavior and overall performance. Numerical results underscore the efficacy of hybrid approaches in comparison to optimal solutions, random agents, proposed heuristics, and conventional RL methods across networks of varying sizes. In conclusion, this thesis contributes to intelligent transportation systems and future smart cities by offering innovative solutions for vehicular communications. These approaches hold the potential to enhance data transmission efficiency and reliability for autonomous vehicles, paving the way for safer and more responsive autonomous driving experiences.



Committee Members:
Dr. Thiago E Alves de Oliveira (co-supervisor, committee chair), Dr. Dariush Ebrahimi (supervisor), Dr. Xing Tan, Dr. Salama Ikki (Electrical Engineering). 

Please contact grad.compsci@lakeheadu.ca for the Zoom link. Everyone is welcome.

Please join the Computer Science Department for the upcoming thesis defense:

Presenter: Mohamed Elshafei

Thesis title: Neural Synergy in Compact Biomedical IoT Devices: Spintronic Pathways for MEG-EEG Integration and Portability

Abstract: The human brain, a marvel of nature, consists of intricate neural networks that have fascinated and perplexed the scientific community for generations. As scientists and researchers globally endeavour to unravel the mysteries of bioelectrical activities that form the basis of our cognitive functions and experiences, our research emerges at the nexus of biology and cutting-edge technology. Specifically, we spotlight the remarkable capabilities of magnetoencephalography (MEG) and electroencephalography (EEG). These potent neuroimaging tools, celebrated for their unparalleled spatial and temporal precision, are synergistically combined in our study. We aim to map MEG innovatively signals onto their EEG replicas, employing avant-garde spintronic devices, with a particular emphasis on Magnetic Tunnel Junctions (MTJ).
Drawing inspiration from the wonders of nature, such as the awe-inspiring magnetoreception abilities exhibited by homing pigeons, our exploration is driven by a desire to harness and amplify similar bio-magnetic potentials latent within the human brain. Methodically segmented into distinct chapters, our research unfolds a series of groundbreaking contributions:
• First: Venturing into uncharted territories, we introduce the integration of artificial intelligence (AI) into MEG/EEG mapping. This novel approach propels our understanding of cerebral activities into exciting new directions.
• Second: Taking a deeper plunge, we explore the temporal features of the M/EEG signals as a further step toward optimizing the mapping solution. This insight paves the way for envisioning a future where bulky equipment gives way to compact, efficient neuroimaging devices.
• Third: In a display of our team’s innovative spirit, we simulate the MTJ sensor’s noise and utilize the AI approaches to denoise that noised dataset.
• Finally: Transitioning to the tangible realm of practical implementations, our focus gravitates towards the intricate facets of hardware design. We particularly emphasize the potential of quantizing the BiLSTM model to optimize and revolutionize the biomagnetic sensing ecosystem.
In essence, this research serves as a confluence of biology and state-of-the-art technological advancements. It meticulously lays a solid foundation for future explorations, from early detection and prediction of neurological disorders to pioneering strides in federated learning. Our fervent hope is that through our findings, we not only expand the horizons of current knowledge but also inspire a renewed perspective on how we understand and harness the myriad activities of the human brain.


Committee Members:
Dr. Zubair Fadlullah (supervisor, committee chair), Dr. Garima Bajwa, Dr. Ahmed Elnakib (University of Louisville, USA, & Mansoura University, Egypt)

Please contact grad.compsci@lakeheadu.ca for the Zoom link. Everyone is welcome.

Please join the Computer Science Department for the upcoming thesis defense:

Presenter: Laurent Yves Emile Ramos Cheret

Thesis title: Texture Recognition from Robotic Tactile Surface Reconstruction: A Reinforcement Learning Approach

Abstract: The ability to handle objects and recognize them and their properties by touch is a crucial ability that humans have. Thanks to tactile sensing, robots can do something similar by perceiving specific physical characteristics of the objects they are in contact with. However, to do so in unstructured environments remains a challenge. The present work proposes a novel method for blind texture classification on uneven surfaces, using data from a robotic manipulator's kinematic chain and a compliant tactile sensing module composed of MARG and barometer sensors. The data from the manipulator’s kinematic chain and the deformation of the sensing module are used to estimate the contact position and the vector normal to the surface. Contact points and normal vectors are then used to estimate control points for splines used to generate patches of surfaces. The reconstructions were validated in experiments with five surfaces, and a comparison with a vision system shows that it can achieve slightly better estimates. These estimations are used to train a Reinforcement Learning model for pressure-control, which adjusts the position of the manipulator's end effector based on barometer readings, allowing the tactile sensing module to keep in touch with the surface without applying too much pressure on it. Trajectories for sliding motions are created by selecting points from the reconstructions and adjusting their position. Tactile data from trajectories with and without adjustment are collected and used for classification. Results show that the adjustment leads to an improvement of up to 30% in top-1 accuracy, reaching 90% on four textures. This work is a first proposal for texture classification on uneven surfaces where the exploratory motions depend on the object pose and shape, and could serve as a complementary system where vision is compromised.


Committee Members:
Dr. Thiago E Alves de Oliveira (supervisor, committee chair), Dr. Garima Bajwa, Dr. Paulo Fernando Ferreira Rosa (Instiuto Militar de Engenharia)


Please contact grad.compsci@lakeheadu.ca for the Zoom link. Everyone is welcome.

The Department of Geography and the Environment at Lakehead University invite you to join us in Thunder Bay, September 29-30, for Canadian Association of Geographers-Prairie Division Conference 2023! Connect with colleagues, share research, and explore North of Superior.

Register now: https://pcag2023.lakeheadu.ca

A live Q&A WebEx event, NSERC’s Q&A sessions are supported by a series of informational videos available on the NSERC YouTube channel (updates for 2023 are currently in progress). Participants should watch these videos in advance and come to the Q&A session with specific questions in mind:

Playlist – Scholarships & Fellowships program application tutorials (English): https://www.youtube.com/playlist?list=PL6ox0GB7vXYlhaAY7mEqwmMqYK9TGCp1E

Wednesday, Sept. 6 from 11 am to 12 pm.

Join Webex webinar: https://nsercvideo.webex.com/nsercvideo/j.php?MTID=m0014d0ae606ef903fcaa... Webinar number (access code): 2773 534 2810 Webinar password: NSERCinfo2023 (67372463 from phones and video systems)

On behalf of the Hiring Committee for the Faculty of Education Tier 2 Canada Research Chair in Indigegogy, we would like to invite the university community to public presentations from each of the selected candidates.

Presentations will take place at 9:30am on the following dates:

Tuesday, August 22 - Melissa Twance
Wednesday, August 23 - Holly Prince

Please email Rain in the Office of the Dean at officer.educ@lakeheadu.ca to request presentation Zoom links.

Title: "Impacts of Invasive Spiny Water Flea (Bythotrephes cederströmii) on Walleye (Sander vitreus) Mercury Accumulation, Biomagnification and Bioenergetics"

Supervisory Committee:
Dr. Mike Rennie (Supervisor)
Dr. Rob Mackereth
Dr. Rob Stewart
Dr. Tom Johnston (External)

All are welcome to attend. You can attend the in-person defence in Thunder Bay in ATAC 3004, or contact biology@lakeheadu.ca for the meeting ID and password to attend virtually.

Lakehead University's Department of Geography and the Environment is hosting the 2023 Annual Conference of the Canadian Association of Geographers, Prairie Division! We invite you to join us at the Delta Hotel to share research from Northern Ontario and the Prairies, in the form of oral and poster presentations, and take part in a fun and informative local field trip.

Details and registration: https://pcag2023.lakeheadu.ca/

The Biotechnology PhD candidate Chris Chon Long Chio will present his research:

Advancing the utilization of agricultural waste with mutagenic enzymes and exploring its potential as feedstock for producing various bioproducts from Bacillus velezensis PhCL

Bioconversion of renewable resources has been considered an alternative option for obtaining eco-friendly and sustainable chemicals and energy for industrial applications. Bacterium Bacillus velezensis has attracted numerous researchers’ interest due to its ability to produce various economic and environmentally-friendly biomolecules, such as industrial enzymes, biosurfactants, antioxidants, and antibiotics. In this study, a newly isolated strain B. velezensis PhCL was characterized and its production of various biomolecules was optimized via statistical design. Furthermore, various agricultural wastes such as rice husk, wheat straw, and oat straw, were used as the fermentation feedstock for lowering the production cost of the biomolecules. Moreover, a GH11 xylanase was mutated based on the simulation and calculation. The result suggested that the mutant had a higher efficiency in degrading wheat straw than the original xylanase. Overall, this study has further explored the potential of Bacillus velezensis and agricultural waste in developing green and sustainable economics.

Committee Members: Drs. Wensheng Qin (supervisor), Dr. Kam Leung, Dr. Justin Jiang and Dr. Jinguang Hu (external)

August 11, 2023 at 1:00 pm
zoom link available on request

Everyone is welcome

Contact Brenda Magajna for more information phd.ses@lakeheadu.ca

You are invited to attend the Biotechnology PhD Defense of Nadia Sufdar Ali on Monday, August 14 at 1 pm in CB 4058.

Nadia will present her Biotechnology PhD research: A high throughput screening and characterization of laccase-producing bacterium Serratia quinivorans AORB19 that exhibits lignin degradation traits, dye de-colorization efficiency, and enhanced laccase production in biomass

Natural biodegradation processes hold promises for lignin degradation; coupled with high throughput (HTP) screening methods that focus on "microorganisms that we don't yet have" but are supposedly on the way, help scale up lignin reduction initiatives in industrial settings. Our study successfully isolated and identified ten new bacterial species and five fungal species from wood, that secrete significant extracellular lignin-degrading enzymes by HTP screening methods. Among them, a bacterial strain Serratia quinivorans AORB19, was extensively studied and characterized for its laccase production and lignin degrading potential to the genomic level. The strain showed remarkable efficiency in decolorization of textile dyes invitro, and potential for bioremediation due to its stability and tolerance to various harsh conditions. Furthermore, its capacity for enhanced laccase production while utilizing agro-industrial residues (Pea hull, canola meal, barley malt sprouts, flax meal and okara) as carbon sources indicates its potential for facilitating the biological pretreatment of lignocellulosic biomasses. Notably, the strain exhibited the ability to convert alkaline lignin into valuable intermediates such as p-hydroxybenzaldehyde and vanillin, indicating its potential for industrial use as a platform for value-added chemical production. Overall, these findings highlight the importance of this strain and its enzymes in harnessing the abundant biopolymer lignin, showcasing its potential for multiple applications in environmental remediation and sustainable lignocellulosic biorefineries.

Committee Members: Drs. Wensheng Qin and Trent Yang (co-supervisors), Dr. Jinqiang Hou, Dr. Ingeborg Zehbe and Dr. Daniel Shun-Chang Yang (external)

Everyone is welcome