Seminar

Grad Seminar: Agent-based simulation to evaluate the impact of seismic retrofit promotion policies

Amanda Brown — Thu, 19 Jun 2025 20:03:36 +0000

Grad Seminar: Agent-based simulation to evaluate the impact of seismic retrofit promotion policies Amanda Brown Thu, 06/19/2025 - 16:03

Presenter

Alireza Ahmadi, MASc candidate in Systems Design Engineering

Attending this seminar will count towards the graduate student seminar attendance milestone!

Join on Teams
https://teams.microsoft.com/l/meetup-join/19%3ameeting_YjQ1ZjljN2ItZTgzMC00NTJlLTllNjMtNjE5MTA2M2ZlOWNl%40thread.v2/0?context=%7b%22Tid%22%3a%22723a5a87-f39a-4a22-9247-3fc240c01396%22%2c%22Oid%22%3a%2258336da6-a40f-4126-bc7c-acbdf5d6610d%22%7d

Grad Seminar: Design and Evaluation of a Novel Framework Inspired by Affect Control Theory to Create Social Robot Affective Identities

Amanda Brown — Thu, 12 Jun 2025 16:16:17 +0000

Grad Seminar: Design and Evaluation of a Novel Framework Inspired by Affect Control Theory to Create Social Robot Affective Identities Amanda Brown Thu, 06/12/2025 - 12:16

Abstract

Developing agent personalities and behaviours that can be adjusted based on individual factors such as personal preferences, context, and lived experiences is important to improve user acceptance and engagement with social robots in varying scenarios, such as for assistive robots. Current approaches used in the design of social robot personalities (e.g., extroversion manipulation-based) often do not encompass the entire personality (e.g., Big 5) as only a subset of dimensions can be manipulated.

We propose a novel framework using Affect Control Theory (ACT) that enables the manipulation of all aspects of an agents' affective identities, as a proxy for personality. We evaluate this framework in two studies, one online and one in-person, involving an "at-home" medication sorting task to determine (1) whether participants are able to identify the manipulations in the social robot behaviours, and (2) whether this framework can be used for personalizing social robot identities, in other words, if participants will prefer to interact with specific robot identities considering their own affective identities. The results confirmed the design and manipulation of two out of three ACT dimensions and showed that participants preferred interacting with robots that are perceived to have an affective identity closer to them. Proposed framework and results can have significant contributions to the personalization of social robot behaviours in assistive robots and beyond.

Presenter

Andrea Chakma, MASc candidate in Systems Design Engineering

Attending this seminar will count towards the graduate student seminar attendance milestone!

Join Zoom Meeting
https://uwaterloo.zoom.us/j/99505929293?pwd=1rwYgNO6WfcIkwMvfAgmOlZHDOPKgi.1

Meeting ID: 995 0592 9293
Passcode: 107588

Grad Seminar: Active upper-limb prosthesis for swimming

Amanda Brown — Fri, 06 Jun 2025 19:37:25 +0000

Grad Seminar: Active upper-limb prosthesis for swimming Amanda Brown Fri, 06/06/2025 - 15:37

Abstract

Swimming offers valuable physical and psychological benefits, particularly during musculoskeletal rehabilitation. However, for individuals with upper limb amputations, the lack of active prosthetic solutions limits performance and accessibility. This work presents a novel swimming prosthesis that uses real-time data from an inertial measurement unit (IMU) to adjust wrist positioning based on the swimmer’s stroke phase. The system aims to improve stroke symmetry, propulsion efficiency, and balanced muscle engagement. The prosthesis integrates embedded electronics, a compact actuator, and custom control algorithms to support more natural movement in water, offering new possibilities for both rehabilitation and sport.

Presenter

Vasylysa Korovkina, MASc candidate in Systems Design Engineering

Attending this seminar will count towards the graduate student seminar attendance milestone!

Join on Teams

Measuring neuromuscular transmission time variability in motor units

Amanda Brown — Fri, 06 Jun 2025 16:22:08 +0000

Measuring neuromuscular transmission time variability in motor units Amanda Brown Fri, 06/06/2025 - 12:22

Join us for a special seminar with Dr. Armando Malanda Trigueros.

Motor units (MU) are the basic element of voluntary muscle contraction and are composed of a motor-neuron and the muscle fiber innervated by it. The transmission time that an electrical impulse traveling through the motor neuron takes to reach the fibers and fire action potentials in these fibers vary across successive motor neuron impulses. This variability, technically known as ´jitter´ may be increased when the motor unit is affected by disease or age and can be measured from intramuscular EMG recordings. In the extreme case called ´blocking,´ the potential in a fiber is not elicited at all. The processes of measuring jitter and detecting blocking potentials are time consuming and subjective, so that automatic algorithms may help doctors to do these tasks more reliably and efficiently.

To analyze the EMG signal, successive potentials fired from single motor units (MUPs), are extracted by manual or automatic procedures. These MUP trains are usually contaminated by MUPs originated in other motor units. The problem of cleaning out these alien MUPs is of major importance in clinical neurophysiology practice, and doctors spend much of their time cleaning up these potentials.

In the first part of this seminar, several new algorithms for cleaning up MUP trains will be discussed and compared. In the second part, new automatic methods that provide jitter estimation and blocking detection from EMG signals will be described.

Attending this seminar will count towards the graduate student seminar attendance milestone!

Armando Malanda Trigueros was born in Madrid, Spain. In 1992, he graduated in Telecommunication Engineering from Madrid Polytechnic University. In 1999, he received his PhD degree from Carlos III University, Madrid, his Doctoral Thesis work being related to the use of genetic algorithms for improving the efficiency in coding of signals and images.

In 1992, a few months after completing his undergraduate degree, he joined the Public University of Navarra (UPNA), where he started teaching at the School of Industrial and Telecommunication Engineering. He became an Associate Professor in 2003. He has taught 20 different courses at the Bachelor and Master’s levels related to telecommunication engineering and biomedical engineering. He is currently the Director of the Master of Biomedical Engineering at UPNA.

Among his research merits, he has published 65 international scientific papers and 4 book chapters, presented over 79 works at international conferences and 45 at national conferences, participated in 11 publicly financed projects, being the project leader of 5 of them and supervised 5 PhD Doctoral Thesis.

His area of expertise is the processing of biomedical signals, mainly electromyography (EMG). He leads a research team at UPNA which has actively collaborated with several institutions in the world and particularly with the Neurophysiology Service of the Navarra University Hospital, through multiple projects and studies with the main objective of improving the techniques for capturing, analyzing and interpreting EMG signals.

In 2008, he came to Canada for 6 months to work with Professor Daniel Stashuk in the Department of Systems Design Engineering at the University of ��ݮ��Ƶ. Professor Stashuk is a notorious researcher in the area of EMG signal analysis, and they both set out to find techniques for measuring motor unit instability. They finally came up with a new algorithm that solved the problem very precisely. Neurologist specialists from two Hospitals in Madrid and Lisbon joined this research and provided the signals to test the algorithm.

Six years later, Professor Malanda has come again to ��ݮ��Ƶ, to enjoy a sabbatical year and extend his research with Professor Stashuk, now retired from teaching but still active as a scientist.

This seminar is sponsored by

Grad Seminar: Towards Urban Digital Twins With Gaussian Splatting, Large-Language-Models, and Cloud Mapping Services

Amanda Brown — Tue, 08 Apr 2025 19:44:40 +0000

Grad Seminar: Towards Urban Digital Twins With Gaussian Splatting, Large-Language-Models, and Cloud Mapping Services Amanda Brown Tue, 04/08/2025 - 15:44

Abstract

Urban Digital Twin cities are powerful tools leveraging 3D modelling, multi-source data, and online geographic information systems to assist urban planning, infrastructure management, and decision-making. However, traditional 3D reconstruction methods face significant limitations in meeting the demands of next-generation Digital Twins. These conventional approaches struggle with scalability, lack photorealism, and struggle with computational efficiency. This thesis addresses these challenges by proposing a comprehensive framework that leverages recent advances in AI-driven 3D reconstruction and large language models (LLMs), paving the way for efficient, accurate, and user accessible Urban Digital Twins of the future.

To address the challenge of generating accurate and efficient large-scale outdoor 3D point clouds from remote sensing images, this thesis introduces a novel pipeline that combines Google Earth imagery with Gaussian Splatting techniques. This approach enables dense and photorealistic 3D reconstruction at the city scale, significantly improving view synthesis quality and reconstruction accuracy compared to traditional photogrammetry, multi-view stereo, and neural radiance field methods. The proposed framework is demonstrated through the reconstruction of the City of ��ݮ��Ƶ, representing one of the first large-scale applications of Gaussian Splatting in urban modelling.

For the challenge of efficiently generating precise 3D mesh representations of individual buildings, a new pipeline is developed that integrates open-set foundational object segmentation models with the latest Gaussian Splatting techniques. This enables the reconstruction of building meshes from multi-view 2D images using simple text or click-based prompts. Unlike dense point clouds, mesh representations are better suited for simulations and numerical modelling. The pipeline leverages Google Earth Studio, allowing users to generate detailed 3D building models from basic inputs such as an address, postal code, geographic coordinates, or place name.

To improve the accessibility and usability of Digital Twin systems, this thesis presents the Digital Twin Buildings framework, combining mesh-based 3D reconstruction with cloud mapping services and a novel multi-agent system powered by large language models. This framework enables the automated retrieval, visualization, and analysis of 3D building models alongside GIS-integrated data. It supports natural language interactions, automated code generation, and multi-modal analytics. A case study on air quality analysis during a major wildfire event illustrates the system's potential to support decision-making and interdisciplinary urban research.

By unifying these contributions, this thesis demonstrates a significant step toward accurate and efficient digital twin systems for urban modelling. It provides a blueprint for developing the next generation of Urban Digital Twins accessible to users through AI assisted tools supporting natural language interactions.

Presenter

Kyle Gao, PhD candidate in Systems Design Engineering

Attending this seminar will count towards the graduate student seminar attendance milestone!

Join on Teams

Grad Seminar: New Attack Detection Methods for Connected and Automated Vehicles

Amanda Brown — Fri, 04 Apr 2025 20:37:43 +0000

Grad Seminar: New Attack Detection Methods for Connected and Automated Vehicles Amanda Brown Fri, 04/04/2025 - 16:37

Abstract

We first propose a vehicle dynamics-based attack detector that integrates the Unscented Kalman Filter (UKF) with machine learning techniques. This approach monitors physical system behaviour and identifies anomalies when sensor readings deviate from predicted states. Our enhanced model captures nonlinear vehicle dynamics while maintaining real- time performance, enabling the detection of sophisticated attacks that traditional linear models would miss.

We develop a complementary trajectory-based detection framework that analyzes driving behaviour rationality to address the limitations of purely physics-based detection. This system evaluates vehicle trajectories within their environmental context, incorporating road conditions, traffic signals, and surrounding vehicle data. By leveraging neural networks for trajectory prediction and evaluation, our approach can identify malicious interventions even when attackers manipulate vehicle behaviour within physically plausible limits.

Integrating these two detection perspectives—one based on vehicle dynamics modelling and the other on trajectory rationality analysis—provides a comprehensive security framework that significantly improves detection accuracy while reducing false positives. Experimental results demonstrate our system's effectiveness against various attack vectors, including false data injection, adversarial control perturbations, and sensor spoofing attacks.

Our research contributes to autonomous vehicle security by developing a holistic detection approach that considers both immediate physical anomalies and broader behavioural inconsistencies, enhancing system resilience against increasingly sophisticated cyber-physical threats.

Presenter

Shuhao Bian, MASc candidate in Systems Design Engineering

Attending this seminar will count towards the graduate student seminar attendance milestone!

Join on Teams

SYDE Graduate Symposium 2025

Amanda Brown — Wed, 26 Mar 2025 18:54:04 +0000

SYDE Graduate Symposium 2025 Amanda Brown Wed, 03/26/2025 - 14:54

Symposium Schedule

Time	Presenter	Session Title
10:00 - 10:30 a.m.	Welcome coffee and snacks with faculty and students
10:30 a.m - 11:45 a.m.	Student Research Seminar Session 1 – Co-Chaired by Dr. Eihab Abdel-Rahman and Dr. Jessie Ma
10:30 a.m.	Sabrina Saiko	Therapeutic Applications of Social Robotics for Autism Spectrum Disorder
10:45 a.m.	Yasser Shama	Bifurcation Drift in Electrostatic MEMS Sensors: Characterization and Mitigation Strategies
11:00 a.m.	Wendy Ding	Age-Related Differences in Eye Movements During Level 3 Autonomous Vehicle Takeover
11:15 a.m.	Marco Moran-Ledesma	TRAIN-KNEE: Developing a Haptic Manikin for Knee Injury Assessment Training
11:30 a.m.	Rui Zhou	Sensitive, Accurate and Fast Terahertz Detectors Design
12:00 p.m. - 1:00 p.m.	Pizza lunch Special guest speaker Dr. Dan Mashatan, Senior Manager – Autonomy & AI SW - Teledyne FLIR Unmanned Systems North America on "Autonomous Missions for Aerial Unmanned Systems in Challenging Environments"
1:15 pm. - 2:15 p.m.	Student Research Seminar Session 2 – Co-Chaired by Dr. Nasser Lashgarian Azad and Dr. Nima Maftoon
1:15 p.m.	Chang Liu	Language-guided Context-aware Unsupervised Semantic Segmentation Under Distribution Shift
1:30 p.m.	Yaoxin Li	Mamba Fusion for Multimodality Action Quality Assessment
1:45 p.m.	Nima Abbasi Firoozjah	A General Computational Framework for Restoring Cellular-Resolution in Optical Coherence Tomography Images of the Eye
2:00 p.m.	Abdul Abbasi	Empowering Security Analysts: A User-Centric Approach to Explainable AI for Insider Threat Detection
2:15 p.m.	Nicholas Pellegrino	Improved Machine Learning Methods for Noisy and Hierarchical Data

For any questions, please reach out to Anna Cunningham, Academic Services Coordinator, Graduate Studies.

Grad Seminar: Oxidative damage of the bone collagen as a cause of reduced fracture resistance in human cortical bone

Amanda Brown — Tue, 25 Mar 2025 16:40:01 +0000

Grad Seminar: Oxidative damage of the bone collagen as a cause of reduced fracture resistance in human cortical bone Amanda Brown Tue, 03/25/2025 - 12:40

Abstract

Bone fragility and fracture remain a prominent issue in the populace especially for the older adult population with associated significant health, social and economic implications. The X-ray based clinical tools used to assess bone fracture risk only “see” the mineral and are unable to predict fracture risk accurately in certain individuals especially for those with type 2 diabetes (T2D) and chronic kidney diseases (CKD). This suggest that factors not measured by these X-ray based clinical tools may be important contributors to predicting bone fracture risk. One such factor is bone collagen which forms about 41% by volume of the bone tissue and has been shown to be vital to the fracture resistance of bone consequently an important determinant for bone fracture risk prediction. Ex vivo human bone studies have shown that the quality and integrity of the bone collagen network degrades with age, and this is associated with a reduction in the fracture resistance of cortical bone. However, the exact mechanics that lead to this degradation of quality and connectivity remains inconclusive.

Interestingly, elevated levels of oxidative stress has been implicated in the development and progression of osteoporosis, T2D and CKD, all bone affecting diseases. Oxidative stress is known to cause damage to macromolecules, referred to as oxidative damage, which includes long lived proteins such as collagen. Consequently, the overarching goal of this thesis was to investigate oxidative damage as a cause of collagen network quality and integrity degradation leading to reduced fracture resistance in cortical bone.
However, first, various methods were compared to determine the best way to conduct fracture resistance testing of cortical bone. It was determined that the most widely used approach resulted in errors in these tests. This highlighted a need for rigorous and standardized methods for cortical bone fracture resistance testing. Using results from the prior mentioned study, fracture resistance testing of ex vivo cortical bone specimens from a large heterogenous group of 81 donors with and without a history of T2D and/or CKD were performed. In addition, various biomarkers of oxidative damage alongside collagen network quality measures, cortical porosity as well as mineralization profiles were measured. From this, it was found that the biomarkers for oxidative damage correlated negatively with measures of crosslinking in the collagen network. Consequently, it was proposed that oxidative damage indirectly impacts collagen network integrity and thereby cortical bone’s fracture resistance by disrupting formation of crosslinks in the collagen network.
This work provides a better understanding of how oxidative stress may contribute to cortical bone fragility and loss of fracture resistance and this new knowledge could be critical towards the development of better means to detect, prevent and treat bone fragility.

Presenter

Daniel Dapaah, PhD candidate in Systems Design Engineering

Attending this seminar will count towards the graduate student seminar attendance milestone!

Rethinking Biomechanical Assessments of Orthopaedic Implants with Dr. Jonathan Kusins

Amanda Brown — Fri, 21 Mar 2025 15:46:13 +0000

Rethinking Biomechanical Assessments of Orthopaedic Implants with Dr. Jonathan Kusins Amanda Brown Fri, 03/21/2025 - 11:46

Join us for a special seminar on motion capture with Dr. Jonathan Kusins.

Dr. Jonathan Kusins is an Assistant Professor in Systems Design Engineering at the University of ��ݮ��Ƶ. His research integrates morphological, experimental, and computational modeling to improve musculoskeletal care. He earned his PhD from Western University, developing micro-CT imaging and digital volume correlation (DVC) techniques to study shoulder biomechanics. Jonathan has worked in Research and Development teams at NuVasive and Paragon 28, leading preclinical evaluation strategies to bring novel 3D-printed spinal interbody cages and foot and ankle orthopaedic devices from concept to market. Particularly, Jonathan is a strong advocate for the implementation of preclinical biomechanical assessments to provide evidence surrounding the safety and efficacy of medical devices prior to being placed in patients.

Abstract: Orthopaedic implants play a crucial role in restoring mobility and improving the quality of life for individuals with musculoskeletal conditions. However, a key to their long-term success depends on how well they interact with the body under mechanical loads. This presentation will explore biomechanical evaluation methods that integrate high-resolution micro-CT imaging with mechanical testing to improve our understanding of internal load distribution within human joints. Additionally, current research strategies, standardized testing protocols for orthopaedic implants, and potential future directions will be discussed.

Attending this seminar will count towards the graduate student seminar attendance milestone!

This seminar is sponsored by:

Grad Seminar: Transformer-based Point Cloud Processing and Analysis for LiDAR Remote Sensing

Sarah Landy — Fri, 28 Feb 2025 20:40:06 +0000

Grad Seminar: Transformer-based Point Cloud Processing and Analysis for LiDAR Remote Sensing Sarah Landy Fri, 02/28/2025 - 15:40

Abstract

The processing and analysis of Light Detection and Ranging (LiDAR) point cloud data, a fundamental task in Three-Dimensional (3D) computer vision, is essential for a wide range of remote sensing applications. However, the disorder, sparsity, and uneven spatial distribution of LiDAR point clouds pose significant challenges to effective and efficient processing. In recent years, Transformers have demonstrated notable advantages over traditional deep learning methods in computer vision, yet designing Transformer-based frameworks tailored to point clouds remains an underexplored topic. This thesis investigates the potential of Transformer models for accurate and efficient LiDAR point cloud processing.

Firstly, a 3D Global-Local (GLocal) Transformer Network (3DGTN) is introduced to capture both local and global context, thereby enhancing model accuracy for LiDAR data. This design not only ensures a comprehensive understanding of point cloud characteristics but also establishes a foundation for subsequent efficient Transformer frameworks.

Secondly, a fast point Transformer network with Dynamic Token Aggregation (DTA-Former) is proposed to improve model speed. By optimizing point sampling, grouping, and reconstruction, DTA-Former substantially reduces the time complexity of 3DGTN while retaining its strong accuracy.

Finally, to further reduce time and space complexity, a 3D Learnable Supertoken Transformer (3DLST) is presented. Building on DTA-Former, 3DLST employs a novel supertoken clustering strategy that lowers computational overhead and memory consumption, achieving state-of-the-art performance across multi-source LiDAR point cloud tasks in terms of both accuracy and efficiency.

These Transformer-based frameworks contribute to more robust and scalable LiDAR point cloud processing solutions, supporting diverse remote sensing applications such as urban planning, environmental monitoring, and autonomous navigation. By enabling efficient yet high-accuracy analysis of large-scale 3D data, this work fosters further research and innovation in LiDAR remote sensing.

Presenter

Dening Lu, PhD candidate in Systems Design Engineering

Join online

Seminar

Grad Seminar: Agent-based simulation to evaluate the impact of seismic retrofit promotion policies

Presenter

Attending this seminar will count towards the graduate student seminar attendance milestone!

Join on Teamshttps://teams.microsoft.com/l/meetup-join/19%3ameeting_YjQ1ZjljN2ItZTgzMC00NTJlLTllNjMtNjE5MTA2M2ZlOWNl%40thread.v2/0?context=%7b%22Tid%22%3a%22723a5a87-f39a-4a22-9247-3fc240c01396%22%2c%22Oid%22%3a%2258336da6-a40f-4126-bc7c-acbdf5d6610d%22%7d

Grad Seminar: Design and Evaluation of a Novel Framework Inspired by Affect Control Theory to Create Social Robot Affective Identities

Abstract

Presenter

Attending this seminar will count towards the graduate student seminar attendance milestone!

Join Zoom Meetinghttps://uwaterloo.zoom.us/j/99505929293?pwd=1rwYgNO6WfcIkwMvfAgmOlZHDOPKgi.1Meeting ID: 995 0592 9293Passcode: 107588

Grad Seminar: Active upper-limb prosthesis for swimming

Abstract

Presenter

Attending this seminar will count towards the graduate student seminar attendance milestone!

Join on Teams

Measuring neuromuscular transmission time variability in motor units

Join us for a special seminar with Dr. Armando Malanda Trigueros.

Attending this seminar will count towards the graduate student seminar attendance milestone!

This seminar is sponsored by

Grad Seminar: Towards Urban Digital Twins With Gaussian Splatting, Large-Language-Models, and Cloud Mapping Services

Abstract

Presenter

Attending this seminar will count towards the graduate student seminar attendance milestone!

Join on Teams

Grad Seminar: New Attack Detection Methods for Connected and Automated Vehicles

Abstract

Presenter

Attending this seminar will count towards the graduate student seminar attendance milestone!

Join on Teams

SYDE Graduate Symposium 2025

Symposium Schedule

Register for the Symposium by April 3

Grad Seminar: Oxidative damage of the bone collagen as a cause of reduced fracture resistance in human cortical bone

Abstract

Presenter

Attending this seminar will count towards the graduate student seminar attendance milestone!

Rethinking Biomechanical Assessments of Orthopaedic Implants with Dr. Jonathan Kusins

Attending this seminar will count towards the graduate student seminar attendance milestone!

This seminar is sponsored by:

Grad Seminar: Transformer-based Point Cloud Processing and Analysis for LiDAR Remote Sensing

Abstract

Presenter

Attending this seminar will count towards the graduate student seminar attendance milestone!

Join on Teams
https://teams.microsoft.com/l/meetup-join/19%3ameeting_YjQ1ZjljN2ItZTgzMC00NTJlLTllNjMtNjE5MTA2M2ZlOWNl%40thread.v2/0?context=%7b%22Tid%22%3a%22723a5a87-f39a-4a22-9247-3fc240c01396%22%2c%22Oid%22%3a%2258336da6-a40f-4126-bc7c-acbdf5d6610d%22%7d

Join Zoom Meeting
https://uwaterloo.zoom.us/j/99505929293?pwd=1rwYgNO6WfcIkwMvfAgmOlZHDOPKgi.1

Meeting ID: 995 0592 9293
Passcode: 107588