Electrical and Computer Engineering, Department of
The Department of Electrical and Computer Engineering prides itself on the excellence of both teaching and research, as well as the strong connection that we have with its students.
This community includes research outputs produced by faculty and students. Submitting works to QSpace may enable compliance with the Tri-Agency Open Access Policy on Publications.
When you submit your work to QSpace, you retain copyright and grant the Library a non-exclusive license to distribute and preserve. Works are open access unless restricted by the creator.
Collections in this community
Recent Submissions
-
Toward Self-Supervised and Privacy-Preserving Remote Heart Rate Estimation from Facial Videos
Remote heart rate (HR) estimation has become increasingly feasible through advances in deep learning in recent years. A popular approach for this purpose is remote photoplethysmography (rPPG) which aims to measure the ... -
Empirical Studies on Energy Consumption Issues Based on Stack Overflow and Google Chrome Extensions
The advancement of technology has driven a rise in energy consumption, while energy-related issues prospectively influence every avenue in the software life cycle from design and implementation to maintenance. To conserve ... -
In-Distribution and Out-of-Distribution Self-Supervised ECG Representation Learning For Arrhythmia Detection
This thesis presents a systematic investigation into the effectiveness of self-supervised learning (SSL) methods for electrocardiogram (ECG) arrhythmia detection. We begin by conducting a novel distribution analysis on ... -
Novel Allreduce Algorithms for Distributed Deep Learning
To solve the most computationally challenging problems, scientists and engineers use HPC clusters. These massive-scale systems comprise thousands of servers, each containing multiple GPUs and CPUs, tied together with a web ... -
Enabling High-Precision 5G mmWave-Based Positioning for Autonomous Vehicles in Dense Urban Environments
Autonomous vehicles (AVs) have the potential to transform the transportation industry by altering conventional modes of travel, enhancing road safety measures, and mitigating traffic congestion and greenhouse gas emissions. ... -
Automatic Depression Assessment using Deep Learning Techniques
Early recognition and treatment of depression can avert escalation of the mental disorder and alleviate suffering for the patients and their families. To assist mental health care providers with the early recognition and ... -
5G mmWave Integrated Positioning for Autonomous Vehicles in Urban Environments
Autonomous vehicles (AVs) have the potential to revolutionize the transportation industry. Yet, achieving higher levels of autonomy requires a positioning solution that is accurate, reliable, and independent of the ... -
Modeling the Phase Response of an Optical Filter with Application to Cascaded Filtering in an Optical Link
To accurately characterize the effects of optical filters, it is crucial to model the filter's frequency response as precisely as possible. Given that the amplitude response of an optical filter can be obtained through ... -
Developing Informative and Faithful Image Captioning Systems with Compositional Generalizability
Image captioning systems aim to generate visually grounded descriptions for given images. It has been an active multimodal research problem in artificial intelligence---humans are able to understand the content of images ... -
Pedestrian Data Generation Through Simulation, Diffusion, and Conditional Image Synthesis
Simulated data has been proposed as a solution to the costly process of creating large datasets that deep learning models require through simulation platforms such as CARLA. However, creating a dataset synthetically ... -
Privacy Preservation and Verifiability for Federated Learning
Federated learning is a distributed machine learning framework to address the bottleneck of traditional machine learning on data collection and privacy leakage, which allows training a learning model using distributedly ... -
Kinesthetic Haptic Actuators: A Comparative Study of Motor Technology
This thesis evaluates a BLDC motor for use as a direct drive haptic actuator. This is done by a comparison of the performance and specifications of a direct drive BLDC motor with those a of the actuator used in a common ... -
Force-Myography Based Estimation of Energy Absorption Capabilities of the Human Arm for Robotic Tele-Rehabilitation Therapy
The need for rehabilitation therapy has been significantly increasing in the last few decades, due to neurological disorders caused by stroke. The cost of therapy for such a wide variety of motor impairments is high and ... -
EEG-based Brain Computer Interface with Deep Learning
Electroencephalogram (EEG)-based Brain Computer Interfaces (BCI) are very important and have been widely used in multiple application domains, ranging from human-computer interaction to medical and biomedical applications. ... -
Green Federated Learning over Wireless Networks
Motivated by ever-increasing computational resources at edge devices and increasing privacy concerns, a new machine learning framework called Federated Learning (FL) has been proposed. FL enables user devices, such as ... -
Deep Representation Learning for Speaker Recognition
Automated SR solutions are often used in smart devices that are capable of recording audio for authentication purposes or to personalize the services provided by these devices towards each user. Over that past few years, ... -
Neuro-Symbolic Methods for Natural Language Inference and Question Answering
One of the fundamental problems in deep learning research is how to design neural network models to incorporate logic and symbolic operations. Although deep neural network models have achieved state-of-the-art performance ... -
Learning to Reason over Natural Language via Accessing Diverse Knowledge Resources
Reasoning is the capability of drawing new conclusions from existing information or knowledge, and it has been a central topic in artificial intelligence. Developing intelligent systems that are capable of understanding ... -
Privacy and Regulatory Compliance for Central Bank Digital Currency
Digital payment is becoming increasingly popular, especially in the context of the rapid decline in cash transactions due to the COVID-19 pandemic. Some mobile payment methods, which are also known as mobile wallets such ... -
The Effect of Biased Training Regimes on the Calibration of Deep Neural Networks
Deep learning has advanced significantly in the past decade. Being well-calibrated remains a key property that a model must possess for safe and practical deployment in many high-stakes domains. The confidence of a model's ...
RSS 1.0