Subventions et des contributions :

Subvention ou bourse octroyée s'appliquant à plus d'un exercice financier. (2017-2018 à 2022-2023)

The field of digital signal processing (DSP) has experienced explosive growth during the past couple of decades. The DSP techniques have become integral parts of the products and services that we need or encounter in our daily lives. The research efforts of the applicant in this area during the past five years have led to some very concrete results that have been shared with the international scientific community, both from academia and industry, and have given rise to new ideas and directions that need to be further investigated. The overall objective of the proposed research program is to develop efficient algorithms and architectures and to lay sound mathematical foundations for reliable processing of image, video and biomedical signals, and cost-effective implementation for communication and biomedical applications. For half a decade now, the growth in the internet of things (IoT) and the demand for machine-to-machine connections have been staggering. By 2020, the global IP networks will have to support more than 50 billion devices. In order to establish a reliable and smooth communication among such a large number of devices connected to IoT, while still maintaining efficient and sustainable power consumption, the development of versatile, smart, fast, and real-time direction of arrival (DOA) estimation algorithms is of paramount importance. Deep learning has opened up the limitless possibilities in understanding and recognition of images. Image understanding and analysis is inherently a big data problem. Hence, the use of advanced deep learning concepts can produce meaningful results in image understanding and visual tracking, which play an important role in a wide range of real-life applications such as detection and recognition, human behavior analysis, video indexing and retrieval, medical imaging, and traffic management of smart cities. Alzheimer’s disease is the most common type of dementia affecting elderly people worldwide. There is no cure for this disease, and the disease worsens as it progresses. Early detection is a key to preventing, slowing and stopping Alzheimer’s disease. Around-the-clock observation of patients is expensive, inconvenient, and in some cases, simply impossible. The technology of body area networks proposes a convenient and useful solution that promises to provide physicians access to the patient’s physiological data anytime and anywhere. Application of compressed sensing and statistical learning of biomedical signals can make this technology affordable. This research in the immediate future is aimed at investigating these problems and seeking their solutions by developing efficient DSP algorithms and architectures. The direct beneficiary of this research will be Canadian telecommunication and biomedical industry. This proposal will also contribute to Canadian industry and academia by enabling the training of a number of skilled personnel.