Projets novateurs réalisés

Anomaly detection using AI/ML for Network Correction

Anomaly detection or outlier detection is a technique to identify rare items, observations or events which are differing significantly from most of the data or do not conform to the expected behavior of the system. Typically, anomalous data cause numerous problems in the computer networking and communication system. This project aims to develop an advanced anomaly detection algorithm by utilizing state-of-the-art machine learning and artificial intelligence techniques and combining it with existing anomaly detection techniques. We propose to develop a unique deep learning methodology based on the Modified Support Vector Machine (MSVM) and the Bi-directional Long Short-Term Memory Recurrent Neural Networks (BLSTM RNN) approaches. We will test and evaluate the solution with respect to the accuracy, miscalculation rate, precision, true positive rate and F1 score

AI-Blockchain integration to ensure explainability, accountability, traceability and reproducibility (EATR) in mission critical systems

This project is an effort to integrate two of the emerging technologies of our time, i.e., Artificial Intelligence and Blockchain. The purpose of this integration is to overcome the drawbacks of individual technologies and work in coherence for mutual benefits. Most of the current AI systems currently deployed are black boxes and they do not provide explanations of suggested decisions. With the integration of blockchain with AI, it is possible to create a transparent AI system with trail of data processing to address the ‘Why?’ question. Moreover, in the era of Internet of things, enforcement of GDPR and 5G in sight, it is compulsory for organizations to ensure the data and identity protection of the processes and people utilizing them. The objective of this research is to develop a logic model that complies with the privacy requirements as well as being explainable in its suggested course of action. The possible applications of such systems are in financial and IT compliance/ responsibilities/penalties insurance, governance and security. To that end, a system can be designed integration AI and blockchain technologies to continuously monitor different processes and ensure that all the functionalities are in place and working properly.

Ensemble-based Dimensionality Reduction Model for Wireless Time-Series

The new wireless network technology will provide users with a higher communication quality. However, we will face two critical problems: the wireless traffic will increase considerably, and the wireless signals will contain noise. The Wifi signals are represented as time series, but processing and removing noise from such huge-volume, high-dimensional and complex data pose great challenges. Learning from time-series is an ambitious problem, and the curse of dimensionality makes machine learning algorithms incompetent.

Dimensionality Reduction Algorithms (DRAs) can effectively address the problems above. Still, the DRA application to time series has been limited due to data complexity. We will first examine the characteristics of the wireless data and investigate which DRAs are the most suited. Next, we will define strategies to combine DRAs, a challenging task but significant to improve the DRA accuracy. By conducting an empirical analysis, we will develop the ensemble DRA that best maximizes the network performance.

Crowdsensing-based Wireless Indoor Localization using an Innovative AI & ML Algorithm

Smartphone based indoor navigation services are desperately needed in an indoor GPS-denied environment, such as in Combat-zone Surveillance, Health Monitoring, Fire Detection, etc. The Receive Signal Strength (RSS) based algorithms are commonly used in indoor localization, which rely on the WiFi fingerprint data built by the Mobile Crowdsensing approach. Conventional statistical and probability techniques are used to deal with crowdsensing-based RRS fingerprinting information, but there are some issues such as low localization accuracy, highly relevance to the device/software they used, large database required, unfriendly to new encountered smartphone, etc. The proposed project will develop a novel integrated approach that combines AI technology (e.g., Artificial Neural Networks) and ML methods (e.g., Feed-forward Multilayer Perceptron Regressor and Support Vector Machine) to solve aforementioned problems, as well as build a crowdsensing-based RRS Wi-Fi fingerprinting dataset in a university building in Regina, SK Canada for indoor positioning studies

Extension of feature selection with a ML algorithm for wireless network traffic prediction

The release of 5G network in near future will provide reliable connectivity, higher throughput, better service quality, and more efficient signaling. The network traffic load will continuously rise with more and more mobile users using the internet services. There is a need to forecast wireless network traffic load to manage network resources efficiently and provide better quality of service. This network traffic dataset is complex and nonlinear in nature that contains large number of variables. The proposed research will combine the feature selection techniques with an advanced machine learning (ML) method to handle this network traffic dataset, which employing 4 feature selection techniques to extremely reduce the data size with keeping significant features in the dataset, and further result in the increasing of the prediction accuracy for the ML model. The feature selection aids in better prediction accuracy of machine learning algorithm on wireless network traffic with overall interpretability of the prediction model.

A Realistic Machine Learning-based Model for Failure Prediction and Propagation in Smart Grid Networks

Cyber-Physical Systems (CPS) combine communication and information technology functions to the physical components of a system for purposes of monitoring, controlling, and automation. The power grid is becoming one of the largest CPS, where grid components are controlled based on the synergies in the cyberspace. CPS hold a great promise to improve the efficiency and productivity of numerous sectors in Canada and around the world. However, cyber-security is a major concern in CPS including the smart grid where an intrusion in one part of the system can cause a failure in the entire network if not detected and dealt with in a timely fashion. The main objective of this research project is to develop a realistic model to enable the implementation of machine learning-based algorithms to detect cyber-attacks in a smart grid environment.

Secure blockchain technologies

In the recent years, blockchain technologies have shown promise as infrastructure for decentralized trustless anonymous digital asset exchange. The technology promises to transform how the data is shared in many areas including financial sector, insurance and gaming industries. Yet several obstacles prevent mainstream adoption of this technology – one of these challenges is security. To facilitate trustworthy data collection, and management in blockchain, ensuring secure communication is essential.
The blockchain’s underlying cryptographic theory makes it difficult for an adversary to modify the data provenance. Yet, the technology is not immune to unauthorized access, modifications, and repudiation of origin. This research aims to address these security problems and develop methodologies to predict, track and analyze suspicious users, their behaviour, and corresponding threats in blockchain.

Incorporation de produits alimentaires intermédiaires d’algues dans le yogourt : Impact sur les propriétés fonctionnelles, sensorielles, sur la qualité nutritionnelle et sur la conservation

Les algues sont considérées comme un aliment à haute valeur nutritive. Cependant, la consommation de ces dernières en tant qu’aliments est peu répandue dans les pays occidentaux. Une manière d’augmenter l’apport en algues serait de les incorporer dans des produits traditionnels. Pour ce faire, il est possible de préparer des produits alimentaires intermédiaires (PAI) d’algues sous forme de farines ou de flocons, qui seront livrés à d’autres entreprises alimentaires pour la préparation des produits finis enrichis en algues. Cependant, peu d’études ont été consacrées à mesurer l’effet de l’ajout d’algues sur les propriétés des yogourts. La stagiaire évaluera l’impact de l’incorporation d’algues du Québec dans le yogourt sur ses propriétés fonctionnelles, sensorielles, sur sa qualité nutritionnelle et sa conservation. Ces travaux permettront à l’organisme partenaire de guider des producteurs et transformateurs d’algues dans la diversification de leurs activités.

Design of porous hydrogels for biomedical applications

Biocompatible hydrogels have been used for a long time in biomedical applications (e.g. microcarriers for adherent cell growth; drug delivery vehicles). For these applications, controlled pore size and pore interconnectivity are important parameters. The project aims at better characterizing several physicochemical strategies for pore generation. Then, as second objective, the influence of pore size upon cell growth/survival or drug delivery will be studied.

Affordability Dashboard – Vancouver

The VEC, under its Economic Transformation Lab and in partnership with SFU and MITACS, seeks to research, design, and publish an affordability dashboard that consolidates all important metrics/statistics on affordability, relevant to Vancouver businesses and talent. The Dashboard will not only focus on affordability of office, retail, and industrial space, as well as other pertinent business operation affordability metrics, but will also contain affordability metrics that inform businesses of the cost of living for their talent. The dashboard will also include benchmarking against other ‘peer’ cities; the comparison cities will be identified through similarities in city population, brand, GDP, etc. The intent behind this dashboard is to make all of the metrics available in one place to help inform businesses and talent of current affordability conditions.

Materialized View Performance at Massive Scale for Data Analytics Workloads

View materialization in relational database systems helps in improving the performance of
querying the stored data. With the emergence of large scale data analytics, there are several
challenges that need to be considered for robust view management. In this project, we study
the performance of materialized views at large scale, when there are thousands of users
creating tens of thousands of views. Further, the challenges that emerge from new
computing paradigms like cloud computing wi ll also be investigated

Controlling Flow-Induced Vibrations with Novel 3D-Printed Devices

Continuous flexible systems such as aircraft wings, pipelines, risers, bridges, power towers, and transmission lines are always subjected to unwanted vibrations induced by unsteady wind loading. The typical engineering solution is to add a tuned-mass
damper to these structures. This typically works in removing the unwanted resonance, but it creates new problems as it adds two new natural frequencies. Here, we seek to develop a new class of dampers without a natural frequency, making them useful at damping vibrations over a broad spectrum of frequencies.