Internet of things (IoT) includes of multitude of sensors from a wide variety of applications. These sensors produce high volume and high velocity data. Recently there has been much interest in application of such technologies to improve agricultural practices. The sensors that are installed in the field transmit real time data regarding numerous environmental variables of interest. This data is then used to forecast a future state and to make a well informed business/operation decision according to an expected future state.

The implementation of data structures usually requires checking for certain mathematical properties such as equality. Those properties are usually implemented in methods that reason about the objects stored in these data structures. However, the implementation of such methods is fairly complex, and may exhibit software bugs that may not necessarily lead to program crashes. Therefore, it is often hard to reproduce such bugs.

The goal of the project is to evaluate several clustering algorithms on players’ styles data in the context of Video
Lottery Terminals (VLTs). The previous work has shown that by segmenting anonymous player data by
sessions, and then clustering the sessions using the simple k-means algorithm, we can get a descriptive
statistic on player styles, including problem gambling behavior, recreational player styles, and similar. An open
question is whether the preprocessing techniques were optimal for this purpose and whether the k-means
algorithm is the most appropriate algorithm.

Robust perception in all weather conditions is a critical requirement for autonomous vehicles. This project proposes fusing gated and conventional RGB camera images for robust scenes encoding, depth estimation and trajectory prediction. Conventional approaches using lidar and RGB camera fail to perform robustly in rain, fog and snow. By extending existing computer vision algorithms to Gated-RGB camera pair the fusion algorithms developed will utilize features that are robust in one sensor modality but not the other.

Artificial Intelligence (AI) research has grown rapidly in recent years as the result of faster computers and better algorithms. AI models can be trained to automate the decision process and provide results. However, if the model is not properly or sufficiently trained, the outcome will likely be unpredictable and inaccurate. Besides, training data is not easily available in a lot of applications. To address these issues, our strategy is to integrate classical Computer Vision (CV) algorithms and Deep Learning (DL) techniques. CV can provide solutions without training data.

Vibration analysis is probably the most widely used technique to perform health monitoring of mechanical machinery. Specifically, we are interested in monitoring ‘Vibrating screens’, machines that are for example used by the mining industry to sort aggregate by size. Over the last 10 years the research group of Dr. v. Mohrenschildt has developed hardware, software and theory to accomplish this. The goal is to further the understanding of feature extraction and classification to perform effective predictive maintenance.

Machine learning (ML) has recently achieved impressive success in many applications. As ML starts to penetrate into safety-critical domains, security/robustness concerns on ML systems have received lots of attention lately. Very surprisingly, recent work has shown that current ML models are vulnerable to adversarial attacks, e.g. by perturbing the input slightly ML models can be manipulated to output completely unexpected results. Many attack and defence algorithms have been developed in the field under the convenient but questionable Lp attack model.

Machine learning algorithms are being used in a wide range of applications. It is a branch of computer science where the system can learn from the data and make decisions. Financial fraud is an increasing hazard in the financial industry, and it is important to detect a fraudulent transaction. Machine learning algorithms can be used to decide whether the transaction is fraud or not. After the system makes its prediction, it is important for users to understand the reason behind the prediction in such cases.

BlueNode is a SaaS company focused on the sanitation and analysis of marine shipping data. The research project is focused on increasing the precision and accuracy of shipped goods processed through Canadian ports. Should the research prove the be successful, the technical methods used with be directly incorporated into the BlueNode system.

The project investigates how collaborative tasks can be enhanced in AR environments. The intern will develop three approaches to present shared information in a co-located AR setting and conduct usability studies comparing these approaches.