Detection of Human Presence/Activity through Radio Frequency Signals with Artificial Intelligence

The goal of this porject is to develop a prototype system for human presence/activity detection through radio frequency signals. There have een some recent promising results reported in the literature regarding such detections through WiFi signals using artificial intelligence-based approaches. The postdoc will focus on reproducing earlier results, then move on to enhance the system to detect some human activities of interest. The partner company would like to design, build and commercialize a line of products based on the developed prototype.

Investigating Machine Learning Techniques in Performance Improvement for the Next Generation Wireless Networks

The new generation 5G wireless networks will have a huge impact on the society due to the high bandwidth and capacities they provide. The traffic volume is expected to grow significantly and new varieties of applications, e.g., Internet of Things and vehicular networking, are anticipated. As a result, effective management of the new networks will become much more complicated and challenging. Machine learning techniques have made unprecedented progress in recent years, as they are highly efficient for data-driven applications.

A low-power remote IoT device to sense ultrasonic signals for multiple channel system

In the end of this project, the proposed design will be published in two peer-reviewed journals. Also, the measure the data will be saved and analyzed in the UW-STREAM lab. After the analysis, the data converter speed, the channel selection capability and also the power consumption will be summarized and reported. From those data, both the partner and we can make a commercialized strategy. The desired applications and also the way to integrate the proposed design with the current product can be decided.

Autonomous next generation wireless communication network optimization

Since the mid 1980s, moving access points, such as Wi-Fi, closer to network devices has been the largest contributer to improved data rates and this trend continues, but its scope is more difficult for rural internet service providers. The second technique is from the choice of the assigned spectrum and how this choice relates to other techniques to improve data rates. The third technique is from a combination of advanced signal processing techniques, involving antennas, beamforming, the allocation of available bandwidth and sampling the radio channels.

Quality Assurance and Safety Tools for Emerging Drone Technologies

Drone Delivery Canada (DDC) designs and operates high performance Remotely Piloted Aerial Systems (RPAS) to deliver payloads between depots and warehouses. Safety and quality assurance (QA) play an integral role in assuring that drone technology is accepted by the public, consumers, and the Canadian government. The demand for more advanced testing on both the drone hardware and software must be thoroughly carried out to achieve such acceptance. The proposed research project focuses on meeting this demand by investigating both the physical safety and control system quality of the drone.

Similarity detection on female pelvic anatomy imaging data usingMachine Learning methods and develop a first version of a measuringdevice prototype

Pelvic Organ Prolapse (POP) is a condition 1 in every 10 women is diagnosed with. The current non-surgical treatment for POP is an intravaginal device called pessary which has a 40% failure rate as its shape is not fitted to the female anatomy. Poor pessary design and performance arises from the limited data that is studied on the pelvic anatomy. The current research project will study available imaging data using Machine Learning algorithms to facilitate and automate the process for assessing and treating POP.

Multi-chip Integration of Lasers and Silicon Photonics

In the era of big data, internet of things and cloud computing, the ever-increasing demand for bandwidth density causes a bottleneck in inter and intra-datacenter communication systems. Optical integrated circuits based on the silicon-on-insulator platform is a well-known solution to overcome the bottleneck in data rate transmission. It is an interesting platform as it can be fabricated through existing CMOS technologies and the high index-contrast between core and cladding helps realize compact, and low loss structures.

Understanding and designing the female pelvic anatomy, a measuring device and an intravaginal device using 3-dimensional modeling techniques and Artificial Intelligence

Pelvic Organ Prolapse (POP) is a condition 1 in every 10 women is diagnosed with. The current non-surgical treatment for POP is an intravaginal device called pessary which has a 40% failure rate as its shape is not fitted to the female anatomy. Poor pessary design and performance arises from the limited data that is studied on the pelvic anatomy. The current research project will study available imaging data using Machine Learning algorithms to facilitate and automate the process for assessing and treating POP.

Traffic Estimation and Stable Resource Allocation Using Distributed Machine Learning

The proposed research will develop novel distributed machine learning techniques for stable resource allocation and improving traffic estimation in networks. It is a well-known fact that networks are becoming complex and user demand is growing in many directions including the traditional demand for capacity and less delay, as well as improvements in Quality of Experience (QoE). Backhauling the multiplexed demand over the core networks calls for accurate traffic estimation. On the other hand, control of the resource allocation, based on such predictions, needs stable and robust solutions.

Countermeasures for Hardening Embedded Security

The impact of attacks on Internet of Things (IoT) embedded devices range from threatening lives, such as attacks on wearable/implantable health devices, to threatening infrastructures in financial, transportation, and other sectors. In the IoT realm, hardware is distributed and embedded in our environment and must be hardened against malicious intentional and unintentional attack. Despite advances in hardening software systems using security fixes, attacks on embedded hardware remain feasible with few known defenses.

Pages