University Events

Description: Topic: High Clutter, Close Range, Wi-Fi Imaging and Probabilistic, Learning Classifier

Location: Lester W. Cory Conference Room, Science & Engineering Building (SENG), Room 213A

Abstract:
This proposal plans on using Wi-Fi signal processing and neural networks to identify static and moving objects in a room, which involves many challenges such as very close range, high clutter, running real-time, classifying rough images, and many other problems to be encountered. Radar usually involves distant targets, but creating and identifying images indoors at close range with only Wi-Fi signals is a whole other world of processing. In the past few years, people have worked on using Wi-Fi for identifying actions, but this proposal plans on using Wi-Fi on static (non-moving) and moving objects. The images created will be barely identifiable due to the low resolution of Wi-Fi, but the images need to be classified (identified). Classifying the resultant images will be a challenge and requires some form of Artificial Intelligence (AI).

There are two major portions to this proposal. The first is the signal processing portion, where images are created, and the second is the image classification portion, using AI neural networks.
In the signal processing portion, images will be created by using Wi-Fi signals transmitted and received on Ettus Universal Software Radio Peripheral (USRP) hardware and directional antennas. This situation is unlike typical radar, which has the luxury of transmitting then listening due to large distances to targets. Further, GNU Radio, the interface to USRp's, will allow the proposer to develop new algorithms. The proposer has become a near expert in GNU Radio development.

In the image classification phase, the images created will be very blob-like with different reflective intensities. These are not your typical images for a classifier. These images need some form of intelligence to classify them, and the system needs to improve its classification over time. AI neural networks will be employed and developed to work on the images such as developing weights and new algorithms to improve classification..

NOTE: All ECE Graduate Students are ENCOURAGED to attend.
All interested parties are invited to attend. Open to the public.

Advsior: Dr. Honggang Wang
Committee Members: Dr. Dayalan P. Kasilingam and Dr. Liudong Xing, Department of Electrical & Computer Engineering; Dr. Shaoen Wu, Department of Computer Science, Ball State University

*For further information, please contact Dr. Honggang Wang at 508.999.8469, or via email at hwang1@umassd.edu.