[Topics for Fall 2022] 

Multi-Sensor Data Fusion for Internet of Things Applications

Instructor:

Diliang Chen, Ph.D.

Office: Kingsbury W207

E-mail: diliang.chen@unh.edu

Office hour: Scheduled on request. Please send me an email to schedule office hour.

Course Description:

Multi-sensor data fusion is a technique of combining and integrating of data from multiple sensors to provide a more accurate and reliable view of data. This course aims to provide both insight understanding of theories and hands-on experiences related to multi-sensor data fusion. Lectures will provide a comprehensive introduction to effective sensor and data fusion methods that improve the probability of object tracking, target detection, classification, and identification. Hands-on projects will enhance the understanding and the application of each data fusion methods.

Credits: 3

Topics Covered:

• Introduction on estimation theories and sensor fusion
• Sensor and data fusion architectures
• Kalman Filter (Linear, Extended, Unscented)
• Bayesian Networks
• Particle filter
• Convolutional Neural Networks

Learning Outcomes:

After taking this course, you will be able to:

• Understand the advantages of multi-sensor data fusion for object tracking and state estimation
• Understand the architectures for sensor fusion
• Be familiar with the processes of Multi-sensor data fusion
• Identify suitable multi-sensor data fusion algorithms for practical applications
• Implement different multi-sensor data fusion algorithms with MATLAB