ECE Research Component of PhD Qualifier Exam By: Todd Morehouse
When: Monday,
May 3, 2021
10:00 AM
-
12:00 PM
Where: > See description for location
Cost: Free
Description: Topic: Adaptive Automatic Demodulation of Wireless Communication Signals Using Deep Learning
Zoom Teleconference: https://umassd.zoom.us/j/91747855380
Meeting ID: 917 4785 5380
Abstract:
In wireless communication systems, a received signal is corrupted by various means such as noise, multi-path fading, and defects in hardware. To properly demodulate the signal and obtain the original information, complex schemes are employed. This usually consists of a series of filtering, phase and frequency correction, signal timing recovery, and finally demodulation. Furthermore, the approaches often differ between modulation types. This not only makes systems complex, but also inflexible, not allowing a single system to demodulate multiple modulation types. Intelligent radio, the mix of software defined radio and machine learning, has enabled automatic demodulators using machine learning alone. However, these systems still focus on individual scenarios, such as cases where only one modulation type is handled. With the growing intelligence of radios, the number of devices in a spectrum, and more advanced spectrum sharing techniques, channels become increasingly unknown. It is important for these systems to be able to handle a diverse environment, making them better for generalized use.
In this research, an automatic deep learning (DL) based demodulator capable of handling multiple modulation types was explored. A convolutional neural network is used to perform feature extraction and classification. This research shows the feasibility of automatic and blind demodulation, where the modulation type of the signal is unknown to the demodulator.
NOTE: All ECE Graduate Students are ENCOURAGED to join the zoom teleconference. All interested parties are invited to join.
Advisor: Dr. Ruolin Zhou
Committee Members: Dr. Hong Liu, Dr. Honggang Wang, and Dr. Liudong Xing, Department of Electrical & Computer Engineering, University of Massachusetts Dartmouth
*For further information, please contact Dr. Ruolin Zhou via email at rzhou1@umassd.edu.
Zoom Teleconference: https://umassd.zoom.us/j/91747855380
Meeting ID: 917 4785 5380
Abstract:
In wireless communication systems, a received signal is corrupted by various means such as noise, multi-path fading, and defects in hardware. To properly demodulate the signal and obtain the original information, complex schemes are employed. This usually consists of a series of filtering, phase and frequency correction, signal timing recovery, and finally demodulation. Furthermore, the approaches often differ between modulation types. This not only makes systems complex, but also inflexible, not allowing a single system to demodulate multiple modulation types. Intelligent radio, the mix of software defined radio and machine learning, has enabled automatic demodulators using machine learning alone. However, these systems still focus on individual scenarios, such as cases where only one modulation type is handled. With the growing intelligence of radios, the number of devices in a spectrum, and more advanced spectrum sharing techniques, channels become increasingly unknown. It is important for these systems to be able to handle a diverse environment, making them better for generalized use.
In this research, an automatic deep learning (DL) based demodulator capable of handling multiple modulation types was explored. A convolutional neural network is used to perform feature extraction and classification. This research shows the feasibility of automatic and blind demodulation, where the modulation type of the signal is unknown to the demodulator.
NOTE: All ECE Graduate Students are ENCOURAGED to join the zoom teleconference. All interested parties are invited to join.
Advisor: Dr. Ruolin Zhou
Committee Members: Dr. Hong Liu, Dr. Honggang Wang, and Dr. Liudong Xing, Department of Electrical & Computer Engineering, University of Massachusetts Dartmouth
*For further information, please contact Dr. Ruolin Zhou via email at rzhou1@umassd.edu.
Contact: > See Description for contact information
Topical Areas: General Public, University Community, College of Engineering, Electrical and Computer Engineering