Date of Award
Electrical and Computer Engineering
College of Engineering and Computer Sciences
Type of Degree
Dr. Wook-Sung Yoo, Committee Chairperson
Dr. Imtiaz Ahmed
Dr. Pingping Zhu
Dr. Ramesh Annavajjala
Physical layer (PHY) design in the wireless communication field realizes gratifying achievements in the past few decades, especially in the emerging cellular communication systems starting from the first generation to the fifth generation (5G). With the gradual increase in technical requirements of large data processing and end-to-end system optimization, introducing artificial intelligence (AI) in PHY design has cautiously become a trend. A deep neural network (DNN), one of the population techniques of AI, enables the utilization of its ‘learnable’ feature to handle big data and establish a global system model. In this thesis, we exploited this characteristic of DNN as powerful assistance to implement two receiver designs in two different use-cases. We considered a DNN-based joint baseband demodulator and channel decoder (DeModCoder), and a DNN-based joint equalizer, baseband demodulator, and channel decoder (DeTecModCoder) in two single operational blocks, respectively. The multi-label classification (MLC) scheme was equipped to the output of conducted DNN model and hence yielded lower computational complexity than the multiple output classification (MOC) manner. The functional DNN model can be trained offline over a wide range of SNR values under different types of noises, channel fading, etc., and deployed in the real-time application; therefore, the demands of estimation of noise variance and statistical information of underlying noise can be avoided. The simulation performances indicated that compared to the corresponding conventional receiver signal processing schemes, the proposed AI-aided receiver designs have achieved the same bit error rate (BER) with around 3 dB lower SNR.
Mobile communication systems.
Wireless communication systems.
Cell phone systems -- Standards.
Xu, Wenjie, "Artificial Intelligence Aided Receiver Design for Wireless Communication Systems" (2021). Theses, Dissertations and Capstones. 1376.