Abstract
An equalization scheme employing convolutional neural networks (CNN) is proposed in generalized frequency division multiplexing (GFDM) for propagation in a hybrid microwave-optical system. Batch Gradient Descent is used to train the CNN equalizer quickly. The approach suggested eliminates nonlinearity and produces improved performance. By incorporating the GFDM network with successive interference cancellation (SIC)-based receiver, this solution greatly increases the storage ability of consumers and also offers a larger coverage range. The suggested CNN equalizer is correlated with other approaches, including statistical models and estimator techniques. The experimental finding shows that CNN produces the highest value that is marginally better than the other equalizers with a numerical difficulty reduced to zero. The simulation findings suggest that QAM-GFDM can attain the same bit error rate (BER) as cyclic-prefix (CP) OFDM without compromising spectrum economy. The tests obtained have shown that the new approach works much better than traditional techniques.
DISCLOSURE STATEMENT
No potential conflict of interest was reported by the author(s).
Additional information
Notes on contributors
![](/cms/asset/b390701d-cb55-4717-a239-adc8f2eb9666/tijr_a_2163930_ilg0001.gif)
Asish B. Mathews
Asish B Mathews is currently pursuing his doctoral studies in the Department of Electronics and Communication Engineering in Noorul Islam Centre for Higher Education, Tamil Nadu, India. He has been working as an assistant professor in the Department of Electronics and Communication Engineering at St Thomas College of Engineering Chengannur. He received his BTech in electronics and communication engineering from the University of Kerala, India (2006) and MTech in microwave and TV (Dept of ECE) from the College of Engineering, Trivandrum, India (2009). His areas of research include modeling microwave photonic links, wireless communication systems, optical communication networks, optoelectronic devices, and solid-state electronics. Corresponding author: E-mail: [email protected]
![](/cms/asset/bb6e96c7-4cf5-4270-b4d4-09d36dd019df/tijr_a_2163930_ilg0002.gif)
Arun B. Mathews
Arun B Mathews has done his doctoral studies in the Department of Computer Science at Noorul Islam Centre for Higher Education, Kanyakumari, Tamil Nadu, India. He received an MSc in computer science from the University of Calicut and doing postoral doctoral work at Srinivas University, Mangalore, Karnataka, India. He has 17 years of experience in teaching and research. He has published several articles in SCI, Scopus, and UGC-indexed journals. He has attended and presented papers in seminars at the national and international levels including IEEE conferences. He has attended faculty development programs and short-term courses. His area of research includes image processing. E-mail: [email protected]
![](/cms/asset/113b0e16-bda4-43c0-b11a-3732bd761765/tijr_a_2163930_ilg0003.gif)
C. Agees Kumar
C Agees Kumar received the BE in electronics and instrumentation engineering from National Engineering College, Kovilpatti, India, and ME in process control and instrumentation from Annamalai University, Chidambaram, India, and the PhD degree from the Faculty of Electrical and Electronics Engineering, Anna University, Chennai. He is currently a professor with the Department of EEE, Arunachala College of Engineering for Women, Vellichanthai, India. His current research interests include multiobjective optimization, power electronics, electrical drives, and soft computing. E-mail: [email protected]