Vinayakumar Ravi

Work place: Center for Artificial Intelligence, Prince Mohammad Bin Fahd University, Khobar, Saudi Arabia



Research Interests: Artificial Intelligence, Machine Learning, Data Mining


Dr. Vinayakumar Ravi is an Assistant Research Professor at the Center for Artificial Intelligence, Prince Mohammad Bin Fahd University, Khobar, Saudi Arabia. My previous position was as a Postdoctoral research fellow in developing and implementing novel computational and machine learning algorithms and applications for big data integration and data mining with Cincinnati Children's Hospital Medical Center, Cincinnati, OH, USA. He received a Ph.D. degree in computer science from Computational Engineering & Networking, Amrita School of Engineering, Coimbatore, Amrita Vishwa Vidyapeetham, India. His Ph.D. work centers on the Application of Machine learning (sometimes Deep learning) for Cyber Security and discusses the importance of Natural language processing, Image processing, and big data analytics for Cyber Security. His current research interests include applications of data mining, Artificial Intelligence, machine learning (including deep learning) for biomedical informatics, Cyber Security, image processing, and natural language processing. He has more than 50 research publications in reputed IEEE conferences, IEEE Transactions, and Journals. E-mail:

Author Articles
D2D Communication Using Distributive Deep Learning with Coot Bird Optimization Algorithm

By Nethravathi H. M. Akhila S. Vinayakumar Ravi

DOI:, Pub. Date: 8 Oct. 2023

D2D (Device-to-device) communication has a major role in communication technology with resource and power allocation being a major attribute of the network. The existing method for D2D communication has several problems like slow convergence, low accuracy, etc. To overcome these, a D2D communication using distributed deep learning with a coot bird optimization algorithm has been proposed. In this work, D2D communication is combined with the Coot Bird Optimization algorithm to enhance the performance of distributed deep learning. Reducing the interference of eNB with the use of deep learning can achieve near-optimal throughput. Distributed deep learning trains the devices as a group and it works independently to reduce the training time of the devices. This model confirms the independent resource allocation with optimized power value and the least Bit Error Rate for D2D communication while sustaining the quality of services. The model is finally trained and tested successfully and is found to work for power allocation with an accuracy of 99.34%, giving the best fitness of 80%, the worst fitness value of 46%, mean value of 6.76 and 0.55 STD value showing better performance compared to the existing works.

[...] Read more.
Other Articles