Indian Journal of Science and Technology
DOI: 10.17485/IJST/v15i15.1379
Year: 2022, Volume: 15, Issue: 15, Pages: 677-688
Original Article
Vinod Kumar1*, Om Prakash Roy2
1Research scholar, Department of EE, North Eastern Regional Institute of Science and Technology, Nirjuli – 791109, Arunachal Pradesh, India
2Professor, Department of EE, North Eastern Regional Institute of Science and Technology, Nirjuli - 791109, Arunachal Pradesh, India
*Corresponding Author
Email: [email protected]
Received Date:27 July 2021, Accepted Date:01 March 2022, Published Date:15 April 2022
Objectives: To offer network design for secure Voice over Internet Protocol (VoIP) services with improved Quality of Services (QoS) parameters. Methods: The network area is created with required number of nodes. INTRA-SR process is employed for tracing of the route from the source node and INTER-SR is involved to reach a destination node. Cuckoo Search (CS) based optimization followed for the broadcasted voice packets. The Machine learning classifiers as SVM and ANN applied to decrease the instances of loss of voice packets. Simulation work is performed by using MATLAB 2018 and results obtained plotted in graphs using MS-Excel. Findings: The proposed design evaluated by incorporating CS algorithm to minimize the packet drops. SVM and ANN hybrid used to locate secure routing path. The QoS for throughput, latency and jitter are observed. The results exhibited higher average throughput of 98.8% irrespective of the attack instances. Lower average latency and jitter of 1.9s and 2.51ms are also exhibited by the proposed work. Similarly, latency work employing Ant Colony Optimization (ACO) with multiplex and multicasting (MM) is 2.66s that get increased to 3.16s due to attack. Novelty/Applications: The proposed algorithm significantly enhanced by deployment of highly protected network design with QoS and security. Application of ANN and SVM shown the improvement in performance for VoIP services. In addition to the regression analysis validates the results by applying other optimization algorithms.
Keywords: Voice over Internet Protocol; Cuckoo Search; Support Vector Machine; Artificial Neural Network; Machine Learning
© 2022 Kumar & Prakash Roy. This is an open-access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.
Published By Indian Society for Education and Environment (iSee)
Subscribe now for latest articles and news.