Intelligent adaptation for UEC video/voice over IP with access control. (1st January 2014)

• Record Type: Journal Article
• Authors: Chang, Bao Rong; Chen, Chi-Ming; Huang, Chien-Feng; Tsai, Hsiu-Fen
• Is Part Of: International journal of intelligent information and database systems. Volume 8:Number 1(2014)
• Page Start: 64
• Page End: 80
• Publication Date: 2014-01-01
• Subjects: video/voice over IP -- VVoIP -- Ubuntu enterprise cloud -- UEC -- PSO-ANFIS -- RMTP -- P2P-VVoIP -- UEC-VVoIP; Database management -- Computer programs -- Periodicals; Information retrieval -- Computer programs -- Periodicals; Information storage and retrieval systems -- Computer programs -- Periodicals; Artificial intelligence -- Periodicals; Expert systems (Computer science) -- Periodicals; Intelligent agents (Computer software) -- Periodicals; 006.33
• Languages: English
• ISSNs: 1751-5858

Abstract

In this paper, we introduce a high-performance real-time video/voice over IP (VVoIP) application implemented by Ubuntu enterprise cloud (UEC), denoted UEC-VVoIP. It is much easer to use than the earlier work of P2P connection VVoIP (called P2P-VVoIP) does. This is because user does not need to key-in a real IP and a web interface using TCP-based RMTP protocol achieves a friendly GUI. Furthermore, computation load has been moved to cloud computing server rather than in user device. Thus, this approach reduces computation load and power consumption dramatically at user device. Meanwhile, we have employed adaptive network-based fuzzy inference system (ANFIS) together with particle swarm optimisation (PSO) to properly tune seamless handoff and analyse network traffic over time. As a result, it takes around 1.589 sec for the seamless handoff among different base stations in wireless mobile network. Cloud computing server with access control accomplishes rapid face recognition and fingerprint identification successfully within 2.15 seconds to identify the permitted user. Finally, the experiment result shows that the performance of our proposed approach is better than the earlier work of Hadoop-VVoIP and P2P-VVoIP.