Access-controlled video/voice over IP in Hadoop system with BPNN intelligent adaptation

Abstract

In this paper a real-time video/voice over IP (VVoIP) applications has implemented in Hadoop cloud computing system and it is denoted CLC-IHU. It really outperforms the previous VVoIP using P2P connection (called SCTP-IHU) due to the easy-to-use and high-performance on video phone call. User does not need to know what is a real IP and web interface achieves interaction by adopt TCP-based RMTP instead of PR-SCTP so that CLC-IHU scheme reduces computation load and power consumption dramatically at thin clients. We employed a back-propagation neural network (BPNN) to tune key factors appropriately for adapting handoff and analyzing network traffic at any time. As a result it takes about 1.631 sec for the seamless handoff between base stations under mobile wireless network. In access control for preventing illegal intrusions from the outside of the cloud, the rapid facial recognition and fingerprint identification via cloud computing has been done successfully within 2.2 seconds to identify the exact subject.