Neural Network-based Video Quality via Adaptive FEC in Wireless Environment
Ghaida A. Al–Suhail, Sarah A. Subber · International Journal of Computer Applications · 2013
Neural Network (ANN) has proven capability in wireless communications. Therefore it has been used for a variety of purposes and in different ways. This proposal strives to address QoS of video streaming for the cellular clients in Universal Mobile Telecommunication System (UMTS) through adaptive FEC based on ANN. The model aims to present the idea of configure and recover the corrupted packets in the video flow with a suitable Forward Error Correction (FEC) code addressed by the ANN. The adaptation of the FEC scheme is based on predefined probability equations which are derived from the data loss rates related to the recovery rates at the clients. The client-side is responsible to relay information to the BS by the feedback channel via RTT of TCPFriendly Rate Control Protocol (TFRCP). For each video, the neural network will be trained on the precise data. The simulation results show that a video quality can be adaptable to the tuned optimal FEC codes from ANN via the packet loss probability of the wireless feedback environment. Keywordsof Service, FEC, UMTS, ANN. the varying network conditions. Also using the Artificial Neural Network (ANN) has proven capability in wireless communications in building wireless intelligent systems. The basic purpose of applying neural networks is to change from the lengthy analysis and design cycles required to develop high performance systems to very short product-development times. The rapidly evolving field of neural-network applications in wireless communication has witnessed several excellent contributions (5)(6) different problems have been successfully attacked new methodologies have been introduced and significant progress has been made in this dynamic area. The study in (7) presents a multilayer perceptron (MLP) based media access control protocol (MAC) to secure a CSMA-based wireless sensor network against the denial-of-service attacks launched by adversaries . In (8) a learning model based on Adaptive Neural Fuzzy Inference System (ANFIS) was proposed, the model takes into account the Radio Link control (RLC) loss models to predict the video quality in terms of the Mean Opinion Score (MOS) over UMTS network. This proposal strives to address QoS of video streaming over UMTS network based on ANN. The ANN will be learned to obtain the appropriate FEC code for good desired QoS at the mobile client. The process is based entirely on channel feedback: Packet loss probabilities of the TFRCP acknowledge. The rest of this paper is organized as follows. Section II provides system model. Our proposed analytical models of (ANN_AFEC) control system video transmission, System senior, System settings, Results and performance comparison are presented in Section III. Finally, Section IV summarizes the conclusion and outlines of some future works.