Machine-learning-based saliency detection and its video decoding application in wireless multimedia communications

2019 ◽  
pp. 307-341
Author(s):  
Mai Xu ◽  
Lai Jiang ◽  
Zhiguo Ding
Keyword(s):  
Machine Learning ◽  
Saliency Detection ◽  
Multimedia Communications ◽  
Wireless Multimedia ◽  
Video Decoding

scholarly journals Multimedia Communication over Cognitive Radio Networks from QoS/QoE Perspective; A Comprehensive Survey

2020 ◽  
Author(s):  
Md Jalil Piran
Keyword(s):  
Cognitive Radio ◽  
Channel Coding ◽  
Multimedia Communication ◽  
Radio Spectrum ◽  
Multimedia Communications ◽  
Future Research ◽  
Wireless Multimedia ◽  
Comprehensive Survey ◽  
Feasible Solutions

The stringent requirements of wireless multimedia<br>transmission lead to very high radio spectrum solicitation. Although the radio spectrum is considered as a scarce resource, the<br>issue with spectrum availability is not scarcity, but the inefficient<br>utilization. Unique characteristics of cognitive radio (CR) such<br>as flexibility, adaptability, and interoperability, particularly have<br>contributed to it being the optimum technological candidate to<br>alleviate the issue of spectrum scarcity for multimedia communications. However, multimedia communications over CR<br>networks (MCRNs) as a bandwidth-hungry, delay-sensitive, and<br>loss-tolerant service, exposes several severe challenges specially<br>to guarantee quality of service (QoS) and quality of experience<br>(QoE). As a result, to date, different schemes based on source and<br>channel coding, multicast, and distributed streaming, have been<br>examined to improve the QoS/QoE in MCRNs. In this paper,<br>we survey QoS/QoE provisioning schemes in MCRNs. We first<br>discuss the basic concepts of multimedia communication, CRNs,<br>QoS and QoE. Then, we present the advantages of utilizing CR<br>for multimedia services and outline the stringent QoS and QoE<br>requirements in MCRNs. Next, we classify the critical challenges<br>for QoS/QoE provisioning in MCRNs including spectrum sensing,<br>resource allocation management, network fluctuations management, latency management, and energy consumption management. Then, we survey the corresponding feasible solutions for<br>each challenge highlighting performance issues, strengths, and<br>weaknesses. Furthermore, we discuss several important open<br>research problems and provide some avenues for future research. <br>

Sign in / Sign up

Export Citation Format

Share Document