标题：Research on the Primary Features of the Internet of Things System and the Corresponding Data Communication Characteristics based on Sparse Coding and Joint Deep Neural Network
期刊名称：International Journal of Future Generation Communication and Networking
印刷版ISSN：2233-7857
出版年度：2016
卷号：9
期号：10
页码：135-148
出版社：SERSC
摘要：In this paper, we conduct research on issues related to the primary features of the Internet of things system and the corresponding data communication characteristics based on sparse coding and joint deep neural network. Internet of things is more than the underlying device difference communication method and it is the Internet of things needs to study in the field of hot issue. Using traditional algorithm for Internet communication equipment need particle filter was carried out on the acquisition of communication signal processing. Communication technology enables the Internet of things will perceive the information between different terminals for efficient transmission and exchange, exchange and sharing and the information resources is the key to the functions of things. To enhance the robustness and efficiency of the current IOT systems, we adopt the sparse coded dictionary learning theory to detect the size of the data and optimize the compressive sensing technique to modify the resolution. With the advances of the deep neural network, we analyze the topology of the system network structure and extract the pattern features and characteristics to make the signal transmission process more quickly and feasible. To enhance the objective function, we obtain the restricted optimization algorithm to help terminate the iteration for the higher efficiency. In the final part, we simulation our algorithm for times compared with other well-performed approaches. The result indicates that our method outperforms both in the accuracy layer an in the time-consuming layer which will hold specific meaning.
关键词：Internet of Things; Data Communication; Sparse Coding; Deep Neural ;Network; Signal Detection; Compressive Sensing; Feature Extraction; Mathematical ;Optimization
