The existing Convolutional Neural Network (CNN) models have a large number of redundant parameters. In order to address this problem, two lightweight network models named Fnet1 and Fnet2, based on the SqueezeNet core structure Fire module, were proposed. Then, in the view of the characteristics of distributed data collection and processing of mobile terminals, based on Fnet2, a new network model named FnetDNN, with Fnet2 integrated with Deep Neural Network (DNN), was proposed according to Dempster-Shafer (D-S) evidence theory. Firstly, a neural network named Cent with four convolutional layers was used as the benchmark, and Mel Frequency Cepstral Coefficient (MFCC) as the input feature. From aspects of the network structure characteristics, calculation cost, number of convolution kernel parameters and recognition accuracy, Fnet1, Fnet2 and Cent were analyzed. Results showed that Fnet1 only used 10.3% parameters of that of Cnet, and had the recognition accuracy of 86.7%. Secondly, MFCC and the global feature vector were input into the FnetDNN model, which improved the recognition accuracy of the model to 94.4%. Experimental results indicate that the proposed Fnet network model can compress redundant parameters as well as integrate with other networks, which has the ability to expand the model.

Since the data gathered in Wireless Sensor Network (WSN) are inaccurate and unreliable, a flexible space model based on the spatial correlation of sensor data was defined, and an adaptive neighbor-space approach for data cleansing (ANSA) was proposed. The approach adjusted neighbor-space dynamically according to sensor data fluctuation and calculated the weighted average of neighbors' measurements to clean local raw data. The experimental results show that, the sensor data error after cleansing by the proposed approach is less than 0.5, and compared to the classic Weighted Moving Average (WMA), it is more accurate and the energy consumption is reduced by about 36%.

Under the condition of being confronted with highly concurrent requests, the existing Web services would bring about the increase of the response time, even the problem that server goes down. To solve this problem, a kind of distributed self-elasticity architecture for the Web system named ECAP (self-Elasticity Cloud Application Platform) was proposed based on cloud computing. The architecture built on the Infrastructure as a Service (IaaS) platform of OpenStack. It combined Platform as a Service (PaaS) platform of Cloudify to realize the ECAP. In addition, it realized the fuzzy analytic hierarchy scheduling method by building the fuzzy matrix in the scale values of virtual machine resource template. At last, the test applications were uploaded in the cloud platform, and the test analysis was given by using the tool of pressure test. The experimental result shows that ECAP performs better in the average response time and the load performance than that of the common application server.

To meet the application demand of high speed scanning and massive data transmission in industrial Computed Tomography (CT) of low-energy X-ray, a system of high-speed data acquisition and transmission for low-energy X-ray industrial CT was designed. X-CARD 0.2-256G of DT company was selected as the detector. In order to accommodate the needs of high-speed analog to digital conversion, high-speed time division multiplexing circuit and ping-pong operation for the data cache were combined; a gigabit Ethernet design was conducted with Field Programmable Gate Array (FPGA) selected as the master chip,so as to meet the requirements of high-speed transmission of multi-channel data. The experimental result shows that the speed of data acquisition system reaches 1MHz, the transmission speed reaches 926Mb/s and the dynamic range is greater than 5000. The system can effectively shorten the scanning time of low energy X-ray detection, which can meet the requirements of data transmission of more channels.

Concerning the estimation of fundamental matrix in motion sequences under the unknown environment, a layer-by-layer iterative approach was proposed. This approach was based on optimal robust estimation method, and added the constrained condition of motion continuity and multi-scale correspondence to reduce false correspondence. Then data inliers of model from high level were added into the data set of low level in order to update the data set and estimate the homographic model simultaneously. Finally, global optimization was done on bottom level to rectify the model. The experiments show that geometric transform error is no more than 2.891821pixel and variance of error fluctuated range is no more than 0.295172pixel, both the mean and the fluctuated variance of error are reduced in some degree when the scene surface has relatively plentiful depth levels and good continuity from motion sequences.

As one of the most popular routing protocols proposed by Internet Engineering Task Force (IETF), Ad Hoc on Demand Distance Vector Routing (AODV) has been implanted for many applications in Mobile Ad Hoc Network (MANET). In AODV, enormous broadcasting messages are generated during route discovery procedure, which consumes lots of bandwidth and degrades significantly the Quality of Service (QoS) of networks. To solve this problem, a cross-layer mechanism with a routing protocol Enhanced AODV (E-AODV) was proposed. In E-AODV, the Signal to Noise Ratio (SNR) of received signals was considered as the key criterion to select the next hop. Furthermore, Wireless Transmission Control Protocol (WTCP) was implanted as one important way in E-AODV to obtain a better QoS. The simulation results show that the proposed mechanism can reduce the Data Delivery Latency (DDL) up to 56% and improve the Data Delivery Ratio (DDR) up to 24%.

Concerning the problems of low recognition efficiency and high misreading rate on the occasions of many tags which move fast, an anti-collision algorithm based on packet-first then handling-second was proposed. The algorithm reduced the misreading rate by to grouping the tags according to the order of arriving, it could adaptively adjust frame length based on slot situation to improve the search efficiency, and use jumping dynamic searching algorithm to deal with conflict slots, which could reduce the number of search for readers and the transmission of system. Matlab simulation results show that the algorithm’s communication complexity is lower than other commonly used algorithms, and throughput can achieve 0.59~0.6. The larger the number of tags is the more obvious superiority of the algorithm is.

Disparity estimation is a key technology for stereo video compression. Considering the disadvantage of the epipolar correction algorithm, a fast disparity estimation algorithm based on the features of disparity vector was proposed. The algorithm analyzed the features of disparity vector in parallel camera and convergent camera systems respectively, and explained how to find the best matching block by a three-step search according to their features. The algorithm was tested in both 640×480 and 1280×720 resolution sequences. The experimental results show that compared to the original TZSearch algorithm in JMVC, the proposed algorithm can effectively shorten the encoding time and improve coding efficiency without decreasing the image quality and compression efficiency. Because there is not epipolar correction in the proposed algorithm, the disadvantage caused by epipolar correction will not appear.

Five scheduling mechanisms have been proposed to ensure Quality of Service (QoS) in WiMAX network. Three of them are designed for real-time applications. However, fairness has not been considered while assigning resources in these scheduling mechanisms. In order to guarantee the existing services, new service requests will be rejected when lacking network resources. For resolving this problem, a new scheduling mechanism was proposed for Voice over Internet Protocol (VoIP) service, in which a Priority Decision Maker (PDM) was implanted. When new services and the existing services requested resources simultaneously, higher priority would be assigned to new service requests; and resource allocation would be achieved based on different level priorities by a resource distribution center for guaranteeing fairness. Detailed performance analysis was performed. The simulation results show the proposed scheduling mechanism could significantly increase number of VoIP connections and total throughput, about 15% and 11% respectively.