Traffic mode recognition is an important branch of user behavior recognition, the purpose of which is to identify the user's current traffic mode. Aiming at the demand of the modern intelligent urban transportation system to accurately perceive the user's traffic mode in the mobile device environment, a traffic mode recognition algorithm based on the residual temporal attention neural network was proposed. Firstly, the local features in the sensor time sequence were extracted through the residual network with strong local feature extraction ability. Then, the channel-based attention mechanism was used to recalibrate the different sensor features, and the attention recalibration was performed by focusing on the data heterogeneity of different sensors. Finally, the Temporal Convolutional Network (TCN) with a wider receptive field was used to extract the global features in the sensor time sequence. The data-rich High Technology Computer (HTC) traffic mode recognition dataset was used to evaluate the existing traffic mode recognition algorithms and the residual temporal attention model. Experimental results show that the proposed residual temporal attention model has the accuracy as high as 96.07% with friendly computational overhead for mobile devices, and has the precision and recall for any single class reached or exceeded 90%, which verify the accuracy and robustness of the proposed model. The proposed model can be applied to intelligent transportation, smart city and other domains as a kind of traffic mode detection for supporting mobile intelligent terminal operation.

Recently, botnets, domain name hijacking, phishing websites and other typosquatting attacks are more and more frequent, seriously threatening the security of society and individuals. Therefore, the typosquatting detection is an important part of network protection. The current typosquatting detections mainly focus on public domain names, and the detection methods are mainly based on edit distance which is difficult to fully reflect the visual characteristics of domain names. In addition, using the related information of the given domains for determination can help to increase the detection efficiency, but it also introduces a large additional cost. Based on this, a lightweight detection strategy only based on domain name strings was adopted for typosquatting detection. By comprehensively considering the influence of character locations, character similarities and operation types on the vision of domain names, the edit distance algorithm based on visual characteristics was proposed. According to the characteristics of typosquatting, firstly the domain names were preprocessed, then different weights were given to the characters according to their positions, character similarities and operation types, and finally, the typosquatting determination was performed by calculating the edit distance value. Experimental results show that compared with the detection method based on edit distance, the typosquatting lightweight detection method based on visual features has the F1 value increased by 5.98% and 13.56% respectively when the threshold value is 1 and 2, which proves that the proposed method has a good detection effect.

To solve the problem of k nearest neighbor query in obstacle space, a k nearest neighbor Query method based on improved Parallel Ant colony algorithm (PAQ) was proposed. Firstly, ant colonies with different kinds of pheromones were utilized to search k nearest neighbors in parallel. Secondly, a time factor was added as a condition of judging path length to directly show the searching time of ants. Thirdly, the concentration of initial pheromone was redefined to avoid the blind searching of ants. Finally, visible points were introduced to divide the obstacle path into multiple Euclidean paths, meawhile the heuristic function was improved and the visible points were selected by ants to conduct probability transfer making ants search in more proper direction and prevent the algorithm from falling into local optimum early. Compared to WithGrids method, with number of data points less than 300, the running time for line segment obstacle is averagely reduced by about 91.5%, and the running time for polygonal obstacle is averagely reduced by about 78.5%. The experimental results show that the running time of the proposed method has obvious advantage on small-scale data, and the method can process polygonal obstacles.

In order to solve the problems such as low transmission efficiency and high network resource overhead in Internet of Vehicles (IoV) environment, a new routing algorithm based on node cognitive interaction, which is suitable for urban traffic environment, was proposed. Firstly, based on trust theory, a concept of cognitive interaction degree was proposed. Then, based on this, the vehicle nodes in IoV were classified and given with different initial values of cognitive interaction degree. Meanwhile, the influence factors such as interaction time, interaction frequency, physical distance, hops between nodes and the Time-To-Live of message were introduced, and a cognitive interaction evaluation model of vehicle nodes was constructed. The cognitive interaction degrees of vehicle nodes were calculated and updated by using the proposed model, and a neighbor node with higher cognitive interaction degree than others could be selected as relay node to forward the messages after the comparison between the nodes. Simulation results show that compared with Epidemic and Prophet routing algorithms, the proposed algorithm effectively increases the message delivery rate and reduces the message delivery delay, while significantly reducing the overhead of network resources and helping to improve the quality of message transmission in IoV environment

Aiming at the problem that the indoor mobile fire extinguishing robot can not obtain comprehensive environmental information in time by means of its inner sensors and the absence of remote network control function, a system architecture based on Wireless Sensor Network (WSN) with function of remote network control was proposed. Firstly, a WSN with mesh topology was built to collect indoor environmental information. Secondly, after analyzing the logic of parts of the system, a database and a Web server were completed to achieve the browsing function for remote clients. Finally, the function of remote network control of robot was achieved by developing the software with Socket communication function for network clients. The test results show that the rate of data packet loss for mesh topology without covering the gateway node is 2% at 1.5s sending interval, which is 67% lower than the tree topology in the same situation. By adopting the proposed system architecture, both more comprehensive indoor environment information and reduction of data packet loss rate for WSN are achieved, and the function of remote network control is also realized.

Since the exsiting dictionary learning methods can not effectively construct discriminant structured dictionary, a discriminant dictionary learning method with discriminant and representative ability was proposed and applied in software defect detection. Firstly, sparse representation model was redesigned to train structured dictionary by adding the discriminant constraint term into the object function, which made the class-dictionary have strong representation ability for the corresponding class-samples but poor representation ability for the irrelevant class-samples. Secondly, the Fisher criterion discriminant term was added to make the representative coefficients have discriminant ability in different classes. Finally, the optimization of the designed dictionary learning model was solved to obtain strongly structured and sparsely representative dictionary. The NASA defect dataset was selected as the experiment data, and compared with Principal Component Analysis (PCA), Logistics Regression (LR), decision tree, Support Vector Machine (SVM) and the typical dictionary learning method, the accuracy and F-measure value of the proposed method were both increased. Experimental results indicate that the proposed method can increase detection accuracy with improving the classifier performance.

Conventional watermarking algorithms usually pay more attention to the visual quality of embedded carrier while ignore the security of watermarking. Although some methods provided watermarking encryption procedures, they usually embed watermarks in fixed positions which are prone to be attacked. The sensitivity of watermarking algorithm based on parameterized wavelet transform is difficult to be applied in practice. To address these problems, a public sensitive watermarking algorithm with weighted multilevel wavelet coefficient mean and quantization was proposed. In the proposed algorithm, firstly the Message Digest Algorithm 5 (MD5) value of cover image, user keys and initial parameters were bound with Logistic map which were used to encrypt watermarks and select wavelet coefficients in different decomposition levels; secondly weights of wavelet coefficients in different levels were estimated by absolute variation means of wavelet coefficients before and after Joint Photographic Experts Group (JPEG) compression, and then weighted multilevel wavelet coefficient mean was adjusted to embed watermark; finally an isolated black point filtering strategy was adopted to enhance the quality of fetched watermark. The experiments show the proposed method has better sensitivities of plaintext image and user keys and still is robust for common image attacks such as image clipping, white noise, JPEG compression, covering and graffiti. The Peak Signal-to-Noise Ratio (PSNR) of image after embedding watermarks can reach 45 dB. The embedded watermark is difficult to be tampered or extracted even if all watermarks embedding procedures are published.

In the non-overlapping filed of multi-camera system, the single-shot person identification methods cannot well deal with appearance and viewpoint changes. Based on the multiple frames acquired from surveillance cameras, a new technique which combined Hidden Markov Model (HMM) with appearance-based feature was proposed. First, considering the structural constraint of human body, the whole-body appearance of each individual was equally vertically divided into sub-images. Then multi-level threshold method was used to extract Segment Representative Color (SRC) and Segment Standard Variation (SSV) feature. The feature dataset acquired from multiple frames was applied to train continuous density HMM,and the final recognition was realized by these well-trained model. Extensive experiments on two public datasets show that the proposed method achieves high recognition rate, improves robustness against viewpoint changes and low resolution, and it is simple and easy to realize.

In order to improve the remote authentication efficiency for integrity measurement of computing platforms, this paper proposed a platform remote authentication mechanism based on unbalanced-Hash trees. Hash values of platform's trusted entities were stored in the structure of leaf nodes of unbalanced-Hash trees. Effectiveness of the metrics was verified through seeking corresponding leaf nodes of measured entities, recording the validation paths from leaf nodes to root nodes, passing from root nodes to the prover and finally recalculating the root nodes according to validation paths. The experimental results show that the proposed mechanism can effectively reduce time and space overhead of storing Hash values and the time complexity of integrity measurement authentication is O(lb N).

An index of network evolution speed and a network evolution model were put forward to analyze the effects of network evolution speed on propagation. The definition of temporal correlation coefficient was modified to characterize the speed of the network evolution; meanwhile, a non-Markov model of temporal networks was proposed. For every active node at a time step, a random node from network was selected with probability r, while a random node from former neighbors of the active node was selected with probability 1-r. Edges were created between the active node and its corresponding selected nodes. The simulation results confirm that there is a monotone increasing relationship between the network model parameter r and the network evolution speed; meanwhile, the greater the value of r, the greater the scope of the spread on network becomes. These mean that the temporal networks with high evolution speed are conducive to the spread on networks. More specifically, the rapidly changing network topology is conducive to the rapid spread of information, but not conducive to the suppression of virus propagation.

Software tamper resistance is an important method for software protection. Concerning the control-flow tampering invoked by buffer overflow as well as some other software attacks, a software tamper-proofing method based on Function-Level Control-Flow (FLCF) monitoring was proposed. This method described the software's normal behaviors by FLCF and instrumented one guard at every entrance of functions by binary rewriting technology. The monitoring module decided whether the software was tampered or not by comparing the running status received from the guards' reports with the expected condition. A prototype system was realized and its performance was analyzed. The experimental results show that this method can effectively detect the control-flow tampering with less overhead and no false positives. It can be easily deployed and transplanted as its implementation does not need source code or any modifications of underlying devices, and system security is strengthened by isolating the monitoring module with the software being protected.

Concerning that the lesion areas of leukoaraiosis in Magnetic Resonance (MR) image present hyper intense signal on T ₂ flair sequence, a level set segmentation method based on C-V model was proposed. First, the C-V model was improved to avoid the re-initialization; second, the Otsu threshold method was used for image's pre-segmentation, and then the image's pre-segmentation result was directly used as the initial contour for the improved C-V model; finally, the segmentation result was obtained by curve evolution. The results show that the proposed segmentation method can get better separation effects, and realize fast auto-segmentation. It has certain application value for clinical diagnosis and prognosis on leukoaraiosis.

Concerning the drawbacks of traditional PCI frame grabber, using Altera's DE2 development platform, image acquisition and VGA display system of programmable logic chip based on Field-Programmable Gate Array (FPGA) were designed. This system used the programmable logic chip FPGA which was in-built into soft-core NiosⅡ as the controller. The FPGA has image sensor, digital memory, video D/A converter and VGA display interface as its accessories. System used System On a Programmable Chip (SOPC) technology to obtain control and coding over FPGA and its accessories and eventually to acquire, process and display the real-time images. The design results prove that, the electronic system based on SOPC technique is flexible and efficient in terms of designing, ported strong, easy to achieve high-speed data acquisition, and it has high compatibility.

Fuzzy K-Prototypes(FKP) algorithm integrating K-Means and K-Modes algorithm is suited for clustering mixed numeric and categorical valued data. The use of fuzzy techniques makes it robust against noise and missing values in the databases. But, it is an open problem how to select an appropriate weighting exponent α when run FCM(Fuzzy C-Means algorithm) or FKP. Some researchers have suggested that the best choice for α in FCM be probably in the interval \ based on their experimental results. In this paper, the algorithm for searching suitable α in FKP was presented. The experimental results on several real datasets show that the valid clustering can be achieved when α is under 1.5.