Abstract Linear programming problem is widely applied in engineering group. And artificial neural network is an effective and practical method and approach for solving linear programming problem of nonlinear convex set constraints in engineering field. Most models of artificial neural network are nonlinear dynamic system. If the objective function of optimization calculation problem is corresponding to some energy function of network, steady state... Linear programming problem is widely applied in engineering group. And artificial neural network is an effective and practical method and approach for solving linear programming problem of nonlinear convex set constraints in engineering field. Most models of artificial neural network are nonlinear dynamic system. If the objective function of optimization calculation problem is corresponding to some energy function of network, steady state point is the local or global optimal dynamic process solution for optimizing the problem. This paper studied the optimization problem with nonlinear constrained convex set by the application of nonlinear neural network. First, the inverse optimization problem with nonlinear convex set constraints into nonlinear bilevel programming problem. Then the optimization solution was searched by establishing neural network model. In addition, the stability of model was analyzed and sufficient conditions for global asymptotic stability of the balance point were given. Finally, the validity and effectiveness of the conclusion was verified by example. Read More Read Less

Abstract Multi Processor Systems on Chip (MPSoC) has emerged as a solution to adress the incremental Computational requirements for future applications. The Network-On-Chip (NoC) has been introduced as a power efficient, scalable inter communication, interconnection mechanism between processors. One important phase in architectural exploration in NOC-based MPSOC is the mapping. The application and architectural are represented by processing model, application task graph and architectural... Multi Processor Systems on Chip (MPSoC) has emerged as a solution to adress the incremental Computational requirements for future applications. The Network-On-Chip (NoC) has been introduced as a power efficient, scalable inter communication, interconnection mechanism between processors. One important phase in architectural exploration in NOC-based MPSOC is the mapping. The application and architectural are represented by processing model, application task graph and architectural graph respectively. Mapping parallelized tasks of applications onto these MPSoCs can be done either at design-time (static) or at run-time (dynamic). Static mapping strategies find the best placement of tasks at design-time and hence these are not suitable for dynamic workload and seem incapable of run-time resource management. The number of tasks or applications executing in MPSoC platform can exceed the available resources, requiring efficient run-time mapping strategies to meet with this constraints. In this paper, we propose a new packing strategy to find free resources for run-time mapping of application tasks on NoC-based Heterogeneous MPSoCs. The proposed strategy minimizes the task mapping time in addition to placing the communicating tasks close to each other. To evaluate our approach, a comparative study is carried out. Experiments show that our strategy provides better results when compared to latest dynamic mapping strategies reported in the literature. Read More Read Less

Abstract Digital image sequences taking from the same scene with different exposures often show underexposed or overexposed areas, which make details of the highlight or shadow zones get lost. Image fusion technology aims to solve this problem. However, most of image fusion algorithms are too complex and time consuming. By analyzing the multi-resolution image fusion method, a simple, low complexity algorithm for multi... Digital image sequences taking from the same scene with different exposures often show underexposed or overexposed areas, which make details of the highlight or shadow zones get lost. Image fusion technology aims to solve this problem. However, most of image fusion algorithms are too complex and time consuming. By analyzing the multi-resolution image fusion method, a simple, low complexity algorithm for multi exposure image fusion is proposed in this paper, which is designed to combine three measuring factors of gradient, standard deviation and moderate exposure. To generate the weight diagram of original multi-exposure images, the fusion algorithm assigns weights to pixels of digital images by measuring factors, and is carried out on per pixel basis, thus it is highly efficient in terms of computational complexity. The experimental results show that the algorithm can obtain high-contrast fusion image with greater information entropy. Read More Read Less

Abstract In this paper, a process-aware security task scheduling algorithm is proposed as IOAware. The algorithm evaluates the performance of hardware in computing nodes, and estimates properties of a task while it is being executed. In subsequent assignments, the algorithm assigns tasks based on the performance of the Task Tracker and the task properties. To verify the theoretical feasibility of the proposed IOAware... In this paper, a process-aware security task scheduling algorithm is proposed as IOAware. The algorithm evaluates the performance of hardware in computing nodes, and estimates properties of a task while it is being executed. In subsequent assignments, the algorithm assigns tasks based on the performance of the Task Tracker and the task properties. To verify the theoretical feasibility of the proposed IOAware scheduling algorithm, a schedule model is proposed to implement the method. After applying the scheduling module in a Hadoop cluster with multiple experiments, the results show that, compared with the performances of the FIFO, computing capacity-scheduling, and fair-scheduling algorithms in terms of four aspects: response time, localization ratio of the data, system throughput, and system resources, IOAware scheduling algorithm can reach up to the disk IO effect of the Shared computing nodes, effectively reduce the execution time of the tasks and improve the throughput of the cluster. Read More Read Less

Abstract Criminal behaviors can reflect the characteristics of the criminals to a great extent. To predict the crime types according to characteristics of vast amounts of criminals is an important part of criminal behavior analysis. In order to get high classification accuracy, three typical classification algorithms, including C4.5 algorithm, Naive Bayesian algorithm and K nearest neighbor (KNN) algorithm, are compared using several popular... Criminal behaviors can reflect the characteristics of the criminals to a great extent. To predict the crime types according to characteristics of vast amounts of criminals is an important part of criminal behavior analysis. In order to get high classification accuracy, three typical classification algorithms, including C4.5 algorithm, Naive Bayesian algorithm and K nearest neighbor (KNN) algorithm, are compared using several popular missing data filling algorithms respectively based on a real crime dataset with lots of missing data. The experimental results show that higher classification accuracy can be obtained by combining KNN classification algorithm and GBWKNN missing data filling algorithm which is based on grey relational analysis (GRA) theory. Read More Read Less

Abstract A vehicle license plate recognition system extracts plate information from a digital image through image processing technology. License plate extraction (LPE) is the premise and key concept of license plate recognition systems. In China, two-row license plates are yellow and dirty. Thus, a novel license plate extraction method based on CIELab color space is proposed in this paper. The method involves transforming... A vehicle license plate recognition system extracts plate information from a digital image through image processing technology. License plate extraction (LPE) is the premise and key concept of license plate recognition systems. In China, two-row license plates are yellow and dirty. Thus, a novel license plate extraction method based on CIELab color space is proposed in this paper. The method involves transforming a digital image from RGB color space to CIELab color space and using the b and a channels of CIELab color space to obtain the yellow areas of the digital image. Morphological operations are implemented to filter out noise and identify the license plate candidate areas. Lastly, texture features are utilized to locate the real license plate areas. Experiments indicate that the proposed method makes full use of digital image information to rapidly extract two-row license plate areas in a complicated environment. Read More Read Less

Abstract This study presents a visual attention model for determining image areas to receive different extents of video compression in order to minimize perceived program artefacts whilst maximizing the compression possible. The model integrates features related to motion with existing video image compression algorithms. The proposed visual attention model extracts the color, intensity, textural, and motion features of a video to determine... This study presents a visual attention model for determining image areas to receive different extents of video compression in order to minimize perceived program artefacts whilst maximizing the compression possible. The model integrates features related to motion with existing video image compression algorithms. The proposed visual attention model extracts the color, intensity, textural, and motion features of a video to determine the predicted region of interest (ROI). First, color, intensity, and texture saliency maps are generated by applying the center-surround method and a motion saliency map is produced using a difference operator. Then, a multi-channel weighting method is used to generate a global saliency map and to determine the ROI according to a winner-takes-all network (WTA). The proposed video image compression algorithm performs either low or no compression on the ROI while a high degree of compression is applied to the other regions. Tests indicate that the proposed visual attention model is able swiftly to identify the ROI, allowing the proposed compression algorithm to exert a high compression efficiency yet with minimally noticeable visual degradation. Read More Read Less