Subjects: Computer Science >> Integration Theory of Computer Science submitted time 2020-09-28 Cooperative journals: 《计算机应用研究》
Abstract： This paper presented a novel discriminative K-SVD network (DKSVDN) for face recognition. It embedded discriminative information into traditional K-SVD algorithm by special design of dictionary as well as sparse representation coefficients on the dictionary. The dictionary consisted of label specific atoms and descriptive atoms, while sparse codes contained one-hot label vectors and descriptive codes. In addition, as sparse representation algorithms were time-consuming, DKSVDN attached a co-trained feed-forward neural network to discriminative dictionary learning model to predict sparse codes. Moreover, with generative module in DKSVDN, this work also designed a new dreaming training phase to improve the robustness of DKSVDN for unknown pattern in known class. The experiment results on public face image datasets verified effectiveness of this method.
Subjects: Computer Science >> Integration Theory of Computer Science submitted time 2019-01-28 Cooperative journals: 《计算机应用研究》
Abstract： Sparse representation classification (SRC) has a good performance of classification when the feature space spanned by training samples is sufficient, but the computational cost is expensive. To solve this problem of SRC, this work considered the constraint of reconstruction samples. It introduced a group sparsity effect to enhance the competitions between different subjects in reconstruction procedure, and improves the accuracy of classification finally. Since the proposed method has a closed solution, the computational cost is very low. Moreover, the sparsity of the coefficient produced by the new approach is the same as that obtained by SRC. The experiment results on public face and object image datasets demonstrate that the proposed method has a good performance comparing with other same kind approaches.
Subjects: Computer Science >> Integration Theory of Computer Science submitted time 2018-12-13 Cooperative journals: 《计算机应用研究》
Abstract： This paper proposed an image enhancement method based on multi-layer fusion and detail recovery, to solve the image deterioration such as low contrast and blurred details in undesirable illumination environments. Firstly, this paper copied the V channel equivalently into three layers in HSV color spacce: Retinex enhancement layer, brightness enhancement layer, detail enhancement layer. In Retinex enhancement layer, this paper combined with weighted guided image filtering and morphology to eliminate halo phenomenon. Improved Retinex enhanced brightness and details of images. In detail enhancement layer, this paper used artificial bee colony algorithm to optimize improved model of local linear to obtain more details. Finally, this paper performed gamma correction and pixel arrangement to avoid partial fuzzy details caused fusion. The experimental results show that the proposed method can more effictively highlight image details and improve the contrast. The comprehensive performance is superior while comparing with the related methods in terms of objective quantification, especially in Tenengrad index, which is much higher than other algorithms.
Subjects: Computer Science >> Integration Theory of Computer Science submitted time 2018-05-02 Cooperative journals: 《计算机应用研究》
Abstract： Computer recognition of human emotion has become a hot topic in the field of brain computer interface (BCI) in recently years. By analyzing the various emotional states in people’s life, extracting the features of EEG and classifying emotional states is an important direction in the field of emotional intelligence. Based on the emotion data set induced by the music video, this research extracted the frequency-domain features of EEG. After that, the Accelerated Proximal Gradient (APG) and Orthogonal Matching Pursuit (OMP) algorithms for the sparse representation method were adopted to classify the EEG signals. By comparing with other algorithms, the experimental results show that the APG with L1 norm performs well in the emotion data set with fast convergence speed, and the greedy idea based OMP algorithm can achieve the same effect with other algorithms. The comparative analysis in this paper show the effectiveness and feasibility of the proposed method for emotional EEG signals classification.
Subjects: Computer Science >> Integration Theory of Computer Science submitted time 2018-04-19 Cooperative journals: 《计算机应用研究》
Abstract： Open-source distributed real-time computing framework Storm in the Internet, finance, e-commerce and other fields has been widely used. By default, Storm uses the polling scheduling policy and relies on the user's configuration of Topology tasks in parallel. When the configuration is unreasonable, Storm still causes delays in Topology processing and decreases throughput. To solve this problem, this paper proposes a Greedy Scheduling Algorithm based on best parallelism in Storm. When scheduling, the best parallelism of each component in Topology task is solved first, and then greedy policy is adopted to minimize the network communication between nodes. Compared with the default scheduling algorithm, the online scheduling algorithm and the hot-side scheduling algorithm, the results show that the algorithm can effectively reduce the Storm processing delay and improve the system throughput and resource utilization.
Subjects: Computer Science >> Integration Theory of Computer Science submitted time 2018-04-17 Cooperative journals: 《计算机应用研究》
Abstract： To further improve the multi-relay cooperative transmission efficiency in wireless networks, this paper proposed a dynamic programming scheduling based on network coding with less feedback(DPNC-LF) . The DPNC-LF considered the effective information of each relay and the transmission reliability of each link, and implemented the multi-relay cooperative forwarding to improve transmission effectiveness with the minimum number of retransmissions. In the condition of each link independent mutually and the state transition path selected adaptively, the DPNC-LF determined the optimal forwarding node for the entire transmission process. The simulation results show that the algorithm proposed in this paper is more effective than random selection scheduling in average throughput and the number of retransmission. With the feedback information dependence reduced and the feedback overhead decreased, the performance of this scheme is close to the performance of greedy algorithm scheduling.
Hits
Hits
Downloads
Comment