Most Download articles

Published in last 1 year | In last 2 years| In last 3 years| All| Most Downloaded in Recent Month| Most Downloaded in Recent Year|

Most Downloaded in Recent Month

Please wait a minute...


For Selected: Download Citations EndNote Ris BibTeX Toggle Thumbnails

Select

Computer Engineering and Applications    2022, 58 (9): 0-0.   Abstract （55）      PDF（pc） （38025KB）（263）       Knowledge map    Save Related Articles | Metrics

Select

MTICA-AEO-SVR Model for Stock Price Forecasting DENG Jiali, ZHAO Fengqun, WANG Xiaoxia Computer Engineering and Applications    2022, 58 (8): 257-263.   DOI: 10.3778/j.issn.1002-8331.2108-0433 Abstract （63）      PDF（pc） （2491KB）（196）       Knowledge map    Save In order to improve the stability and separation efficiency of traditional Fast ICA algorithm, a new nonlinear function based on Tukey M estimation is constructed in this paper, and then a MTICA algorithm is obtained. Furthermore, a novel MTICA-AEO-SVR model for stock price forecasting is established combining MTICA and SVR algorithms. Firstly, the original stock data is decomposed into independent components by MTICA algorithm for sorting and denoising, and then different SVR models are selected to predict the independent components and the stock price respectively. Artificial ecosystem optimization is introduced into the SVR algorithm to select parameters, as to improve the model prediction accuracy. The empirical results of the Shanghai B-share index show that MTICA-AEO-SVR model is more accurate and efficient than ICA-AEO-SVR model and ICA-SVR model in stock price prediction. Reference | Related Articles | Metrics

Select

Design of Reward Function in Deep Reinforcement Learning for Trajectory Planning LI Yue, SHAO Zhenzhou, ZHAO Zhendong, SHI Zhiping, GUAN Yong Computer Engineering and Applications    2020, 56 (2): 226-232.   DOI: 10.3778/j.issn.1002-8331.1810-0021 Abstract （420）      PDF（pc） （1421KB）（525）       Knowledge map    Save For the trajectory planning of robot manipulator in unknown environments, current deep reinforcement learning based?methods often suffer from the low learning efficiency and low robustness of planning strategy. To overcome the problems above, a novel azimuth reward function based trajectory planning method called A-DPPO is proposed. A novel azimuth reward function based on relative orientation and relative position is designed to reduce the invalid explorations and improve the learning efficiency. Moreover, it is the first time that Distributed Proximal Policy Optimization（DPPO） is applied to the trajectory planning for robot manipulator to improve the robustness of planning strategy. Experimental results show that the proposed A-DPPO method can increase the learning efficiency, compared to the state-of-the-art methods, and improve the robustness of planning strategy greatly. Related Articles | Metrics

Select

Multi-Scale Transformer Lidar Point Cloud 3D Object Detection SUN Liujie, ZHAO Jin, WANG Wenju, ZHANG Yusen Computer Engineering and Applications    2022, 58 (8): 136-146.   DOI: 10.3778/j.issn.1002-8331.2109-0489 Abstract （74）      PDF（pc） （1383KB）（188）       Knowledge map    Save Point cloud 3D object detection has low detection accuracy for small objects such as pedestrians and bicycles, which is easy to miss detection and false detection. A 3D object detection method MSPT-RCNN（multi-scale point transformer-RCNN） based on multi-scale point cloud transformer is proposed to improve the detection accuracy of point cloud 3D objects. The method consists of two stages, the first stage（RPN） and the second stage（RCNN）. In RPN stage, point cloud features are extracted through multi-scale transformer network, which includes multi-scale neighborhood embedding module and jump connection offset attention module to obtain multi-scale neighborhood geometric information and different levels of global semantic information, and generate high-quality initial 3D bounding box. In the RCNN stage, the multi-scale neighborhood geometric information of point cloud in the bounding box is introduced to optimize the position, size, orientation and confidence of the bounding box. The experimental results show that this method（MSPT-RCNN） has high detection accuracy, especially for distant and small objects. MSPT-RCNN can effectively improve the accuracy of 3D object detection by effectively learning the multi-scale geometric information in point cloud data and extracting different levels of effective semantic information. Reference | Related Articles | Metrics

Select

Application of Improved SSD Algorithm in Parts Detection SHEN Xinfeng, JIANG Ping, ZHOU Genrong Computer Engineering and Applications    2021, 57 (7): 257-262.   DOI: 10.3778/j.issn.1002-8331.2001-0097 Abstract （136）      PDF（pc） （1601KB）（345）       Knowledge map    Save Aiming at the problems of high real-time and accuracy requirements of parts type detection during production, and the small volume of some parts is difficult to detect, a new method of parts detection based on the improved SSD target detection algorithm is proposed. The lightweight network MobileNetV3-Large is used to replace network VGG-16. Resizing image from 300×300 px to 224×224 px, the feature pyramid network is adopted to improve the detection effect of small parts. Taking the detection of pneumatic motor parts to test, during training, data enhancement is applied to improve the robustness of the model. The experimental results show that the improved SSD algorithm improves the speed of real-time detection of components and ensures detection accuracy. Related Articles | Metrics

Select

Review of Cognitive and Joint Anti-Interference Communication in Unmanned System WANG Guisheng, DONG Shufu, HUANG Guoce Computer Engineering and Applications    2022, 58 (8): 1-11.   DOI: 10.3778/j.issn.1002-8331.2109-0334 Abstract （226）      PDF（pc） （913KB）（232）       Knowledge map    Save As the electromagnetic environment becomes more and more complex as well as the confrontation becomes more and more intense, it puts forward higher requirements for the reliability of information transmission of unmanned systems whereas the traditional cognitive communication mode is difficult to adapt to the independent and distributed development trend of broadband joint anti-interference in future. For the need of low anti-interference intercepted communications surrounded in unmanned systems, this paper analyzes the cognitive anti-interference technologies about interference detection and identification, transformation analysis and suppression in multiple domains and so on. The research status of common detection and estimation, classification and recognition are summarized. Then, typical interference types are modeled correspondingly, and transformation methods and processing problems are concluded. Furthermore, traditional interference suppression methods and new interference suppression methods are systematically summarized. Finally, the key problems of restricting the joint interference of broadband are addressed, such as the classification and recognition of unknown interference, the temporal elimination of multiple interference, the joint separation of distributed interference and the optimal control of collaborative interference, which highlight the important role of cognitive interference suppression technology in unmanned system communication. Reference | Related Articles | Metrics

Select

Path Planning Using Improved RRT Algorithm for Indoor Mobile Robot LIU Ziyan，ZHANG Jie Computer Engineering and Applications    2020, 56 (9): 190-197.   DOI: 10.3778/j.issn.1002-8331.1903-0105 Abstract （262）      PDF（pc） （1149KB）（577）       Knowledge map    Save Aiming at the defects of low sampling efficiency and high deviation from optimal solutions of basic RRT algorithm due to randomly selecting extended nodes, an improved RRT algorithm with goal-biased is proposed. After the extended nodes being selected by using the target bias strategy and the odor diffusion, random trees grow to target points. A path smoothing method based on B-spline curve is proposed, which has higher searching efficiency and path quality. The simulation results demonstrate that the path generated by the proposed algorithm is around 22.1% shorter than that of basic RRT algorithm and the path is smoother as well. Furthermore, the proposed algorithm has stronger ability of avoiding obstacles. Finally, the improved RRT algorithm is applied it to Turtlebot2 in real environment. The experimental results illustrate that the improved RRT algorithm achieves higher reliability and practicability. Related Articles | Metrics

Select

Research on Image Style Transfer Technology Based on Semantic Segmentation LI Meili, YANG Chuanying, SHI Bao Computer Engineering and Applications    2020, 56 (24): 207-213.   DOI: 10.3778/j.issn.1002-8331.1910-0238 Abstract （263）      PDF（pc） （1172KB）（390）       Knowledge map    Save With the collision and fusion of national costume culture, this paper studies the image style transfer technology, expounds the current research status of style transfer, integrates Mongolian costume style with Han style, and inherits and promotes the national culture. For large difference of Mongolian costume elements variety, color, decorative pattern characteristics and cause of style such as irregularity extraction is difficult problem, it uses the algorithm of [K]-means and closed natural cutout combination method for image segmentation, extracts the image of style and content based on neural network, uses image reconstruction technology to synthesize results, implements the image style transfer of Mongolian and Han clothing. According to the serious output image artifact, it adopts the migration algorithm, an improved image style will constrain the transform of the input image to the output image in the local affine transformation of color space, the constraints are represented as a differentiable parameter completely, it effectively restrains image distortion, at the same time in real style photos do not match the space problems in the process of migration, it treatments smoothly to ensure the space style is consistent, this method greatly accelerates the speed. Related Articles | Metrics

Select

Field Weed Identification Method Based on Deep Connection Attention Mechanism SHU Yali, ZHANG Guowei, WANG Bo, XU Xiaokang Computer Engineering and Applications    2022, 58 (6): 271-277.   DOI: 10.3778/j.issn.1002-8331.2108-0077 Abstract （85）      PDF（pc） （1037KB）（167）       Knowledge map    Save In order to achieve fast and accurate recognition of field weed images, a field weed recognition model based on deep connected attention mechanism residual network（DCECA-Resnet50-a） is proposed. Using the residual network as a benchmark, this paper improves the position of residual block downsampling, introduces the attention mechanism and connected attention mechanism modules to better extract the feature information in the images, combines the migration learning strategy to alleviate the overfitting phenomenon caused by small sample data sets, improves the generalization of the model and greatly reduces the training time of the model. The experimental results show that the improved model has the best overall performance and high recognition accuracy, with 96.31% accuracy for weeds and fewer model parameters, and achieves the accurate differentiation of four types of common weeds in pea fields, namely, silverleaf daisy, chaparral, matang and pigweed, which provides a corresponding reference for small sample data in the field of agricultural recognition. Reference | Related Articles | Metrics

Select

Temporal and Spatial Fusion of Remote Sensing Images：A Review YANG Guangqi, LIU Hui, ZHONG Xiwu, CHEN Long, QIAN Yurong Computer Engineering and Applications    2022, 58 (10): 27-40.   DOI: 10.3778/j.issn.1002-8331.2111-0131 Abstract （22）      PDF（pc） （1548KB）（125）       Knowledge map    Save Big data of remote sensing image with high temporal and spatial resolution plays an important role in remote sensing field. However, due to technique and budget constraints, a single satellite sensor cannot acquire remote sensing images with both high spatial resolution and high temporal resolution. Therefore, the temporal and spatial fusion technology of remote sensing image is regarded as one of the effective ways to solve the tradeoff between temporal resolution and spatial resolution. With the wide application of deep learning in various fields, deep learning technology has been proved to be a very effective method to solve image problems. According to the research results of scholars at home and abroad, the classical algorithm of remote sensing image spatiotemporal fusion is comprehensively summarized. Meanwhile, the research results of remote sensing image spatiotemporal fusion algorithm based on deep learning are analyzed, which are replicated on three datasets and the experimental results are analyzed, and the future of remote sensing image spatiotemporal fusion is prospected. Reference | Related Articles | Metrics

Select

Channel and Spatial Attention Image Super Resolution Network LIU Jing, SONG Haichuan, HUANG Jianshe, MA Lizhuang Computer Engineering and Applications    2021, 57 (2): 209-216.   DOI: 10.3778/j.issn.1002-8331.1911-0296 Abstract （167）      PDF（pc） （1618KB）（400）       Knowledge map    Save Single image super-resolution plays an important role in the field of computer vision. This technology aims to reconstruct high-resolution images from low-resolution images. In recent years, deep neural networks make performance in SISR task significantly improved. However, recently works based on convolutional neural network equally treat high-frequency and low-frequency features, which makes the reconstruction of high-frequency details poor, the output too smooth and the texture information lack. On the other hand, very deep convolutional network is not easy to converge, and as the depth of the neural network grows, the long-term information from the former layer can easily be weakened or lost in the latter layer, which makes the benefit not proportional to the depth of the network and the computational complexity. To solve these above problems, it proposes a spatial attention module and a channel attention module as the basic block of convolutional neural network for SISR. Firstly, in the same channel, the information of different locations is given different weights by the spatial attention module. Secondly, the weights between different channels are determined by the channel attention module, which makes the high-frequency information gain a higher position in the reconstruction task. The reconstruction performance is improved. It further proposes a short-term and long-term feature modulation module to transform the layer depth of the network into the block depth, which greatly reduces the depth of the network, in order to solve the problem of long-term information loss in the front layer. Compared with other methods based on deep convolution neural network, the Peak Signal-to-Noise Ratio（PSNR） on several benchmark datasets are better, which proves the effectiveness of the proposed method. Related Articles | Metrics

Select

SSD Small Target Detection Algorithm Combining Feature Enhancement and Self-Attention ZHANG Xinyue, JIANG Ailian Computer Engineering and Applications    2022, 58 (5): 247-255.   DOI: 10.3778/j.issn.1002-8331.2109-0356 Abstract （62）      PDF（pc） （1400KB）（142）       Knowledge map    Save SSD is a multi-scale target detection algorithm. Due to the lack of semantic information in shallow feature images, the detection accuracy of small targets is low. To solve this problem, a SSD small target detection algorithm, FA-SSD, which combines feature enhancement and self-attention, is proposed. The algorithm constructs a recursive reverse path from deep to shallow based on SSD, which consists of three modules：the deep feature enhancement module uses the contextual information generated from the deep multi-scale feature map and the semantic information of the deepest feature map to enhance the expression ability of the deep feature information; the up-sampling feature enhancement module enhances the semantic information of the up-sampling feature map in the reverse path by enlarging the receptive field of the feature map. The adaptive feature fusion module adaptively fuses adjacent shallow feature images and up-sampling feature images with self-attention mechanism to generate new feature images with strong semantic and precise location information. Experimental results show that on PASCAL VOC and TT100K datasets, the mAP of FA-SSD is up to 92.5% and 80.2%, indicating that this algorithm can enhance the semantic information of shallow feature images and has a good detection effect on small targets in complex scenes. Reference | Related Articles | Metrics

Select

Real Time Traffic Sign Detection Algorithm Based on Improved YOLOV3 WANG Hao, LEI Yinjie, CHEN Haonan Computer Engineering and Applications    2022, 58 (8): 243-248.   DOI: 10.3778/j.issn.1002-8331.2011-0460 Abstract （120）      PDF（pc） （625KB）（124）       Knowledge map    Save Traffic sign detection is an important part of intelligent driving task. In order to meet the requirements of detection accuracy and real-time detection, an improved real-time traffic sign detection algorithm based on YOLOV3 is proposed. First, the cross stage local network is used as the feature extraction module to optimize the gradient information and reduce the inference computation. At the same time, the path aggregation network is used to replace the feature pyramid network, which not only solves the multi-scale feature fusion, but also preserves more accurate target spatial information and improves the targets detection accuracy. In addition, the complete intersection over union loss function is introduced to replace the mean square error loss to improve the positioning accuracy. Compared with other object detection algorithm on the CCTSDB dataset, experimental results show that, the average precision of the improved algorithm reaches 95.2% and the detection speed reaches 113.6 frame per second, which is 2.37% and 142% higher than YOLOV3 algorithm. Reference | Related Articles | Metrics

Select

Computer Engineering and Applications    2022, 58 (8): 0-0.   Abstract （148）      PDF（pc） （637KB）（132）       Knowledge map    Save Related Articles | Metrics

Select

Survey of IoT Forensics LIANG Guangjun, XIN Jianfang, WANG Qun, NI Xueli, GUO Xiangmin, XIA Lingling Computer Engineering and Applications    2022, 58 (8): 12-32.   DOI: 10.3778/j.issn.1002-8331.2201-0014 Abstract （111）      PDF（pc） （1143KB）（129）       Knowledge map    Save The advent of the Internet of Things era brings great convenience to people, but it also makes the scope of cyberspace attacks wider and brings new cyberspace security threats. Massive IoT devices retain a wealth of digital traces, which can provide insight into people’s various behaviors at home and other places. This is of great significance for digital forensics. This article has an in-depth discussion on IoT forensics, starting with the rise, development and research status of IoT forensics, and further discusses digital forensics models, 1-2-3 regional method models, parallel structure-IoT forensics models, privacy protection forensics models, and forensic model for special applications. Finally, it elaborates on the opportunities and challenges of forensics in the Internet of Things. This article strives to provide readers with help and reference for more in-depth research on the basis of systematically learning IoT forensics technology. Reference | Related Articles | Metrics

Select

YOLOv5 Helmet Wear Detection Method with Introduction of Attention Mechanism WANG Lingmin, DUAN Jun, XIN Liwei Computer Engineering and Applications    2022, 58 (9): 303-312.   DOI: 10.3778/j.issn.1002-8331.2112-0242 Abstract （79）      PDF（pc） （1381KB）（94）       Knowledge map    Save For high-risk industries such as steel manufacturing, coal mining and construction industries, wearing helmets during construction is one of effective ways to avoid injuries. For the current helmet wearing detection model in a complex environment for small and dense targets, there are problems such as false detection and missed detection, an improved YOLOv5 target detection method is proposed to detect the helmet wearing. A coordinate attention mechanism（coordinate attention） is added to the backbone network of YOLOv5, which embeds location information into channel attention so that the network can pay attention on a larger area. The original feature pyramid module in the feature fusion module is replaced with a weighted bi-directional feature pyramid（BiFPN）network structure to achieve efficient bi-directional cross-scale connectivity and weighted feature fusion. The experimental results on the homemade helmet dataset show that the improved YOLOv5 model achieves an average accuracy of 95.9%, which is 5.1 percentage points higher than the YOLOv5 model, and meets the requirements for small and dense target detection in complex environments. Reference | Related Articles | Metrics

Select

Improved YOLOv3 Target Detection Algorithm Combined with DBSCAN LI Yunhong, ZHANG Xuan, LI Chuanzhen, SU Xueping, NIE Mengxuan, BI Yuandong, XIE Rongrong Computer Engineering and Applications    2022, 58 (10): 208-215.   DOI: 10.3778/j.issn.1002-8331.2010-0251 Abstract （24）      PDF（pc） （1223KB）（94）       Knowledge map    Save Aiming at the problems of low recognition rate and low recognition accuracy when the YOLOv3（you only look once） detection algorithm detects small targets and occluded targets, an improved YOLOv3 algorithm is proposed in combination with DBSCAN（density-based spatial clustering of applications with noise） for target detection. Firstly, DBSCAN clustering algorithm is added to YOLOv3 network, and the detection target is extracted to achieve multi-scale clustering of the dataset to obtain the first generation feature map, and then the anchor point location is determined by improving [K]-means clustering algorithm to achieve better clustering. Finally, the improved YOLOv3 algorithm is trained and tested on VOC2007+2012 dataset and MS-COCO dataset. The experimental results show that the improved YOLOv3 algorithm increases the mAP of detection target by 14.9 percentage points and 12.5 percentage points on the VOC dataset and MS-COCO dataset, respectively. The improved YOLOv3 detection algorithm has better detection results in comparison with other deep learning target detection algorithms, as well as good portability and better robustness. Reference | Related Articles | Metrics

Select

Self-Conclusion and Self-Adaptive Variation Particle Swarm Optimization CHEN Bowen, ZOU Hai Computer Engineering and Applications    2022, 58 (8): 67-75.   DOI: 10.3778/j.issn.1002-8331.2105-0151 Abstract （88）      PDF（pc） （1331KB）（113）       Knowledge map    Save Aiming at the shortcomings of particle swarm optimization（PSO） algorithm, which is easy to fall into local optimum and low precision during iteration, this paper proposes a self-conclusion and self-adaptive variation particle swarm optimization（SCVPSO）. Firstly, the position of each particle is dynamically updated by nonlinear turning up and then decreasing inertia weight to avoid premature. Secondly, the local particles are searched backward to improve the efficiency of population optimization. Finally, a new parameter scr（self-conclusion rate） is introduced to summarize the recent solution situation of each particle, and the probability directed variation is used to guide the particles to the global optimum to increase the diversity of particles. With the help of 15 test functions, compared with other variant particle swarm optimization algorithm, the results show that the improved algorithm is significantly better than other algorithms in solving performance, which verifies the effectiveness of the strategy. Reference | Related Articles | Metrics

Select

Image Semantic Segmentation Based on Fully Convolutional Neural Network ZHANG Xin, YAO Qing’an, ZHAO Jian, JIN Zhenjun, FENG Yuncong Computer Engineering and Applications    2022, 58 (8): 45-57.   DOI: 10.3778/j.issn.1002-8331.2109-0091 Abstract （114）      PDF（pc） （1057KB）（120）       Knowledge map    Save Image semantic segmentation is a hot research topic in the field of computer vision. With the rapid rise of fully convolutional neural networks, the development of fusion of image semantic segmentation and fully convolutional networks has shown very bright results. Through the collection of high-quality literature in recent years, the focus is on the summary of full convolutional neural network image semantic segmentation methods. The collected literature is divided into classical semantic segmentation, real-time semantic segmentation and RGBD semantic segmentation according to the application scenarios, and then the representative segmentation methods are described. Commonly used public datasets and evaluation metrics for performance are also summarized, and experiments on commonly used datasets are analyzed and summarized. Finally, the possible future research directions of fully convolutional neural networks are prospected. Reference | Related Articles | Metrics

Select

Adaptive multi-thresholds segmentation of DPM barcode image in complex illumination WANG Juan1，2, WANG Ping2, LIU Min1 Computer Engineering and Applications    2018, 54 (9): 194-200.   DOI: 10.3778/j.issn.1002-8331.1611-0392 Abstract （309）      PDF（pc） （1192KB）（451）       Knowledge map    Save Under complex industrial conditions, two-dimensional DPM barcode captured by a CCD camera easily has large spots or shadow areas owing to the complex illumination. This phenomenon results in the missing information in DPM area and the identification difficulty. Therefore, this paper proposes adaptive multi-threshold segmentation algorithm based on subsection histogram concavity analysis. Firstly, on the basis of smoothed histogram, a series of local peak values are calculated by the simplified formula. Moreover, the histogram is segmented through these local peak values. Then subsection thresholds are computed by recursive algorithm. Secondly, an adaptive correction factor based on the local area information is introduced to modify the subsection threshold for the status of the low local contrast. Experimental results show that the proposed method has superior division performance and more efficient operation to traditional threshold segmentation algorithms. The average running efficiency of this method improves 17.75 times than the fastest one of those conventional algorithms. After the adaptive multi-threshold segmentation, the contrast of uneven illumination area is significantly enhanced and missing DPM regional information is effectively compensated. Therefore, the method in this paper provides a sufficient condition for the accurate identification of the DPM barcode. It can also be applied to the contrast changeable image enhancement. Related Articles | Metrics

Select

Historical Chinese Seal Text Recognition Based on ResNet and Transfer Learning CHEN Yaya, LIU Quanxiang, WANG Kaili, YI Yaohua Computer Engineering and Applications    2022, 58 (10): 125-131.   DOI: 10.3778/j.issn.1002-8331.2101-0247 Abstract （15）      PDF（pc） （3009KB）（82）       Knowledge map    Save It is difficult to recognize historical Chinese seal text due to image degradation and super classification. In addition, the insufficient annotation data lead to poor generalization ability and classification accuracy. According to the above problems, a historical Chinese seal text recognition method based on ResNet and transfer learning is proposed. Firstly, using synthetic dataset as source domain, a pre-trained model is trained on deep residual network. Secondly, transfer learning is introduced to model combining data enhancement and label smoothing. In this process, the historical Chinese seal text dataset is taken as target domain. Finally, the recognition results in different networks are compared and the transfer learning effectiveness is analyzed. The experimental results show that this method can improve recognition accuracy effectively. Reference | Related Articles | Metrics

Select

Fractal Image Compression Algorithm Based on Double-Layer Non-Negative Matrix Factorization FANG Meidong, WANG Hui, ZHANG Aihua Computer Engineering and Applications    2022, 58 (8): 204-213.   DOI: 10.3778/j.issn.1002-8331.2009-0350 Abstract （33）      PDF（pc） （1271KB）（80）       Knowledge map    Save As a structure-based image compression technology, fractal image compression is used in many image processing. However, the encoding stage of fractal image compression is very time-consuming, and the quality of the reconstructed image is not good. To solve these problems, a fractal image compression coding algorithm based on double-layer non-negative matrix factorization（DLNMF） is proposed. In the traditional theory of non-negative matrix factorization（NMF）, the projection non-negative matrix factorization（PNMF） is combined with the [L3/2] norm constraint to extract representative image features in a short time. Firstly, the features of the original image are extracted by double-layer non-negative matrix decomposition; then the image features are clustered by [K]-means, and the classified image blocks are obtained according to the corresponding index; orthogonal sparse decomposition is performed in the corresponding class blocks to obtain the fractal code; and finally, the reconstructed image is obtained according to the fractal code. Experimental results show that compared with images reconstructed by fast sparse fractal image compression theory, the fractal compression algorithm of double-layer non-negative matrix factorization improves the quality of the reconstructed image and shortens the encoding time. Reference | Related Articles | Metrics

Select

Review of Development and Application of Artificial Neural Network Models ZHANG Chi, GUO Yuan, LI Ming Computer Engineering and Applications    2021, 57 (11): 57-69.   DOI: 10.3778/j.issn.1002-8331.2102-0256 Abstract （537）      PDF（pc） （781KB）（665）       Knowledge map    Save Artificial neural networks are increasingly closely related to other subject areas. People solve problems in various fields by exploring and improving the layer structure of artificial neural networks. Based on the analysis of artificial neural networks related literature, this paper summarizes the history of artificial neural network growth and presents relevant principles of artificial neural networks based on the development of neural networks, including multilayer perceptron, back-propagation algorithm, convolutional neural network and recurrent neural network, explains the classic convolutional neural network model in the development of the convolutional neural network and the widely used variant network structure in the recurrent neural network, reviews the application of each artificial neural network algorithm in related fields, summarizes the possible direction of development of the artificial neural network. Related Articles | Metrics

Select

Research on parallel clustering of power load based on improved K-Means algorithm XU Yuanbin1, LI Guohui2，3, GUO Kun2，3, GUO Songrong2，3, LIN Wei2，3 Computer Engineering and Applications    2017, 53 (17): 260-265.   DOI: 10.3778/j.issn.1002-8331.1603-0110 Abstract （301）      PDF（pc） （1070KB）（581）       Knowledge map    Save The electrical power enterprise usually based on power load data, uses the traditional K-Means algorithm to classify the customers, but the biggest drawback of this method must be specified by the user manual clustering number of clusters. It proposes a method combining Canopy algorithm and K-Means algorithm based on load clustering, without the need to manually specify the number of clusters, the automatic division of the customer. First of all, it collects users’ electricity data, uses the parallel computing framework MapReduce to preprocess the original data. Then, it uses Canopy and K-Means algorithm to establish the clustering model of automatic load. Finally, in the real consumption data on the empirical analysis, by using the Silhouette index to evaluate, it shows that the proposed method is more stable and convenient, and has wider applicability. Related Articles | Metrics

Select

[(t,n)] threshold signature scheme with safety and tracability without trusted party XIE Junqin, ZHANG Jianzhong Computer Engineering and Applications    2013, 49 (16): 77-81.   Abstract （1465）      PDF（pc） （524KB）（520）       Knowledge map    Save The threshold signature can be classified into the two categories, solutions with the assistance of a trusted party and solutions without the assistance of a trusted party. In some special cases, as an authority which can be trusted by all members does not always exist, a threshhold signature scheme without a trusted party seems more attractive. A new traceability threshhold signature scheme without a trusted party is proposed based on Wang-Li scheme after analyzing WLC threshhold signature scheme. The security of this scheme is analyzed. The results show that the proposed scheme can not only resist conspiracy attacks and forgery attacks, but also provide anonymity and tracebility simultaneously. Besides, it can realize the unknow ability of groups secret by constructing a secure distributed key generation protocol. Related Articles | Metrics

Select

Summary of Research and Application of Neighborhood Field Optimization Algorithm WU Zhou, ZHANG Hongrui, ZHANG Haijun, SONG Qing Computer Engineering and Applications    2022, 58 (9): 1-8.   DOI: 10.3778/j.issn.1002-8331.2111-0563 Abstract （66）      PDF（pc） （969KB）（66）       Knowledge map    Save Neighborhood field optimization algorithm（NFO）?is a new swarm intelligence optimization algorithm inspired by the learning behavior of biological individuals from neighbors. The algorithm has the advantages of few parameters, simple structure and good local optimization performance, and it has attracted domestic and foreign many scholars have carried out research on it.?This paper briefly describes the optimization mechanism and search steps of NFO algorithm, the improvement of the algorithm is analyzed, including hybrid algorithm, coding mode and search step size, etc., and summarizes the applications of the algorithm in energy efficiency, path planning, economic scheduling and so on.?Combined with the characteristics of NFO algorithm and the existing research results, the future research content and direction of the algorithm are prospected. Reference | Related Articles | Metrics

Select

Survey of Intelligent Question Answering Research Based on Knowledge Graph WANG Zhiyue, YU Qing, WANG Nan, WANG Yaoguo Computer Engineering and Applications    2020, 56 (23): 1-11.   DOI: 10.3778/j.issn.1002-8331.2004-0370 Abstract （785）      PDF（pc） （774KB）（1043）       Knowledge map    Save The answer selection model based on knowledge graph has become one of the hottest directions at present. This paper introduces the implementation of answer selection model based on knowledge graph from four aspects of template method, semantic parsing, deep learning and knowledge graph embedding, sums up their advantages, disadvantages and unsolved problem. Combined with the development of artificial intelligence technology, this paper introduces intelligent question-answer system based on deep learning. This research is helpful for more researchers to devote themselves to the intelligent question-answer system and develops different kinds of intelligent question-answer system to improve the social intelligent information service. Related Articles | Metrics

Select

Review of Research on Approximate Reinforcement Learning Algorithms SI Yanna, PU Jiexin, SUN Lifan Computer Engineering and Applications    2022, 58 (8): 33-44.   DOI: 10.3778/j.issn.1002-8331.2112-0082 Abstract （107）      PDF（pc） （678KB）（83）       Knowledge map    Save Reinforcement learning（RL） is one of the most important techniques for artificial intelligence（AI）. However, traditional tabular reinforcement learning is difficult to deal with control problems with large scale or continuous space. Approximate reinforcement learning is inspired by the idea of function approximation to parameterize the value function or strategy function, and obtains the optimal strategy indirectly through parameter optimization. It has been widely used in video games, Go game, robot control, etc. and obtained remarkable performance. In view of this, this paper reviews the research status and application progress of approximate reinforcement learning algorithms. Firstly, the basic theory of approximate reinforcement learning is introduced. Then the classical algorithms of approximate reinforcement learning are classified and expounded, including some corresponding improvement methods. Finally, the research progress of approximate reinforcement learning in robotics is summarized, and some major problems are summarized to provide reference for future research. Reference | Related Articles | Metrics

Select

Comprehensive Survey on Knowledge Graph Embedding XU Youwei, ZHANG Hongjun, CHENG Kai, LIAO Xianglin, ZHANG Zixuan, LI Lei Computer Engineering and Applications    2022, 58 (9): 30-50.   DOI: 10.3778/j.issn.1002-8331.2111-0248 Abstract （58）      PDF（pc） （991KB）（59）       Knowledge map    Save With the rapid development of Internet technology and application mode, knowledge graph has received much attention due to its rich and intuitive expressivity, and a large number of researches in knowledge representation learning have been accumulated, playing an important role in vertical searching, intelligent question answering and other application fields. On the basis of summarizing the existing research on knowledge graph embedding, knowledge graph embedding models are divided into two categories based on the number of knowledge graphs: link prediction models oriented to a single knowledge graph and entity alignment models oriented to multiple knowledge graphs. The standard processing flow of knowledge graph embedding models are also analyzed by categories. Detail information are combed according to model assumptions, implementation methods, semantic-capturing levels and other aspects. By fully discussing on the existed problems of knowledge graph embedding models, future research directions of knowledge graph embedding are prospected. Reference | Related Articles | Metrics

Select

Memory-Related Vulnerability Detection Method Based on Abstract Memory Model XU Jian, CHEN Pinghua, XIONG Jianbin Computer Engineering and Applications    2022, 58 (8): 96-108.   DOI: 10.3778/j.issn.1002-8331.2010-0354 Abstract （59）      PDF（pc） （994KB）（67）       Knowledge map    Save Aiming at the problems of the existing memory-related vulnerability detection model algorithms that rely on pointer data flow which is resulting in a large number of false positives and false negatives, lack of formal description of vulnerability characteristics, and incomplete description of vulnerability characteristics, a method for memory-related vulnerability detection based on abstract memory model is proposed. Firstly, it defines the abstract memory model. Then, based on the abstract memory model, it formalizes and symbolizes the characteristics of the three types of memory-related vulnerabilities：memory leak, double free, and use after free. Secondly, based on the control flow graph of the code, it uses the feasible path solving algorithm to obtain all feasible paths of the code, and the runtime state of the abstract memory is determined on all feasible paths to detect whether the code has memory-related vulnerabilities. Finally, the detection method is verified on the three test data sets of CWE401, CWE415, and CWE416 related to memory vulnerabilities in Juliet Test Suite, and the experimental results show that compared with the detection methods that rely on pointer data flow, the false positive rate and false negative rate of the method in the detection of memory-related vulnerabilities are reduced. Reference | Related Articles | Metrics

Select

Chinese Named Entity Recognition Based on Gated Multi-Feature Extractors YANG Rongying, HE Qing, DU Nisuo Computer Engineering and Applications    2022, 58 (8): 117-124.   DOI: 10.3778/j.issn.1002-8331.2009-0363 Abstract （89）      PDF（pc） （933KB）（82）       Knowledge map    Save Without introducing other auxiliary features, only focusing on the text, it constructs multiple feature extractors to capture more abstract, deeper, and higher-dimensional features of the text sequence. It uses the BERT pre-training model to obtain more rich information of word embedding. Word embedding is input into BiLSTM and IDCNN respectively for the first round of feature extraction. In order to obtain higher-dimensional features, transmitting information on multi-channel and control the flow, a gating mechanism is introduced in the IDCNN. In order to improve the efficiency of feature extraction, multi-head self-attention mechanism is added. It constructs share-BiLSTM, realizes the interactive circulation of features, improves the strength of feature representation. It creates two CRF to enrich feature distribution and cross-layer transmission, to promote the accuracy of predicting tag sequence. Tested on two data sets and compared with four NER models, the results show that the F1 value has been improved to a certain extent. Reference | Related Articles | Metrics

Select

Survey of Interpretability Research on Deep Learning Models ZENG Chunyan, YAN Kang, WANG Zhifeng, YU Yan, JI Chunmei Computer Engineering and Applications    2021, 57 (8): 1-9.   DOI: 10.3778/j.issn.1002-8331.2012-0357 Abstract （379）      PDF（pc） （677KB）（582）       Knowledge map    Save With the characteristics of data-driven learning, deep learning technology has made great achievements in the fields of natural language processing, image processing, and speech recognition. However, due to the deep learning model featured by deep networks, many parameters, high complexity and other characteristics, the decisions and intermediate processes made by the model are difficult for humans to understand. Therefore, exploring the interpretability of deep learning has become a new topic in the current artificial intelligence field. This review takes the interpretability of deep learning models as the research object and summarizes its progress. Firstly, the main interpretability methods are summarized and analyzed from four aspects：self-explanatory model, model-specific explanation, model-agnostic explanation, and causal interpretability. At the same time, it enumerates the application of interpretability related technologies, and finally discusses the existing problems of current interpretability research to promote the further development of the deep learning interpretability research framework. Related Articles | Metrics

Select

Summary of crossover operator of genetic algorithm LI Shuquan1, SUN Xue1, SUN Dehui1, BIAN Weipeng2 Computer Engineering and Applications    2012, 48 (1): 36-39.   Abstract （1423）      PDF（pc） （545KB）（3048）       Knowledge map    Save Crossover is an important operator in genetic algorithm. This paper gives a brief introduction about some mature crossover operators, discusses some improved crossover operators from different aspects, such as the application of theory, mechanism and so on. Through the analysis, it is found that the improved crossover operators can overcome the shortcomings of the traditional genetic algorithm, improve search efficiency and accuracy and avoid premature convergence. This paper points out the crossover operators’ research direction, which makes the foundation for the development and application of genetic algorithms in the future. Related Articles | Metrics

Select

Survey on Attention Mechanisms in Deep Learning Recommendation Models GAO Guangshang Computer Engineering and Applications    2022, 58 (9): 9-18.   DOI: 10.3778/j.issn.1002-8331.2112-0382 Abstract （55）      PDF（pc） （944KB）（57）       Knowledge map    Save Aims to explore how the attention mechanism helps the recommendation model to dynamically focus on specific parts of the input that help to perform the current recommendation task. This paper analyzes the attention mechanism network framework and the weight calculation method of its input data, and then summarizes from the five perspectives of vanillaattention mechanism, co-attention mechanism, self-attention mechanism, hierarchical attention mechanism, and multi-head attention mechanism. Analyze how it uses key strategies, algorithms, or techniques to calculate the weight of the current input data, and use the calculated weights so that the recommendation model can focus on the necessary parts of the input at each step of the recommendation task, more effective user or item feature representation can be generated, and the operating efficiency and generalization ability of the recommendation model are improved. The attention mechanism can help the recommendation model assign different weights to each part of the input, extract more critical and important information, and enable the recommendation model to make more accurate judgments, and it will not bring more overhead to the calculation and storage of the recommendation model. Although the existing deep learning recommendation model with the attention mechanism can meet the needs of most recommendation tasks to a certain extent, it is certain that the uncertainty of human needs and the explosive growth of information under certain circumstances factors, it will still face the challenges of recommendation diversity, recommendation interpretability, and the integration of multiple auxiliary information. Reference | Related Articles | Metrics

Select

Intelligent Routing Algorithm Based on SDN Environment Awareness ZHAO Jihong, ZHANG Mengxue, QIAO Linlin, ZHANG Wenjuan, LU Liwei Computer Engineering and Applications    2022, 58 (8): 90-95.   DOI: 10.3778/j.issn.1002-8331.2011-0217 Abstract （80）      PDF（pc） （711KB）（70）       Knowledge map    Save With the access of a large number of devices in the network, the environment in the network is becoming more and more complex and diversified. The traditional software-defined network（SDN） routing algorithm does not consider the environmental factors in the network when it finds the way. If these factors are not considered, the real-time status awareness of network nodes cannot be better realized, then users cannot have a better network experience. In response to this problem, combined with network environment information, an intelligent routing algorithm based on SDN network environment awareness is proposed. This algorithm divides two-dimensionally in time, integrates the attribute information of nodes, calculates the probability of encounter between nodes, and then predicts through BP neural network, and finally selects a suitable relay node to complete the data transmission. Simulation experiments have proved the effectiveness of the algorithm in data transmission rate, delay and transmission hops. Reference | Related Articles | Metrics

Select

Review of Application of Transfer Learning in Medical Image Field GAO Shuang, XU Qiaozhi Computer Engineering and Applications    2021, 57 (24): 39-50.   DOI: 10.3778/j.issn.1002-8331.2107-0300 Abstract （288）      PDF（pc） （896KB）（432）       Knowledge map    Save Deep learning technology has developed rapidly and achieved significant results in the field of medical image treatment. However, due to the small number of medical image samples and difficult annotation, the effect of deep learning is far from reaching the expectation. In recent years, using transfer learning method to alleviate the problem of insufficient medical image samples and improve the effect of deep learning technology in the field of medical image has become one of the research hotspots. This paper first introduces the basic concepts, types, common strategies and models of transfer learning methods, then combs and summarizes the representative related research in the field of medical images according to the types of transfer learning methods, and finally summarizes and prospects the future development of this field. Reference | Related Articles | Metrics

Select

Research on Graph Neural Network Recommendation Method LIU Xin, MEI Hongyan, WANG Jiahao, LI Xiaohui Computer Engineering and Applications    2022, 58 (10): 41-49.   DOI: 10.3778/j.issn.1002-8331.2110-0345 Abstract （31）      PDF（pc） （984KB）（51）       Knowledge map    Save Graph neural network has a good application effect in many application fields because of its characteristics, the combination of graph neural network and recommendation has become one of the research hot spots. Using graph neural network in recommendation can significantly improve the level of recommendation in complex environment. In this paper, the graph neural network method, personalized recommendation and group recommendation are introduced respectively. The recommendation methods based on graph neural network are summarized, focusing on graph neural network and its recent research achievements in the field of recommendation. The recommendation research status and the difficulties in further development are analyzed. According to the advantages of graph neural network, the feasibility of combining graph neural network with group recommendation is analyzed and prospected. Reference | Related Articles | Metrics

Select

Review of Text Sentiment Analysis Methods WANG Ting, YANG Wenzhong Computer Engineering and Applications    2021, 57 (12): 11-24.   DOI: 10.3778/j.issn.1002-8331.2101-0022 Abstract （441）      PDF（pc） （906KB）（510）       Knowledge map    Save Text sentiment analysis is an important branch of natural language processing, which is widely used in public opinion analysis and content recommendation. It is also a hot topic in recent years. According to different methods used, it is divided into sentiment analysis based on emotional dictionary, sentiment analysis based on traditional machine learning, and sentiment analysis based on deep learning. Through comparing these three methods, the research results are analyzed, and the paper summarizes the advantages and disadvantages of different methods, introduces the related data sets and evaluation index, and application scenario, analysis of emotional subtasks is simple summarized. The future research trend and application field of sentiment analysis problem are found. Certain help and guidance are provided for the researchers in the related areas. Related Articles | Metrics

Select

Attention Mechanism-Based CNN-LSTM Model and Its Application LI Mei1，2, NING Dejun1, GUO Jiacheng1，2 Computer Engineering and Applications    2019, 55 (13): 20-27.   DOI: 10.3778/j.issn.1002-8331.1901-0246 Abstract （862）      PDF（pc） （914KB）（2219）       Knowledge map    Save Time series have temporal property, and the characteristics of its short sequences are different in importance. Aiming at the characteristics of time series, a neural network prediction model based on Convolution Neural Network（CNN） and Long Short-Term Memory（LSTM） is proposed, which combines coarse and fine grain features to achieve accurate time series prediction. The model consists of two parts. CNN based on attention mechanism adds attention branch to standard CNN network to extract important fine-grained features. The back end is LSTM, which extracts the coarse-grained features of the hidden time series from fine-grained features. Experiments on real cogeneration heat load dataset demonstrate that the model is better than the autoregressive integrated moving average, support vector regression, CNN and LSTM models. Compared with the pre-determined method currently used by enterprises, the Mean Absolute Scaled Error（MASE） and Root Mean Square Error（RMSE） have been increased by 89.64% and 61.73% respectively. Related Articles | Metrics

Select

Low Illumination Image Enhancement Method Based on DenseNet GAN WANG Zhaoqian, KONG Weiwei, TENG Jinbao, TIAN Qiaoxin Computer Engineering and Applications    2022, 58 (8): 214-220.   DOI: 10.3778/j.issn.1002-8331.2010-0011 Abstract （81）      PDF（pc） （926KB）（73）       Knowledge map    Save Aiming at the problems of low SNR, low resolution and low illumination in low illumination environment, a low illumination image enhancement method based on DenseNet generation countermeasure network is proposed. Firstly, the DenseNet framework is used to establish the generator network, and PatchGAN is used as the discriminator network. Secondly, the low illumination image is transferred into the generator network to generate the illumination enhanced image, and the discriminator network is used to supervise the enhancement effect of the generator on the low illumination image. Through the game between the generator and the discriminator, the network weight is continuously optimized, and finally the generator has good enhancement effect on low illumination image. Experimental results show that, compared with the existing mainstream methods, this method not only has obvious advantages in brightness enhancement and clarity restoration of low illumination images, but also has significant advantages in objective evaluation indexes of image quality such as peak signal-to-noise ratio and structure similarity. Reference | Related Articles | Metrics