Most Read articles

    Published in last 1 year |  In last 2 years |  In last 3 years |  All

    Published in last 1 year
    Please wait a minute...
    For Selected: Toggle Thumbnails
    Research Progress of Transformer Based on Computer Vision
    LIU Wenting, LU Xinming
    Computer Engineering and Applications    2022, 58 (6): 1-16.   DOI: 10.3778/j.issn.1002-8331.2106-0442
    Abstract452)      PDF(pc) (1089KB)(401)       Save
    Transformer is a deep neural network based on the self-attention mechanism and parallel processing data. In recent years, Transformer-based models have emerged as an important area of research for computer vision tasks. Aiming at the current blanks in domestic review articles based on Transformer, this paper covers its application in computer vision. This paper reviews the basic principles of the Transformer model, mainly focuses on the application of seven visual tasks such as image classification, object detection and segmentation, and analyzes Transformer-based models with significant effects. Finally, this paper summarizes the challenges and future development trends of the Transformer model in computer vision.
    Reference | Related Articles | Metrics
    Research Progress of Natural Language Processing Based on Deep Learning
    JIANG Yangyang, JIN Bo, ZHANG Baochang
    Computer Engineering and Applications    2021, 57 (22): 1-14.   DOI: 10.3778/j.issn.1002-8331.2106-0166
    Abstract422)      PDF(pc) (1781KB)(123)       Save

    This paper comprehensively analyzes the research of deep learning in the field of natural language processing through a combination of quantitative and qualitative methods. It uses CiteSpace and VOSviewer to draw a knowledge graph of countries, institutions, journal distribution, keywords co-occurrence, co-citation network clustering, and timeline view of deep learning in the field of natural language processing to clarify the research. Through mining important researches in the field, this paper summarizes the research trend, the main problems, development bottlenecks, and gives corresponding solutions and ideas. Finally, suggestions are given on how to track the research of deep learning in the field of natural language processing, and provides references for subsequent research and development in the field.

    Reference | Related Articles | Metrics
    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
    Abstract360)      PDF(pc) (896KB)(526)       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
    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
    Abstract357)      PDF(pc) (1381KB)(333)       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
    Multi-channel Attention Mechanism Text Classification Model Based on CNN and LSTM
    TENG Jinbao, KONG Weiwei, TIAN Qiaoxin, WANG Zhaoqian, LI Long
    Computer Engineering and Applications    2021, 57 (23): 154-162.   DOI: 10.3778/j.issn.1002-8331.2104-0212
    Abstract348)      PDF(pc) (844KB)(227)       Save

    Aiming at the problem that traditional Convolutional Neural Network(CNN) and Long Short-Term Memory (LSTM) can not reflect the importance of each word in the text when extracting features, this paper proposes a multi-channel text classification model based on CNN and LSTM. Firstly, CNN and LSTM are used to extract the local information and context features of the text; secondly, multi-channel attention mechanism is used to extract the attention score of the output information of CNN and LSTM; finally, the output information of multi-channel attention mechanism is fused to achieve the effective extraction of text features and focus attention on important words. Experimental results on three public datasets show that the proposed model is better than CNN, LSTM and their improved models, and can effectively improve the effect of text classification.

    Reference | Related Articles | Metrics
    Survey of Opponent Modeling Methods and Applications in Intelligent Game Confrontation
    WEI Tingting, YUAN Weilin, LUO Junren, ZHANG Wanpeng
    Computer Engineering and Applications    2022, 58 (9): 19-29.   DOI: 10.3778/j.issn.1002-8331.2202-0297
    Abstract325)      PDF(pc) (904KB)(116)       Save
    Intelligent game confrontation has always been the focus of artificial intelligence research. In the game confrontation environment, the actions, goals, strategies, and other related attributes of agent can be inferred by opponent modeling, which provides key information for game strategy formulation. The application of opponent modeling method in competitive games and combat simulation is promising, and the formulation of game strategy must be premised on the action strategy of all parties in the game, so it is especially important to establish an accurate model of opponent behavior to predict its intention. From three dimensions of connotation, method, and application, the necessity of opponent modeling is expounded and the existing modeling methods are classified. The prediction method based on reinforcement learning, reasoning method based on theory of mind, and optimization method based on Bayesian are summarized. Taking the sequential game(Texas Hold’em), real-time strategy game(StarCraft), and meta-game as typical application scenarios, the role of opponent modeling in intelligent game confrontation is analyzed. Finally, the development of adversary modeling technology prospects from three aspects of bounded rationality, deception strategy and interpretability.
    Reference | Related Articles | Metrics
    COVID-19 Medical Imaging Dataset and Research Progress
    LIU Rui, DING Hui, SHANG Yuanyuan, SHAO Zhuhong, LIU Tie
    Computer Engineering and Applications    2021, 57 (22): 15-27.   DOI: 10.3778/j.issn.1002-8331.2106-0118
    Abstract317)      PDF(pc) (1013KB)(241)       Save

    As imaging technology has been playing an important role in the diagnosis and evaluation of the new coronavirus(COVID-19), COVID-19 related datasets have been successively published. But few review articles discuss COVID-19 image processing, especially in datasets. To this end, the new coronary pneumonia datasets and deep learning models are sorted and analyzed, through COVID-19-related journal papers, reports, and related open-source dataset websites, which include Computer Tomography(CT) image and X-rays(CXR)image datasets. At the same time, the characteristics of the medical images presented by these datasets are analyzed. This paper focuses on collating and describing open-source datasets related to COVID-19 medical imaging. In addition, some important segmentation and classification models that perform well on the related datasets are analyzed and compared. Finally, this paper discusses the future development trend on lung imaging technology.

    Reference | Related Articles | Metrics
    Intelligent Analysis of Text Information Disclosure of Listed Companies
    LYU Pin, WU Qinjuan, XU Jia
    Computer Engineering and Applications    2021, 57 (24): 1-13.   DOI: 10.3778/j.issn.1002-8331.2106-0270
    Abstract287)      PDF(pc) (724KB)(229)       Save

    The analysis of the text disclosure issued by listed companies is an important way for investors to understand the companies’ operating conditions and to make investment decisions. However, the method based on manual reading and analysis has low efficiency and high cost. The development of artificial intelligence technology provides an opportunity for intelligent analysis of companies’ text information, which can mine valuable information from massive enterprise text data, fulfill the advantages of data-driven, and greatly improve the analysis efficiency. Hence, it has become a research hotspot in recent years. The research work in recent ten years about the announcement of listed companies is summarized from three aspects:the event types of the text information disclosure, intelligent analysis method and application scenario. The current challenges in this field are also discussed, and possible future research directions according to the existing shortcomings are finally pointed out.

    Reference | Related Articles | Metrics
    Overview on Reinforcement Learning of Multi-agent Game
    WANG Jun, CAO Lei, CHEN Xiliang, LAI Jun, ZHANG Legui
    Computer Engineering and Applications    2021, 57 (21): 1-13.   DOI: 10.3778/j.issn.1002-8331.2104-0432
    Abstract271)      PDF(pc) (779KB)(429)       Save

    The use of deep reinforcement learning to solve single-agent tasks has made breakthrough progress. Since the complexity of multi-agent systems, common algorithms cannot solve the main difficulties. At the same time, due to the increase in the number of agents, taking the expected value of maximizing the cumulative return of a single agent as the learning goal often fails to converge and some special convergence points do not satisfy the rationality of the strategy. For practical problems that there is no optimal solution, the reinforcement learning algorithm is even more helpless. The introduction of game theory into reinforcement learning can solve the interrelationship of agents very well and explain the rationality of the strategy corresponding to the convergence point. More importantly, it can use the equilibrium solution to replace the optimal solution in order to obtain a relatively effective strategy. Therefore, this article investigates the reinforcement learning algorithms that have emerged in recent years from the perspective of game theory, summarizes the important and difficult points of current game reinforcement learning algorithms and gives several breakthrough directions that may solve the above-mentioned difficulties.

    Reference | Related Articles | Metrics
    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
    Abstract244)      PDF(pc) (913KB)(237)       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
    Research on Local Path Planning Algorithm Based on Improved TEB Algorithm
    DAI Wanyu, ZHANG Lijuan, WU Jiafeng, MA Xianghua
    Computer Engineering and Applications    2022, 58 (8): 283-288.   DOI: 10.3778/j.issn.1002-8331.2108-0290
    Abstract230)      PDF(pc) (878KB)(63)       Save
    When the traditional TEB(time elastic band) algorithm is used to plan the path in a complex dynamic environment, path vibrations caused by the unsmooth speed control amount will occur, which will bring greater impact to the robot and prone to collisions. Aiming at the above problems, the traditional TEB algorithm is improved. The detected irregular obstacles are expansion treatment and regional classification strategy, and the driving route in the safe area is given priority to make the robot run more safely and smoothly in the complex environment. Adding the obstacle distance to the speed constraint in the algorithm can effectively reduce the vibration amplitude and the impact of the robot during the path driving process caused by the speed jump after the robot approaches the obstacle, so as to ensure the safety of the robot during operation. A large number of comparative simulations in the ROS environment show that in a complex dynamic environment, the path planned by the improved TEB algorithm is safer and smoother, which can effectively reduce the impact of the robot.
    Reference | Related Articles | Metrics
    Review on Integration Analysis and Application of Multi-omics Data
    ZHONG Yating, LIN Yanmei, CHEN Dingjia, PENG Yuzhong, ZENG Yuanpeng
    Computer Engineering and Applications    2021, 57 (23): 1-17.   DOI: 10.3778/j.issn.1002-8331.2106-0341
    Abstract218)      PDF(pc) (806KB)(323)       Save

    With the continuous emergence and popularization of new omics sequencing technology, a large number of omics data have been produced, which is of great significance for people to further study and reveal the mysteries of life. Using multi-omics data to integrate and analyze life science problems can obtain more abundant and more comprehensive information related to life system, which has become a new direction for scientists to explore the mechanism of life. This paper introduces the research background and significance of multi-omics data integration analysis, summarizes the methods of data integration analysis of multiomics in recent years and the applied research in related fields, and finally discusses the current existing problems and future prospects of multi-omics data integration analysis methods.

    Reference | Related Articles | Metrics
    Summary of Intrusion Detection Models Based on Deep Learning
    ZHANG Hao, ZHANG Xiaoyu, ZHANG Zhenyou, LI Wei
    Computer Engineering and Applications    2022, 58 (6): 17-28.   DOI: 10.3778/j.issn.1002-8331.2107-0084
    Abstract208)      PDF(pc) (997KB)(192)       Save
    With the continuous in-depth development of deep learning technology, intrusion detection model based on deep learning has become a research hotspot in the field of network security. This paper summarizes the commonly used data preprocessing operations in network intrusion detection. The popular intrusion detection models based on deep learning, such as convolutional neural network, long short-term memory network, auto-encode and generative adversarial networks, are analyzed and compared. The data sets commonly used in the research of intrusion detection model based on deep learning are introduced. It points out the problems of the existing intrusion detection models based on deep learning in data set timeliness, real-time, universality, model training time and other aspects, and the possible research focus in the future.
    Reference | Related Articles | Metrics
    Computer Engineering and Applications    2021, 57 (24): 0-0.  
    Abstract207)      PDF(pc) (1168KB)(284)       Save
    Related Articles | Metrics
    Review of Research on Small Target Detection Based on Deep Learning
    ZHANG Yan, ZHANG Minglu, LYU Xiaoling, GUO Ce, JIANG Zhihong
    Computer Engineering and Applications    2022, 58 (15): 1-17.   DOI: 10.3778/j.issn.1002-8331.2112-0176
    Abstract194)      PDF(pc) (995KB)(161)       Save
    The task of target detection is to quickly and accurately identify and locate predefined categories of objects from an image. With the development of deep learning techniques, detection algorithms have achieved good results for large and medium targets in the industry. The performance of small target detection algorithms based on deep learning still needs further improvement and optimization due to the characteristics of small targets in images such as small size, incomplete features and large gap between them and the background. Small target detection has a wide demand in many fields such as autonomous driving, medical diagnosis and UAV navigation, so the research has high application value. Based on extensive literature research, this paper firstly defines small target detection and finds the current difficulties in small target detection. It analyzes the current research status from six research directions based on these difficulties and summarizes the advantages and disadvantages of each algorithm. It makes reasonable predictions and outlooks on the future research directions in this field by combining the literature and the development status to provide a certain basic reference for subsequent research. This paper makes a reasonable prediction and outlook on the future research direction in this field, combining the literature and the development status to provide some basic reference for subsequent research.
    Reference | Related Articles | Metrics
    Review of Knowledge Tracing Preprocessing Based on Deep Learning
    LIANG Kun, REN Yimeng, SHANG Yuhu, ZHANG Yiying, WANG Cong
    Computer Engineering and Applications    2021, 57 (21): 41-58.   DOI: 10.3778/j.issn.1002-8331.2106-0552
    Abstract193)      PDF(pc) (920KB)(234)       Save

    As education informatization keep deepening, knowledge tracing with the goal of predicting students’ knowledge status is becoming an important and challenging task in individualized education. As a time sequence task of educational data mining, knowledge tracing combines with the powerful feature extraction and modeling capabilities of deep learning models, and it has the unique advantage when dealing with sequential tasks. To this end, this article discusses knowledge tracing from the following four aspects. Firstly, the article briefly analyzes the characteristics and limitations of traditional knowledge tracing models. Then, through taking the development process of in-depth knowledge tracing as the main line, it summarizes knowledge tracing models based on recurrent neural networks, memory augmented neural networks, graph neural networks and their improved models; and categorizes and organizes the existing models in this field according to methods and strategies. Besides, this article sorts out the public data sets and model evaluation indicators which can be used by researchers, compares and analyzes the characteristics of different modeling methods. Finally, it discusses and prospects the future development direction of knowledge tracing based on deep learning, and lays the foundation for further in-depth knowledge tracing research.

    Reference | Related Articles | Metrics
    Summary of Dynamic Gesture Recognition Based on Vision
    XIE Yinggang, WANG Quan
    Computer Engineering and Applications    2021, 57 (22): 68-77.   DOI: 10.3778/j.issn.1002-8331.2105-0314
    Abstract190)      PDF(pc) (598KB)(288)       Save

    Gestures have played a very important role in human communication since ancient times, and the visual dynamic gesture identification technology is to use new technologies such as computer vision and IOT(Internet of Things) perception, and 3D visual sensors, allowing the machine to understand human gestures, thus making humanity and machine more good communication, because of far-reaching research significance for human-machine interaction. The sensor techniques used in dynamic gesture identification are introduced, and the technical parameters of the related sensors are compared. By tracking the dynamic gesture recognition technology of vision at home and abroad, the processing process of dynamic gesture recognition is first stated:gesture detection and segmentation, gesture tracking, gesture classification. By comparing the methods involved in each process, it can be seen that deep learning has strong fault tolerance, robustness, high parallelism, anti-interference, etc., which has achieved great achievements above the traditional learning algorithm in the field of gesture identification. Finally, the challenges currently encountering and the future possible development of dynamic gesture identification are analyzed.

    Reference | Related Articles | Metrics
    TLS Malicious Encrypted Traffic Identification Research
    KANG Peng, YANG Wenzhong, MA Hongqiao
    Computer Engineering and Applications    2022, 58 (12): 1-11.   DOI: 10.3778/j.issn.1002-8331.2110-0029
    Abstract190)      PDF(pc) (747KB)(151)       Save
    With the advent of the 5G era and the increasing public awareness of the Internet, the public has paid more and more attention to the protection of personal privacy. Due to malicious communication in the process of data encryption, to ensure data security and safeguard social and national interests, the research work on encrypted traffic identification is particularly important. Therefore, this paper describes the TLS traffic in detail and analyzes the improved technology of early identification method, including common traffic detection technology, DPI detection technology, proxy technology, and certificate detection technology. It also introduces machine learning models for selecting different TLS encrypted traffic characteristics, as well as many recent research results of deep learning models without feature selection. The deficiencies of the related research work are summarized, and the future research work and development trend of the technology have been prospected.
    Reference | Related Articles | Metrics
    Aspect-Level Sentiment Analysis Model Incorporating Multi-layer Attention
    YUAN Xun, LIU Rong, LIU Ming
    Computer Engineering and Applications    2021, 57 (22): 147-152.   DOI: 10.3778/j.issn.1002-8331.2104-0019
    Abstract189)      PDF(pc) (699KB)(168)       Save

    Aspect sentiment analysis aims to analyze the sentiment polarity of a specific aspect in a given text. In order to solve the problem of insufficient introduction of aspect emotional attention in current research methods, this paper proposes an aspect level emotion classification model based on the fusion of BERT and Multi-Layer Attention(BMLA). Firstly, the model extracts the multi-layer aspect emotional attention information from the inner part of BERT, and designs the multi-layer aspect attention by fusing the encoded aspect information with the representation vector of the hidden layer of BERT, then cascades the multi-layer aspect attention with the encoded output text, finally enhances the long dependency relationship between sentences and aspect words. Experiments on the SemEval2014 Task4 and the AI Challenger 2018 datasets show that the proposed model is effective to enhance the weight of the target aspect and interact in context for aspect sentiment classification.

    Reference | Related Articles | Metrics
    Research of Deep Learning-Based Semantic Segmentation for 3D Point Cloud
    WANG Tao, WANG Wenju, CAI Yu
    Computer Engineering and Applications    2021, 57 (23): 18-26.   DOI: 10.3778/j.issn.1002-8331.2107-0142
    Abstract185)      PDF(pc) (682KB)(171)       Save

    This paper summarizes the methods of deep learning-based semantic segmentation for 3D point cloud. The literature research method is used to describe deep learning-based semantic segmentation methods for 3D point cloud according to the representation of data. It discusses the current situation of domestic and foreign development in recent years, and analyzes the advantages and disadvantages of the current related methods, and prospects the future development trend. Deep learning plays an extremely important role in the research of semantic segmentation technology for point cloud, and promotes the manufacturing, packaging fields and etc to development in the direction of intelligence. According to the advantages and disadvantages of various methods, it is an important research direction to construct a framework model of semantic segmentation combined with 2D-3D for projection, voxel, multi-view and point cloud in the future.

    Reference | Related Articles | Metrics
    Overview of Image Quality Assessment Method Based on Deep Learning
    CAO Yudong, LIU Haiyan, JIA Xu, LI Xiaohui
    Computer Engineering and Applications    2021, 57 (23): 27-36.   DOI: 10.3778/j.issn.1002-8331.2106-0228
    Abstract180)      PDF(pc) (646KB)(256)       Save

    Image quality evaluation is a measurement of the visual quality of an image or video. The researches on image quality evaluation algorithms in the past 10 years are reviewed. First, the measurement indicators of image quality evaluation algorithm and image quality evaluation datasets are introduced. Then, the different classification of image quality evaluation methods are analyzed, and image quality evaluation algorithms with deep learning technology are focused on, basic model of which is deep convolutional network, deep generative adversarial network and transformer. The performance of algorithms with deep learning is often higher than that of traditional image quality assessment algorithms. Subsequently, the principle of image quality assessment with deep learning is described in detail. A specific no-reference image quality evaluation algorithm based on deep generative adversarial network is introduced, which improves the reliability of simulated reference images through enhanced confrontation learning. Deep learning technology requires massive data support. Data enhancement methods are elaborated to improve the performance of the model. Finally, the future research trend of digital image quality evaluation is summarized.

    Reference | Related Articles | Metrics
    Research on Improved BERT’s Chinese Multi-relation Extraction Method
    HUANG Meigen, LIU Jiale, LIU Chuan
    Computer Engineering and Applications    2021, 57 (21): 234-240.   DOI: 10.3778/j.issn.1002-8331.2011-0199
    Abstract177)      PDF(pc) (973KB)(159)       Save

    There are few studies on extracting multiple triples from text sentences when constructing triples, and most of them are based on English context. For this reason, a BERT-based Chinese multi-relation extraction model BCMRE is proposed, which consists of relation classification and element extraction. Two mission models are connected in series. BCMRE predicts the possible relationships through the relationship classification task, fuses the predicted relationship code into the word vector, copies an instance of each relationship, and then enters the element extraction task to predict the triplet through named entity recognition. BCMRE adds different pre-models based on the characteristics of the two tasks. Word vectors are designed to optimize the shortcomings of BERT in Chinese characters when processing Chinese. Different loss functions are designed to make the model better. BERT’s multi-head and self-attention mechanism are used to fully extract the feature completes the extraction of triples. BCMRE compares experiments with other models and changes to different pre-models. It has achieved relatively good results under the F1 evaluation, which proves that the model can effectively improve the effect of extracting multi-relational triples.

    Reference | Related Articles | Metrics
    Improved YOLOv5 Ship Target Detection in SAR Image
    TAN Xiandong, PENG Hui
    Computer Engineering and Applications    2022, 58 (4): 247-254.   DOI: 10.3778/j.issn.1002-8331.2108-0308
    Abstract175)      PDF(pc) (2147KB)(140)       Save
    In recent years, the ship detection technology for the lack of color and texture details in synthetic aperture radar(SAR) images has been extensively studied in the field of deep learning. The use of deep learning technology can effectively avoid traditional complex feature design, and the accuracy of detection is greatly improved. For the problems of high aspect ratio and dense arrangement of ship targets detection, a target detection method based on improved YOLOv5 is proposed. According to the characteristics of ship targets detection, the length and width of detection are taken into comprehensive consideration and the loss function curve is optimized, and the coordinate attention mechanism(CA) is combined to achieve high-speed and high-precision detection of ship targets while the model is lightweight. The experimental results show that:Compared with the original YOLOv5 method, the detection accuracy of this method is increased from 92.3% to 96.7%, the mAP index is increased from 92.5% to 97.2%, which is significantly better than the comparison method. By improving the detection frame loss function and feature extraction methods, the detection effect of ship targets in SAR images is improved.
    Reference | Related Articles | Metrics
    Research on Object Detection Algorithm Based on Improved YOLOv5
    QIU Tianheng, WANG Ling, WANG Peng, BAI Yan’e
    Computer Engineering and Applications    2022, 58 (13): 63-73.   DOI: 10.3778/j.issn.1002-8331.2202-0093
    Abstract172)      PDF(pc) (1109KB)(129)       Save
    YOLOv5 is an algorithm with good performance in single-stage target detection at present, but the accuracy of target boundary regression is not too high, so it is difficult to apply to scenarios with high requirements on the intersection ratio of prediction boxes. Based on YOLOv5 algorithm, this paper proposes a new model YOLO-G with low hardware requirements, fast model convergence and high accuracy of target box. Firstly, the feature pyramid network(FPN) is improved, and more features are integrated in the way of cross-level connection, which prevents the loss of shallow semantic information to a certain extent. At the same time, the depth of the pyramid is deepened, corresponding to the increase of detection layer, so that the laying interval of various anchor frames is more reasonable. Secondly, the attention mechanism of parallel mode is integrated into the network structure, which gives the same priority to spatial and channel attention module, then the attention information is extracted by weighted fusion, so that the network can fuse the mixed domain attention according to the attention degree of spatial and channel attention. Finally, in order to prevent the loss of real-time performance due to the increase of model complexity, the network is lightened to reduce the number of parameters and computation of the network. PASCAL VOC datasets of 2007 and 2012 are used to verify the effectiveness of the algorithm. Compared with YOLOv5s, YOLO-G reduces the number of parameters by 4.7% and the amount of computation by 47.9%, while mAP@0.5 and mAP@0.5:0.95 increases by 3.1 and 5.6 percentage points respectively.
    Reference | Related Articles | Metrics
    Improved Leukocyte Detection Algorithm of YOLOv5
    WANG Jing, SUN Ziyun, GUO Ping, ZHANG Longmei
    Computer Engineering and Applications    2022, 58 (4): 134-142.   DOI: 10.3778/j.issn.1002-8331.2107-0332
    Abstract171)      PDF(pc) (1380KB)(191)       Save
    Aiming at the problems of low accuracy and poor effect caused by small white blood cell data samples, small difference between classes and small target size, this paper proposes a white blood cell detection algorithm YOLOv5-CHE based on improved YOLOv5. Firstly, coordinate attention mechanism is added to the convolutional layer of the backbone feature extraction network to improve the feature extraction capability of the algorithm. Secondly, the purpose of using four-scale feature detection and reacquiring anchor point frame is to increase the detection scale of shallow layer and improve the recognition accuracy of small targets. Finally, the purpose of changing the bounding box regression loss function is to improve the accuracy of check box detection. Experimental results show that the mean average precision(mAP), precision and recall of YOLOv5-CHE are improved by 3.8 percentage points, 1.8 percentage points and 1.5 percentage points in comparison with the benchmark YOLOv5 algorithm, respectively, which shows that the proposed algorithm is effective for leukocyte detection.
    Reference | Related Articles | Metrics
    Survey on Deep Learning Based Image Super-Resolution
    XIA Hao, LYU Hongfeng, LUO Jun, CAI Nian
    Computer Engineering and Applications    2021, 57 (24): 51-60.   DOI: 10.3778/j.issn.1002-8331.2105-0418
    Abstract167)      PDF(pc) (914KB)(243)       Save

    Image super-resolution reconstruction is the process of using low-resolution images to reconstruct the corresponding high-resolution images. At present, image super-resolution technology has been successfully applied in the fields of computer vision and image processing. In recent years, due to deep learning’s ability of self-learning from a large amount of data, it has been widely used in the field of image super-resolution. This article introduces the background of image super-resolution reconstruction, and summarizes the deep learning based image super-resolution model in detail, and then elaborates the image super-resolution technology in satellite remote sensing images, medical imaging, video surveillance, and industrial inspection tasks application. Finally, this article summarizes the current research status and future development directions of image super-resolution algorithms.

    Reference | Related Articles | Metrics
    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
    Abstract164)      PDF(pc) (625KB)(153)       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
    Summary of Application Research on Helmet Detection Algorithm Based on Deep Learning
    ZHANG Liyi, WU Wenhong, NIU Hengmao, SHI Bao, DUAN Kaibo, SU Chenyang
    Computer Engineering and Applications    2022, 58 (16): 1-17.   DOI: 10.3778/j.issn.1002-8331.2203-0580
    Abstract158)      PDF(pc) (967KB)(151)       Save
    Safety helmet is the most common and practical personal protective tool on the construction site, which can effectively prevent and reduce head injury caused by accidents. Helmet detection is the main work of personnel safety management on the construction site, and it is also an important content of intelligent monitoring technology on the construction site. With the development of deep learning, it has become an important part of smart site construction. In order to comprehensively analyze the research status of deep learning in helmet detection, aiming at the research of helmet detection algorithm, the commonly used helmet detection algorithm and helmet detection algorithm based on deep learning are summarized, and their advantages and disadvantages are explained in detail. On this basis, aiming at the existing problems, this paper systematically summarizes and analyzes the relevant improvement methods of helmet detection algorithm, and combs the characteristics, advantages and limitations of various methods. Finally, the future development direction of helmet detection algorithm based on deep learning is prospected.
    Reference | Related Articles | Metrics
    Research on Transformer-Based Single-Channel Speech Enhancement
    FAN Junyi, YANG Jibin, ZHANG Xiongwei, ZHENG Changyan
    Computer Engineering and Applications    2022, 58 (12): 25-36.   DOI: 10.3778/j.issn.1002-8331.2201-0371
    Abstract157)      PDF(pc) (1155KB)(94)       Save
    Deep learning can effectively solve the complex mapping problem between noisy speech signals and clean speech signals to improve the quality of single-channel speech enhancement, but the enhancement effect based on network models is not satisfactory. Transformer has been widely used in the field of speech signal processing due to the fact that it integrates multi-headed attention mechanism and can focus on the long-term correlation existing in speech. Based on this, deep learning-based speech enhancement models are reviewed,  the Transformer model and its internal structure are summarized, Transformer-based speech enhancement models are classified in terms of different implementation structures, and several example models are analyzed in detail. Furthermore, the performance of Transformer-based single-channel speech enhancement is compared on the public datasets, and their advantages and disadvantages are analyzed. The shortcomings of the related research work are summarized and future developments are envisaged.
    Reference | Related Articles | Metrics
    Remote Sensing Military Target Detection Algorithm Based on Lightweight YOLOv3
    QIN Weiwei, SONG Tainian, LIU Jieyu, WANG Hongwei, LIANG Zhuo
    Computer Engineering and Applications    2021, 57 (21): 263-269.   DOI: 10.3778/j.issn.1002-8331.2106-0026
    Abstract157)      PDF(pc) (14418KB)(319)       Save

    In the process of intelligent missile penetration, detecting enemy anti-missile positions from massive remote sensing image data has great application value. Due to the limited computing power of the missile-borne deployment environment, this paper designs a remote sensing target detection algorithm that takes into account lightweight, detection accuracy and detection speed. A typical remote sensing military target data set is produced, and the data set is clustered and analyzed by the K-means algorithm. The MobileNetV2 network is used to replace the backbone network of the YOLOv3 algorithm to ensure the lightweight and detection speed of the network. A lightweight and efficient channel coordinated attention module and a target rotation invariance detection module suitable for remote sensing target characteristics are proposed, and they are embedded in the detection algorithm to improve the detection accuracy on the basis of network lightweight. Experimental results show that the accuracy rate of the algorithm in this paper reaches 97.8%, an increase of 6.7 percentage points, the recall rate reaches 95.7%, an increase of 3.9 percentage points, the average detection accuracy reaches 95.2%, an increase of 4.4 percentage points, and the detection speed reached 34.19 images per, and the network size is only 17.5?MB. The results show that the algorithm in this paper can meet the comprehensive requirements of intelligent missile penetration.

    Reference | Related Articles | Metrics
    Review of Computer Aided Diagnosis Technology in Mammography
    CHEN Zhili, GAO Hao, PAN Yixuan, XING Feng
    Computer Engineering and Applications    2022, 58 (4): 1-21.   DOI: 10.3778/j.issn.1002-8331.2108-0205
    Abstract157)      PDF(pc) (1022KB)(167)       Save
    In recent years, breast cancer has seriously threatened the health of women all over the world. Mammography is an effective imaging examination tool for breast cancer screening. Computer aided diagnosis(CAD) uses advanced artificial intelligence technologies such as computer vision, image processing, machine learning, etc. to automatically analyze and process mammographic images, which can provide important diagnostic references for doctors in clinical practice. This paper mainly focuses on the detection, segmentation and classification of masses and microcalcifications in mammograms, and reviews the development status of computer aided diagnosis technology in mammography, from the perspectives of traditional and deep learning methods. Considering the breakthrough achievements of deep learning, this paper reviews classical deep learning network models, focuses on the latest application of deep learning in mammography, and compares and analyzes the disadvantages of traditional methods and the advantages of deep learning methods. Finally, the problems of the existing technology are analyzed and the future development direction is prospected.
    Reference | Related Articles | Metrics
    Mixed Strategy Improved Sparrow Search Algorithm
    ZHANG Weikang, LIU Sheng, REN Chunhui
    Computer Engineering and Applications    2021, 57 (24): 74-82.   DOI: 10.3778/j.issn.1002-8331.2101-0161
    Abstract156)      PDF(pc) (1182KB)(245)       Save

    Aiming at the shortcomings of the sparrow search algorithm in the iterations of population diversity reduction, easy to fall into local optimality and slow convergence speed, a Mixed Strategy improved Sparrow Search Algorithm(MSSSA) is proposed. Circle map is used to initialize the individual positions of sparrows to increase the diversity of the initial population. Combining the butterfly optimization algorithm the location update method of the discoverer is improved to enhance global exploration ability of the algorithm. The dimensional-by-dimensional mutation method is used to perturb the individual position and improve the algorithm’s ability to jump out of the local optimum. In the simulation experiment, it compares with 4 basic algorithms and 5 improved algorithms based on 10 benchmark functions and performs Wilcoxon rank sum test. The results show that the proposed algorithm has better convergence and solution accuracy, global optimization ability has been greatly improved.

    Reference | Related Articles | Metrics
    Research and Prospect of Brain-Inspired Model for Visual Object Recognition
    YANG Xi, YAN Jie, WANG Wen, LI Shaoyi, LIN Jian
    Computer Engineering and Applications    2022, 58 (7): 1-20.   DOI: 10.3778/j.issn.1002-8331.2110-0253
    Abstract156)      PDF(pc) (906KB)(128)       Save
    Visual object recognition is one of the most fundamental and challenging research topics in the field of computer vision. The research on the neural mechanism of the primates’ recognition function may bring revolutionary breakthroughs in brain-inspired vision. This review aims to systematically review the recent works on the intersection of computational neuroscience and computer vision. It attempts to investigate the current brain-inspired object recognition models and their underlying visual neural mechanism. According to the technical architecture and exploitation methods, the paper describes the brain-inspired object recognition models and their advantages and disadvantages in realizing brain-inspired object recognition. It focuses on analyzing the similarity between the artificial and biological neural network, and studying the biological credibility of the current popular DNN-based visual benchmark models. The analysis provides a guide for researchers to measure the occasion and condition when conducting visual object recognition research.
    Reference | Related Articles | Metrics
    Facial Expression Recognition Based on Multi-scale Feature Attention Mechanism
    ZHANG Peng, KONG Weiwei, TENG Jinbao
    Computer Engineering and Applications    2022, 58 (1): 182-189.   DOI: 10.3778/j.issn.1002-8331.2106-0174
    Abstract155)      PDF(pc) (719KB)(130)       Save
    Aiming at the problems that the effective feature extraction is not strong and the recognition accuracy is not high in the process of facial expression recognition with traditional convolutional neural network, a facial expression recognition method based on multi-scale feature attention mechanism is proposed. Firstly, a two-layer convolutional layer is used to extract shallow feature information. Secondly, the dilated convolution is added to the Inception structure parallelly to extract multi-scale feature information, and then the channel attention mechanism is introduced to improve model’s ability of expressing important feature information. Finally, it inputs the obtained features into the Softmax layer for classification. The simulation experimenal results show that the proposed model achieves 68.8% and 96.04% recognition accuracy on the public datasets FER2013 and CK+, respectively, which have better recognition performance than many classic algorithms.
    Reference | Related Articles | Metrics
    Computer Engineering and Applications    2022, 58 (8): 0-0.  
    Abstract154)      PDF(pc) (637KB)(138)       Save
    Related Articles | Metrics
    Research Progress Review of Hyperspectral Remote Sensing Image Band Selection
    YANG Hongyan, DU Jianmin
    Computer Engineering and Applications    2022, 58 (10): 1-12.   DOI: 10.3778/j.issn.1002-8331.2111-0403
    Abstract154)      PDF(pc) (776KB)(119)       Save
    Hyperspectral imaging remote sensing can obtain abundant spectral, radiation and spatial information of ground objects, which has been widely used in various fields of national economy. But its narrow band spacing brings not only rich spectral information, but also information redundancy and the difficulty of data processing. Therefore, before the practical application of hyperspectral remote sensing data, band selection is needed to extract spectral features and reduce the data dimension. This review summarizes the research progress of band selection for hyperspectral remote sensing images. Based on the analysis and summary of band selection strategies, the related technology and the latest research status are expounded from six aspects:the evaluation criteria of band selection, the band selection based on the combination of spatial and spectral features, the band selection based on semi-supervised learning, the band selection based on sparse representation, the band selection based on intelligent search and the band selection based on deep learning. Then, the current problems and challenges faced by hyperspectral image band selection are discussed. Finally, the future development direction of hyperspectral image band selection is predicted.
    Reference | Related Articles | Metrics
    Survey on Adversarial Example Attack and Defense Technology for Automatic Speech Recognition
    LI Kezi, XU Yang, ZHANG Sicong, YAN Jiale
    Computer Engineering and Applications    2022, 58 (14): 1-15.   DOI: 10.3778/j.issn.1002-8331.2202-0196
    Abstract154)      PDF(pc) (972KB)(115)       Save
    Speech recognition technology is an important way of human-computer interaction. With the continuous development of deep learning, automatic speech recognition system based on deep learning has also made important progress. However, well-designed audio adversarial examples can cause errors in the automatic speech recognition system based on neural network, and bring security risks to the application of combined speech recognition system. In order to improve the security of automatic speech recognition system based on neural network, it is necessary to study the attack and defense of audio adversarial examples. Firstly, the research status of adversarial examples generation and defense technology is analyzed and summarized. Then automatic speech recognition system audio adversarial examples attack and defense techniques and related challenges and solutions are introduced.
    Reference | Related Articles | Metrics
    Systematic Review on Graph Deep Learning in Medical Image Segmentation
    WANG Guoli, SUN Yu, WEI Benzheng
    Computer Engineering and Applications    2022, 58 (12): 37-50.   DOI: 10.3778/j.issn.1002-8331.2112-0225
    Abstract150)      PDF(pc) (1194KB)(109)       Save
    High precision segmentation of organs or lesions in medical image is a vital challenge issue for intelligent analysis of medical image, it has important clinical application value for auxiliary diagnosis and treatment of diseases. Recently, in solving challenging problems such as medical image information representation and accurate modeling of non-Euclidean spatial physiological tissue structures, the graph deep learning based medical image segmentation technology has made important breakthroughs, and it has shown significant information feature extraction and characterization advantages. The merged technology also can obtain more accurate segmentation results, which has become an emerging research hotspot in this field. In order to better promote the research and development of the deep learning segmentation algorithm for medical image graphs, this paper makes a systematic summary of the technological progress and application status in this field. The paper introduces the definition of graphs and the basic structure of graph convolutional networks, and elaborates on spectral graph convolution and spatial graph convolution operations. Then, according to the three technical structure modes of GCN combined with residual module, attention mechanism module and learning module, the research progress in medical image segmentation has been encapsulated. The application and development of graph deep learning algorithms based medical image segmentation are summarized and prospected to provide references and guiding principles for the technical development of related researches.
    Reference | Related Articles | Metrics
    Review of Research on Face Mask Wearing Detection
    WANG Xinran, TIAN Qichuan, ZHANG Dong
    Computer Engineering and Applications    2022, 58 (10): 13-26.   DOI: 10.3778/j.issn.1002-8331.2110-0396
    Abstract149)      PDF(pc) (733KB)(136)       Save
    Face mask wearing detection is an emerging research topic that has developed rapidly in the past two years in the context of the global COVID-19 epidemic. Under regular epidemic situation, wearing masks is an important means of effective epidemic prevention, therefore it is essential to remind and check people whether to wear masks in public places. Using artificial intelligence to complete mask wearing detection can achieve the purpose of real-time supervision, save human resources and effectively avoid mistakes, missed detection and other problems. The models and relevant algorithms used in current mask wearing detection research are reviewed. Firstly, the task and application background of mask wearing detection are described. Then, the detection algorithms based on deep neural networks and object detection models are summarized and  analyzed, the advantages and disadvantages, improvement methods and application scenarios of different research schemes are discussed. Secondly, common related data sets are introduced, and the detection performance of each algorithm is compared. Finally, the existing problems and the direction of future development are discussed and prospected.
    Reference | Related Articles | Metrics
    Review of Classification Methods for Unbalanced Data Sets
    WANG Le, HAN Meng, LI Xiaojuan, ZHANG Ni, CHENG Haodong
    Computer Engineering and Applications    2021, 57 (22): 42-52.   DOI: 10.3778/j.issn.1002-8331.2107-0097
    Abstract149)      PDF(pc) (586KB)(135)       Save

    The characteristics of unbalanced data sets lead to many difficult problems in classification. The classification methods of unbalanced data sets are analyzed and summarized. Firstly, the classification methods of unbalanced data sets are introduced from three perspectives of under-sampling, over-sampling and mixed sampling in detail. In the under-sampling method, it is divided into three technical methods based on [K]-Nearest Neighbor[(KNN)], Bagging and Boosting. In the over-sampling method, the classification method is analyzed from the perspectives of Synthetic Minority Over-sampling Technology(SMOTE) and Support Vector Machine(SVM). The advantages and disadvantages of the algorithm are compared, and the performance of the algorithm is analyzed and summarized under the same data sets. Then, the classification methods of unbalanced data sets are summarized from four aspects:deep learning, extreme learning machine, cost sensitivity and feature selection. Finally, the future work direction is prospected.

    Reference | Related Articles | Metrics