Most Read articles

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

    Please wait a minute...
    For Selected: Toggle Thumbnails
    Parameter calculation algorithm of structural graph clustering driven by instance clusters
    Chuanyu ZONG, Chao XIAN, Xiufeng XIA
    Journal of Computer Applications    2023, 43 (2): 398-406.   DOI: 10.11772/j.issn.1001-9081.2022010082
    Abstract1209)   HTML9)    PDF (2584KB)(46)       Save

    Clustering results of the pSCAN (pruned Structural Clustering Algorithm for Network) algorithm are influenced by the density constraint parameter and the similarity threshold parameter. If the requirements cannot be satisfied by the clustering results obtained by the clustering parameters provided by the user, then the user’s own clustering requirements can be expressed through instance clusters. Aiming at the problem of instance clusters expressing clustering query requirements, an instance cluster-driven structural graph clustering parameter calculation algorithm PART and its improved algorithm ImPART were proposed. Firstly, the influences of two clustering parameters on the clustering results were analyzed, and correlation subgraph of instance cluster was extracted. Secondly, the feasible interval of the density constraint parameter was obtained by analyzing the correlation subgraph, and the nodes in the instance cluster were divided into core nodes and non-core nodes according to the current density constraint parameter and the structural similarity between nodes. Finally, according to the node division result, the optimal similarity threshold parameter corresponding to the current density constraint parameter was calculated, and the obtained parameters were verified and optimized on the relevant subgraph until the clustering parameters that satisfy the requirements of the instance cluster were obtained. Experimental results on real datasets show that a set of effective parameters can be returned for user instance clusters by using the proposed algorithm, and the proposed improved algorithm ImPART is more than 20% faster than the basic algorithm PART, and can return the optimal clustering parameters that satisfy the requirements of instance clusters quickly and effectively for the user.

    Table and Figures | Reference | Related Articles | Metrics
    Transformer based U-shaped medical image segmentation network: a survey
    Liyao FU, Mengxiao YIN, Feng YANG
    Journal of Computer Applications    2023, 43 (5): 1584-1595.   DOI: 10.11772/j.issn.1001-9081.2022040530
    Abstract1090)   HTML46)    PDF (1887KB)(774)       Save

    U-shaped Network (U-Net) based on Fully Convolutional Network (FCN) is widely used as the backbone of medical image segmentation models, but Convolutional Neural Network (CNN) is not good at capturing long-range dependency, which limits the further performance improvement of segmentation models. To solve the above problem, researchers have applied Transformer to medical image segmentation models to make up for the deficiency of CNN, and U-shaped segmentation networks combining Transformer have become the hot research topics. After a detailed introduction of U-Net and Transformer, the related medical image segmentation models were categorized by the position in which the Transformer module was located, including only in the encoder or decoder, both in the encoder and decoder, as a skip-connection, and others, the basic contents, design concepts and possible improvement aspects about these models were discussed, the advantages and disadvantages of having Transformer in different positions were also analyzed. According to the analysis results, it can be seen that the biggest factor to decide the position of Transformer is the characteristics of the target segmentation task, and the segmentation models of Transformer combined with U-Net can make better use of the advantages of CNN and Transformer to improve segmentation performance of models, which has great development prospect and research value.

    Table and Figures | Reference | Related Articles | Metrics
    Survey of multimodal pre-training models
    Huiru WANG, Xiuhong LI, Zhe LI, Chunming MA, Zeyu REN, Dan YANG
    Journal of Computer Applications    2023, 43 (4): 991-1004.   DOI: 10.11772/j.issn.1001-9081.2022020296
    Abstract1030)   HTML114)    PDF (5539KB)(826)    PDF(mobile) (3280KB)(77)    Save

    By using complex pre-training targets and a large number of model parameters, Pre-Training Model (PTM) can effectively obtain rich knowledge from unlabeled data. However, the development of the multimodal PTMs is still in its infancy. According to the difference between modals, most of the current multimodal PTMs were divided into the image-text PTMs and video-text PTMs. According to the different data fusion methods, the multimodal PTMs were divided into two types: single-stream models and two-stream models. Firstly, common pre-training tasks and downstream tasks used in validation experiments were summarized. Secondly, the common models in the area of multimodal pre-training were sorted out, and the downstream tasks of each model and the performance and experimental data of the models were listed in tables for comparison. Thirdly, the application scenarios of M6 (Multi-Modality to Multi-Modality Multitask Mega-transformer) model, Cross-modal Prompt Tuning (CPT) model, VideoBERT (Video Bidirectional Encoder Representations from Transformers) model, and AliceMind (Alibaba’s collection of encoder-decoders from Mind) model in specific downstream tasks were introduced. Finally, the challenges and future research directions faced by related multimodal PTM work were summed up.

    Table and Figures | Reference | Related Articles | Metrics
    Review on privacy-preserving technologies in federated learning
    Teng WANG, Zheng HUO, Yaxin HUANG, Yilin FAN
    Journal of Computer Applications    2023, 43 (2): 437-449.   DOI: 10.11772/j.issn.1001-9081.2021122072
    Abstract978)   HTML95)    PDF (2014KB)(641)       Save

    In recent years, federated learning has become a new way to solve the problems of data island and privacy leakage in machine learning. Federated learning architecture does not require multiple parties to share data resources, in which participants only needed to train local models on local data and periodically upload parameters to the server to update the global model, and then a machine learning model can be built on large-scale global data. Federated learning architecture has the privacy-preserving nature and is a new scheme for large-scale data machine learning in the future. However, the parameter interaction mode of this architecture may lead to data privacy disclosure. At present, strengthening the privacy-preserving mechanism in federated learning architecture has become a new research hotspot. Starting from the privacy disclosure problem in federated learning, the attack models and sensitive information disclosure paths in federated learning were discussed, and several types of privacy-preserving techniques in federated learning were highlighted and reviewed, such as privacy-preserving technology based on differential privacy, privacy-preserving technology based on homomorphic encryption, and privacy-preserving technology based on Secure Multiparty Computation (SMC). Finally, the key issues of privacy protection in federated learning were discussed, the future research directions were prospected.

    Table and Figures | Reference | Related Articles | Metrics
    Survey of single target tracking algorithms based on Siamese network
    Mengting WANG, Wenzhong YANG, Yongzhi WU
    Journal of Computer Applications    2023, 43 (3): 661-673.   DOI: 10.11772/j.issn.1001-9081.2022010150
    Abstract741)   HTML115)    PDF (2647KB)(611)       Save

    Single object tracking is an important research direction in the field of computer vision, and has a wide range of applications in video surveillance, autonomous driving and other fields. For single object tracking algorithms, although a large number of summaries have been conducted, most of them are based on correlation filter or deep learning. In recent years, Siamese network-based tracking algorithms have received extensive attention from researchers for their balance between accuracy and speed, but there are relatively few summaries of this type of algorithms and it lacks systematic analysis of the algorithms at the architectural level. In order to deeply understand the single object tracking algorithms based on Siamese network, a large number of related literatures were organized and analyzed. Firstly, the structures and applications of the Siamese network were expounded, and each tracking algorithm was introduced according to the composition classification of the Siamese tracking algorithm architectures. Then, the commonly used datasets and evaluation metrics in the field of single object tracking were listed, the overall and each attribute performance of 25 mainstream tracking algorithms was compared and analyzed on OTB 2015 (Object Tracking Benchmark) dataset, and the performance and the reasoning speed of 23 Siamese network-based tracking algorithms on LaSOT (Large-scale Single Object Tracking) and GOT-10K (Generic Object Tracking) test sets were listed. Finally, the research on Siamese network-based tracking algorithms was summarized, and the possible future research directions of this type of algorithms were prospected.

    Table and Figures | Reference | Related Articles | Metrics
    Temporal convolutional knowledge tracing model with attention mechanism
    Xiaomeng SHAO, Meng ZHANG
    Journal of Computer Applications    2023, 43 (2): 343-348.   DOI: 10.11772/j.issn.1001-9081.2022010024
    Abstract730)   HTML34)    PDF (2110KB)(328)       Save

    To address the problems of insufficient interpretability and long sequence dependency in the deep knowledge tracing model based on Recurrent Neural Network (RNN), a model named Temporal Convolutional Knowledge Tracing with Attention mechanism (ATCKT) was proposed. Firstly, the student historical interactions embedded representations were learned in the training process. Then, the exercise problem-based attention mechanism was used to learn a specific weight matrix to identify and strengthen the influences of student historical interactions on the knowledge state at each moment. Finally, the student knowledge states were extracted by Temporal Convolutional Network (TCN), in which dilated convolution and deep neural network were used to expand the scope of sequence learning, and alleviate the problem of long sequence dependency. Experimental results show that compared with four models such as Deep Knowledge Tracing (DKT) and Convolutional Knowledge Tracing (CKT) on four datasets (ASSISTments2009、ASSISTments2015、Statics2011 and Synthetic-5), ATCKT model has the Area Under the Curve (AUC) and Accuracy (ACC) significantly improved, especially on ASSISTments2015 dataset, with an increase of 6.83 to 20.14 percentage points and 7.52 to 11.22 percentage points respectively, at the same time, the training time of the proposed model is decreased by 26% compared with that of DKT model. In summary, this model can accurately capture the student knowledge states and efficiently predict student future performance.

    Table and Figures | Reference | Related Articles | Metrics
    Review of multi-modal medical image segmentation based on deep learning
    Meng DOU, Zhebin CHEN, Xin WANG, Jitao ZHOU, Yu YAO
    Journal of Computer Applications    2023, 43 (11): 3385-3395.   DOI: 10.11772/j.issn.1001-9081.2022101636
    Abstract642)   HTML9)    PDF (3904KB)(445)       Save

    Multi-modal medical images can provide clinicians with rich information of target areas (such as tumors, organs or tissues). However, effective fusion and segmentation of multi-modal images is still a challenging problem due to the independence and complementarity of multi-modal images. Traditional image fusion methods have difficulty in addressing this problem, leading to widespread research on deep learning-based multi-modal medical image segmentation algorithms. The multi-modal medical image segmentation task based on deep learning was reviewed in terms of principles, techniques, problems, and prospects. Firstly, the general theory of deep learning and multi-modal medical image segmentation was introduced, including the basic principles and development processes of deep learning and Convolutional Neural Network (CNN), as well as the importance of the multi-modal medical image segmentation task. Secondly, the key concepts of multi-modal medical image segmentation was described, including data dimension, preprocessing, data enhancement, loss function, and post-processing, etc. Thirdly, different multi-modal segmentation networks based on different fusion strategies were summarized and analyzed. Finally, several common problems in medical image segmentation were discussed, the summary and prospects for future research were given.

    Table and Figures | Reference | Related Articles | Metrics
    Review of interactive machine translation
    Xingbin LIAO, Xiaolin QIN, Siqi ZHANG, Yangge QIAN
    Journal of Computer Applications    2023, 43 (2): 329-334.   DOI: 10.11772/j.issn.1001-9081.2021122067
    Abstract613)   HTML90)    PDF (1870KB)(439)       Save

    With the development and maturity of deep learning, the quality of neural machine translation has increased, yet it is still not perfect and requires human post-editing to achieve acceptable translation results. Interactive Machine Translation (IMT) is an alternative to this serial work, that is performing human interaction during the translation process, where the user verifies the candidate translations produced by the translation system and, if necessary, provides new input, and the system generates new candidate translations based on the current feedback of users, this process repeats until a satisfactory output is produced. Firstly, the basic concept and the current research progresses of IMT were introduced. Then, some common methods and state-of-the-art works were suggested in classification, while the background and innovation of each work were briefly described. Finally, the development trends and research difficulties of IMT were discussed.

    Table and Figures | Reference | Related Articles | Metrics
    Survey of label noise learning algorithms based on deep learning
    Boyi FU, Yuncong PENG, Xin LAN, Xiaolin QIN
    Journal of Computer Applications    2023, 43 (3): 674-684.   DOI: 10.11772/j.issn.1001-9081.2022020198
    Abstract608)   HTML55)    PDF (2083KB)(387)    PDF(mobile) (733KB)(36)    Save

    In the field of deep learning, a large number of correctly labeled samples are essential for model training. However, in practical applications, labeling data requires high labeling cost. At the same time, the quality of labeled samples is affected by subjective factors or tool and technology of manual labeling, which inevitably introduces label noise in the annotation process. Therefore, existing training data available for practical applications is subject to a certain amount of label noise. How to effectively train training data with label noise has become a research hotspot. Aiming at label noise learning algorithms based on deep learning, firstly, the source, classification and impact of label noise learning strategies were elaborated; secondly, four label noise learning strategies based on data, loss function, model and training method were analyzed according to different elements of machine learning; then, a basic framework for learning label noise in various application scenarios was provided; finally, some optimization ideas were given, and challenges and future development directions of label noise learning algorithms were proposed.

    Table and Figures | Reference | Related Articles | Metrics
    Automatic detection and recognition of electric vehicle helmet based on improved YOLOv5s
    Zhouhua ZHU, Qi QI
    Journal of Computer Applications    2023, 43 (4): 1291-1296.   DOI: 10.11772/j.issn.1001-9081.2022020313
    Abstract552)   HTML31)    PDF (2941KB)(215)    PDF(mobile) (3142KB)(37)    Save

    Aiming at the problems of low detection precision, poor robustness, and imperfect related systems in the current small object detection of electric vehicle helmet, an electric vehicle helmet detection model was proposed based on improved YOLOv5s algorithm. In the proposed model, Convolutional Block Attention Module (CBAM) and Coordinate Attention (CA) module were introduced, and the improved Non-Maximum Suppression (NMS) - Distance Intersection over Union-Non Maximum Suppression (DIoU-NMS) was used. At the same time, multi-scale feature fusion detection was added and densely connected network was combined to improve feature extraction effect. Finally, a helmet detection system for electric vehicle drivers was established. The improved YOLOv5s algorithm had the mean Average Precision (mAP) increased by 7.1 percentage points when the Intersection over Union (IoU) is 0.5, and Recall increased by 1.6 percentage points compared with the original YOLOv5s on the self-built electric vehicle helmet wearing dataset. Experimental results show that the improved YOLOv5s algorithm can better meet the requirements for detection precision of electric vehicles and the helmets of their drivers in actual situations, and reduce the incidence rate of electric vehicle traffic accidents to a certain extent.

    Table and Figures | Reference | Related Articles | Metrics
    Review of application analysis and research progress of deep learning in weather forecasting
    Runting DONG, Li WU, Xiaoying WANG, Tengfei CAO, Jianqiang HUANG, Qin GUAN, Jiexia WU
    Journal of Computer Applications    2023, 43 (6): 1958-1968.   DOI: 10.11772/j.issn.1001-9081.2022050745
    Abstract519)   HTML39)    PDF (1570KB)(589)       Save

    With the advancement of technologies such as sensor networks and global positioning systems, the volume of meteorological data with both temporal and spatial characteristics has exploded, and the research on deep learning models for Spatiotemporal Sequence Forecasting (STSF) has developed rapidly. However, the traditional machine learning methods applied to weather forecasting for a long time have unsatisfactory effects in extracting the temporal correlations and spatial dependences of data, while the deep learning methods can extract features automatically through artificial neural networks to improve the accuracy of weather forecasting effectively, and have a very good effect in encoding long-term spatial information modeling. At the same time, the deep learning models driven by observational data and Numerical Weather Prediction (NWP) models based on physical theories are combined to build hybrid models with higher prediction accuracy and longer prediction time. Based on these, the application analysis and research progress of deep learning in the field of weather forecasting were reviewed. Firstly, the deep learning problems in the field of weather forecasting and the classical deep learning problems were compared and studied from three aspects: data format, problem model and evaluation metrics. Then, the development history and application status of deep learning in the field of weather forecasting were looked back, and the latest progress in combining deep learning technologies with NWP was summarized and analyzed. Finally, the future development directions and research focuses were prospected to provide a certain reference for future deep learning research in the field of weather forecasting.

    Table and Figures | Reference | Related Articles | Metrics
    Unsupervised time series anomaly detection model based on re-encoding
    Chunyong YIN, Liwen ZHOU
    Journal of Computer Applications    2023, 43 (3): 804-811.   DOI: 10.11772/j.issn.1001-9081.2022010006
    Abstract512)   HTML30)    PDF (1769KB)(232)       Save

    In order to deal with the problem of low accuracy of anomaly detection caused by data imbalance and highly complex temporal correlation of time series, a re-encoding based unsupervised time series anomaly detection model based on Generative Adversarial Network (GAN), named RTGAN (Re-encoding Time series based on GAN), was proposed. Firstly, multiple generators with cycle consistency were used to ensure the diversity of generated samples and thereby learning different anomaly patterns. Secondly, the stacked Long Short-Term Memory-dropout Recurrent Neural Network (LSTM-dropout RNN) was used to capture temporal correlation. Thirdly, the differences between the generated samples and the real samples were compared in the latent space by improved re-encoding. As the re-encoding errors, these differences were served as a part of anomaly score to improve the accuracy of anomaly detection. Finally, the new anomaly score was used to detect anomalies on univariate and multivariate time series datasets. The proposed model was compared with seven baseline anomaly detection models on univariate and multivariate time series. Experimental results show that the proposed model obtains the highest average F1-score (0.815) on all datasets. And the overall performance of the proposed model is 36.29% and 8.52% respectively higher than those of the original AutoEncoder (AE) model Dense-AE (Dense-AutoEncoder) and latest benchmark model USAD (UnSupervised Anomaly Detection on multivariate time series). The robustness of the model was detected by different Signal-to-Noise Ratio (SNR). The results show that the proposed model consistently outperforms LSTM-VAE (Variational Autoencoder based on LSTM), USAD and OmniAnomaly, especially in the case of 30% SNR, the F1-score of RTGAN is 13.53% and 10.97% respectively higher than those of USAD and OmniAnomaly. It can be seen that RTGAN can effectively improve the accuracy and robustness of anomaly detection.

    Table and Figures | Reference | Related Articles | Metrics
    Bimodal emotion recognition method based on graph neural network and attention
    Lubao LI, Tian CHEN, Fuji REN, Beibei LUO
    Journal of Computer Applications    2023, 43 (3): 700-705.   DOI: 10.11772/j.issn.1001-9081.2022020216
    Abstract503)   HTML44)    PDF (1917KB)(392)       Save

    Considering the issues of physiological signal emotion recognition, a bimodal emotion recognition method based on Graph Neural Network (GNN) and attention was proposed. Firstly, the GNN was used to classify ElectroEncephaloGram (EEG) signals. Secondly, an attention-based Bi-directional Long Short-Term Memory (Bi-LSTM) network was used to classify ElectroCardioGram (ECG) signals. Finally, the results of EEG and ECG classification were fused by Dempster-Shafer evidence theory, thus improving the comprehensive performance of the emotion recognition task. To verify the effectiveness of the proposed method, 20 subjects were invited to participate in the emotion elicitation experiment, and the EEG signals and ECG signals of the subjects were collected. Experimental results show that the binary classification accuracies of the proposed method are 91.82% and 88.24% in the valence dimension and arousal dimension, respectively, which are 2.65% and 0.40% higher than those of the single-modal EEG method respectively, and are 19.79% and 24.90% higher than those of the single-modal ECG method respectively. It can be seen that the proposed method can effectively improve the accuracy of emotion recognition and provide decision support for medical diagnosis and other fields.

    Table and Figures | Reference | Related Articles | Metrics
    Embedded road crack detection algorithm based on improved YOLOv8
    Journal of Computer Applications    DOI: 10.11772/j.issn.1001-9081.2023050635
    Online available: 01 September 2023

    Survey of online learning resource recommendation
    Yongfeng DONG, Yacong WANG, Yao DONG, Yahan DENG
    Journal of Computer Applications    2023, 43 (6): 1655-1663.   DOI: 10.11772/j.issn.1001-9081.2022091335
    Abstract453)   HTML51)    PDF (824KB)(400)       Save

    In recent years, more and more schools tend to use online education widely. However, learners are hard to search for their needs from the massive learning resources in the Internet. Therefore, it is very important to research the online learning resource recommendation and perform personalized recommendations for learners, so as to help learners obtain the high-quality learning resources they need quickly. The research status of online learning resource recommendation was analyzed and summarized from the following five aspects. Firstly, the current work of domestic and international online education platforms in learning resource recommendation was summed up. Secondly, four types of algorithms were analyzed and discussed: using knowledge point exercises, learning paths, learning videos and learning courses as learning resource recommendation targets respectively. Thirdly, from the perspectives of learners and learning resources, using the specific algorithms as examples, three learning resource recommendation algorithms based on learners’ portraits, learners’ behaviors and learning resource ontologies were introduced in detail respectively. Moreover, the public online learning resource datasets were listed. Finally, the current challenges and future research directions were analyzed.

    Table and Figures | Reference | Related Articles | Metrics
    Review on blockchain smart contract vulnerability detection and automatic repair
    Juncheng TONG, Bo ZHAO
    Journal of Computer Applications    2023, 43 (3): 785-793.   DOI: 10.11772/j.issn.1001-9081.2022020179
    Abstract444)   HTML34)    PDF (2782KB)(344)    PDF(mobile) (582KB)(29)    Save

    Smart contract technology, as a milestone of blockchain 2.0, has received widespread attention from both academic and industry circles. It runs on an underlying infrastructure without trusted computing environment and has characteristics that distinguish it from traditional programs, and there are many vulnerabilities with huge influence in its own security, so that the research on security auditing for it has become a popular and urgent key scientific problem in the field of blockchain security. Aiming at the detection and automatic repair of smart contract vulnerabilities, firstly, main types and classifications of smart contract vulnerabilities were introduced. Secondly, three most important methods of smart contract vulnerability detection in the past five years were reviewed, and representative and innovative research techniques of each method were introduced. Thirdly, smart contract upgrade schemes and cutting-edge automatic repair technologies were introduced in detail. Finally, challenges and future work of smart contract vulnerability detection and automatic repair technologies for online, real-time, multi-platform, automatic, and intelligent requirements were analyzed and prospected as a framework of technical solutions.

    Table and Figures | Reference | Related Articles | Metrics
    Review of lifelong learning in computer vision
    Yichi CHEN, Bin CHEN
    Journal of Computer Applications    2023, 43 (6): 1785-1795.   DOI: 10.11772/j.issn.1001-9081.2022050766
    Abstract437)   HTML56)    PDF (2053KB)(401)       Save

    LifeLong learning (LLL), as an emerging method, breaks the limitations of traditional machine learning and gives the models the ability to accumulate, optimize and transfer knowledge in the learning process like human beings. In recent years, with the wide application of deep learning, more and more studies attempt to solve catastrophic forgetting problem in deep neural networks and get rid of the stability-plasticity dilemma, as well as apply LLL methods to a wide varieties of real-world scenarios to promote the development of artificial intelligence from weak to strong. Aiming at the field of computer vision, firstly, LLL methods were classified into four types in image classification tasks: data-driven methods, optimization process based methods, network structure based methods and knowledge combination based methods. Then, typical applications of LLL methods in other visual tasks and related evaluation indicators were introduced. Finally, the deficiencies of LLL methods at current stage were discussed, and the future development directions of LLL methods were proposed.

    Table and Figures | Reference | Related Articles | Metrics
    Object detection algorithm based on attention mechanism and context information
    Hui LIU, Linyu ZHANG, Fugang WANG, Rujin HE
    Journal of Computer Applications    2023, 43 (5): 1557-1564.   DOI: 10.11772/j.issn.1001-9081.2022040554
    Abstract436)   HTML25)    PDF (3014KB)(260)       Save

    Aiming at the problem of small object miss detection in object detection process, an improved YOLOv5 (You Only Look Once) object detection algorithm based on attention mechanism and multi-scale context information was proposed. Firstly, Multiscale Dilated Separable Convolutional Module (MDSCM) was added to the feature extraction structure to extract multi-scale feature information, increasing the receptive field while avoiding the loss of small object information. Secondly, the attention mechanism was added to the backbone network, and the location awareness information was embedded in the channel information, so as to further enhance the feature expression ability of the algorithm. Finally, Soft-NMS (Soft-Non-Maximum Suppression) was used instead of the NMS (Non-Maximum Suppression) used by YOLOv5 to reduce the missed detection rate of the algorithm. Experimental results show that the improved algorithm achieves detection precisions of 82.80%, 71.74% and 77.11% respectively on PASCAL VOC dataset, DOTA aerial image dataset and DIOR optical remote sensing dataset, which are 3.70, 1.49 and 2.48 percentage points higer than those of YOLOv5, and it has better detection effect on small objects. Therefore, the improved YOLOv5 can be better applied to small object detection scenarios in practice.

    Table and Figures | Reference | Related Articles | Metrics
    Small object detection algorithm of YOLOv5 for safety helmet
    Zongzhe LYU, Hui XU, Xiao YANG, Yong WANG, Weijian WANG
    Journal of Computer Applications    2023, 43 (6): 1943-1949.   DOI: 10.11772/j.issn.1001-9081.2022060855
    Abstract433)   HTML26)    PDF (3099KB)(252)       Save

    Safety helmet wearing is a powerful guarantee of workers’ personal safety. Aiming at the collected safety helmet wearing pictures have characteristics of high density, small pixels and difficulty to detect, a small object detection algorithm of YOLOv5 (You Only Look Once version 5) for safety helmet was proposed. Firstly, based on YOLOv5 algorithm, the bounding box regression loss function and confidence prediction loss function were optimized to improve the learning effect of the algorithm on the features of dense small objects in training. Secondly, slicing aided fine-tuning and Slicing Aided Hyper Inference (SAHI) were introduced to make the small object produce a larger pixel area by slicing the pictures input into the network, and the effect of network inference and fine-tuning was improved. In the experiments, a dataset containing dense small objects of safety helmets in the industrial scenes was used for training. The experimental results show that compared with the original YOLOv5 algorithm, the improved algorithm can increase the precision by 0.26 percentage points, the recall by 0.38 percentage points. And the mean Average Precision (mAP) of the proposed algorithm reaches 95.77%, which is improved by 0.46 to 13.27 percentage points compared to several algorithms such as the original YOLOv5 algorithm. The results verify that the introduction of slicing aided fine-tuning and SAHI improves the precision and confidence of small object detection and recognition in the dense scenes, reduces the false detection and missed detection cases, and can satisfy the requirements of safety helmet wearing detection effectively.

    Table and Figures | Reference | Related Articles | Metrics
    Key node mining in complex network based on improved local structural entropy
    Peng LI, Shilin WANG, Guangwu CHEN, Guanghui YAN
    Journal of Computer Applications    2023, 43 (4): 1109-1114.   DOI: 10.11772/j.issn.1001-9081.2022040562
    Abstract425)   HTML26)    PDF (1367KB)(200)       Save

    The identification of key nodes in complex network plays an important role in the optimization of network structure and effective propagation of information. Local structural Entropy (LE) can be used to identify key nodes by using the influence of the local network on the whole network instead of the influence of nodes on the whole network. However, the cases of the highly aggregative network and nodes forming a loop with neighbor nodes are not considered in LE, which leads to some limitations. To address these limitations, firstly, an improved LE based node importance evaluation method, namely PLE (Penalized Local structural Entropy), was proposed, in which based on the LE, the Clustering Coefficient (CC) was introduced as a penalty term to penalize the highly aggregative nodes in the network appropriately. Secondly, due to the fact that the penalty of PLE penalizing the nodes in triadic closure structure is too much, an improved method of PLE, namely PLEA (Penalized Local structural Entropy Advancement) was proposed, in which control coefficient was introduced in front of the penalty term to control the penalty strength. Selective attack experiments on five real networks with different sizes were conducted. Experimental results show that in the western US states grid and the US Airlines, PLEA has the identification accuracy improved by 26.3% and 3.2% compared with LE respectively, by 380% and 5.43% compared with K-Shell (KS) method respectively, and by 14.4% and 24% compared with DCL (Degree and Clustering coefficient and Location) method respectively. The key nodes identified by PLEA can cause more damage to the network, verifying the rationality of introducing the CC as a penalty term, and the effectiveness and superiority of PLEA. The integration of the number of neighbors and the local network structure of nodes with the simplicity of computation makes it more effective in describing the reliability and invulnerability of large-scale networks.

    Table and Figures | Reference | Related Articles | Metrics
    Improved method of convolution neural network based on matrix decomposition
    Zhenliang LI, Bo LI
    Journal of Computer Applications    2023, 43 (3): 685-691.   DOI: 10.11772/j.issn.1001-9081.2022010032
    Abstract414)   HTML37)    PDF (1694KB)(220)       Save

    Aiming at the difficulty of optimizing the traditional Convolutional Neural Network (CNN) in the training process, an improved method of CNN based on matrix decomposition was proposed. Firstly, the convolution kernel parameter tensor of the model convolution layer during training was converted into the product of multiple parameter matrices through matrix decomposition to form overparameterization. Secondly, these additional linear parameters were added to the back propagation of the network and updated synchronously with other parameters of the model to improve the optimization process of gradient descent. After completing the training, the matrix product was restored to the standard convolution kernel parameters, so that the computational complexity of forward propagation during inference was able to be the same as before the improvement. With thin QR decomposition and reduced Singular Value Decomposition (SVD) applied, the classification effect experiments were carried out on CIFAR-10 (Canadian Institute For Advanced Research, 10 classes) dataset, and further generalization experiments were carried out by using different image classification datasets and different initialization methods. Experimental results show that the classification accuracies of 7 models of different depths of Visual Geometry Group (VGG) and Residual Network (ResNet) based on matrix decomposition are higher than those of the original convolutional neural network models. It can be seen that the matrix decomposition method can make CNN achieve higher classification accuracy, and eventually converge to a better local optimum.

    Table and Figures | Reference | Related Articles | Metrics
    Few-shot text classification method based on prompt learning
    Bihui YU, Xingye CAI, Jingxuan WEI
    Journal of Computer Applications    2023, 43 (9): 2735-2740.   DOI: 10.11772/j.issn.1001-9081.2022081295
    Abstract407)   HTML32)    PDF (884KB)(183)       Save

    Text classification tasks usually rely on sufficient labeled data. Concerning the over-fitting problem of classification models on samples with small size in low resource scenarios, a few-shot text classification method based on prompt learning called BERT-P-Tuning was proposed. Firstly, the pre-trained model BERT (Bidirectional Encoder Representations from Transformers) was used to learn the optimal prompt template from labeled samples. Then, the prompt template and vacancy were filled in each sample, and the text classification task was transformed into the cloze test task. Finally, the final labels were obtained by predicting the word with the highest probability of the vacant positions and combining the mapping relationship between it and labels. Experimental results on the short text classification tasks of public dataset FewCLUE show that the proposed method have significantly improved the evaluation indicators compared to the BERT fine-tuning based method. In specific, the proposed method has the accuracy and F1 score increased by 25.2 and 26.7 percentage points respectively on the binary classification task, and the proposed method has the accuracy and F1 score increased by 6.6 and 8.0 percentage points respectively on the multi-class classification task. Compared with the PET (Pattern Exploiting Training) method of constructing templates manually, the proposed method has the accuracy increased by 2.9 and 2.8 percentage points respectively on two tasks, and the F1 score increased by 4.4 and 4.2 percentage points respectively on two tasks. The above verifies the effectiveness of applying pre-trained model on few-shot tasks.

    Table and Figures | Reference | Related Articles | Metrics
    Hierarchical access control and sharing system of medical data based on blockchain
    Meng CAO, Sunjie YU, Hui ZENG, Hongzhou SHI
    Journal of Computer Applications    2023, 43 (5): 1518-1526.   DOI: 10.11772/j.issn.1001-9081.2022050733
    Abstract398)   HTML22)    PDF (2871KB)(123)       Save

    Focusing on coarse granularity of access control, low sharing flexibility and security risks such as data leakage of centralized medical data sharing platform, a blockchain-based hierarchical access control and sharing system of medical data was proposed. Firstly, medical data was classified according to sensitivity, and a Ciphertext-Policy Attribute-Based Hierarchical Encryption (CP-ABHE) algorithm was proposed to achieve access control of medical data with different sensitivity. In the algorithm, access control trees were merged and symmetric encryption methods were combinined to improve the performance of Ciphertext-Policy Attribute-Based Encryption (CP-ABE) algorithm, and the multi-authority center was used to solve the key escrow problem. Then, the medical data sharing mode based on permissioned blockchain was used to solve the centralized trust problem of centralized sharing platform. Security analysis shows that the proposed system ensures the security of data during the data sharing process, and can resist user collusion attacks and authority collusion attacks. Experimental results also show that the proposed CP-ABHE algorithm has lower computational cost than CP-ABE algorithm, the maximum average delay of the proposed system is 7.8 s, and the maximum throughput is 236 transactions per second, which meets the expected performance requirements.

    Table and Figures | Reference | Related Articles | Metrics
    Lightweight ship target detection algorithm based on improved YOLOv5
    Jiadong LI, Danpu ZHANG, Yaqiong FAN, Jianfeng YANG
    Journal of Computer Applications    2023, 43 (3): 923-929.   DOI: 10.11772/j.issn.1001-9081.2022071096
    Abstract397)   HTML20)    PDF (4960KB)(189)       Save

    Aiming at the problem of low accuracy of ship target detection at sea, a lightweight ship target detection algorithm YOLOShip was proposed on the basis of the improved YOLOv5. Firstly, dilated convolution and channel attention were introduced into Spatial Pyramid Pooling-Fast (SPPF) module, which integrated spatial feature details of different scales, strengthened semantic information, and improved the model’s ability to distinguish foreground and background. Secondly, coordinate attention and lightweight mixed depthwise convolution were introduced into Feature Pyramid Network (FPN) and Path Aggregation Network (PAN) structures to strengthen important features in the network, obtain features with more detailed information, and improve model detection ability and positioning precision. Thirdly, considering the uneven distribution and relatively small scale changes of targets in the dataset, the model performance was further improved while the model was simplified by modifying the anchors and decreasing the number of detection heads. Finally, a more flexible Polynomial Loss (PolyLoss) was introduced to optimize Binary Cross Entropy Loss (BCE Loss) to improve the model convergence speed and model precision. Experimental results show that on dataset SeaShips, in comparison with YOLOv5s, YOLOShip has the Precision, Recall, mAP@0.5 and mAP@0.5:0.95 increased by 4.2, 5.7, 4.6 and 8.5 percentage points. Thus, by using the proposed algorithm, better detection precision can be obtained while meeting the requirements of detection speed, effectively achieving high-speed and high-precision ship detection.

    Table and Figures | Reference | Related Articles | Metrics
    Federated learning algorithm based on personalized differential privacy
    Chunyong YIN, Rui QU
    Journal of Computer Applications    2023, 43 (4): 1160-1168.   DOI: 10.11772/j.issn.1001-9081.2022030337
    Abstract392)   HTML17)    PDF (1800KB)(227)       Save

    Federated Learning (FL) can effectively protect users' personal data from attackers. Differential Privacy (DP) is applied to enhance the privacy of FL, which can solve the problem of privacy disclose caused by parameters in the model training. However, existing FL methods based on DP on concentrate on the unified privacy protection budget and ignore the personalized privacy requirements of users. To solve this problem, a two-stage Federated Learning with Personalized Differential Privacy (PDP-FL) algorithm was proposed. In the first stage, the user's privacy was graded according to the user's privacy preference, and the noise meeting the user's privacy preference was added to achieve the purpose of personalized privacy protection. At the same time, the privacy level corresponding to the privacy preference was uploaded to the central aggregation server. In the second stage, in order to fully protect the global data, the simultaneous local and central protection strategy was adopted. And according to the privacy level uploaded by the user, the noise conforming to the global DP threshold was added to quantify the global privacy protection level. Experimental results show that on MNIST and CIFAR-10 datasets, the classification accuracy of PDP-FL algorithm reaches 93.8% to 94.5% and 43.4% to 45.2% respectively, which is better than those of Federated learning with Local Differential Privacy (LDP-Fed) algorithm and Federated Learning with Global Differential Privacy (GDP-FL) algorithm, PDP-FL algorithm meets the needs of personalized privacy protection.

    Table and Figures | Reference | Related Articles | Metrics
    Prompt learning based unsupervised relation extraction model
    Menglin HUANG, Lei DUAN, Yuanhao ZHANG, Peiyan WANG, Renhao LI
    Journal of Computer Applications    2023, 43 (7): 2010-2016.   DOI: 10.11772/j.issn.1001-9081.2022071133
    Abstract384)   HTML13)    PDF (1353KB)(158)       Save

    Unsupervised relation extraction aims to extract the semantic relations between entities from unlabeled natural language text. Currently, unsupervised relation extraction models based on Variational Auto-Encoder (VAE) architecture provide supervised signals to train model through reconstruction loss, which offers a new idea to complete unsupervised relation extraction tasks. Focusing on the issue that this kind of models cannot understand contextual information effectively and relies on dataset inductive biases, a Prompt-based learning based Unsupervised Relation Extraction (PURE) model was proposed, including a relation extraction module and a link prediction module. In the relation extraction module, a context-aware Prompt template function was designed to fuse the contextual information, and the unsupervised relation extraction task was converted into a mask prediction task, so as to make full use of the knowledge obtained during pre-training phase to extract relations. In the link prediction module, supervised signals were provided for the relation extraction module by predicting the missing entities in the triples to assist model training. Extensive experiments on two public real-world relation extraction datasets were carried out. The results show that PURE model can use contextual information effectively and does not rely on dataset inductive biases, and has the evaluation index B-cubed F1 improved by 3.3 percentage points on NYT dataset compared with the state-of-the-art VAE architecture-based model UREVA (Variational Autoencoder-based Unsupervised Relation Extraction model).

    Table and Figures | Reference | Related Articles | Metrics
    Sentiment boosting model for emotion recognition in conversation text
    Yu WANG, Yubo YUAN, Yi GUO, Jiajie ZHANG
    Journal of Computer Applications    2023, 43 (3): 706-712.   DOI: 10.11772/j.issn.1001-9081.2022010044
    Abstract384)   HTML19)    PDF (1123KB)(191)       Save

    To address the problems that many existing studies ignore the correlation between interlocutors’ emotions and sentiments, a sentiment boosting model for emotion recognition in conversation text was proposed, namely Sentiment Boosting Graph Neural network (SBGN). Firstly, themes and dialogue intent were integrated into the text, and the reconstructed text features were extracted by fine-tuning the pre-trained language model. Secondly, a symmetric learning structure for emotion analysis was given, with the reconstructed features fed into a Graph Neural Network (GNN) emotion analysis model and a Bi-directional Long Short-Term Memory (Bi-LSTM) sentiment classification model. Finally, by fusing emotion analysis and sentiment classification models, a new loss function was constructed with sentiment classification loss function as a penalty, and the optimal penalty factor was adjusted and obtained by learning. Experimental results on public dataset DailyDialog show that SBGN model improves 16.62 percentage points compared with Dialogue Graph Convolutional Network (DialogueGCN) model, and improves 14.81 percentage points compared with the state-of-art model Directed Acyclic Graph-Emotion Recognition from Conversation (DAG-ERC) in micro-average F1. It can be seen that SBGN model can effectively improve the performance of emotion analysis in dialogue system.

    Table and Figures | Reference | Related Articles | Metrics
    Object detection algorithm for remote sensing images based on geometric adaptation and global perception
    Yongxiang GU, Xin LAN, Boyi FU, Xiaolin QIN
    Journal of Computer Applications    2023, 43 (3): 916-922.   DOI: 10.11772/j.issn.1001-9081.2022010071
    Abstract384)   HTML17)    PDF (2184KB)(195)       Save

    Aiming at the problems such as small object size, arbitrary object direction and complex background of remote sensing images, on the basis of YOLOv5 (You Only Look Once version 5) algorithm, an algorithm involved with geometric adaptation and global perception was proposed. Firstly, deformable convolutions and adaptive spatial attention modules were stacked alternately in series through dense connections. As a result, a Dense Context-Aware Module (DenseCAM) which can model local geometric features was constructed on the basis of taking full advantage of different levels of semantic and location information. Secondly, by introducing Transformer in the end of the backbone network, the global perception ability of the model was enhanced at a low cost and the relationships between objects and scenario content were modeled. On UCAS-AOD and RSOD datasets, compared with YOLOv5s6 algorithm, the proposed algorithm has the mean Average Precision (mAP) increased by 1.8 percentage points and 1.5 percentage points, respectively. Experimental results show that the proposed algorithm can effectively improve the precision of object detection in remote sensing images.

    Table and Figures | Reference | Related Articles | Metrics
    Discriminative multidimensional scaling for feature learning
    Haitao TANG, Hongjun WANG, Tianrui LI
    Journal of Computer Applications    2023, 43 (5): 1323-1329.   DOI: 10.11772/j.issn.1001-9081.2022030419
    Abstract375)   HTML73)    PDF (1101KB)(320)       Save

    Traditional multidimensional scaling method achieves low-dimensional embedding, which maintains the topological structure of data points but ignores the discriminability of the low-dimensional embedding itself. Based on this, an unsupervised discriminative feature learning method based on multidimensional scaling method named Discriminative MultiDimensional Scaling model (DMDS) was proposed to discover the cluster structure while learning the low-dimensional data representation. DMDS can make the low-dimensional embeddings of the same cluster closer to make the learned data representation be more discriminative. Firstly, a new objective function corresponding to DMDS was designed, reflecting that the learned data representation could maintain the topology and enhance discriminability simultaneously. Secondly, the objective function was reasoned and solved, and a corresponding iterative optimization algorithm was designed according to the reasoning process. Finally, comparison experiments were carried out on twelve public datasets in terms of average accuracy and average purity of clustering. Experimental results show that DMDS outperforms the original data representation and the traditional multidimensional scaling model based on the comprehensive evaluation of Friedman statistics, the low-dimensional embeddings learned by DMDS are more discriminative.

    Table and Figures | Reference | Related Articles | Metrics
    Review of zero trust network and its key technologies
    Qun WANG, Quan YUAN, Fujuan LI, Lingling XIA
    Journal of Computer Applications    2023, 43 (4): 1142-1150.   DOI: 10.11772/j.issn.1001-9081.2022030453
    Abstract368)   HTML29)    PDF (2001KB)(252)       Save

    With increasingly severe network security threats and increasingly complex security defense means, zero trust network is a new evaluation and review of traditional boundary security architecture. Zero trust emphasizes never always trusting anything and verifying things continuously. Zero trust network emphasizes that the identity is not identified by location, all access controls strictly execute minimum permissions, and all access processes are tracked in real time and evaluated dynamically. Firstly, the basic definition of zero trust network was given, the main problems of traditional perimeter security were pointed out, and the zero trust network model was described. Secondly, the key technologies of zero trust network, such as Software Defined Perimeter (SDP), identity and access management, micro segmentation and Automated Configuration Management System (ACMS), were analyzed. Finally, zero trust network was summarized and its future development was prospected.

    Table and Figures | Reference | Related Articles | Metrics
    Fusion imaging-based recurrent capsule classification network for time series
    Rongjun CHEN, Xuanhui YAN, Chaocheng YANG
    Journal of Computer Applications    2023, 43 (3): 692-699.   DOI: 10.11772/j.issn.1001-9081.2022010089
    Abstract358)   HTML23)    PDF (2586KB)(205)       Save

    To address the problem of lack of temporal correlations and spatial location relationships in imaging time series, Fusion-Imaing Recurrent Capsule Neural Network (FIR-Capsnet) for time series was proposed to fuse and extract spatial-temporal information from time series images. Firstly, the multi-level spatial-temporal features of time series images were captured by using Gramian Angular Field (GAF), Markov Transition Field (MTF) and Recurrence Plot (RP). Then, the spatial relationships of time series images were learnt by the rotation invariance of capsule neural network and iterative routing algorithm. Finally, the temporal correlations hidden in the time series data were learnt by the gate mechanism of Long-Short Term Memory (LSTM) network. Experimental results show that FIR-Capsnet achieves 15 wins on 30 UCR public datasets and outperforms Fusion-CNN by 7.2 percentage points in classification accuracy on Human Activity Recognition (HAR) dataset, illustrating the advantages of FIR-Capsnet in processing time series data.

    Table and Figures | Reference | Related Articles | Metrics
    Few-shot object detection algorithm based on Siamese network
    Junjian JIANG, Dawei LIU, Yifan LIU, Yougui REN, Zhibin ZHAO
    Journal of Computer Applications    2023, 43 (8): 2325-2329.   DOI: 10.11772/j.issn.1001-9081.2022121865
    Abstract354)   HTML37)    PDF (1472KB)(379)       Save

    Deep learning based algorithms such as YOLO (You Only Look Once) and Faster Region-Convolutional Neural Network (Faster R-CNN) require a huge amount of training data to ensure the precision of the model, and it is difficult to obtain data and the cost of labeling data is high in many scenarios. And due to the lack of massive training data, the detection range is limited. Aiming at the above problems, a few-shot object Detection algorithm based on Siamese Network was proposed, namely SiamDet, with the purpose of training an object detection model with certain generalization ability by using a few annotated images. Firstly, a Siamese network based on depthwise separable convolution was proposed, and a feature extraction network ResNet-DW was designed to solve the overfitting problem caused by insufficient samples. Secondly, an object detection algorithm SiamDet was proposed based on Siamese network, and based on ResNet-DW, Region Proposal Network (RPN) was introduced to locate the interested objects. Thirdly, binary cross entropy loss was introduced for training, and contrast training strategy was used to increase the distinction among categories. Experimental results show that SiamDet has good object detection ability for few-shot objects, and SiamDet improves AP50 by 4.1% on MS-COCO 20-way 2-shot and 2.6% on PASCAL VOC 5-way 5-shot compared with the suboptimal algorithm DeFRCN (Decoupled Faster R-CNN).

    Table and Figures | Reference | Related Articles | Metrics
    Deep graph matching model based on self-attention network
    Zhoubo XU, Puqing CHEN, Huadong LIU, Xin YANG
    Journal of Computer Applications    2023, 43 (4): 1005-1012.   DOI: 10.11772/j.issn.1001-9081.2022030345
    Abstract348)   HTML51)    PDF (2118KB)(239)       Save

    Node feature representation was learned by Graph Convolutional Network (GCN) by deep graph matching models in the stage of node feature extraction. However, GCN was limited by the learning ability for node feature representation, affecting the distinguishability of node features, which causes poor measurement of node similarity, and leads to the loss of model matching accuracy. To solve the problem, a deep graph matching model based on self-attention network was proposed. In the stage of node feature extraction, a new self-attention network was used to learn node features. The principle of the network is improving the feature description of nodes by utilizing spatial encoder to learn the spatial structures of nodes, and using self-attention mechanism to learn the relations among all the nodes. In addition, in order to reduce the loss of accuracy caused by relaxed graph matching problem, the graph matching problem was modelled to an integer linear programming problem. At the same time, structural matching constraints were added to graph matching problem on the basis of node matching, and an efficient combinatorial optimization solver was introduced to calculate the local optimal solution of graph matching problem. Experimental results show that on PASCAL VOC dataset, compared with Permutation loss and Cross-graph Affinity based Graph Matching (PCA-GM), the proposed model has the average matching precision on 20 classes of images increased by 14.8 percentage points, on Willow Object dataset, the proposed model has the average matching precision on 5 classes of images improved by 7.3 percentage points, and achieves the best results on object matching tasks such as bicycles and plants.

    Table and Figures | Reference | Related Articles | Metrics
    Ultra-short-term photovoltaic power prediction by deep reinforcement learning based on attention mechanism
    Zhengkai DING, Qiming FU, Jianping CHEN, You LU, Hongjie WU, Nengwei FANG, Bin XING
    Journal of Computer Applications    2023, 43 (5): 1647-1654.   DOI: 10.11772/j.issn.1001-9081.2022040542
    Abstract340)   HTML12)    PDF (3448KB)(249)       Save

    To address the problem that traditional PhotoVoltaic (PV) power prediction models are affected by random power fluctuation and tend to ignore important information, resulting in low prediction accuracy, ADDPG and ARDPG models were proposed by combining the attention mechanism with Deep Deterministic Policy Gradient (DDPG) and Recurrent Deterministic Policy Gradient (RDPG), respectively, and a PV power prediction framework was proposed on this basis. Firstly, the original PV power data and meteorological data were normalized, and the PV power prediction problem was modeled as a Markov Decision Process (MDP), where the historical power data and current meteorological data were used as the states of MDP. Then the attention mechanism was added to the Actor networks of DDPG and RDPG, giving different weights to different components of the state to highlight important and critical information, and learning critical information in the data through the interaction of Deep Reinforcement Learning (DRL) agents and historical data. Finally, the MDP problem was solved to obtain the optimal strategy and make accurate prediction. Experimental results on DKASC and Alice Springs PV system data show that ADDPG and ARDPG achieve the best results in Root Mean Square Error (RMSE), Mean Absolute Error (MAE) and R2. It can be seen that the proposed models can effectively improve the prediction accuracy of PV power, and can also be extended to other prediction fields such as grid prediction and wind power generation prediction.

    Table and Figures | Reference | Related Articles | Metrics
    Multi-view ensemble clustering algorithm based on view-wise mutual information weighting
    Jinghuan LAO, Dong HUANG, Changdong WANG, Jianhuang LAI
    Journal of Computer Applications    2023, 43 (6): 1713-1718.   DOI: 10.11772/j.issn.1001-9081.2022060925
    Abstract335)   HTML13)    PDF (1573KB)(161)       Save

    Many of the existing multi-view clustering algorithms lack the ability to estimate the reliability of different views and thus weight the views accordingly, and some multi-view clustering algorithms with view-weighting ability generally rely on the iterative optimization of specific objective function, whose real-world applications may be significantly influenced by the practicality of the objective function and the rationality of tuning some sensitive hyperparameters. To address these problems, a Multi-view Ensemble Clustering algorithm based on View-wise Mutual Information Weighting (MEC-VMIW) was proposed, whose overall process consists of two phases: the view-wise mutual weighting phase and the multi-view ensemble clustering phase. In the view-wise mutual weighting phase, multiple random down-samplings were performed to the dataset, so as to reduce the problem size in the evaluating and weighting process. After that, a set of down-sampled clusterings of multiple views was constructed. And, based on multiple runs of mutual evaluation among the clustering results of different views, the view-wise reliability was estimated and used for view weighting. In the multi-view ensemble clustering phase, the ensemble of base clusterings was constructed for each view, and multiple base clustering sets were weighted to model a bipartite graph structure. By performing efficient bipartite graph partitioning, the final multi-view clustering results were obtained. Experiments on several multi-view datasets confirm the robust clustering performance of the proposed multi-view ensemble clustering algorithm.

    Table and Figures | Reference | Related Articles | Metrics
    Traffic flow prediction model based on time series decomposition
    Jin XIA, Zhengqun WANG, Shiming ZHU
    Journal of Computer Applications    2023, 43 (4): 1129-1135.   DOI: 10.11772/j.issn.1001-9081.2022030473
    Abstract326)   HTML11)    PDF (2485KB)(171)       Save

    Short-term traffic flow prediction is not only related to historical data, but also affected by the traffic of adjacent areas. Since the trend and spatial correlation of traffic flow are ignored by traditional Time Series Decomposition (TSD) models, a time series processing model based on the combination of Time Series Decomposition and Spatio-Temporal features (TSD-ST) was proposed. Firstly, the trend component and periodic component were obtained by using Empirical Mode Decomposition (EMD) and Discrete Fourier Transform (DFT), the Spatio-Temporal (ST) correlation of the fluctuation component was mined by Mutual Information algorithm (MI), and the state vector was reconstructed on the basis of the above. Then, the fluctuation component was predicted by using the state vector through Long Short-Term Memory (LSTM) network. Finally, the final predicted value was obtained by reconstructing the prediction results of the three parts of the sequence. The validity of the model was verified on the real data of Interstate I090 in Washington State, USA. Experimental results show that the Root Mean Square Error (RMSE) of the proposed model TSD-ST-LSTM is reduced by 16.5%, 34.0%, and 36.6% compared with that of Support Vector Regression (SVR), Gradient Boosting Regression Tree (GBRT) and LSTM, respectively. It can be seen that the proposed model is very effective in improving prediction accuracy.

    Table and Figures | Reference | Related Articles | Metrics
    Weakly-supervised text classification with label semantic enhancement
    Chengyu LIN, Lei WANG, Cong XUE
    Journal of Computer Applications    2023, 43 (2): 335-342.   DOI: 10.11772/j.issn.1001-9081.2021122221
    Abstract323)   HTML60)    PDF (1987KB)(256)       Save

    Aiming at the problem of category vocabulary noise and label noise in weakly-supervised text classification tasks, a weakly-supervised text classification model with label semantic enhancement was proposed. Firstly, the category vocabulary was denoised on the basis of the contextual semantic representation of the words in order to construct a highly accurate category vocabulary. Then, a word category prediction task based on MASK mechanism was constructed to fine-tune the pre-training model BERT (Bidirectional Encoder Representations from Transformers), so as to learn the relationship between words and categories. Finally, a self-training module with label semantics introduced was used to make full use of all data information and reduce the impact of label noise in order to achieve word-level to sentence-level semantic conversion, thereby accurately predicting text sequence categories. Experimental results show that compared with the current state-of-the-art weakly-supervised text classification model LOTClass (Label-name-Only Text Classification), the proposed method improves the classification accuracy by 5.29, 1.41 and 1.86 percentage points respectively on the public datasets THUCNews, AG News and IMDB.

    Table and Figures | Reference | Related Articles | Metrics
    Poisoning attack toward visual classification model
    Jie LIANG, Xiaoyan HAO, Yongle CHEN
    Journal of Computer Applications    2023, 43 (2): 467-473.   DOI: 10.11772/j.issn.1001-9081.2021122068
    Abstract323)   HTML9)    PDF (3264KB)(111)       Save

    In data poisoning attacks, backdoor attackers manipulate the distribution of training data by inserting the samples with hidden triggers into the training set to make the test samples misclassified so as to change model behavior and reduce model performance. However, the drawback of the existing triggers is the sample independence, that is, no matter what trigger mode is adopted, different poisoned samples contain the same triggers. Therefore, by combining image steganography and Deep Convolutional Generative Adversarial Network (DCGAN), an attack method based on sample was put forward to generate image texture feature maps according to the gray level co-occurrence matrix, embed target label character into the texture feature maps as a trigger by using the image steganography technology, and combine texture feature maps with trigger and clean samples into poisoned samples. Then, a large number of fake pictures with trigger were generated through DCGAN. In the training set samples, the original poisoned samples and the fake pictures generated by DCGAN were mixed together to finally achieve the effect that after the poisoner injecting a small number of poisoned samples, the attack rate was high and the effectiveness, sustainability and concealment of the trigger were ensured. Experimental results show that this method avoids the disadvantages of sample independence and has the model accuracy reached 93.78%. When the proportion of poisoned samples is 30%, data preprocessing, pruning defense and AUROR defense have the least influence on the success rate of attack, and the success rate of attack can reach about 56%.

    Table and Figures | Reference | Related Articles | Metrics
    2D/3D spine medical image real-time registration method based on pose encoder
    Shaokang XU, Zhancheng ZHANG, Haonan YAO, Zhiwei ZOU, Baocheng ZHANG
    Journal of Computer Applications    2023, 43 (2): 589-594.   DOI: 10.11772/j.issn.1001-9081.2021122147
    Abstract321)   HTML5)    PDF (2007KB)(139)       Save

    2D/3D medical image registration is a key technology in 3D real-time navigation of orthopedic surgery. However, the traditional 2D/3D registration methods based on optimization iteration require multiple iterative calculations, which cannot meet the requirements of doctors for real-time registration during surgery. To solve this problem, a pose regression network based on autoencoder was proposed. In this network, the geometric pose information was captured through hidden space decoding, thereby quickly regressing the 3D pose of preoperative spine pose corresponding to the intraoperative X-ray image, and the final registration image was generated through reprojection. By introducing new loss functions, the model was constrained by “Rough to Fine” combined registration method to ensure the accuracy of pose regression. In CTSpine1K spine dataset, 100 CT scan image sets were extracted for 10-fold cross-validation. Experimental results show that the registration result image generated by the proposed model has the Mean Absolute Error (MAE) with the X-ray image of 0.04, the mean Target Registration Error (mTRE) with the X-ray image of 1.16 mm, and the single frame consumption time of 1.7 s. Compared to the traditional optimization based method, the proposed model has registration time greatly shortened. Compared with the learning-based method, this model ensures a high registration accuracy with quick registration. Therefore, the proposed model can meet the requirements of intraoperative real-time high-precision registration.

    Table and Figures | Reference | Related Articles | Metrics
    Improved instruction obfuscation framework based on obfuscator low level virtual machine
    Yayi WANG, Chen LIU, Tianbo HUANG, Weiping WEN
    Journal of Computer Applications    2023, 43 (2): 490-498.   DOI: 10.11772/j.issn.1001-9081.2021122234
    Abstract318)   HTML19)    PDF (2140KB)(108)       Save

    Focusing on the issue that only one instruction substitution with 5 operators and 13 substitution schemes is supported in Obfuscator Low Level Virtual Machine (OLLVM) at the instruction obfuscation level, an improved instruction obfuscation framework InsObf was proposed. InsObf, including junk code insertion and instruction substitution, was able to enhance the obfuscation effect at the instruction level based on OLLVM. For junk code insertion, firstly, the dependency of the instruction inside the basic block was analyzed, and then two kinds of junk code, multiple jump and bogus loop, were inserted to disrupt the structure of the basic block. For instruction substitution, based on OLLVM, it was expanded to 13 operators, with 52 instruction substitution schemes. The framework prototype was implemented on Low Level Virtual Machine (LLVM). Experimental results show that compared to OLLVM, InsObf has the cyclomatic complexity and resilience increased by almost four times, with a time cost of about 10 percentage points and a space cost of about 20 percentage points higher. Moreover, InsObf can provide higher code complexity compared to Armariris and Hikari, which are also improved on the basis of OLLVM, at the same order of magnitude of time and space costs. Therefore, InsObf can provide effective protection at the instruction level.

    Table and Figures | Reference | Related Articles | Metrics
2023 Vol.43 No.11

Current Issue
Honorary Editor-in-Chief: ZHANG Jingzhong
Editor-in-Chief: XU Zongben
Associate Editor: SHEN Hengtao XIA Zhaohui
Domestic Post Distribution Code: 62-110
Foreign Distribution Code: M4616
No. 9, 4th Section of South Renmin Road, Chengdu 610041, China
Tel: 028-85224283-803
Join CCF