Top Read Articles

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

Please wait a minute...


For Selected: Download Citations EndNote Ris BibTeX Toggle Thumbnails

Select

Mobile Robot Path Planning Based on Fusion of Improved A* and DWA Algorithms PANG Yong-xu, YUAN De-cheng Computer and Modernization    2022, 0 (01): 103-107.   Abstract （1311）      PDF（pc） （2046KB）（1019）       Knowledge map    Save Aiming at the path planning requirements of mobile robot to achieve global optimal path in complex environment and dynamic and real-time obstacle avoidance in unknown environment, the traditional A* (A-star) algorithm is improved, and Dynamic Window Approach (DWA) is integrated to achieve dynamic and real-time obstacle avoidance. Firstly, the obstacle proportion in the grid environment is analyzed. The obstacle proportion is introduced into the traditional A* algorithm to optimize the heuristic function h(n), so as to improve the evaluation function f(n) and improve its search efficiency in different environments. Secondly, in view of the intersection between the trajectory and the vertex of obstacles optimized by the traditional A* algorithm in the complex grid environment, the selection method of child nodes is optimized, and the redundant nodes in the path are deleted to improve the smoothness of the path. Finally, Dynamic Window Approach is integrated to realize dynamic and real-time obstacle avoidance of mobile robot in complex environment. The comparative simulation experiments under MATLAB show that the improved algorithm is optimized in the path length, path smoothness and elapsed time, meets the global optimal and can realize dynamic and real-time obstacle avoidance, and has better path planning effect. Reference | Related Articles | Metrics | Comments（0）

Select

Intention Recognition and Classification Based on BERT-FNN ZHENG Xin-yue, REN Jun-chao Computer and Modernization    2021, 0 (07): 71-76.   Abstract （759）      PDF（pc） （989KB）（157）       Knowledge map    Save Intention recognition classification is an important question in the field of natural language processing. How to understand the user’s intention based on context is a key and difficult problem in intelligent robots and intelligent customer service. Traditional intention recognition classification is mainly based on regularization methods or machine learning methods. However, there are problems of high computational cost and poor generalization ability. In response to the above problems, the design of this paper is based on Google’s BERT pre-training language model to perform context modeling and sentence-level semantic representation of the text, uses the vector corresponding to the ［cls］ token to represent the context of the text, then, extracts the feature of sentences through fully-connected neural network (FNN). In order to make full use of the data, this paper uses the idea of disassembly method to convert the multi-classification problem into multiple binary classification problems. Each time, one category is used as a positive example, and the remaining categories are used as negative examples, which generates multiple two-classification tasks so as to achieve intention classification. Experimental results show that the performance of this method is better than the traditional model, and the accuracy of this method is 94%. Reference | Related Articles | Metrics | Comments（0）

Select

Review on Fault Diagnosis Technology of Transformer LIN Fan-qin, LI Ming-ming, GUO Hong Computer and Modernization    2022, 0 (03): 116-126.   Abstract （746）      PDF（pc） （1589KB）（122）       Knowledge map    Save Transformer equipment plays an essential role in the power system. Its healthy and stable operation is related to realizing the function of power distribution voltage conversion, and fault diagnosis technology can escort for the transformer’s regular operation. This paper summarizes the research status of transformer fault diagnosis technology at home and abroad, analyzes the development process of transformer fault diagnosis, compares the merits of different diagnosis methods, and analyzes the traditional method of extracting transformer fault data——dissolved gas extraction method and sound signal. Finally, the research focus and development trend of transformer fault diagnosis in the future are put forward to provide some reference for transformer fault diagnosis. Reference | Related Articles | Metrics | Comments（0）

Select

A Text Classification Model Based on BERT and Pooling Operation ZHNAG Jun, QIU Long-long Computer and Modernization    2022, 0 (06): 1-7.   Abstract （739）      PDF（pc） （948KB）（136）       Knowledge map    Save The fine-tuning method using the pre-trained language model has achieved good results in many natural language processing tasks represented by text classification, BERT model based on the Transformer framework as a typical representative especially. However, BERT uses the vector corresponding to ［CLS］ as the text representation directly, and does not consider the local features and global features of texts, which limits the classification performance of the model. Therefore, this paper proposes a text classification model that introduces a pooling operation, and uses pooling methods such as average pooling, maximum pooling, and K-MaxPooling to extract the representation vector of texts from the output matrix of BERT. The experimental results show that compared with the original BERT model, the text classification model with pooling operation proposed in this paper has better performance. In all text classification tasks in the experiment, its accuracy and F1-Score value are better than BERT model. Reference | Related Articles | Metrics | Comments（0）

Select

Microblog Rumor Detection Based on Sentiment Analysis and Transformer Model FENG Ru-jia, ZHANG Hai-jun, PAN Wei-min Computer and Modernization    2021, 0 (10): 1-7.   Abstract （730）      PDF（pc） （1087KB）（537）       Knowledge map    Save Aiming at realizing the rumor detection on microblog, this paper deeply excavates the semantic information of the body content of microblog, and emphasizes the emotional tendency reflected by users in microblog comments, so as to improve the effect of rumor identification. In order to improve the rumor detection accuracy, based on XLNet word embedding method, the Transformer’s Encoder model is used to extract the semantic features of microblog body content. Combined with the BiLSTM+Attention network, the emotional feature extraction of microblog comments is realized. Two kinds of feature vectors are spliced and fused to further enrich the input features of neural network. Then, the microblog event classification results are output, and the microblog rumors detection is achieved. The experimental results show that the accuracy of the model in rumor recognition reaches 94.8%. Reference | Related Articles | Metrics | Comments（0）

Select

Stock Movement Prediction Algorithm Based on Deep Learning ZHOU Run-jia Computer and Modernization    2023, 0 (01): 69-73.   Abstract （701）      PDF（pc） （1263KB）（146）       Knowledge map    Save To improve the accuracy of stock movement prediction， this paper proposes a stock movement prediction algorithm AACL（Adversarial Attentive CNN-LSTM）which utilizes CNN and LSTM for feature extraction and combines attention mechanism and adversarial training. The algorithm uses CNN to extract the overall trend information of the stock， LSTM to extract the short-term fluctuation information of the stock， and connects multiple stocks through the attention mechanism to capture the rising and falling relationship between stocks. The algorithm also introduces adversarial training to improve the robustness of the algorithm by interfering the data. To verify the effectiveness of the AACL algorithm， experiments are carried out on three data sets KDD17， ACL18， and China50， and compared with existing algorithms. Experiments results show that the algorithm proposed in this paper can obtain the best result. Reference | Related Articles | Metrics | Comments（0）

Select

A Survey of Encrypted Traffic Classification Based on Deep Learning LENG Tao , Computer and Modernization    2021, 0 (08): 112-120.   Abstract （644）      PDF（pc） （1055KB）（258）       Knowledge map    Save In recent years, in order to protect the public privacy, a lot of traffic on the Internet is encrypted. The accuracy of traditional deep packet inspection and machine learning methods in the face of encrypted traffic has dropped significantly. With the application of deep learning automatic learning features, the encryption flow identification and classification technology based on deep learning algorithms have been rapidly developed. This article reviews these studies. First, this paper briefly introduces the application scenarios of encrypted traffic detection based on deep learning. Then, it summarizes and evaluates the existing works from three aspects: the use and construction of data sets, the detection model and the detection performance. The detection technology focuses on data preprocessing, unbalanced data set processing, neural network construction, real-time detection, etc. Finally, the problems in current research and future development directions and prospects are discussed, so as to provide some references for researchers in this field. Reference | Related Articles | Metrics | Comments（0）

Select

A Review of Deep Neural Networks Combined with Attention Mechanism HUANGFU Xiao-ying, QIAN Hui-min, HUANG Min Computer and Modernization    2023, 0 (02): 40-49.   Abstract （611）      PDF（pc） （2408KB）（88）       Knowledge map    Save Attention mechanism has become one of the research hotspots in improving the learning ability of deep neural network. In view of the wide attention paid to the attention mechanism， this paper aims to give a comprehensive analysis and elaboration of attention mechanism in deep neural network from three aspects: the classification of attention mechanism， the way of combining with deep neural network， and the specific applications in natural language processing and computer vision. Specifically， attention mechanism has been divided into soft attention mechanism， hard attention mechanism and self-attention mechanism， and their advantages and disadvantages are compared. Then， the common ways of combining attention mechanism in recursive neural network and convolutional neural network are discussed respectively， and the representative model structures of each way are given. After that， the applications of attention mechanism in natural language processing and computer vision are illustrated. Finally， several future developments of attention mechanism are illustrated expecting to provide clues and directions for subsequent researches. Reference | Related Articles | Metrics | Comments（0）

Select

Prediction of COVID-19 Based on Mixed SEIR-ARIMA Model DONG Zhang-gong, SONG Bo, MENG You-xin Computer and Modernization    2022, 0 (02): 1-6.   Abstract （587）      PDF（pc） （1176KB）（503）       Knowledge map    Save Novel coronavirus pneumonia, referred to as COVID-19, is an acute infectious pneumonia caused by novel coronavirus, which is of highly infectious and generally susceptible to the population. Therefore, the prediction of the number of novel coronavirus pneumonia infections is not only beneficial for the country to make scientific decisions in the face of the epidemic, but also facilitates the timely integration of epidemic prevention resources. In this paper, a hybrid model SEIR-ARIMA constructed by the model SEIR based on the traditional infectious disease dynamics and the differential integrated moving average autoregressive model ARIMA is proposed to make prediction and analysis of the novel coronavirus pneumonia epidemic in different time periods and locations. From the experimental results, the prediction based on the SEIR-ARIMA hybrid model has better prediction effect than the common logistic regression Logistic, long short-term memory artificial neural network LSTM, SEIR model, and ARIMA model used for COVID-19 prediction. In order to truly reflect whether the improvement of the experimental effect originates from the advantage of combining SEIR and ARIMA models, this paper also implements the SEIR-Logistic hybrid model and SEIR-LSTM hybrid model, and compares the analysis with SEIR-ARIMA to conclude that both SEIR-ARIMA predictions achieve better prediction results. Therefore, the analysis of the development trend of COVID-19 based on the SEIR-ARIMA hybrid model is relatively reliable, which is conducive to the scientific decision-making of the country in the face of the epidemic and has good application value for the prevention of other types of infectious diseases in China in the future. Reference | Related Articles | Metrics | Comments（0）

Select

A Survey of Text Classification Based on Deep Learning JIA Peng-tao, SUN Wei Computer and Modernization    2021, 0 (07): 29-37.   Abstract （585）      PDF（pc） （1071KB）（264）       Knowledge map    Save With the continuous development of the Internet, there is an increasing number of text data on the Internet. If these data can be effectively classified, it is more conducive to mining valuable information. Therefore, the management and integration of text data is very important. Text classification is a basic task in natural language processing tasks. It is mainly used in the fields of public opinion detection and news text classification. The purpose is to sort and classify text resources. The text classification based on deep learning shows a good classification effect in the processing of text data. The article elaborates on the deep learning algorithms used for text classification, classifies according to different deep learning algorithms, and analyzes the characteristics of various algorithms, and finally summarizes the future research directions of deep learning algorithms in the field of text classification. Reference | Related Articles | Metrics | Comments（0）

Select

Road Pothole Detection Algorithm Based on Improved YOLOv5s BAI Rui, XU Yang, WANG Bin, ZHANG Wen-wen Computer and Modernization    2023, 0 (06): 69-75.   DOI: 10.3969/j.issn.1006-2475.2023.06.012 Abstract （547）      PDF（pc） （3457KB）（55）       Knowledge map    Save Aiming at the problem that existing target detection algorithms are difficult to accurately detect road potholes and the detection speed is slow, a road pothole detection algorithm based on improved YOLOv5s is proposed. Firstly, CA （Coordinate attention） module is integrated into YOLOv5s backbone network, so that the model can capture not only cross-channel information, but also direction perception and position sensitive information, which is helpful for the model to locate and identify the detected object more accurately. Then, SoftPool is adopted in Spatial Pyramid Pool （SPP） module to improve the maximum pooling operation and retain more detailed characteristic information. In the feature fusion stage, Content-Aware ReAssembly of FEatures （CARAFE） is used to improve the up-sampling of multi-scale feature fusion and dynamically generate an adaptive kernel, which can gather context information in a large receptive field. Finally, Alpha-IoU is used to improve the loss function and improve the margin regression accuracy. Experimental results show that the average accuracy of the improved YOLOv5s algorithm is 4.6 percentage points higher than that of the original network, and the detection accuracy of the improved YOLOv5s algorithm is greatly improved compared with other mainstream algorithms such as SSD, Faster R-CNN, YOLOv3, YOLOv3-tiny and YOLOv4-tiny. Reference | Related Articles | Metrics | Comments（0）

Select

Recipe Recommendation Algorithm Based on Knowledge Graph and Collaborative Filtering GENG Hua-cong, LIANG Hong-tao, LIU Guo-zhu Computer and Modernization    2021, 0 (08): 24-29.   Abstract （525）      PDF（pc） （920KB）（175）       Knowledge map    Save In view of the traditional collaborative filtering-based recipe recommendation algorithm that only uses the user-item score matrix and does not consider the semantic information of the item itself resulting in low recommendation accuracy, this paper introduces the semantic information between recipes as an important recommendation basis by constructing a knowledge graph, and proposes a personalized diet recommendation algorithm based on knowledge graph embedding and collaborative filtering. By representing the recipe entity and relationship in two different low-dimensional continuous vector spaces, the semantic similarity between the dishes is calculated, and the semantic similarity is incorporated into the collaborative filtering recommendation for recommendation. The method in this paper alleviates the problems of data sparsity and cold start by strengthening the use of hidden information between dishes, and makes the recommendation result more reasonable. Experiments on the dataset show that the method has a significant effect on recipe recommendation, and it has a significant improvement in recall and AUC. Reference | Related Articles | Metrics | Comments（0）

Select

Data Augmentation for Chinese Named Entity Recognition Task LI Jian, ZHANG Ke-liang, TANG Liang, XIA Rong-jing, REN Jing-jing Computer and Modernization    2022, 0 (04): 1-6.   Abstract （519）      PDF（pc） （1025KB）（198）       Knowledge map    Save In low-resource natural language processing (NLP) tasks, the existing data is not enough to train an ideal deep learning model. Text data augmentation is an effective method to improve the training effect of such tasks. This paper proposes a group of data augmentation methods based on instance substitution for the task of Chinese named entity recognition. A named entity in the training sample can be replaced by another entity of the same kind without changing the label. The specific algorithms include: 1) crossover substitution between existing entities; 2) synonymous replacement of entity components; 3) automatic generation of Chinese names. These methods are applied to PeopleDailyNER and CLUENER2020 datasets respectively, and the augmentation data is used to train the BERT+CRF model. The experimental results show that the F1 value of the model can be improved by about 10% and 7% respectively on the two datasets with only adding the same amount of augmentation data as the original data under the condition of small samples, and it also has a significant improvement when the training samples increase. Reference | Related Articles | Metrics | Comments（0）

Select

PSWGAN-GP: Improved Wasserstein Generative Adversarial Network with Gradient Penalty CHEN Yun-xiang, WANG Wei, NING Juan, CHEN Yi-dan, ZHAO Yong-xin, ZHOU Qing-hua Computer and Modernization    2022, 0 (04): 21-26.   Abstract （516）      PDF（pc） （2806KB）（116）       Knowledge map    Save The emergence of generative adversarial network (GAN) plays a great role in solving the problem of insufficient sample data in the field of deep learning. In order to solve the detail quality problems of images generated by GAN such as foreground and background separation and contour blurring, this paper proposes an improved Wasserstein generative adversarial network with gradient penalty (PSWGAN-GP) method. Based on the Wasserstein distance loss and gradient penalty of WGAN-GP, this method uses the features extracted from the three pooling layers of the VGG-16 network in the discriminator and calculates the style-loss and perceptual-loss from these features as penalty terms of the original loss, which improves the discriminator’s ability to acquire and discriminate deep features and enhance the details of the generated images. The experimental results show that PSWGAN-GP can effectively improve the quality of generated images with the same generator and discriminator network structure and the same hyperparameters, and the scores in IS and FID are improved relative to other image generation methods. Reference | Related Articles | Metrics | Comments（0）

Select

An Improved Whale Optimization Algorithm Base on Hybrid Strategy LI Ru, FAN Bing-bing Computer and Modernization    2022, 0 (06): 13-20.   Abstract （510）      PDF（pc） （1185KB）（126）       Knowledge map    Save In order to solve the problems of the original whale optimization algorithm (WOA) with slow convergence speed, weak global search ability, low solution accuracy and easy to fall into local optimization, a hybrid strategy is proposed to improve the whale optimization algorithm (LGWOA). Firstly, the Levy flight strategy is introduced into the position update formula of the whale random search, and the global search step is increased through Levy flight, the search space is enlarged, and the global search capability is improved. Secondly, the adaptive weight is introduced into the whale spiral upward position update formula to improve the algorithm’s local search ability and optimization accuracy. Finally, the idea combining the genetic algorithm’s cross mutation is used to balance the algorithm’s global search and local search capabilities, maintain the diversity of the population, and avoid falling into the local optimum. Simulation experiments on 12 benchmark test functions in different dimensions show that the improved whale algorithm has faster convergence speed and higher optimization accuracy. Reference | Related Articles | Metrics | Comments（0）

Select

Survey of Model Pruning Algorithms LI Yi, WEI Jian-guo, LIU Guan-wei Computer and Modernization    2022, 0 (09): 51-59.   Abstract （508）      PDF（pc） （1096KB）（151）       Knowledge map    Save The model pruning algorithms apply different standards or methods to prune the redundant neurons in the deep neural network, which can compress the model to the maximum extent without losing the accuracy of the model, so as to reduce the storage and improve the speed. Firstly, the research status of model pruning algorithm and the main research direction are summarized and classified. The main research areas of model pruning include the granularity of pruning, the method to evaluate the importance of pruning elements, the sparsity of pruning, the theoretical foundation of model pruning, pruning for different tasks and so on. Then, the recent representative pruning algorithms are described in detail as well. Finally, the future research direction in this field is brought forward. Reference | Related Articles | Metrics | Comments（0）

Select

Review of Relation Extraction Based on Pre-training Language Model WANG Hao-chang, LIU Ru-yi Computer and Modernization    2023, 0 (01): 49-57.   Abstract （503）      PDF（pc） （1190KB）（149）       Knowledge map    Save In recent years, with the continuous innovation of deep learning technology， the application of pre-training models in natural language processing has become more and more extensive, and relation extraction is no longer purely dependent on the traditional pipeline method. The development of pre-training language models has greatly promoted the related research of relation extraction， and has surpassed traditional methods in many fields. First， this paper briefly introduces the development of relationship extraction and classic pre-training models；secondly, summarizes the current commonly used data sets and evaluation methods, and analyzes the performance of the model on each data set; finally， discusses the development challenges of relationship extraction and future research trends. Reference | Related Articles | Metrics | Comments（0）

Select

Modeling Method of 3D Printing Full Contact Insole Based on Triply Periodic Minimal Surface JIANG Chao-qun, TONG Jing, GUO Ming-deng, LU Rong-jie, CHEN Zheng-ming Computer and Modernization    2021, 0 (05): 13-19.   Abstract （491）      PDF（pc） （4484KB）（146）       Knowledge map    Save The full-contact insole can reduce the peak plantar pressure to improve and prevent neurotic ulcer symptoms in diabetic foot. The traditional full-contact insole design method is complex to operate. In this paper, a novel 3D printing modeling method for full-contact insole is proposed based on triply periodic minimal surface （TPMS）. Through three steps of data collection, full-contact model construction and model porousness, a full-contact insole based on TPMS structure is constructed and produced using 3D printing technology. First, the user foot model and the scan insole model are collected. Then the lower boundary of the pre-designed insole model is approximated to the scan insole model by Laplace transform algorithm, and the full-contact insole model is constructed by adjusting the upper surface of the pre-designed insole model to the bottom of foot. Finally, the Marching Cubes mesh reconstruction method is applied to reconstruct the full-contact insole into a TPMS structure based mesh model. The experiment verifies that the method proposed in this paper can design a full-contact insole with the ability to reduce the peak pressure of the sole. Reference | Related Articles | Metrics | Comments（0）

Select

Fast Paper Edge Detection Method Based on HED Network ZHAO Qi-wen, XU Kun, XU Yuan Computer and Modernization    2021, 0 (05): 1-5.   Abstract （484）      PDF（pc） （2564KB）（188）       Knowledge map    Save The Holistically-nested Edge Detection （HED） network is one of the deep learning network models with better edge detection performance at present. However, when the HED is used for edge detection of paper, the detection speed is slow and cannot meet the real-time requirements. On the premise of ensuring the detection accuracy, this paper proposes a fast paper edge detection method based on HED network. This article uses the lightweight network MobileNetV2 as the HED backbone network, and removes the last two bottleneck modules of the MobileNetV2 network and the convolutional layer with a large number of output channels to further accelerate the detection speed. In addition, the pooling layer in the network is removed, and a 5×5 convolutional layer with a step length of 1 is added to improve the detection accuracy. A paper data set MPDS containing a variety of situations is produced, the method proposed in this paper is trained and tested on MPDS. The experimental results show that the proposed model increases the ODS and OIS indicators to 0.867 and 0.876, respectively. The detection speed is 42.68 FPS. The method proposed in this paper can quickly and accurately detect the edge of the paper and meet the requirements of the desktop enhancement system for paper detection. Reference | Related Articles | Metrics | Comments（0）

Select

Vehicle Key Point Detection Based on CPN Network ZHANG Zhi-gang, YOU An-qing Computer and Modernization    2021, 0 (10): 75-80.   Abstract （478）      PDF（pc） （2037KB）（149）       Knowledge map    Save Aiming at the need to use vehicle key points to obtain vehicle 3D posture in smart transportation and self-driving systems, a vehicle key point detection model based on CPN network is proposed. The model integrates deep semantic information and shallow spatial resolution information in the form of a U-type structure with ResNet50 as the backbone network to build a Gaussian heat map pyramid. Then, SoftArgmax is used to decode the key point coordinates from the Gaussian heat map end to the end. The vehicle key point detection model is trained on a training set of 200000 sheets, which can predict the coordinates and visibility of 78 key points on defined cars and SUV models at the same time. The normalized pixel error of the prediction point under the input image of 256×256 is 1.57, and the visibility prediction of the point reaches the accuracy of 0.96 at the recall rate of 0.95. The experimental results show that the vehicle key point detection model based on the CPN network has high accuracy and has been applied to intelligent transportation systems in Beijing, Wuhan and other cities. Reference | Related Articles | Metrics | Comments（0）

Select

Multi-objective Optimization Algorithm for Flexible Job Shop Scheduling Problem XU Ming, ZHANG Jian-ming, CHEN Song-hang, CHEN Hao Computer and Modernization    2021, 0 (12): 1-6.   Abstract （473）      PDF（pc） （1427KB）（406）       Knowledge map    Save Flexible job shop scheduling problems have the characteristics of diversified solution sets and complex solution spaces. Traditional multi-objective optimization algorithms may fall into local optimality and lose the diversity of solutions when solving those problems. In the case of establishing a flexible job shop scheduling model with the maximum completion time, maximum energy consumption and total machine load as the optimization goals, an improved non-dominated sorting genetic algorithm (INSGA-II) was proposed to solve this problem. Firstly, the INSGA-II algorithm  combines random initialization and heuristic initialization methods to improve population diversity. Then it adopts a targeted crossover and mutation strategies for the process part and the machine part to improve the algorithm’s global searching capabilities. Finally,  adaptive crossover and mutation operators are designed to take into account the global convergence and local optimization capabilities of the algorithm. The experimental results on the mk01～mk07 standard data set show that the INSGA-II algorithm has better algorithm convergence and solution set diversity. Reference | Related Articles | Metrics | Comments（0）

Select

Flame Detection Algorithm Based on Improved YOLOV5 WANG Hong-yi, KONG Mei-mei, XU Rong-qing Computer and Modernization    2023, 0 (01): 103-107.   Abstract （467）      PDF（pc） （1474KB）（144）       Knowledge map    Save Aiming at the existing flame detection algorithms having problems of low average detection accuracy and high missed detection rate of small target flames， an improved YOLOV5 flame detection algorithm is proposed. The algorithm uses the Transformer Encode module to replace the CSP bottleneck module at the end of the YOLOV5 backbone network， which enhances the network's ability to capture different local information and improves the average accuracy of flame detection. In addition， the CBAM attention module is added to the YOLOV5 networker， which enhances the network's ability to extract image features， and can better extract features for small target flames， reducing the missed detection rate of small target flames. Experiment with the algorithm on the public datasets BoWFire and Bilkent， the experimental results show that the average flame detection accuracy of the improved YOLOV5 network is higher， reaching 83.9%， the small target flame missed detection rate is lower， only 1.6%， and the detection rate is 34 frames/s. Compared with the original YOLOV5 network， the average accuracy is improved 2.4 percentage points， the small target flame missed detection rate is reduced by 4.1 percentage points， the improved YOLOV5 network can meet the real-time and precision requirements of flame detection. Reference | Related Articles | Metrics | Comments（0）

Select

Character Network Analysis of Ordinary World WANG Jun, HE Jin-rong, MA Le-rong Computer and Modernization    2022, 0 (06): 32-36.   Abstract （458）      PDF（pc） （1405KB）（119）       Knowledge map    Save The construction and quantitative analysis of the relationship network of characters in literary works is an important content of intelligent interpretation of literary works. This article takes Mr. Lu Yao’s literary work "The Ordinary World" as the research object and uses complex network analysis methods to construct and analyze the social network in the literary works. Firstly, the social network relationship in the work is extracted, where the characters in the novel correspond to the nodes in the network, the relationships between the characters correspond to the edges of the network, and the number of times the characters appear together in each chapter corresponds to the weight of the edges. Then we analyze the betweenness and aggregation coefficient correlation， hierarchical clustering and predicting link on the constructed network. The experimental results show that the character relationship network of Ordinary World is a heterogenous network with small-world characteristics. This research is helpful to promote the analysis of character relationship network in literary works. Reference | Related Articles | Metrics | Comments（0）

Select

Helmet-wearing Detection Based on Improved YOLOv5 YUE Heng, HUANG Xiao-ming, LIN Ming-hui, GAO Ming, LI Yang, CHEN Ling Computer and Modernization    2022, 0 (06): 104-108.   Abstract （450）      PDF（pc） （2508KB）（152）       Knowledge map    Save To the problem that YOLOv5 cannot be focused by weights and cannot produce more distinguishable features, thereby reducing the accuracy of helmet detection, attention module was used. Besides, squeeze and excitation layer and efficient channel attention module were studied. To the problem that the non maximum suppression used by YOLOv5 to remove redundant results will only retain the highest confidence prediction frame of the same class when objects were highly overlapped, the Soft-NMS algorithm was used to keep more prediction boxes. Weighted non maximum suppression was used to fuse multiple prediction boxes information to improve the accuracy of the prediction boxes. For the problem of information loss caused by down-sampling , focus modules was used to improve the detection effect, and the various modules were integrated to obtain the optimal FESW-YOLO algorithm. Compared with YOLOv5, the algorithm improves the mAP@0.5 by 2.1 percentage points and the mAP@0.5:0.95 by1.2 percentage points on the helmet data set respectively, which improves the accuracy of safety helmet supervision. Reference | Related Articles | Metrics | Comments（0）

Select

Optimization of DS-TWR Ranging Algorithm in Indoor Positioning YUAN Feng, JIAO Liang-bao, CHEN Nan, GU Hui-dong Computer and Modernization    2021, 0 (10): 100-106.   Abstract （449）      PDF（pc） （2657KB）（153）       Knowledge map    Save In order to solve the problems of more communication conflicts and high label power consumption in the ranging process of UWB indoor positioning at present, an improved DS-TWR algorithm is proposed. This method calculates the time slots of the labels and base stations through a time slot allocation method based on Hash algorithm, so that each label and base station has a unique time slot, so as to reduce the label conflict phenomenon in the communication process. At the same time, different from the traditional TOA ranging process, this method sets up a master base station, the label only needs to communicate with the master base station, and the slave base station only needs to monitor. The DS-TWR algorithm is used to realize the ranging process between the label and the master-slave base station, and finally the indoor positioning is completed. The experimental results show that the improved scheme can effectively reduce the number of positioning communication. Assuming that there are N positioning base stations, the number of communication of the improved algorithm is about 4/3N of that of the traditional DS-TWR algorithm, and the more base stations, the more times to reduce, which has strong engineering application value. By reducing the number of communication, the label power consumption can be optimized and saved by 33.3%. Aiming at the problem of communication conflict in traditional ranging algorithm, after adding Hash algorithm, the communication conflict rate of base station label in the ranging process can be reduced by 13%, thus increasing the capacity of the system. Reference | Related Articles | Metrics | Comments（0）

Select

Group Activity Recognition Algorithm Based on Interaction Relationship Grouping Modeling Fusion WANG Chuan-xu, LIU Ran Computer and Modernization    2022, 0 (01): 1-9.   Abstract （448）      PDF（pc） （3063KB）（429）       Knowledge map    Save The modeling of interaction relationship between group members is the core technology of group activity recognition. High complexity and information redundancy in relational reasoning are tough problems in complex scenarios when modeling its group interactions. In order to solve these problems, we propose a model of grouping interactive relation. Firstly, CNN and RoIAlign are used to extract the scene information and personal information as initial features in each frame, and the whole group is divided into two subgroups by the personal spatial coordinates (For example, in the Volleyball data set, the X coordinates of participants’bounding boxes are used to rank, then, everyone set is set up an ordinal ID and 12 people are divided into two group from left to right). Secondly, the two local groups and the global scene groups are divided, the Graph Convolutional Network （GCN） is used to deduce their interaction relationship respectively, and the key persons in each group are determined. Then, we can regard global relationship features as the real value, and merge the characteristics of local relation of two groups as predicted value. In order to match the key figures of two groups with key figures from the whole group successfully, the cross-entropy loss function is built between the two and feedback to optimize the upper-level group GCN interaction relationship network. Next, with the information of key figures in the global interaction relationship as a guide, the key figures in the two subgroups are matched respectively. After successful matching, the matched key figures in the two subgroups are taken as the target nodes to establish a relationship graph between these two subgroups, and then it is deduced by GCN. Finally, the initial features are fused with intergroup and global interaction characteristics respectively to obtain two group behavior branches, and the final recognition result is obtained through decision fusion. The experiment shows that the accuracy is 93.1% on Volleyball data set and the accuracy is 48.1% on NBA data set. Reference | Related Articles | Metrics | Comments（0）

Select

Survey of Fruit Object Detection Algorithms in Computer Vision LI Wei-qiang, WANG Dong, NING Zheng-tong, LU Ming-liang, QIN Peng-fei Computer and Modernization    2022, 0 (06): 87-95.   Abstract （447）      PDF（pc） （1939KB）（164）       Knowledge map    Save Fruit target detection and recognition based on computer vision is an important cross-disciplinary research topic of target detection, computer vision, agricultural robots, etc. It has important theoretical research significance and practical application value in the fields of smart agriculture, agricultural modernization, and automatic picking robots. As deep learning is widely used in the field of image processing and has achieved good results, fruit target detection and recognition algorithms combining computer vision technology with deep learning methods gradually become the mainstream. This article introduces the tasks, difficulties and development status of fruit target detection and recognition based on computer vision, as well as two types of fruit target detection and recognition algorithms based on deep learning methods. Finally, the public data set used for the training and learning of the algorithm model and the evaluation index for evaluating the performance of the model are introduced, and the current problems in the detection and recognition of fruit targets and the possible future development directions are discussed. Reference | Related Articles | Metrics | Comments（0）

Select

Passenger-vehicle Matching and Route Optimization of Network Carpooling CHEN Ling-juan, KOU Si-jia, LIU Zu-peng Computer and Modernization    2021, 0 (07): 6-11.   Abstract （425）      PDF（pc） （1353KB）（135）       Knowledge map    Save Urban road congestion and the prevalence of shared concepts have brought the rise of carpooling. Passengers with similar travel routes share the same car, which can increase the vehicle’s seat resources, save costs and relieve traffic pressure. Taking the problem of multi-vehicle static carpooling without transfer with time window constraints as the research background, the objective function of passenger-vehicle matching and path optimization is established from three aspects: vehicle usage fee, travel cost on the way and penalty cost of arrival time window, constructing model constraint conditions based on vehicle capacity, passenger departure and arrival time windows, no detours, no overlap between passenger and vehicle matching, etc. The evolution strategy algorithm is used to solve the problem, and the coding and decoding rules are designed according to the model characteristics. The decoding results can obtain the matching relationship between the vehicle and the passengers and the traveling path at the same time, and the cross-mutation operation is used to update the iterative individual population to obtain the optimal solution. Using MATLAB to solve the calculation example to verify the feasibility of the model and the effectiveness of the algorithm, the results show that the algorithm can quickly respond to the static carpooling problem, and can provide the matching relationship between passengers and vehicles and the path of the vehicle in a short time, the carpooling scheme can save more costs than traveling alone. Reference | Related Articles | Metrics | Comments（0）

Select

3D Dynamic Visualization Design and Simulation of Wind Field on Web TIAN Mao-chun, ZOU Xian-yong, YANG Yue, FAN Guang-wei, LAI Hang Computer and Modernization    2022, 0 (04): 97-102.   Abstract （422）      PDF（pc） （3827KB）（96）       Knowledge map    Save In view of the difficulty in displaying the wind field quickly and visually on the Web, a Web-based 3D dynamic wind field visualization design and simulation method was proposed. Firstly, in order to solve the problem that wind field data is difficult to obtain and inconvenient to deal with, the process of wind field data acquisition, conversion, and application was given. Secondly, a method was designed to use Web Worker multi-threading technology to calculate and generate streamlines in parallel to reduce the generation time of wind field streamline tracing and improve the efficiency of streamline generation. Thirdly, combined with color mapping technology, a method to dynamically modify the streamline’s Alpha color channel to characterize the wind field movement was designed. Finally, the WebGL-based visualization engine Cesium was extended to perform the three-dimensional visualization rendering of the wind field, which can directly demonstrate the wind field. The results show that this method not only improves the efficiency of wind field visualization simulation on the Web, but also helps mitigating windstorm disaster. Reference | Related Articles | Metrics | Comments（0）

Select

Text Clustering Algorithm Based on RoBERTa-WWM and HDBSCAN LIU kun, ZENG Xi, QIU Zi-heng, CHEN Zhou-guo, Computer and Modernization    2022, 0 (03): 48-52.   Abstract （419）      PDF（pc） （1092KB）（72）       Knowledge map    Save In the big data environment, obtaining hot topics from massive Internet data is the basis for studying public opinion and sentiments in the current Internet. Among them, text clustering is one of the most common methods to get hot topics, which can be divided into two steps: text vectorization representation and clustering. However, in the task of vectorized text representation, the traditional text representation model cannot accurately represent the contextual information of texts such as news and posts. In the clustering task, the K-Means algorithm and DBSCAN algorithm are most commonly used, but their clustering method is not consistent with the actual distribution of topic data, which makes the existing text clustering algorithms very poorly applied in the actual Internet environment. Therefore, this paper proposes a text clustering algorithm based on RoBERTa-WWM and HDBSCAN according to the data distribution of topics in the Internet. Firstly, the pre-trained language model RoBERTa-WWM is used to obtain the text vector of each text. Secondly, the t-SNE algorithm is used to reduce the dimension of the high-dimensional text vector. Finally, the HDBSCAN algorithm based on hierarchical density clustering algorithm is used to cluster the low-dimensional text vector. The experimental results show that compared with the existing text clustering algorithms, the proposed algorithm has a great improvement in the clustering effect on data sets that contain noisy data and are unevenly distributed. Reference | Related Articles | Metrics | Comments（0）

Select

Enhanced Image Caption Based on Improved Transformer_decoder LIN Zhen-xian, QU Jia-xin, LUO Liang Computer and Modernization    2023, 0 (01): 7-12.   Abstract （419）      PDF（pc） （1421KB）（89）       Knowledge map    Save Transformer's decoder model（Transformer_decoder）has been widely used in image caption tasks. Self Attention captures fine-grained features to achieve deeper image understanding. This article makes two improvements to the Self Attention, including Vision-Boosted Attention（VBA）and Relative-Position Attention（RPA）. Vision-Boosted Attention adds a VBA layer to Transformer_decoder, and introduces visual features as auxiliary information into the attention model, which can be used to guide the decoder model to generate more matching description semantics with the image content. On the basis of Self Attention, Relative-Position Attention introduces trainable relative position parameters to add the relative position relationship between words to the input sequence. Based on COCO2014 experiments, the results show that the two attention mechanisms of VBA and RPA have improved image caption tasks to a certain extent， and the decoder model combining the two attention mechanisms has better semantic expression effects. Reference | Related Articles | Metrics | Comments（0）

Select

Recommendation Algorithm Based on Knowledge Graph and Bi-LSTM WANG Yu-ying, WANG Yong Computer and Modernization    2021, 0 (09): 90-98.   Abstract （416）      PDF（pc） （1255KB）（203）       Knowledge map    Save At present, most of the existing model-based recommendation algorithms input the score data into the deep learning model for training to get the recommendation results. Its defect is that it is unable to analyze the interpretability of the prediction results. In addition, the algorithm can not effectively solve the cold start problem. Therefore, this paper proposes a recommendation algorithm based on knowledge map and Bi-LSTM to effectively solve the problem of interpretability and cold start of the algorithm. Firstly, the data set is preprocessed to generate precoding vector. According to the connectivity of data aggregation points, the domain knowledge map is constructed. Secondly, the meta path extraction technology of knowledge map is used to obtain multiple user item path information, which is input into Bi-LSTM. A layer of attention mechanism is added to each node of the path, so that the model could effectively obtain the information of remote nodes. Finally, the training results of multiple paths are input into the average pooling layer to distinguish the importance of different paths. The cross-entropy loss function is used to train the model and the prediction results are obtained. The experimental results show that, compared with the traditional recommendation algorithm based on the cyclic neural network model, this algorithm can effectively improve the interpretability and prediction accuracy of the algorithm, and alleviate the cold start problem of the algorithm. Reference | Related Articles | Metrics | Comments（0）

Select

Research Review of Single-channel Speech Separation Technology Based on TasNet LU Wei, ZHU Ding-ju Computer and Modernization    2022, 0 (11): 119-126.   Abstract （414）      PDF（pc） （1016KB）（72）       Knowledge map    Save Speech separation is a fundamental task in acoustic signal processing with a wide range of applications. Thanks to the development of deep learning, the performance of single-channel speech separation systems has been significantly improved in recent years. In particular, with the introduction of a new speech separation method called time-domain audio separation network （TasNet）, speech separation technology is also gradually transitioning from the traditional method based on time-frequency domain to the one based on time domain methods. This paper reviews the research status and prospect of single-channel speech separation technology based on TasNet. After reviewing the traditional methods of speech separation based on time-frequency domain, this paper focuses on the TasNet-based Conv-TasNet model and DPRNN model, and compares the improvement research on each model. Finally, this paper expounds the limitations of the current single-channel speech separation model based on TasNet, and discusses future research directions from the aspects of model, dataset, number of speakers, and how to solve speech separation in complex scenarios. Reference | Related Articles | Metrics | Comments（0）

Select

Track Data Hot Spot Mining Algorithm Based on K-means XU Wen-jin, GUAN Ke-hang, MA Yue, HUANG Hai-guang Computer and Modernization    2021, 0 (10): 23-28.   Abstract （411）      PDF（pc） （1759KB）（217）       Knowledge map    Save In view of the characteristics of time series and large quantity of fishing boat trajectory data, this paper proposes a trajectory hot spot mining algorithm, which overcomes the disadvantage that K-means algorithm cannot capture hot spot distribution in fishing boat trajectory data. The main idea is as follows: firstly, time dimension is used to process the data, and based on confidence and KL divergence to measure the reliability and correctness of the selected data, data with high information content is selected from a large number of trajectory data, and then the K-means clustering algorithm is used to cluster the processed data. The algorithm proposed in this paper only needs to set the significant level parameter a and time interval T, the algorithm itself can independently complete the data selection and the calculation of the confidence, KL divergence by using the method of time dimension data processing, and the clustering validity measure method is introduced to realize the whole process of hot spot mining by self-searching K value of K-means. The comparison test between the proposed algorithm and K-means algorithm and the reference test of data heat map are carried out on the trajectory data of fishing boats. The results show that the proposed algorithm is superior and correct in finding hot spots of trajectory data. Reference | Related Articles | Metrics | Comments（0）

Select

Categorical Data Clustering Based on Extraction of Associations from Co-association Matrix GUAN Yun-peng, LIU Yu-long Computer and Modernization    2022, 0 (11): 1-8.   Abstract （405）      PDF（pc） （1703KB）（89）       Knowledge map    Save Categorical data clustering is widely used in different fields in the real world, such as medical science, computer science,  etc. The usual categorical data clustering is studied based on the dissimilarity measure. For data sets with different characteristics, the clustering results will be affected by the characteristics of the data set itself and noise information. In addition, the categorical data clustering based on representation learning is too complicated to implement, and the clustering results are greatly affected by the representation results. Based on the co-association matrix, this paper proposes a clustering method that can directly consider the relationship between the original information of categorical data, categorical data clustering based on extraction of associations from co-association matrix (CDCBCM). The co-association matrix can be regarded as a summary of the information association in the original data space. The co-association matrix is constructed by calculating the co-association frequency value of different objects in each attribute subspace, and some noise information is removed from the co-association matrix, and then the clustering result is obtained by normalized cut. The method is tested on 16 publicly available datasets in various aspects, compared with 8 existing methods, and detected using the F1-score metric. The experimental results show that this method has the best effect on 7 data sets, the average ranking is the best, and it can better complete the clustering task of categorical data. Reference | Related Articles | Metrics | Comments（0）

Select

Review of Radar Imaging Simulation ZHOU Xiu-zhi, CUI Yi-peng, SUN Zhong-yun Computer and Modernization    2021, 0 (08): 30-34.   Abstract （393）      PDF（pc） （3750KB）（143）       Knowledge map    Save Radar imaging for military flight simulator training plays an important role in simulation training because of its advantages of no limitation of time and space, controllability and strong security. In this paper, three main ground surrveying and mapping methods (RBM, DBS and SAR) for airborne fire control radar, domestic and foreign fighter radar models and their imaging systems are introduced. The research and development status of foreign radar imaging simulation software and domestic radar simulator are described. The advantages and disadvantages of existing products, their applicable scope and technologies are described in detail. The main methods and realization process of radar image simulation are summarized, which are divided into three categories: echo signal simulation, transfer function and fusion of radar image features. It is predicted that radar imaging simulation will develop in the direction of establishing general database, expanding imaging range, and improving real-time performance and fidelity. Reference | Related Articles | Metrics | Comments（0）

Select

Review of Research on Human Behavior Detection Methods Based on Deep Learning SHEN Jia-wei, LU Yi-ming, CHEN Xiao-yi, QIAN Mei-ling, LU Wei-zhong, Computer and Modernization    2023, 0 (09): 1-9.   DOI: 10.3969/j.issn.1006-2475.2023.09.001 Abstract （388）      PDF（pc） （2112KB）（88）       Knowledge map    Save Human behavior recognition has always been a hot topic of research in the field of computer vision and video understanding and is widely used in other areas such as intelligent video surveillance and human-computer interaction in smart homes. While traditional human behavior detection algorithms have the disadvantages of relying on too many data samples and being susceptible to environmental noise， evolving deep learning techniques are gradually showing their advantages and can be a good solution to these problems. Based on this， this paper firstly introduces some commonly used behavioral recognition datasets and analyses the current research status of human behavioral recognition based on deep learning， then describes the basic process of behavioral recognition and commonly used behavioral recognition methods， finally summarizes the performance， existing problems of various existing behavioral recognition methods， and outlooks the future development directions. Reference | Related Articles | Metrics | Comments（0）

Select

Application of Edge Computing in Intelligent Transportation Systems WU Jian-bo, ZHU Wen-xia, JU Liang, XU Zhi-fang Computer and Modernization    2021, 0 (12): 103-109.   Abstract （383）      PDF（pc） （1839KB）（217）       Knowledge map    Save With the popularization of automobiles, traffic congestion is becoming increasingly serious. Although the cloud-based intelligent transportation systems (ITS) can relieve traffic pressure, it can no longer meet the demand of transmission bandwidth and delay requirements of new on-board applications such as assisted driving and autonomous driving. In order to realize the data real-time processing, ensure public information and traffic safety, and improve the transportation system efficiency, edge computing (EC) is applied to ITS. The development of ITS is described and the overall architecture of edge-based ITS is proposed, which makes full use of the characteristics of edge computing such as physical proximity, high bandwidth, low latency and location recognition to solve the problems of information transmission delay, data processing delay and large transmission load. Next, the key technologies of edge computing in ITS are discussed from the aspects of wireless transmission, information perception, computing offloading and collaborative processing. Finally, the future opportunities and challenges for the application of EC in ITS are pointed out. Reference | Related Articles | Metrics | Comments（0）

Select

Multi-UAV Hunting Based on Improved Whale Optimization Algorithm LING Wen-tong, NI Jian-jun, CHEN Yan, TANG Guang-yi Computer and Modernization    2021, 0 (06): 1-5.   Abstract （377）      PDF（pc） （1931KB）（420）       Knowledge map    Save UAV hunting is a challenging and realistic task. In order to enable UAVs to hun moving targets successfully and effectively, a multi-UAV hunting algorithm based on dynamic prediction of hunting points and improved whale optimization algorithm is proposed. When the environment is unknown and the target motion trajectory is unknown, this paper first uses polynomial fitting to predict the target motion trajectory, obtains the prediction point by dynamically predicting the number of steps, sets up hunting points around it, and then uses the two-way negotiation method to make reasonable assign each target point. Aiming at the shortcomings of the whale optimization algorithm that it is easy to fall into the local optimum, a method based on adaptive weights and changing the position of the spiral is proposed to improve the development ability and search ability of the algorithm. Finally, several experimental simulations were carried out in different experimental environments, and the experimental results showed the effectiveness of the proposed algorithm. Reference | Related Articles | Metrics | Comments（0）

Select

High Illumination Visible Image Generation Based on Generative Adversarial Networks ZHUANG Wen-hua, TANG Xiao-gang, ZHANG Bin-quan, YUAN Guang-ming Computer and Modernization    2023, 0 (01): 1-6.   Abstract （376）      PDF（pc） （7034KB）（96）       Knowledge map    Save To solve the problem of low accuracy of target detection under low illumination conditions at night， this paper proposes a generative adversarial network-based algorithm for high illumination visible light image generation. To improve the ability of the generator to extract features， a CBAM attention module is introduced in the converter module； To avoid the noise interference of artifacts in the generated images， the decoder of the generator is changed from the deconvolution method to the up-sampling method of nearest neighbour interpolation plus convolution layer； to improve the stability of the network training， the adversarial loss function is replaced from the cross-entropy function to the least-squares function. The generated visible images have the advantages of spectral information， rich detail information and good visibility enhancement compared with infrared images and night visible images， which can effectively obtain information about the target and scene. We verified the effectiveness of the method by image generation metrics and target detection metrics respectively， in which the mAP obtained from the test on the generated visible image improved by 11.7 percentage points and 30.2 percentage points respectively compared to the infrared image and the real visible image， which can effectively improve the detection accuracy and anti-interference capability of nighttime targets. Reference | Related Articles | Metrics | Comments（0）