Loading...
Office Online
Instruction More>>
Highlights More>>
Links More>>
Visited
    Total visitors:
    Visitors of today:
    Now online:

Table of Content

    30 August 2023, Volume 0 Issue 08
    Previous Issue    Next Issue
    Hippocampus Segmentation Based on Feature Fusion
    CHEN Jia-min, ZHANG Bo-quan, MAI Hai-peng
    2023, 0(08):  1-6.  doi:10.3969/j.issn.1006-2475.2023.08.001
    Asbtract ( 154 )   PDF (1332KB) ( 48 )  
    Related Articles | Metrics
    Abstract: Aiming at the problem that the existing hippocampal segmentation algorithm can not segment the target accurately， a novel hippocampal segmentation model based on feature fusion using codec structure is studied. Firstly， Resnet34 is used as the model feature encoding layer to extract richer semantic features; Secondly， the ASPP module based on mixed expansion convolution is introduced into the coding and decoding transition layer to obtain multi-scale feature information. Finally， the attention feature fusion mechanism is used as the connection layer between the encoding and decoding layers to effectively combine the deep features with the shallow features， provide the location information of the hippocampus for subsequent segmentation， and improve the segmentation performance of the model. The experiment is carried out on ADNI dataset to verify the validity of the proposed model. The accuracy of the network model in the four evaluation indicators of IoU， DICE， accuracy and recall rate reaches 84.67%， 88.51%， 87.90% and 89.01% respectively. Compared with the existing advanced medical segmentation algorithm， the experimental results also show that the model has better segmentation ability and achieves better automatic segmentation effect of hippocampus image.
    Multi Path Planning Based on Constrained Clustering and Particle Swarm Optimization
    HAN Xue
    2023, 0(08):  7-11.  doi:10.3969/j.issn.1006-2475.2023.08.002
    Asbtract ( 108 )   PDF (1639KB) ( 47 )  
    Related Articles | Metrics
    Abstract: In Large-scale logistics center ， if logistics management information system can be used normally， it is necessary to study the problem of vehicle routing in multi-distribution centers.We want to use as few vehicles as possible to complete the delivery of goods and minimize the total mileage.K-shortest paths in multi-center path planning has conducted in-depth research， the multi-path planning problem has been realized by using the traditional clustering algorithm.However， in the real multi-distribution-center vehicle routing planning， there are specific restrictions on the transportation capacity of transportation vehicles and the needs of users. We introduce constraint mechanism on the clustering algorithm to reduce the dimension of multi distribution center problem to single distribution center problem by clustering algorithm， and particle swarm optimization is introduced to solve the optimal solution of multi-path planning for single distribution center.The experiment proves the superiority of this method：the practice proves that the convergence speed of this method is at least n （number of distribution centers) times faster than that of the traditional particle swarm optimization algorithm， which provides a new solution for path planning.
    Surface Anomaly Detection Algorithm of Flexible Plastic Packaging Based on Improved ConvNeXt
    NONG Hao-cheng, REN De-jun, REN Qiu-lin, LIU Peng-li, HUANG De-cheng
    2023, 0(08):  12-17.  doi:10.3969/j.issn.1006-2475.2023.08.003
    Asbtract ( 88 )   PDF (1995KB) ( 50 )  
    Related Articles | Metrics
    Abstract： As for the artificial detection of flexible plastic packaging is slow and easily influenced by subjective factors which bring the problems such as error checking，as well as machine vision based on the deep learning only got a few of negative sample  which is difficult to obtain， the article proposed a ConvNeXt based asymmetirc dual network method to detect the outer surface of the tissue which is taken as the research object. Firstly， the method of machine vision based on threshold segmentation and image filtering is used to preprocess the image foreground extraction and correction， according to the situation of the industrial field images collected. Then， the anomaly detection network structure is constructed according to the characteristics of images. Finally， the preprocessed images were constructed as data sets to train and test the surface quality detection network of tissue. As a result， the experiment shows that the image-level AUROC is 99.75%， the pixel-level AUROC is 99.37%， and the detection time is 45 ms. The result meets the requirements of industrial real-time detection.
    An Environmental Target Recognition Method for Airport Special Vehicle Operation
    LIU Xu, ZHA Ke-ke
    2023, 0(08):  18-24.  doi:10.3969/j.issn.1006-2475.2023.08.004
    Asbtract ( 79 )   PDF (2221KB) ( 49 )  
    Related Articles | Metrics
    Abstract: The autonomous and safe operation of airport special vehicles is essential to ensure the safety of the airfield area. At present， most airport special vehicle operations are mainly completed by driver’s operation and the visual command of controllers， in which such challenges as over-reliance on manpower and low autonomy. To improve its safety and autonomy， this paper presents a target recognition method for the airport environment based on the 3D point cloud segmentation. Firstly， a simulation-based approach is used to construct a point cloud dataset （Airfield Area of Airport Point Cloud Data，3A-PCD） of the airfield area environment. Secondly， based on PointNet++， a semantic segmentation network 3A-Net for large-scale point cloud data is designed， and a combined sampling point spatial encoding module and attentive pooling module are proposed to address the problem of traditional segmentation networks in terms of low segmentation accuracy and lack of ability to retain detailed features of objects. Finally， experiments were designed based on the 3A-PCD dataset， the ablation experiment result shows that the MIoU of the model increases by 6.0 percentage points with the addition of the spatial encoding module and by 3.9 percentage points with the addition of the AP module. 3A-Net achieves a 6.7 percentage points improvement in MIoU compared to the benchmark model PointNet++. In comparison with 6 existing advanced semantic segmentation models， the performance of the proposed model has been improved to varying degrees and is more suitable for target recognition in large outdoor scenes.
    Key words：target recognition； airport special vehicle； semantic segmentation； attention mechanism； 3D scene simulation
    SOC Estimation of Lithium Battery Based on Improved LSTM
    PAN Si-yuan, ZHANG Wei
    2023, 0(08):  25-30.  doi:10.3969/j.issn.1006-2475.2023.08.005
    Asbtract ( 89 )   PDF (3576KB) ( 45 )  
    Related Articles | Metrics
    Absrtact: Aiming at the low accuracy of the state of charge（SOC） estimation of lithium batteries， a neural network model based on improved LSTM algorithm is proposed to obtain the mapping relationship between voltage and current input and SOC output. By extending the Kalman filter to filter the noise of the output estimate， the stability of the model is enhanced. In the process of neural network modeling， the improved particle swarm optimization algorithm is used to optimize the number of neurons， learning rate， step size and other super parameters， which further improves the efficiency and accuracy of lithium battery SOC estimation. Finally， the DST condition data in the university of Maryland CALCE dataset is used for model training， and the FUDS and US06 condition data-sets are used for comparative experiments on the improved LSTM algorithm， CNN-LSTM、GRU algorithm and CatBoost algorithm. The experimental results show that the improved LSTM estimation model has high stability and accuracy， which verifies the feasibility of the improved scheme.
    Research on Stock Classification and Forecast Based on DTW-TCN
    SUN Zi-yu, REN Ran, WEI Xi-zhe
    2023, 0(08):  31-37.  doi:10.3969/j.issn.1006-2475.2023.08.006
    Asbtract ( 157 )   PDF (8512KB) ( 51 )  
    Related Articles | Metrics
    Abstract: With the development of society and information technology， financial instruments and stock transactions have taken on a new form， namely， the number of financial data increases. Therefore， stock trend prediction is particularly important in high-frequency trading. Stock trend prediction in high-frequency trading is particularly important to improve the accuracy of stock trend prediction in high-frequency trading. A temporal convolutional network （TCN） model based on dynamic time warping （DTW） clustering analysis is proposed. In the model， the opening price， the highest price， the lowest price， the closing price， the trading volume， and the trading volume are used as the stock characteristic variables. In order to avoid the influence of magnitude， the feature vector is standardized first， and then the stock is classified by using the dynamic time warping to measure the similarity of time series， Then， temporal convolutional network （TCN） extracts the common characteristics of the categories to predict the opening and closing price trends of the stocks of the categories， and compares them with the actual trends. The experiment is conducted with the minute-level data of 19 industry universal stocks. Compared with traditional time series model and LSTM network model， it has greater time characteristics. The results show that the model can effectively classify the stocks with the same trend into the same category， and achieve accurate trend prediction in the minute-level high-frequency trading.
    Lithofacies Identification Method Based on LSTM Stacked Residual Network
    ZENG Li-li, TANG Hua-bei, NIU Yi-xiao, MENG Fan-yue
    2023, 0(08):  38-43.  doi:10.3969/j.issn.1006-2475.2023.08.007
    Asbtract ( 53 )   PDF (1874KB) ( 26 )  
    Related Articles | Metrics
    Abstract: In order to improve the accuracy of lithofacies identification， this paper developed a heterogeneous reservoir lithofacies intelligent identification model based on residual connection long short-term memory network （LSTM_res）. Firstly， a sequence feature module is constructed based on long short-term memory neural network to obtain key logging features. The multi-layer stacking of this module further enhances the model’s ability to extract key feature information. Secondly， the residual connection technology is introduced on the basis of the sequence feature module to realize the extraction and fusion of the feature information between different layers of the network， which can effectively solve the degradation problem of the deep neural network. Finally， taking the logging data in the shallow sea area of the North Sea near Norway as the research object， six logging parameters （RMED， RHOB， GR， NPHI， PEF and SP） are selected through sensitivity analysis of logging parameters to realize intelligent identification of reservoir lithofacies. Compared with LSTM， CNN_res and CNN models under the same conditions， the experimental results show that the lithofacies identification accuracy of LSTM_res model is improved by 2， 4 and 6 porcentage points， respectively. It provides fast and effective data support for reservoir modeling and geological research.
    Cross Modal Hash Retrieval Based on Attention Mechanism and Semantic Similarity
    WANG Hong, GE Hong
    2023, 0(08):  44-53.  doi:10.3969/j.issn.1006-2475.2023.08.008
    Asbtract ( 118 )   PDF (2748KB) ( 58 )  
    Related Articles | Metrics
    Abstract： Nowadays， cross-modal hash retrieval has been widely and successfully used in multimedia similarity search applications. There are two challenged questions in deep hash retrieval methods：1）How to measure multiple modal’s similarity more accurately. 2）How to fuse multiple modal’s features to gain more abundant feature representations， so as to avoid key information loss. Therefore， in order to solve these two problems， we propose a novel cross-modal hashing method， called cross-modal hash retrieval model based on attention mechanism and semantic similarity （ASSH）， by defining a new multi-label similarity measurement method to distinguish the importance of different labels， designing an attention fusion module to fuse the features and enhance the interaction between different modal. Experimental results demonstrate that the proposed method outperforms the previous methods in all problem modes on the three common datasets MIRFLICKR-25K， NUS-WIDE and IAPR TC-12. Compared to the state-of-the-art method， when the hash code length is 16 bit， the mean Average Precision （mAP） is improved by 1.1% and 0.63%. At the same time， the ablation experiment also fully proved the effectiveness of the method.
    Short-Term Natural Gas Load Forecasting Based on SARIMA Model
    SHAO Bi-lin, CHENG Wan-rong
    2023, 0(08):  54-59.  doi:10.3969/j.issn.1006-2475.2023.08.009
    Asbtract ( 83 )   PDF (2381KB) ( 26 )  
    Related Articles | Metrics
    Abstract： Natural gas load forecasting plays a decisive role in residential life， commercial development and industrial production. And accurate short-term load forecasting can effectively quantify the uncertainty of natural gas load forecasting， which is critical for energy system operation and scheduling risk avoidance. The natural gas load affected by the seasonal effects will appear giant peak characteristics， the traditional point prediction model does not take into account the seasonal effects of natural gas， the accuracy of the prediction results is low. The SARIMA model can handle time series data with seasonal fluctuation trends and stochastic disturbances. Therefore， the SARIMA model is used to de-periodize the natural gas load as well as the first-order difference， capture the linear and seasonal features in the time series， determine the optimal parameter model based on the red pool information criterion and grid search， and proportionally divide the short-term interval forecast values. Taking the natural gas usage in Xi’an as an example， the results show that the SARIMA model used has a small error in the strong seasonal interval of the series and has a high accuracy when compared with the traditional model.
    Pedestrian Detection Algorithm for Ship-borne Vehicles Based on YOLOX Combined#br# with DeepSort
    LIU Yu-shan, LIU Wei-kang, LIU Qing-hua, ZHE Tian-tian, WANG Jia-cheng
    2023, 0(08):  60-67.  doi:10.3969/j.issn.1006-2475.2023.08.010
    Asbtract ( 78 )   PDF (1515KB) ( 45 )  
    Related Articles | Metrics
    Abstract：Aiming at the lack of real-time capture， detection and tracking of boarding vehicles and pedestrians in the current domestic ferry vehicle pedestrian control， this paper proposes a ship-borne vehicle and pedestrian detection method based on improved YOLOX. Firstly， the enhanced channel attention module is added to the three output heads of the enhanced feature extraction network of the original model to improve the feature extraction capability of the network for vehicles and pedestrians. Secondly， we use the improved ASPP module to replace the original SPP module. Among them， the improved ASPP module prunes the original module， and uses the addition of atrous convolution layers with different atrous convolution rates to solve the problem of local information loss of the original ASPP module. After the model is trained and verified with the validation set， it is combined with DeepSort for tracking detection. Compared with the original YOLOX algorithm， the average accuracy index （mAP） of the improved algorithm in this paper is increased by 3.3%， the accuracy rate is increased by 4.4%， and the test running speed on the GPU reaches 55 FPS. The experimental results show that the improved algorithm in this paper is suitable for real-time detection of vehicles and pedestrians in the ferry entrance environment.
    Garbage Classification and Detection Method Based on Improved YOLOX
    OUYANG Fei, WU Xu, XIANG Dong-sheng
    2023, 0(08):  68-73.  doi:10.3969/j.issn.1006-2475.2023.08.011
    Asbtract ( 84 )   PDF (2467KB) ( 58 )  
    Related Articles | Metrics
    Abstract: Garbage classification and recycling can improve environmental pollution， protect residents’ living environment and ensure sustainable ecological development. However， traditional artificial garbage classification methods are inefficient and subjective. This paper proposes a garbage classification and detection method based on improved YOLOX to improve the efficiency and accuracy of garbage classification. By training YOLOX network on self-made garbage classification dataset， garbage detection and classification have been realized. In order to achieve better detection effect， ECA attention mechanism is introduced into the network to improve the information transmission ability between features. Improving the up sampling and down sampling times of the feature extraction network to improve the feature extraction ability of small targets. The classification and regression loss functions are improved to improve the learning ability of the network. The experimental results show that the mAP@0.75 of the improved YOLOX algorithm is 89.9%， which is 4 percentage points higher than that of the original algorithm， and the number of detected frames per second only decreases by 0.3. The detection accuracy is significantly improved without loss of performance.
    Low-light Image Enhancement Based on Adaptive Local Gamma Correction
    ZHANG Mei-di, YU Shun-yuan
    2023, 0(08):  74-78.  doi:10.3969/j.issn.1006-2475.2023.08.012
    Asbtract ( 70 )   PDF (4708KB) ( 31 )  
    Related Articles | Metrics
    Abstract: For images with uneven illumination， an adaptive local Gamma correction method for low-illumination image enhancement is designed. The algorithm uses the modified probability density function of the local area as the calculation basis of the Gamma correction coefficient， and adjusts the Gamma coefficient adaptively according to the content of the local scene of the image. Meanwhile， by correcting the hue and color saturation， the color deviation problem in the process of low illumination image enhancement can be improved. The idea of the whole algorithm is simple， and it can adapt to the image enhancement of different scenes without manually adjusting the parameters. The experimental results show that the method in this paper can improve the brightness and local contrast of low-illumination color images， and at the same time obtain higher contrast， it can effectively highlight the details of dark areas， without the phenomenon of overexposure and underexposure， and the enhanced image can  present better color richness and naturalness.
    Review of Infrared Small Target Detection
    HU Rui-jie, CHE Dou
    2023, 0(08):  79-86.  doi:10.3969/j.issn.1006-2475.2023.08.013
    Asbtract ( 229 )   PDF (5630KB) ( 95 )  
    Related Articles | Metrics
    bstract： This article aims to review three infrared small target detection methods based on traditional feature extraction， local comparison， and widely used deep learning today. Then， by comparing the cutting-edge applications of these three methods， their advantages and disadvantages in target detection performance， robustness， and real-time performance are analyzed. We find that feature extraction based methods exhibit good real-time and robustness in simple scenarios， but may have limitations under complex conditions. The method based on local comparison is relatively robust to changes in object size and shape， but sensitive to background interference. The method based on deep learning performs well in object detection performance， but requires large-scale data and larger computing resources. Therefore， in practical applications， the advantages and disadvantages of these methods should be comprehensively considered based on specific scenario requirements， and appropriate methods should be applied to infrared small target detection.
    Research Status and Prospect of Edge Computing in Smart Distribution Network
    HE Yu-peng, TAO Yong, WANG Bing-heng, ZHAO Ying-nan
    2023, 0(08):  87-92.  doi:10.3969/j.issn.1006-2475.2023.08.014
    Asbtract ( 85 )   PDF (1132KB) ( 48 )  
    Related Articles | Metrics
    Abstract： With the rapid development of artificial intelligence technology and the Internet of Things， the distribution network is gradually becoming intelligent. However， massive data faces cloud computing face problems such as longer delay， network congestion， and privacy leakage. As a new computing paradigm， edge computing can handle network edge nodes and effectively solve the above problems， and is increasingly used in smart distribution networks. This paper reviews the edge computing technology of smart distribution networks in recent years. Firstly， it summarizes the characteristics of smart distribution network and the definition and architecture of edge computing in this application scenario. Secondly， it summarizes typical applications from different dimensions， including fault diagnosis and detection， data analysis， optimal scheduling， and data security and protection.. The research challenges in grid scenarios are summarized and prospected in three aspects， refinement management of data， modular sharing of resources and edge security maintenance.
    Mobile Edge Computing Task Offloading Based on Feasible Point Tracking Continuous#br# Convex Approximation
    CHEN Gang, WANG Zhi-jian, XU Sheng-chao
    2023, 0(08):  93-97.  doi:10.3969/j.issn.1006-2475.2023.08.015
    Asbtract ( 40 )   PDF (1979KB) ( 39 )  
    Related Articles | Metrics
    Abstract: The task unloading of mobile edge computing will be interfered by adjacent servers， which makes it difficult to accurately unload computing tasks to network edge servers. Therefore， a task unloading method of mobile edge computing based on feasible point tracking continuous approximation method is designed. This method firstly establishes the dependency model of mobile edge computing tasks， and analyzes the unloading requirements of mobile edge computing tasks. Secondly， considering the task unloading delay and energy consumption， the task unloading model is established based on the task dependency model. Finally， the feasible point tracking continuous convex approximation method is used to transform the problem of solving the unloading model into a linear relaxation problem. Iterative filter functions are introduced to track the feasible points to avoid interference from adjacent servers. The relaxation variables are continuously convex approximated to obtain the optimal solution of the task unloading model， so as to realize the unloading of mobile edge computing tasks. The experimental results show that the proposed method has low load， low energy consumption and high unloading accuracy.
    Tuple Space Coordination Model for Multi-robot Systems
    SHEN Shi-fan, WANG Li-song, WANG Xin-meng, QIN Xiao-lin
    2023, 0(08):  98-106.  doi:10.3969/j.issn.1006-2475.2023.08.016
    Asbtract ( 32 )   PDF (2373KB) ( 24 )  
    Related Articles | Metrics
    Abstract： In the field of multi-robot coordination， although the traditional coordination model solves the problems of information interaction， sharing and communication between collaborative entities， the decision-making mechanism required by the complex and changeable collaborative environment is not supported at the model level and can only be implemented through applications， which leads to difficulties in the development of collaborative systems and affects the execution efficiency of the collaborative decision-making process. To solve the problem that traditional coordination models cannot flexibly support user decisions， this paper proposes an event based tuple space coordination model DEBC （Decision and Event Based Coordination） with decision-making capabilities. The DEBC model introduces a decision mechanism into the tuple space framework， and partially abstracts the collaborative tasks of the application layer. By giving the tuple space a set of operations to support decision-making， the development of collaborative applications has a high degree of flexibility and adaptability. At the same time， the event mechanism is introduced to ensure the flexibility and efficiency of the collaborative behavior between collaborative entities. Finally， an example of DEBC model is analyzed and compared with the existing models through experiments. It is verified that DEBC model has good expression ability and higher execution efficiency， and the decision mechanism and event mechanism it provided are widely applicable.
    Security Protection Method of Cloud Network Special Line Scenarios Based on SRv6#br# Service Chain
    YANG Bo, XU Sheng-chao
    2023, 0(08):  107-111.  doi:10.3969/j.issn.1006-2475.2023.08.017
    Asbtract ( 33 )   PDF (2080KB) ( 34 )  
    Related Articles | Metrics
    Abstract: Under the background of cloud network convergence， the security and reliability of dedicated line scenarios are threatened. Therefore， this paper proposes a security protection method for dedicated line scenarios in cloud network based on SRv6 service chain technology. Starting from data， voice and the Internet， we should clarify the business characteristics of the cloud network dedicated line scenario， introduce SRv6 service chain technology into the cloud network structure， achieve node level by level jump， and improve the efficiency of network resource conversion； Analyze the security requirements of cloud network dedicated line scenarios， divide the security protection of cloud network dedicated line scenarios into two stages: uploading data and downloading files， calculate network traffic limit functions and constraints， create data sharing keys under the premise of shared connection protection mechanism， uniformly process data sharing seeds， and complete the security protection goals of cloud network dedicated line scenarios. The experimental results show that the proposed method can sensitively perceive abnormal attack behavior， and has fast security protection speed and strong robustness.
    A Feature Modeling Based Bidding Trading Mechanism in Power Blockchain
    LYU Zhi-xing, YU Hui, KANG Kai, LI Teng-chang, DU Guo-li
    2023, 0(08):  112-118.  doi:10.3969/j.issn.1006-2475.2023.08.018
    Asbtract ( 51 )   PDF (3124KB) ( 30 )  
    Related Articles | Metrics
    Abstract: With the gradual improvement of the requirement of power service and marketization of the power industry， how to reasonably trade and effectively utilize power has become a key requirement for China. Due to the centralized trade mode in the traditional power system， there are many problems， such as long-term processing， high trading cost， lack of supervision， potential attack risk， which means that the adaptive trading business processing rules and workflow are required. As an innovative information technology， blockchain has combined the advantages of decentralization， immutability， data provenance and contract operation automatically， which can be used to solve the abovementioned issues. Taking the individual credibility and liveness into account， a feature modeling based bidding trading mechanism in power blockchain is proposed. This approach fully mobilizes the enthusiasm and initiative of nodes， which can save amount of intermediary cost and reduce behaviors of breaching promises. In addition， the secure and effective trading service of power is provided. The corresponding trade is deployed under the smart contract with distributed mode. The experimental results using Hyperledger demonstrate that the proposed mechanism is feasible and effective， which can be applied to large scale power trading business scenarios.
    Security Handover Architecture and Method for Software Defined Space-ground#br# Integration Network
    LEI Yi-han, CAO Li-feng, HAN Meng-da, HAN Xue
    2023, 0(08):  119-126.  doi:10.3969/j.issn.1006-2475.2023.08.019
    Asbtract ( 30 )   PDF (2663KB) ( 26 )  
    Related Articles | Metrics
    Abstract： The space-ground integrated network has the characteristics of large scale， complex structure， node exposure and dynamic topology. To ensure the security and efficiency of network handover of user nodes in the whole system， this paper proposed a new space-earth integrated network security handover architecture based on the idea of separation of control plane and forwarding plane in software-defined network. The function of each functional module of the application layer， control layer and device layer of the architecture is expounded in detail， to achieve the goal of safe handover， manageable and controllable， accurate and efficient， flexible and definable. According to the characteristics of the architecture， considering the handover reservation time and the related attribute values that affect the handover， a multi-attribute weight adaptive handover decision algorithm based on the received signal strength prediction is proposed. The experimental simulation results show that the handover decision is accurate and can meet the needs of the security handover of the space-ground integrated network.