Pub Date : 2021-12-10DOI: 10.1109/ICCSS53909.2021.9722029
Min Deng, Chuandong Li
Spiking neural networks (SNNs), regarded as the third generation artificial neural networks (ANNs), can well explain the behavior of biological neurons. Recently, the research on the application of spiking neural networks has attracted much attention, especially in the image recognition field. To solve the problem of ANNs' lack of biological rationality, this paper combines Spike Timing Dependent Plasticity (STDP) with competitive learning to realize the MNIST dataset classification. A simple two-layer network structure, which includes an input layer and a processing layer is adopted. With the MNIST dataset as input, spike trains are generated based on frequency coding. A competitive learning mechanism is adopted in the processing layer to train the network, while during the learning and training process, we adopted the STDP power-law learning rule to update weights to achieve unsupervised learning image classification, and the classification accuracy reaches 83.179%. The results show that the network proposed in this paper achieves good performance, fast training speed and more biological rationality.
{"title":"STDP and Competition Learning in Spiking Neural Networks and its application to Image Classification","authors":"Min Deng, Chuandong Li","doi":"10.1109/ICCSS53909.2021.9722029","DOIUrl":"https://doi.org/10.1109/ICCSS53909.2021.9722029","url":null,"abstract":"Spiking neural networks (SNNs), regarded as the third generation artificial neural networks (ANNs), can well explain the behavior of biological neurons. Recently, the research on the application of spiking neural networks has attracted much attention, especially in the image recognition field. To solve the problem of ANNs' lack of biological rationality, this paper combines Spike Timing Dependent Plasticity (STDP) with competitive learning to realize the MNIST dataset classification. A simple two-layer network structure, which includes an input layer and a processing layer is adopted. With the MNIST dataset as input, spike trains are generated based on frequency coding. A competitive learning mechanism is adopted in the processing layer to train the network, while during the learning and training process, we adopted the STDP power-law learning rule to update weights to achieve unsupervised learning image classification, and the classification accuracy reaches 83.179%. The results show that the network proposed in this paper achieves good performance, fast training speed and more biological rationality.","PeriodicalId":435816,"journal":{"name":"2021 8th International Conference on Information, Cybernetics, and Computational Social Systems (ICCSS)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132014040","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-12-10DOI: 10.1109/ICCSS53909.2021.9722024
Xiaohong Zheng, Xiao‐Meng Li, Wenbin Xiao, Qi Zhou, Renquan Lu
This article discusses a fixed-time consensus tracking control problem for multi-agent systems (MASs) suffering from input delays. First, the Pade approximation technique is employed to deal with input delays. Second, unknown nonlinearities in MASs are reconstructed by command filtering technique and neural network (NN). Convex optimization technique is used to design NN weight update law. To guarantee the transient performance of MASs, fixed-time control is utilized, while the resulting singularity problem is solved by curve fitting method. Under the fixed-time stability criterion and Lyapunov stability theorem, it is shown that all signals of the closed-loop system are bounded in fixed time. Finally, the validity of the presented algorithm is checked by simulation.
{"title":"NN-based Fixed-Time Tracking Control for Multi-Agent Systems With Input Delays","authors":"Xiaohong Zheng, Xiao‐Meng Li, Wenbin Xiao, Qi Zhou, Renquan Lu","doi":"10.1109/ICCSS53909.2021.9722024","DOIUrl":"https://doi.org/10.1109/ICCSS53909.2021.9722024","url":null,"abstract":"This article discusses a fixed-time consensus tracking control problem for multi-agent systems (MASs) suffering from input delays. First, the Pade approximation technique is employed to deal with input delays. Second, unknown nonlinearities in MASs are reconstructed by command filtering technique and neural network (NN). Convex optimization technique is used to design NN weight update law. To guarantee the transient performance of MASs, fixed-time control is utilized, while the resulting singularity problem is solved by curve fitting method. Under the fixed-time stability criterion and Lyapunov stability theorem, it is shown that all signals of the closed-loop system are bounded in fixed time. Finally, the validity of the presented algorithm is checked by simulation.","PeriodicalId":435816,"journal":{"name":"2021 8th International Conference on Information, Cybernetics, and Computational Social Systems (ICCSS)","volume":"121 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124173696","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-12-10DOI: 10.1109/ICCSS53909.2021.9722028
Di Ning, Junhao Hu
The paper mainly copes with bounded synchronization of multiplex networks with time-varying delay via asynchronous impulsive control, where the system structure is the same but the system parameters are mismatched within each layer. Firstly, a novel multiplex network in which the interlayer interactions cross different layers only exist at discrete impulsive instants is put forward. Secondly, in view of different impulse sequences within each layer, based on the average impulse interval and extended comparison principle for impulsive systems, some sufficient criteria for reaching bounded synchronization of heterogenous multiplex networks are addressed. Finally, numerical simulation explicates the validity of some main theoretical results.
{"title":"Asynchronous Impulsive Bounded Synchronization of Multiplex Networks with Parameter Mismatches and Time-varying Delay","authors":"Di Ning, Junhao Hu","doi":"10.1109/ICCSS53909.2021.9722028","DOIUrl":"https://doi.org/10.1109/ICCSS53909.2021.9722028","url":null,"abstract":"The paper mainly copes with bounded synchronization of multiplex networks with time-varying delay via asynchronous impulsive control, where the system structure is the same but the system parameters are mismatched within each layer. Firstly, a novel multiplex network in which the interlayer interactions cross different layers only exist at discrete impulsive instants is put forward. Secondly, in view of different impulse sequences within each layer, based on the average impulse interval and extended comparison principle for impulsive systems, some sufficient criteria for reaching bounded synchronization of heterogenous multiplex networks are addressed. Finally, numerical simulation explicates the validity of some main theoretical results.","PeriodicalId":435816,"journal":{"name":"2021 8th International Conference on Information, Cybernetics, and Computational Social Systems (ICCSS)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128600646","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-12-10DOI: 10.1109/ICCSS53909.2021.9721981
Zhiguo Zhou, Lijing Huang, R. Lin, Fengqi Yan
As the main vehicle for entering space and deploying space equipment, launch vehicles have high energy density and complex electrical structures. Once mission fail, It will suffer serious losses. Fault detection technology aims to reduce the failures of launch vehicles and provide effective criteria for fault-tolerant processing. It has become the research focus of the aerospace departments of various countries. Based on the scientific metrology software Citespace, the fault detection technology of launch vehicle is analyzed scientifically in this paper, including co-occurrence of keywords, emergence of keywords, citation clustering and so on. Systematically summarizes relevant research in the WOS and CNKI databases, and predicts the development trend of this field. At the same time, this paper summarizes the development of the field of launch vehicle fault detection technology and the advantages and disadvantages of classic algorithms. Finally looks forward to the research development and engineering realization of fault detection algorithms.
{"title":"Visualization analysis of rocket fault detection technology based on Citespace","authors":"Zhiguo Zhou, Lijing Huang, R. Lin, Fengqi Yan","doi":"10.1109/ICCSS53909.2021.9721981","DOIUrl":"https://doi.org/10.1109/ICCSS53909.2021.9721981","url":null,"abstract":"As the main vehicle for entering space and deploying space equipment, launch vehicles have high energy density and complex electrical structures. Once mission fail, It will suffer serious losses. Fault detection technology aims to reduce the failures of launch vehicles and provide effective criteria for fault-tolerant processing. It has become the research focus of the aerospace departments of various countries. Based on the scientific metrology software Citespace, the fault detection technology of launch vehicle is analyzed scientifically in this paper, including co-occurrence of keywords, emergence of keywords, citation clustering and so on. Systematically summarizes relevant research in the WOS and CNKI databases, and predicts the development trend of this field. At the same time, this paper summarizes the development of the field of launch vehicle fault detection technology and the advantages and disadvantages of classic algorithms. Finally looks forward to the research development and engineering realization of fault detection algorithms.","PeriodicalId":435816,"journal":{"name":"2021 8th International Conference on Information, Cybernetics, and Computational Social Systems (ICCSS)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128649360","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In this paper, a stock trend forecasting model is constructed based on Bert’s text sentiment analysis and the forecasting method of LSTM. In order to improve the traditional forecasting model, which does not take into account the influence of market sentiment on stock prices, we use Bert’s model to extract textual information features from social media information, market news, and stockholders’ comments after using historical stock trading data as features in the model for forecasting and carry out text sentiment analysis. The text features are then combined with historical stock data, and the fusedmax function is used to filter out the most likely outcomes to predict stock trends.
{"title":"ISSPM: A stock prediction model incorporating investor sentiment calculations based on fusedmax","authors":"Yuer Yang, Siting Chen, Zeguang Chen, Shaobo Chen, Ruolanxin Li, Zhiye Cai, Haotian Gu, Hongyi Yin, Yujuan Quan","doi":"10.1109/ICCSS53909.2021.9721973","DOIUrl":"https://doi.org/10.1109/ICCSS53909.2021.9721973","url":null,"abstract":"In this paper, a stock trend forecasting model is constructed based on Bert’s text sentiment analysis and the forecasting method of LSTM. In order to improve the traditional forecasting model, which does not take into account the influence of market sentiment on stock prices, we use Bert’s model to extract textual information features from social media information, market news, and stockholders’ comments after using historical stock trading data as features in the model for forecasting and carry out text sentiment analysis. The text features are then combined with historical stock data, and the fusedmax function is used to filter out the most likely outcomes to predict stock trends.","PeriodicalId":435816,"journal":{"name":"2021 8th International Conference on Information, Cybernetics, and Computational Social Systems (ICCSS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116221945","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-12-10DOI: 10.1109/ICCSS53909.2021.9722012
Boyu Li, Tao Jin, Yuanheng Zhu, Haoran Li, Yingnian Wu, Dongbin Zhao
Robots are playing a more and more important role in people’s production and life, recently. However, robot control in dynamic environment is still a difficulty. With the great breakthrough of deep reinforcement learning in the field of video games, this method is also extended to the field of robots. Due to the gap between the simulation environment and the real environment, the deep reinforcement learning algorithm trained in the simulation environment is difficult to be applied to the real environment. Aiming at the gimbal control with two degrees of freedom (DOF), a pipline combining system identification and deep reinforcement learning is proposed. On the one hand, the shooting accuracy of the gimbal to moving objects is improved through deep reinforcement learning algorithm. On the other hand, the gap between simulation and reality is reduced through system identification. The method is verified in the RoboMaster University AI Challenge (RMUA) shooting system. The results show that the shooting accuracy is better than the classical control method.
{"title":"Moving Target Shooting Control Policy Based on Deep Reinforcement Learning","authors":"Boyu Li, Tao Jin, Yuanheng Zhu, Haoran Li, Yingnian Wu, Dongbin Zhao","doi":"10.1109/ICCSS53909.2021.9722012","DOIUrl":"https://doi.org/10.1109/ICCSS53909.2021.9722012","url":null,"abstract":"Robots are playing a more and more important role in people’s production and life, recently. However, robot control in dynamic environment is still a difficulty. With the great breakthrough of deep reinforcement learning in the field of video games, this method is also extended to the field of robots. Due to the gap between the simulation environment and the real environment, the deep reinforcement learning algorithm trained in the simulation environment is difficult to be applied to the real environment. Aiming at the gimbal control with two degrees of freedom (DOF), a pipline combining system identification and deep reinforcement learning is proposed. On the one hand, the shooting accuracy of the gimbal to moving objects is improved through deep reinforcement learning algorithm. On the other hand, the gap between simulation and reality is reduced through system identification. The method is verified in the RoboMaster University AI Challenge (RMUA) shooting system. The results show that the shooting accuracy is better than the classical control method.","PeriodicalId":435816,"journal":{"name":"2021 8th International Conference on Information, Cybernetics, and Computational Social Systems (ICCSS)","volume":"111 4","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114096172","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-12-10DOI: 10.1109/ICCSS53909.2021.9721953
Hong Li, N. Xiao
Face rotation can enrich imbalanced data and improve face recognition performance. However most of the previous methods focus on identity information. Therefore, this paper firstly proposes a novel attended pose-guided generative adversarial network (APGAN) to synthesize an arbitrary target posed photorealistic human face from the original one, while maintaining the identity and the expression information. The proposed model is mainly composed of heatmap-based generator with attention and dual discriminators with attention. Adaptive attention mechanism is proposed to concentrate on critical facial organs and maintain local structure during face rotation, for achieving more precise information preservation. Integrated expression learning exploits the shared low-level features and the inherited correlation between the two tasks, furtherly improves the expression recognition capability. Attribute purification, dynamic loss weights and alternative dataset training strengthen the performance and alienate the overfitting problem together. APGAN model is trained on small-scale dataset KDEF, challenging the robustness of the networks. The extensive experimental results on the qualitative analysis and the quantitative comparison, demonstrate that the proposed model outperformances the previous face rotation methods and expression recognition methods.
{"title":"Face Rotation and Recognition Based on Attention Mechanism and Generative Adversarial Networks","authors":"Hong Li, N. Xiao","doi":"10.1109/ICCSS53909.2021.9721953","DOIUrl":"https://doi.org/10.1109/ICCSS53909.2021.9721953","url":null,"abstract":"Face rotation can enrich imbalanced data and improve face recognition performance. However most of the previous methods focus on identity information. Therefore, this paper firstly proposes a novel attended pose-guided generative adversarial network (APGAN) to synthesize an arbitrary target posed photorealistic human face from the original one, while maintaining the identity and the expression information. The proposed model is mainly composed of heatmap-based generator with attention and dual discriminators with attention. Adaptive attention mechanism is proposed to concentrate on critical facial organs and maintain local structure during face rotation, for achieving more precise information preservation. Integrated expression learning exploits the shared low-level features and the inherited correlation between the two tasks, furtherly improves the expression recognition capability. Attribute purification, dynamic loss weights and alternative dataset training strengthen the performance and alienate the overfitting problem together. APGAN model is trained on small-scale dataset KDEF, challenging the robustness of the networks. The extensive experimental results on the qualitative analysis and the quantitative comparison, demonstrate that the proposed model outperformances the previous face rotation methods and expression recognition methods.","PeriodicalId":435816,"journal":{"name":"2021 8th International Conference on Information, Cybernetics, and Computational Social Systems (ICCSS)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127119385","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-12-10DOI: 10.1109/ICCSS53909.2021.9721977
Zipeng Xu, Longlong Fan, Yongli Zhang, Hongxing Li
In this paper, a variable universe fuzzy exponential rate reaching law sliding mode controller (VFSMC) is designed for obstacle avoidance and stabilization of the unmanned bicycle. First, a variable universe fuzzy controller is used to adjust the parameter of the sliding mode controller. Then, a fuzzy controller is considered to realize the error correction of the sliding mode controller to improve the accuracy of the controller. Further, the artificial potential field method is adopted to achieve obstacle avoidance control of the unmanned bicycle. Some numerical simulations are provided to illustrate the validity of the proposed controller.
{"title":"Obstacle avoidance control of the unmanned bicycle based on variable universe fuzzy exponential rate reaching law sliding mode control","authors":"Zipeng Xu, Longlong Fan, Yongli Zhang, Hongxing Li","doi":"10.1109/ICCSS53909.2021.9721977","DOIUrl":"https://doi.org/10.1109/ICCSS53909.2021.9721977","url":null,"abstract":"In this paper, a variable universe fuzzy exponential rate reaching law sliding mode controller (VFSMC) is designed for obstacle avoidance and stabilization of the unmanned bicycle. First, a variable universe fuzzy controller is used to adjust the parameter of the sliding mode controller. Then, a fuzzy controller is considered to realize the error correction of the sliding mode controller to improve the accuracy of the controller. Further, the artificial potential field method is adopted to achieve obstacle avoidance control of the unmanned bicycle. Some numerical simulations are provided to illustrate the validity of the proposed controller.","PeriodicalId":435816,"journal":{"name":"2021 8th International Conference on Information, Cybernetics, and Computational Social Systems (ICCSS)","volume":"13 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127595891","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-12-10DOI: 10.1109/ICCSS53909.2021.9721986
Yunchao Jiang, Shunyi Zhao, Songjie Guo
Underwater sludge greatly affects water quality, and it is an important task of urban maintenance to clean up the sludge in the urban rivers. To remove sludge, a critical step is to measure the location and depth of sludge accurately, which leads to a refined calculation of maintenance fee. A traditional method of measuring sludge is based on human experience, which is costly, and more importantly, calculation errors and low efficiency. In this paper, we introduce an intelligent and automatic underwater sludge detection system. Two sonars equipped on an unmanned ship provide the measurements of depth, which are fused using the Kalman-like method to obtain accurate measures of sludge depth. Our experiment shows that the system can detect sludge depth conveniently.
{"title":"Underwater Sludge Detection System Based on Multi-Data Fusion","authors":"Yunchao Jiang, Shunyi Zhao, Songjie Guo","doi":"10.1109/ICCSS53909.2021.9721986","DOIUrl":"https://doi.org/10.1109/ICCSS53909.2021.9721986","url":null,"abstract":"Underwater sludge greatly affects water quality, and it is an important task of urban maintenance to clean up the sludge in the urban rivers. To remove sludge, a critical step is to measure the location and depth of sludge accurately, which leads to a refined calculation of maintenance fee. A traditional method of measuring sludge is based on human experience, which is costly, and more importantly, calculation errors and low efficiency. In this paper, we introduce an intelligent and automatic underwater sludge detection system. Two sonars equipped on an unmanned ship provide the measurements of depth, which are fused using the Kalman-like method to obtain accurate measures of sludge depth. Our experiment shows that the system can detect sludge depth conveniently.","PeriodicalId":435816,"journal":{"name":"2021 8th International Conference on Information, Cybernetics, and Computational Social Systems (ICCSS)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125200635","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-12-10DOI: 10.1109/ICCSS53909.2021.9722018
Jia Chen, Xinxin Liu, Xiaojie Su
This paper investigates the nonlinear sliding mode observer-based load frequency control design of multi-area power systems subject to quantization output measurement. Firstly, the multi-area power systems are modeled. Then, a nonlinear sliding surface is developed. Finally, a nonlinear control law is synthesized to guarantee the reachability of the sliding surface.
{"title":"Improved Sliding Mode-based Load Frequency Control in Multi-Area Power Systems","authors":"Jia Chen, Xinxin Liu, Xiaojie Su","doi":"10.1109/ICCSS53909.2021.9722018","DOIUrl":"https://doi.org/10.1109/ICCSS53909.2021.9722018","url":null,"abstract":"This paper investigates the nonlinear sliding mode observer-based load frequency control design of multi-area power systems subject to quantization output measurement. Firstly, the multi-area power systems are modeled. Then, a nonlinear sliding surface is developed. Finally, a nonlinear control law is synthesized to guarantee the reachability of the sliding surface.","PeriodicalId":435816,"journal":{"name":"2021 8th International Conference on Information, Cybernetics, and Computational Social Systems (ICCSS)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122748911","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：