Pub Date : 2021-12-01DOI: 10.1109/ICA54137.2021.00012
T. Koça, T. Baarslag, C. Jonker
This work presents the Autonomous Bidding & Coordinated Acceptance framework (ABCA): an agent-team design that allows general bilateral agents to engage in oneto-many negotiations in a setting where (possibly overlapping) deals with multiple opponents are desirable. We propose also a coordinated acceptance strategy that uses the estimated outcomes of its bilateral negotiations while deciding to accept a deal.
{"title":"Autonomous Bidding & Coordinated Acceptance in One-to-Many Negotiations","authors":"T. Koça, T. Baarslag, C. Jonker","doi":"10.1109/ICA54137.2021.00012","DOIUrl":"https://doi.org/10.1109/ICA54137.2021.00012","url":null,"abstract":"This work presents the Autonomous Bidding & Coordinated Acceptance framework (ABCA): an agent-team design that allows general bilateral agents to engage in oneto-many negotiations in a setting where (possibly overlapping) deals with multiple opponents are desirable. We propose also a coordinated acceptance strategy that uses the estimated outcomes of its bilateral negotiations while deciding to accept a deal.","PeriodicalId":273320,"journal":{"name":"2021 IEEE International Conference on Agents (ICA)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115617694","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}
Thermal defect affects the normal operation of power equipment, which is crucial to the reliability of the power system. To solve this problem, a thermal defect detection and location method based on neural network is proposed. According to the characteristics of infrared images, a visual geometry group network (VGG16) based on transfer learning is established for temperature recognition. After screening the thermal defect images with abnormal temperature, an improved connected component method is used for defect region location. The results demonstrate that the recognition accuracy of the proposed method is 99.6%. The thermal defect region can be located more accurately. It is significant to realize intelligent detection for power equipment.
{"title":"Thermal Defect Detection and Location for Power Equipment based on Improved VGG16","authors":"Kaixuan Wang, Fuji Ren, Xin Kang, Shuaishuai Lv, Hongjun Ni, Haifeng Yuan","doi":"10.1109/ICA54137.2021.00014","DOIUrl":"https://doi.org/10.1109/ICA54137.2021.00014","url":null,"abstract":"Thermal defect affects the normal operation of power equipment, which is crucial to the reliability of the power system. To solve this problem, a thermal defect detection and location method based on neural network is proposed. According to the characteristics of infrared images, a visual geometry group network (VGG16) based on transfer learning is established for temperature recognition. After screening the thermal defect images with abnormal temperature, an improved connected component method is used for defect region location. The results demonstrate that the recognition accuracy of the proposed method is 99.6%. The thermal defect region can be located more accurately. It is significant to realize intelligent detection for power equipment.","PeriodicalId":273320,"journal":{"name":"2021 IEEE International Conference on Agents (ICA)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127123147","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 : 2021-12-01DOI: 10.1109/ICA54137.2021.00008
Kohei Yamaguchi, Tsunenori Mine
A system in which citizens and the government work together to solve regional issues is known as Government 2.0. To promote this system, the collection of regional issues through mobile crowd sensing and collaborative IoT is being promoted. On the other hand, although prioritization is essential to solve the collected issues, conventional methods only classify the issues and do not identify the precedence relations between the issues. In addition, the latest deep learning models have not been applied to this task. In this study, we apply BERT to the task to identify the priorities of the collected issues based on the safety and security of citizens. We conduct experiments on a data set of regional complaint citizen reports. Experimental results illustrate that the BERT (fine-tuned approach) outperformed the other baseline methods even in the case of data sets with small vocabulary and biases among priority labels, such as the one in this task.
{"title":"Estimation of Precedence Relations to Deal with Regional Complaint Reports","authors":"Kohei Yamaguchi, Tsunenori Mine","doi":"10.1109/ICA54137.2021.00008","DOIUrl":"https://doi.org/10.1109/ICA54137.2021.00008","url":null,"abstract":"A system in which citizens and the government work together to solve regional issues is known as Government 2.0. To promote this system, the collection of regional issues through mobile crowd sensing and collaborative IoT is being promoted. On the other hand, although prioritization is essential to solve the collected issues, conventional methods only classify the issues and do not identify the precedence relations between the issues. In addition, the latest deep learning models have not been applied to this task. In this study, we apply BERT to the task to identify the priorities of the collected issues based on the safety and security of citizens. We conduct experiments on a data set of regional complaint citizen reports. Experimental results illustrate that the BERT (fine-tuned approach) outperformed the other baseline methods even in the case of data sets with small vocabulary and biases among priority labels, such as the one in this task.","PeriodicalId":273320,"journal":{"name":"2021 IEEE International Conference on Agents (ICA)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128012952","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 : 2021-12-01DOI: 10.1109/ICA54137.2021.00011
Shiyao Ding, Donghui Lin, Xingxuan Zhou
In edge computing, an important problem is how to allocate dependent tasks to resource-limited edge servers, where some tasks can only be performed after accomplishing some other tasks. Most related studies assume that server status remains unchanged, which might be invalid in some real-world scenarios. Thus, this paper studies the new problem of how to dynamically allocate dependent tasks in resource-limited edge computing. This problem poses two challenges: 1) how to cope with dynamic changes in server status and task arrival, and 2) how to handle the dependency information for decisionmaking in task allocation. Our solution is a graph convolutional reinforcement learning-based task-allocation agent consisting of an encoding part and a decision-making part. The encoding part represents the dependent tasks as directed acyclic graphs and employs a graph convolutional network (GCN) to embed the dependency information of the tasks. It can effectively deal with the dependency and so permit decision-making. The decision-making part formulates the task allocation problem as a Markov decision process to cope with the dynamic changes. Specially, the agent employs deep reinforcement learning to achieve dynamic decision-making for task allocation with the target of optimizing some metric (e.g., minimizing delay costs and energy cost). Experiments verify that our algorithm offers significantly better performance than the existing algorithms examined.
{"title":"Graph Convolutional Reinforcement Learning for Dependent Task Allocation in Edge Computing","authors":"Shiyao Ding, Donghui Lin, Xingxuan Zhou","doi":"10.1109/ICA54137.2021.00011","DOIUrl":"https://doi.org/10.1109/ICA54137.2021.00011","url":null,"abstract":"In edge computing, an important problem is how to allocate dependent tasks to resource-limited edge servers, where some tasks can only be performed after accomplishing some other tasks. Most related studies assume that server status remains unchanged, which might be invalid in some real-world scenarios. Thus, this paper studies the new problem of how to dynamically allocate dependent tasks in resource-limited edge computing. This problem poses two challenges: 1) how to cope with dynamic changes in server status and task arrival, and 2) how to handle the dependency information for decisionmaking in task allocation. Our solution is a graph convolutional reinforcement learning-based task-allocation agent consisting of an encoding part and a decision-making part. The encoding part represents the dependent tasks as directed acyclic graphs and employs a graph convolutional network (GCN) to embed the dependency information of the tasks. It can effectively deal with the dependency and so permit decision-making. The decision-making part formulates the task allocation problem as a Markov decision process to cope with the dynamic changes. Specially, the agent employs deep reinforcement learning to achieve dynamic decision-making for task allocation with the target of optimizing some metric (e.g., minimizing delay costs and energy cost). Experiments verify that our algorithm offers significantly better performance than the existing algorithms examined.","PeriodicalId":273320,"journal":{"name":"2021 IEEE International Conference on Agents (ICA)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125855424","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 : 2021-12-01DOI: 10.1109/ICA54137.2021.00016
Shota Yamaguchi, Kenji Iseya, Kazuma Kobayashi, Satoshi Mitsui, T. Satake, Naoki Igo
Decommissioning Robot Competition is a robotics competition for decommissioning of reactor. The purpose of this study is to develop human resources which will be responsible for decommissioning technology in the future by giving them knowledge and interest in decommissioning work itself, as well as experience gained in the process. The task of the fourth competition is to go through a narrow pipe, to the pedestal section, and then to take a golf or tennis ball at the bottom of the hole in the pedestal section and a return. This study aims to build a robot that can perform the tasks in the 4th Decommissioning Robot Competition. The robot is composed of the main unit and sub-unit. The purpose of the main unit is to hang and lift the sub-unit safely and to pass the cables connected to the sub-unit safely. The purpose of the main unit is to hang and lift the subunit safely and to pass the cables connected to the sub-unit safely. An infinite track is used for the footrest, and a slide rail is attached to the top of the main unit to lift the sub-unit with a cable. The cable was bitten to a pulley attached to the slide rail, and the cable was collected by moving the pulley. The purpose of the sub-unit is to search for and hold the object to be recovered. We prepared a terminal to operate the sub-unit and a terminal to check the camera image. To hold the object, an arm is attached to the front of the sub-unit and the object is sandwiched between the arm and the front of the sub-unit. As a result, the robot was able to perform the tasks, but due to the lack of prior testing and coordination, it was not able to clear all the competition tasks.
{"title":"Decommissioning Robot Retrieves Fuel Debris from High Altitude","authors":"Shota Yamaguchi, Kenji Iseya, Kazuma Kobayashi, Satoshi Mitsui, T. Satake, Naoki Igo","doi":"10.1109/ICA54137.2021.00016","DOIUrl":"https://doi.org/10.1109/ICA54137.2021.00016","url":null,"abstract":"Decommissioning Robot Competition is a robotics competition for decommissioning of reactor. The purpose of this study is to develop human resources which will be responsible for decommissioning technology in the future by giving them knowledge and interest in decommissioning work itself, as well as experience gained in the process. The task of the fourth competition is to go through a narrow pipe, to the pedestal section, and then to take a golf or tennis ball at the bottom of the hole in the pedestal section and a return. This study aims to build a robot that can perform the tasks in the 4th Decommissioning Robot Competition. The robot is composed of the main unit and sub-unit. The purpose of the main unit is to hang and lift the sub-unit safely and to pass the cables connected to the sub-unit safely. The purpose of the main unit is to hang and lift the subunit safely and to pass the cables connected to the sub-unit safely. An infinite track is used for the footrest, and a slide rail is attached to the top of the main unit to lift the sub-unit with a cable. The cable was bitten to a pulley attached to the slide rail, and the cable was collected by moving the pulley. The purpose of the sub-unit is to search for and hold the object to be recovered. We prepared a terminal to operate the sub-unit and a terminal to check the camera image. To hold the object, an arm is attached to the front of the sub-unit and the object is sandwiched between the arm and the front of the sub-unit. As a result, the robot was able to perform the tasks, but due to the lack of prior testing and coordination, it was not able to clear all the competition tasks.","PeriodicalId":273320,"journal":{"name":"2021 IEEE International Conference on Agents (ICA)","volume":"92 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117284831","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 : 2021-12-01DOI: 10.1109/ICA54137.2021.00015
Jiali Ling, Jialong Li, K. Tei, Shinichi Honiden
Although autonomous driving is expected to pave the way for the future of transportation, it is often met with resistance. One of the reasons for this may be that, as of this writing, autonomous driving still cannot meet the individual needs of people. Furthermore, the unfamiliarity and discomfort when riding in an autonomous vehicle can cause drivers to feel stressed and distrustful of the vehicle. To this end, we propose an Emotion Preference Style Adaptation (EPSA) framework. The framework can analyze and determine a driver’s driving preferences from the emotion which is recognized from their EEG signals. And then it will adapt the style of the vehicle’s driving behavior to suit the driver’s preference.
{"title":"Towards Personalized Autonomous Driving: An Emotion Preference Style Adaptation Framework","authors":"Jiali Ling, Jialong Li, K. Tei, Shinichi Honiden","doi":"10.1109/ICA54137.2021.00015","DOIUrl":"https://doi.org/10.1109/ICA54137.2021.00015","url":null,"abstract":"Although autonomous driving is expected to pave the way for the future of transportation, it is often met with resistance. One of the reasons for this may be that, as of this writing, autonomous driving still cannot meet the individual needs of people. Furthermore, the unfamiliarity and discomfort when riding in an autonomous vehicle can cause drivers to feel stressed and distrustful of the vehicle. To this end, we propose an Emotion Preference Style Adaptation (EPSA) framework. The framework can analyze and determine a driver’s driving preferences from the emotion which is recognized from their EEG signals. And then it will adapt the style of the vehicle’s driving behavior to suit the driver’s preference.","PeriodicalId":273320,"journal":{"name":"2021 IEEE International Conference on Agents (ICA)","volume":"46 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126383407","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 : 2021-12-01DOI: 10.1109/ICA54137.2021.00017
S. Okuhara, Rafik Hadfi, Takayuki Ito
Decision-makers have to reason about the fairness of their choices when other parties are involved. This situation has called for the use of preference models that could codify notions like selfishness, fairness, and altruism. There are cases of problems where the decision-maker’s partners have interdependent preferences about the available alternatives. This gives rise to multiple forms of influence between all the partners. In this preliminary study, we propose a canonical case for this problem with subordinate and independent alternatives. We show how probabilistic dependency could influence the fairness and private payoffs of the decision-maker.
{"title":"Shame in two-stage choice problems with interdependent alternatives","authors":"S. Okuhara, Rafik Hadfi, Takayuki Ito","doi":"10.1109/ICA54137.2021.00017","DOIUrl":"https://doi.org/10.1109/ICA54137.2021.00017","url":null,"abstract":"Decision-makers have to reason about the fairness of their choices when other parties are involved. This situation has called for the use of preference models that could codify notions like selfishness, fairness, and altruism. There are cases of problems where the decision-maker’s partners have interdependent preferences about the available alternatives. This gives rise to multiple forms of influence between all the partners. In this preliminary study, we propose a canonical case for this problem with subordinate and independent alternatives. We show how probabilistic dependency could influence the fairness and private payoffs of the decision-maker.","PeriodicalId":273320,"journal":{"name":"2021 IEEE International Conference on Agents (ICA)","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127286101","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}
Steel strip is one of the main products of traditional steel manufacturing enterprises. It is of great significance to accurately identify the types of defects on the surface of the steel strip. This paper innovatively proposes a pre-training method of network weights based on ResNet18. The network is optimized by dynamically adjusting the learning rate. This method can classify steel strip images with high accuracy of 98.585%, avoid overfitting and enhance the stability of training process.
{"title":"Classification of Steel Strip Surface Defects Based on Optimized ResNet18","authors":"Zhuangzhuang Hao, Fuji Ren, Xin Kang, Hongjun Ni, Shuaishuai Lv, Hui Wang","doi":"10.1109/ICA54137.2021.00018","DOIUrl":"https://doi.org/10.1109/ICA54137.2021.00018","url":null,"abstract":"Steel strip is one of the main products of traditional steel manufacturing enterprises. It is of great significance to accurately identify the types of defects on the surface of the steel strip. This paper innovatively proposes a pre-training method of network weights based on ResNet18. The network is optimized by dynamically adjusting the learning rate. This method can classify steel strip images with high accuracy of 98.585%, avoid overfitting and enhance the stability of training process.","PeriodicalId":273320,"journal":{"name":"2021 IEEE International Conference on Agents (ICA)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125601640","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 : 2021-12-01DOI: 10.1109/ICA54137.2021.00010
Yuto Iwata, S. Matsubara
We propose a novel distributed user-car matching method based on a contract between users to mitigate the imbalance problem between vehicle distribution and demand in free-floating car sharing. The previous contract-based regulation method assumes that contracts are binding. However, car-sharing systems users are in dynamic environments, and such binding fails to accommodate future events. Therefore, to overcome this drawback, we introduce a leveled-commitment contract into contract-based coordination among drop-off and pick-up users. In our method, an auction is conducted for drop-off users’ intended drop-off locations, and users are allowed to decommit from contracts by paying penalties. The amount of penalty is determined by considering the trade-off between the sunk cost due to movement and social surplus. We thoroughly evaluated the proposed method with a baseline method on a free-floating car-sharing simulator. The results show that it achieved a higher social surplus than the existing method when demand frequently occurred.
{"title":"Usage Coordination Utilizing Flexible Contracts in Free-floating Car Sharing","authors":"Yuto Iwata, S. Matsubara","doi":"10.1109/ICA54137.2021.00010","DOIUrl":"https://doi.org/10.1109/ICA54137.2021.00010","url":null,"abstract":"We propose a novel distributed user-car matching method based on a contract between users to mitigate the imbalance problem between vehicle distribution and demand in free-floating car sharing. The previous contract-based regulation method assumes that contracts are binding. However, car-sharing systems users are in dynamic environments, and such binding fails to accommodate future events. Therefore, to overcome this drawback, we introduce a leveled-commitment contract into contract-based coordination among drop-off and pick-up users. In our method, an auction is conducted for drop-off users’ intended drop-off locations, and users are allowed to decommit from contracts by paying penalties. The amount of penalty is determined by considering the trade-off between the sunk cost due to movement and social surplus. We thoroughly evaluated the proposed method with a baseline method on a free-floating car-sharing simulator. The results show that it achieved a higher social surplus than the existing method when demand frequently occurred.","PeriodicalId":273320,"journal":{"name":"2021 IEEE International Conference on Agents (ICA)","volume":"126 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115459222","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 : 2021-12-01DOI: 10.1109/ICA54137.2021.00013
Jundong Chen, M. Hossain, Abdul Serwadda, Fei Han
In online social networks (OSN), followers count is a sign of the social influence of an account. Some users expect to increase the followers count by following more accounts. However, in reality more followings do not generate more followers. In this paper, we propose a two player follow-unfollow game model and then introduce a factor for promoting cooperation. Based on the two player follow-unfollow game, we create an evolutionary follow-unfollow game with more players to simulate a miniature social network. We design an algorithm and conduct the simulation. From the simulation, we find that our algorithm for the evolutionary follow-unfollow game is able to converge and produce a stable network. Results obtained with different values of the cooperation promotion factor show that the promotion factor increases the total connections in the network especially through increasing the number of the follow follow connections.
{"title":"Modeling Follow-Unfollow Mechanism in Social Networks with Evolutionary Game","authors":"Jundong Chen, M. Hossain, Abdul Serwadda, Fei Han","doi":"10.1109/ICA54137.2021.00013","DOIUrl":"https://doi.org/10.1109/ICA54137.2021.00013","url":null,"abstract":"In online social networks (OSN), followers count is a sign of the social influence of an account. Some users expect to increase the followers count by following more accounts. However, in reality more followings do not generate more followers. In this paper, we propose a two player follow-unfollow game model and then introduce a factor for promoting cooperation. Based on the two player follow-unfollow game, we create an evolutionary follow-unfollow game with more players to simulate a miniature social network. We design an algorithm and conduct the simulation. From the simulation, we find that our algorithm for the evolutionary follow-unfollow game is able to converge and produce a stable network. Results obtained with different values of the cooperation promotion factor show that the promotion factor increases the total connections in the network especially through increasing the number of the follow follow connections.","PeriodicalId":273320,"journal":{"name":"2021 IEEE International Conference on Agents (ICA)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117108435","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：