Supercomputer reliability decreases with the increase of its scale. In this situation, the method to reduce the supercomputer MTTR (mean time to repair) plays a critical role in system management. Engineers at present typically use supercomputer metrics to construct anomaly detection methods and reduce the MTTR of supercomputers. However, the infrastructure data, including chilled water data, of supercomputers are neglected. This paper proposes an ensemble learning method for anomaly detection, which includes LSTM (long short-term memory) and linear regression algorithm. On the basis of this method, we construct an anomaly monitor system by using chilled water data. Experimental results show that the method can help engineers precisely detect anomalies.
{"title":"Anomaly Detection Method for Chiller System of Supercomputer","authors":"Yuqi Li, Jinghua Feng, Changsong Li","doi":"10.1145/3341069.3341076","DOIUrl":"https://doi.org/10.1145/3341069.3341076","url":null,"abstract":"Supercomputer reliability decreases with the increase of its scale. In this situation, the method to reduce the supercomputer MTTR (mean time to repair) plays a critical role in system management. Engineers at present typically use supercomputer metrics to construct anomaly detection methods and reduce the MTTR of supercomputers. However, the infrastructure data, including chilled water data, of supercomputers are neglected. This paper proposes an ensemble learning method for anomaly detection, which includes LSTM (long short-term memory) and linear regression algorithm. On the basis of this method, we construct an anomaly monitor system by using chilled water data. Experimental results show that the method can help engineers precisely detect anomalies.","PeriodicalId":411198,"journal":{"name":"Proceedings of the 2019 3rd High Performance Computing and Cluster Technologies Conference","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114525210","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 global path planning method for mobile robots based on improved ant colony algorithm was proposed. Which overcome the problem that the traditional ant colony algorithm was prone to deadlock, may not get the global optimal solution and easily get into the local optimal problem. The transfer probability of ants in the traditional ant colony algorithm was adjusted to improve the occurrence of deadlock in the paper. And the roulette wheel algorithm in genetic algorithm was introduced to avoid the ant colony algorithm falling into the local optimal solution. At last the optimal parameter combination of the improved ant colony algorithm was obtained through simulation experiment. It could be seen from the simulation experimental data that the number of iterations to find the shortest path under the same conditions was reduced to 47.8%, which proved that the adoption of improved ant colony algorithm for path planning of mobile robot greatly improves the operating efficiency.
{"title":"Application of Improved Ant Colony Algorithm in the Path Planning Problem of Mobile Robot","authors":"Min Cao, Yang Yang, Lianqing Wang","doi":"10.1145/3341069.3341073","DOIUrl":"https://doi.org/10.1145/3341069.3341073","url":null,"abstract":"In this paper a global path planning method for mobile robots based on improved ant colony algorithm was proposed. Which overcome the problem that the traditional ant colony algorithm was prone to deadlock, may not get the global optimal solution and easily get into the local optimal problem. The transfer probability of ants in the traditional ant colony algorithm was adjusted to improve the occurrence of deadlock in the paper. And the roulette wheel algorithm in genetic algorithm was introduced to avoid the ant colony algorithm falling into the local optimal solution. At last the optimal parameter combination of the improved ant colony algorithm was obtained through simulation experiment. It could be seen from the simulation experimental data that the number of iterations to find the shortest path under the same conditions was reduced to 47.8%, which proved that the adoption of improved ant colony algorithm for path planning of mobile robot greatly improves the operating efficiency.","PeriodicalId":411198,"journal":{"name":"Proceedings of the 2019 3rd High Performance Computing and Cluster Technologies Conference","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125968278","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 several businesses, chatbots are used for providing customer information, answering questions, helping customer reservations, virtual assistants; serve as call centers to serve ten million customers automatically. This research presents a method for developing chatbots to serve their users. A deep learning based conversational artificial intelligence technique was used as tools for learning conversation between machine and customer. The convolution neural network technique by using Tensorflow training was used to improve the accuracy of these chatbots. Moreover, in this research, we developed a system for online sales assistant application system via Facebook Page.
{"title":"Using Chatbot in Trading System for Small and Medium Enterprise (SMEs) by Convolution Neural Network Technique","authors":"Sathit Prasomphan","doi":"10.1145/3341069.3341092","DOIUrl":"https://doi.org/10.1145/3341069.3341092","url":null,"abstract":"In several businesses, chatbots are used for providing customer information, answering questions, helping customer reservations, virtual assistants; serve as call centers to serve ten million customers automatically. This research presents a method for developing chatbots to serve their users. A deep learning based conversational artificial intelligence technique was used as tools for learning conversation between machine and customer. The convolution neural network technique by using Tensorflow training was used to improve the accuracy of these chatbots. Moreover, in this research, we developed a system for online sales assistant application system via Facebook Page.","PeriodicalId":411198,"journal":{"name":"Proceedings of the 2019 3rd High Performance Computing and Cluster Technologies Conference","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131595143","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}
With the development of deep learning, reinforcement learning also gradually into the eye, reinforcement learning has made remarkable achievements in games, go games and other fields, but most of the control problems involved in these fields or tasks are discrete action control with sufficient rewards. Continuous action control in reinforcement learning is closer to the actual control problem, and is considered as one of the main channels leading to artificial intelligence, so it is also one of the research hotspots of researchers. The traditional continuous control algorithm for reinforcement learning evaluates the network with multiple outputs of a single scalar value. In this paper, an accurate evaluation mechanism and corresponding objective function are proposed to accelerate the reinforcement learning training process. The experimental results show that the accurate evaluation of log-cosh objective function can make the robot arm grasp the task more quickly, converge and complete the training task.
{"title":"Precise Evaluation for Continuous Action Control in Reinforcement Learning","authors":"Fengkai Ke, Daxing Zhao, Guodong Sun, Wei Feng","doi":"10.1145/3341069.3341082","DOIUrl":"https://doi.org/10.1145/3341069.3341082","url":null,"abstract":"With the development of deep learning, reinforcement learning also gradually into the eye, reinforcement learning has made remarkable achievements in games, go games and other fields, but most of the control problems involved in these fields or tasks are discrete action control with sufficient rewards. Continuous action control in reinforcement learning is closer to the actual control problem, and is considered as one of the main channels leading to artificial intelligence, so it is also one of the research hotspots of researchers. The traditional continuous control algorithm for reinforcement learning evaluates the network with multiple outputs of a single scalar value. In this paper, an accurate evaluation mechanism and corresponding objective function are proposed to accelerate the reinforcement learning training process. The experimental results show that the accurate evaluation of log-cosh objective function can make the robot arm grasp the task more quickly, converge and complete the training task.","PeriodicalId":411198,"journal":{"name":"Proceedings of the 2019 3rd High Performance Computing and Cluster Technologies Conference","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129744432","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}
This research presents a method for panoramic traffic sign images detection for regulatory signs and guide signs especially blue and green sign. A new approach for detecting the signs inside a large panoramic image was considered. A convolution neural network technique was used as tools for detecting. In addition, the steps required are the technique used in conjunction with the convolution neural network technique by using Tensorflow training to improve the accuracy of traffic sign detection. Moreover, to improve the accuracy of image detection, some image processing technique was added. For example, adding brightness to an image. From the experimental results, detection of traffic signs from panoramic images (360°) by using trained convolution neural network model to improve a traffic sign detection, the accuracy from panoramic images (360°) is better than the traditional model.
{"title":"Traffic Sign Detection for Panoramic Images Using Convolution Neural Network Technique","authors":"Sathit Prasomphan, Thanthip Tathong, Primpisa Charoenprateepkit","doi":"10.1145/3341069.3341090","DOIUrl":"https://doi.org/10.1145/3341069.3341090","url":null,"abstract":"This research presents a method for panoramic traffic sign images detection for regulatory signs and guide signs especially blue and green sign. A new approach for detecting the signs inside a large panoramic image was considered. A convolution neural network technique was used as tools for detecting. In addition, the steps required are the technique used in conjunction with the convolution neural network technique by using Tensorflow training to improve the accuracy of traffic sign detection. Moreover, to improve the accuracy of image detection, some image processing technique was added. For example, adding brightness to an image. From the experimental results, detection of traffic signs from panoramic images (360°) by using trained convolution neural network model to improve a traffic sign detection, the accuracy from panoramic images (360°) is better than the traditional model.","PeriodicalId":411198,"journal":{"name":"Proceedings of the 2019 3rd High Performance Computing and Cluster Technologies Conference","volume":"75 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126176712","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}
Lei Bao, Chun-yang Wang, Juan Bai, ShengTeng Wei, Ming Tan, Yuan-jie Lv
Based on the research background of target formation characteristics of dual stealth aircraft, how to effectively compare and analyze the actual change characteristics of target formation RCS under different formation flying modes in penetration operation is discussed. The model of two-plane horizontal flight path, two-plane hovering track and two-plane formation infiltration maneuvering track are proposed. Based on the model, the attitude sensitivity of dual stealth aircraft formation is analyzed firstly, and then the line-of-sight attitude angle of dual stealth aircraft formation is calculated. Based on the static RCS data of dual stealth aircraft in the whole airspace, the time-varying dynamic RCS sequence is simulated. The simulation results show that the real-time RCS sequence distribution of the two-aircraft formation is more suitable than that of the single-aircraft formation at 150 meters interval when compared with the real-time RCS sequence of the single stealth aircraft under three different track attitudes, and the formation has less influence on the stealth performance.
{"title":"Time-varying Target Characteristic Analysis of Dual Stealth Aircraft Formation","authors":"Lei Bao, Chun-yang Wang, Juan Bai, ShengTeng Wei, Ming Tan, Yuan-jie Lv","doi":"10.1145/3341069.3342977","DOIUrl":"https://doi.org/10.1145/3341069.3342977","url":null,"abstract":"Based on the research background of target formation characteristics of dual stealth aircraft, how to effectively compare and analyze the actual change characteristics of target formation RCS under different formation flying modes in penetration operation is discussed. The model of two-plane horizontal flight path, two-plane hovering track and two-plane formation infiltration maneuvering track are proposed. Based on the model, the attitude sensitivity of dual stealth aircraft formation is analyzed firstly, and then the line-of-sight attitude angle of dual stealth aircraft formation is calculated. Based on the static RCS data of dual stealth aircraft in the whole airspace, the time-varying dynamic RCS sequence is simulated. The simulation results show that the real-time RCS sequence distribution of the two-aircraft formation is more suitable than that of the single-aircraft formation at 150 meters interval when compared with the real-time RCS sequence of the single stealth aircraft under three different track attitudes, and the formation has less influence on the stealth performance.","PeriodicalId":411198,"journal":{"name":"Proceedings of the 2019 3rd High Performance Computing and Cluster Technologies Conference","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115481347","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}
DeepLabv3+ is one of the most accurate algorithms in semantic segmentation. CBAM is an attention mechanism proposed to improve the performance of obect detection model which can be used in a convolutional neural network. Given an intermediate feature map, CBAM sequentially infers attention maps along two separate dimensions, channel and spatial, then the attention maps are multiplied to the input feature map for adaptive feature refinement. In the image segmentation tasks, in order to achieve the goal of enhancing feature representation and improving segmentation accuracy without extra overheads. In this paper, we proposed AMNet which is an end-to-end semantic segmentation network based on DeepLabv3+ which is embeded with CBAM. Further, CBAM activates when the input image passes through CNN.Channel attention module in CBAM focues on 'what' is meaningful given an input image and spatial attention module focus on 'where'. Our network acheives 77.66% mIoU on the PASCAL VOC2012, which is a 2.73% better mIoU than DeepLabv3+ with 6 batchsize using only one single Nvidia 2080 GPU. Beyond that, for getting a faster segmentation model, we also embed the attention mechanism into ENet, one of the fastest lightweight networks. After our evaluation on the Cityscapes dataset, we got a better performance in the case of fast training speed. The feasibility that attention mechanism can be integrated into semantic segmentaion network is proved.
{"title":"AMNet","authors":"Baiyi Shu, Jiong Mu, Yu Zhu","doi":"10.1145/3341069.3342988","DOIUrl":"https://doi.org/10.1145/3341069.3342988","url":null,"abstract":"DeepLabv3+ is one of the most accurate algorithms in semantic segmentation. CBAM is an attention mechanism proposed to improve the performance of obect detection model which can be used in a convolutional neural network. Given an intermediate feature map, CBAM sequentially infers attention maps along two separate dimensions, channel and spatial, then the attention maps are multiplied to the input feature map for adaptive feature refinement. In the image segmentation tasks, in order to achieve the goal of enhancing feature representation and improving segmentation accuracy without extra overheads. In this paper, we proposed AMNet which is an end-to-end semantic segmentation network based on DeepLabv3+ which is embeded with CBAM. Further, CBAM activates when the input image passes through CNN.Channel attention module in CBAM focues on 'what' is meaningful given an input image and spatial attention module focus on 'where'. Our network acheives 77.66% mIoU on the PASCAL VOC2012, which is a 2.73% better mIoU than DeepLabv3+ with 6 batchsize using only one single Nvidia 2080 GPU. Beyond that, for getting a faster segmentation model, we also embed the attention mechanism into ENet, one of the fastest lightweight networks. After our evaluation on the Cityscapes dataset, we got a better performance in the case of fast training speed. The feasibility that attention mechanism can be integrated into semantic segmentaion network is proved.","PeriodicalId":411198,"journal":{"name":"Proceedings of the 2019 3rd High Performance Computing and Cluster Technologies Conference","volume":"50 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121921122","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}
The government has increased investment in the informationization area of education in ethnic areas over the decades, aiming at promoting the process of education informatization. It selects the literature resources related to national education informatization from 1998 to 2018 CNKI for comprehensive research and analysis. And it makes a visual analysis of the research hotspots and development of educational informationization in ethnic regions from the aspects of literature volume, word frequency analysis, co-word analysis, multi-dimensional scale analysis, using SATI 3.2, UCINET 6.0, NetDraw and SPSS software. Through visualization analysis, we can further explore the trend of national education informationization research and development, and provides basis and reference for promoting the in-depth research and practice of education informationization.
{"title":"Visual Analysis of Hotspots in Educational Informationization in Ethnic Areas","authors":"Xiaoyu Zhu, Xiaodong Yan","doi":"10.1145/3341069.3341085","DOIUrl":"https://doi.org/10.1145/3341069.3341085","url":null,"abstract":"The government has increased investment in the informationization area of education in ethnic areas over the decades, aiming at promoting the process of education informatization. It selects the literature resources related to national education informatization from 1998 to 2018 CNKI for comprehensive research and analysis. And it makes a visual analysis of the research hotspots and development of educational informationization in ethnic regions from the aspects of literature volume, word frequency analysis, co-word analysis, multi-dimensional scale analysis, using SATI 3.2, UCINET 6.0, NetDraw and SPSS software. Through visualization analysis, we can further explore the trend of national education informationization research and development, and provides basis and reference for promoting the in-depth research and practice of education informationization.","PeriodicalId":411198,"journal":{"name":"Proceedings of the 2019 3rd High Performance Computing and Cluster Technologies Conference","volume":"41 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123682990","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 the processing of cotton, a large variety of data is generated, and researchers can use this data to conduct a large number of studies to improve the quality of cotton processing. Before mining the historical data, it is necessary to pre-process the dirty data of the actual application. According to the actual data provided by the cotton factory, the data is preprocessed by the raw data. By comparing the advantages and disadvantages of various algorithms, Regression filling method is used to process data missing values. The data is standardized by Z-score method, the data is processed into the same dimension, and the seed cotton data is clustered by K-means algorithm. We choose SPSS as the data preprocessing simulation software to provide effective high-quality data for the next step of data mining.
{"title":"Pretreatment of Cotton Processing Data Based on SPSS","authors":"Xue Han, Yong Zhang, J. Qiao","doi":"10.1145/3341069.3342978","DOIUrl":"https://doi.org/10.1145/3341069.3342978","url":null,"abstract":"In the processing of cotton, a large variety of data is generated, and researchers can use this data to conduct a large number of studies to improve the quality of cotton processing. Before mining the historical data, it is necessary to pre-process the dirty data of the actual application. According to the actual data provided by the cotton factory, the data is preprocessed by the raw data. By comparing the advantages and disadvantages of various algorithms, Regression filling method is used to process data missing values. The data is standardized by Z-score method, the data is processed into the same dimension, and the seed cotton data is clustered by K-means algorithm. We choose SPSS as the data preprocessing simulation software to provide effective high-quality data for the next step of data mining.","PeriodicalId":411198,"journal":{"name":"Proceedings of the 2019 3rd High Performance Computing and Cluster Technologies Conference","volume":"80 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124637351","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}
Inefficient scheduling of tasks on cloud datacenter resources can result in underutilization leading to poor revenue generation. To show efficient tasks scheduling on cloud datacenter, the makespan time needs to be minimized. In this paper, we introduced a conventional Cat Swarm Optimization (CSO) task scheduling technique as an ideal solution. Although the CSO is promising in terms of convergence speed, certain improvements are required to make it efficient for cloud task scheduling since it suffers entrapment at the local search. To overcome this, we incorporated a Linear Descending Inertia Weight (LDIW) equation at the local search of the CSO technique. This led to better convergence speed and possibly ensured efficient tasks mapping on virtual resources that minimizes the makespan time. The proposed CSO-LDIW technique is implemented on CloudSim simulator tool with five (5) heterogeneous Virtual Machines (VMs) under consideration to show its performance. The results of the simulation indicate that a comparison with that of the Particle Swarm Optimization-Linear Descending Inertia Weight (PSO-LDIW) and the CSO shows that our proposed CSO-LDIW can schedule task effectively on cloud resource with a promising makespan time.
{"title":"Minimized Makespan Based Improved Cat Swarm Optimization for Efficient Task Scheduling in Cloud Datacenter","authors":"Danlami Gabi, A. Ismail, Nasiru Muhammad Dankolo","doi":"10.1145/3341069.3341074","DOIUrl":"https://doi.org/10.1145/3341069.3341074","url":null,"abstract":"Inefficient scheduling of tasks on cloud datacenter resources can result in underutilization leading to poor revenue generation. To show efficient tasks scheduling on cloud datacenter, the makespan time needs to be minimized. In this paper, we introduced a conventional Cat Swarm Optimization (CSO) task scheduling technique as an ideal solution. Although the CSO is promising in terms of convergence speed, certain improvements are required to make it efficient for cloud task scheduling since it suffers entrapment at the local search. To overcome this, we incorporated a Linear Descending Inertia Weight (LDIW) equation at the local search of the CSO technique. This led to better convergence speed and possibly ensured efficient tasks mapping on virtual resources that minimizes the makespan time. The proposed CSO-LDIW technique is implemented on CloudSim simulator tool with five (5) heterogeneous Virtual Machines (VMs) under consideration to show its performance. The results of the simulation indicate that a comparison with that of the Particle Swarm Optimization-Linear Descending Inertia Weight (PSO-LDIW) and the CSO shows that our proposed CSO-LDIW can schedule task effectively on cloud resource with a promising makespan time.","PeriodicalId":411198,"journal":{"name":"Proceedings of the 2019 3rd High Performance Computing and Cluster Technologies Conference","volume":"273 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-06-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116435935","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：