Traveling Salesman Problem (TSP) is one of the most famous NP-hard problems which is hard to find an optimal solution. Many heuristic algorithms are applied to find a suboptimal solution in a limited time. In this paper, we employ a Genetic Algorithm (GA) to solve the TSP, and a further study is conducted by evaluating the performance of different crossover and mutation methods with a heuristic strategy. Four experiments with different parameters are designed, which apply instances from benchmark TSPLIB. Partial-mapped crossover and rotate mutation with offspring-parent competition strategy has shown efficient gets the best results.
{"title":"Genetic algorithm for Traveling Salesman Problem","authors":"Haojie Xu, Yisu Ge, Guodao Zhang","doi":"10.1145/3581792.3581798","DOIUrl":"https://doi.org/10.1145/3581792.3581798","url":null,"abstract":"Traveling Salesman Problem (TSP) is one of the most famous NP-hard problems which is hard to find an optimal solution. Many heuristic algorithms are applied to find a suboptimal solution in a limited time. In this paper, we employ a Genetic Algorithm (GA) to solve the TSP, and a further study is conducted by evaluating the performance of different crossover and mutation methods with a heuristic strategy. Four experiments with different parameters are designed, which apply instances from benchmark TSPLIB. Partial-mapped crossover and rotate mutation with offspring-parent competition strategy has shown efficient gets the best results.","PeriodicalId":436413,"journal":{"name":"Proceedings of the 2022 5th International Conference on Computational Intelligence and Intelligent Systems","volume":"76 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127442865","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 physical properties of rough surfaces are important research objects in geometry and tribology. The reason why rough surfaces are widely used in many fields is that their spatial topologies are uneven geometric shapes. In order to simulate the spatial topology of the rough surface, based on Gaussian distribution, numerical filtering, topology analysis and mathematical derivation, a new simulation algorithm for accurately generating rough surfaces with different features is established with five parameters. Roughness parameters, autocorrelation parameters, anisotropy parameters can be precisely controlled by algorithms, and the parameters are independent of each other. After experimental verification, the simulation results generated by the algorithm are similar to the real shape, and the numerical statistical results tend to converge.
{"title":"The Spatial Topological Shape of the Rough Surface is Simulated and Generated by a New Gaussian Filtering Algorithm","authors":"Jianan Zhang, Min Yang, Can Zhao, Cheng-Wu Liu","doi":"10.1145/3581792.3581797","DOIUrl":"https://doi.org/10.1145/3581792.3581797","url":null,"abstract":"The physical properties of rough surfaces are important research objects in geometry and tribology. The reason why rough surfaces are widely used in many fields is that their spatial topologies are uneven geometric shapes. In order to simulate the spatial topology of the rough surface, based on Gaussian distribution, numerical filtering, topology analysis and mathematical derivation, a new simulation algorithm for accurately generating rough surfaces with different features is established with five parameters. Roughness parameters, autocorrelation parameters, anisotropy parameters can be precisely controlled by algorithms, and the parameters are independent of each other. After experimental verification, the simulation results generated by the algorithm are similar to the real shape, and the numerical statistical results tend to converge.","PeriodicalId":436413,"journal":{"name":"Proceedings of the 2022 5th International Conference on Computational Intelligence and Intelligent Systems","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117239294","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}
Through statistical analysis, it is found that with the development of social and economic development, people's income level and quality of life continue to improve, more and more people begin to enjoy intelligent life. According to the survey the proportion of people who care for pets is increasing, and the demand for intelligent pet cages is also increasing. This project designs a shared intelligent pet management cage based on mobile internet to address the defects of traditional pet cages. The intelligent pet cage based on the Internet of Things also has many advantages such as remote control, scene control, timing control, intelligent linkage, and security prevention. Through WiFi technology, the intelligent service control terminal and environmental monitoring equipment are integrated to ensure the health of pets, monitor pet activities and facilitate interaction between pet owners at all times, so as to jointly create a civilized community and make pets properly integrated into people's lives.
{"title":"Research on the Design of Shared Intelligent Pet Management Cage in the Context of Mobile Internet","authors":"Xiaolong Hu, Ruiting Zhang, Zefan Zhang","doi":"10.1145/3581792.3581806","DOIUrl":"https://doi.org/10.1145/3581792.3581806","url":null,"abstract":"Through statistical analysis, it is found that with the development of social and economic development, people's income level and quality of life continue to improve, more and more people begin to enjoy intelligent life. According to the survey the proportion of people who care for pets is increasing, and the demand for intelligent pet cages is also increasing. This project designs a shared intelligent pet management cage based on mobile internet to address the defects of traditional pet cages. The intelligent pet cage based on the Internet of Things also has many advantages such as remote control, scene control, timing control, intelligent linkage, and security prevention. Through WiFi technology, the intelligent service control terminal and environmental monitoring equipment are integrated to ensure the health of pets, monitor pet activities and facilitate interaction between pet owners at all times, so as to jointly create a civilized community and make pets properly integrated into people's lives.","PeriodicalId":436413,"journal":{"name":"Proceedings of the 2022 5th International Conference on Computational Intelligence and Intelligent Systems","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128689343","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}
Most of the existing trackers have high performance and good effect, but it is difficult to have fast speed and can not meet the real-time requirements. Therefore, the development of target tracking system with high accuracy and good robustness has become an urgent task for researchers. This paper proposes to add an Region Proposal Network (RPN) module based on the structure of the traditional Siamese Network (SiamFC), calculate the template and branch of the Siamese sub network in advance in the reasoning stage, and decompose the tracking task into task nodes that are detected first and then matched for real-time online tracking. The experimental results on VOT2015, VOT2018 and OTB2015 data sets show that compared with other trackers, the model based on SiamRPN proposed in this paper shows better performance in achieving the dual goals of high accuracy and low robustness.
{"title":"Research on Object Tracking Technology Based on Region Proposal Siamese Network","authors":"Zhe Gu, Yanjing Lei, Di Cao, Lue Zhan","doi":"10.1145/3581792.3581793","DOIUrl":"https://doi.org/10.1145/3581792.3581793","url":null,"abstract":"Most of the existing trackers have high performance and good effect, but it is difficult to have fast speed and can not meet the real-time requirements. Therefore, the development of target tracking system with high accuracy and good robustness has become an urgent task for researchers. This paper proposes to add an Region Proposal Network (RPN) module based on the structure of the traditional Siamese Network (SiamFC), calculate the template and branch of the Siamese sub network in advance in the reasoning stage, and decompose the tracking task into task nodes that are detected first and then matched for real-time online tracking. The experimental results on VOT2015, VOT2018 and OTB2015 data sets show that compared with other trackers, the model based on SiamRPN proposed in this paper shows better performance in achieving the dual goals of high accuracy and low robustness.","PeriodicalId":436413,"journal":{"name":"Proceedings of the 2022 5th International Conference on Computational Intelligence and Intelligent Systems","volume":"2012 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116052587","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}
Sailing is not a new concept. The use of artificial intelligence (AI) within the field of sailing however is a relatively new concept. AI is being applied to a variety of different aspects within the field of sailing such as AI plotting unmanned vessels across the globe as well as in the optimization of racing vessels in a variety of prestigious regatta. This paper aims to explore the application of AI to the route creation and plotting aspect of AI in sailing, the objective being to create a system that efficiently assists sailors with their route creation within a complex environment. The approach used is through the creation of a model that uses an adapted A* (star) search algorithm where the weightings of the heuristic values used better represent the costs associated with the complex environment the algorithm operates in. The environment devised in this paper is a combination of geographical and meteorological data and coordinates to create a semi-dynamic environment in which the system operates. The resulting system successfully creates optimized routes within the semi-dynamic environment devised by the system.
{"title":"Route Optimization for Sailing Vessels using Artificial Intelligence Techniques","authors":"John M. Anderson, S. Sithungu, E. M. Ehlers","doi":"10.1145/3581792.3581803","DOIUrl":"https://doi.org/10.1145/3581792.3581803","url":null,"abstract":"Sailing is not a new concept. The use of artificial intelligence (AI) within the field of sailing however is a relatively new concept. AI is being applied to a variety of different aspects within the field of sailing such as AI plotting unmanned vessels across the globe as well as in the optimization of racing vessels in a variety of prestigious regatta. This paper aims to explore the application of AI to the route creation and plotting aspect of AI in sailing, the objective being to create a system that efficiently assists sailors with their route creation within a complex environment. The approach used is through the creation of a model that uses an adapted A* (star) search algorithm where the weightings of the heuristic values used better represent the costs associated with the complex environment the algorithm operates in. The environment devised in this paper is a combination of geographical and meteorological data and coordinates to create a semi-dynamic environment in which the system operates. The resulting system successfully creates optimized routes within the semi-dynamic environment devised by the system.","PeriodicalId":436413,"journal":{"name":"Proceedings of the 2022 5th International Conference on Computational Intelligence and Intelligent Systems","volume":"102 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121697173","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}
AdaptiveSGA is a method for achieving Adaptive Game Artificial Intelligence-Based Dynamic Difficulty Balancing through the Symbiotic Game Agent Model. Previous work has shown that AdaptiveSGA can achieve Dynamic Difficulty Balancing in simulated soccer by effectively changing a team's strategy based on the opponent's performance. AdaptiveSGA pre-existing strategies and switches between them during runtime to increase the game's replayability by adapting the challenge it poses to the human player. Although this method works, its limitation is that if the human player surpasses the most intelligent strategy of the computer opponent, there is no way for the model to generate a new strategy during runtime that can potentially overcome the human player. AdaptiveSGA can only maintain engagement with the human player if the human player has not overcome the best strategy for the pool of pre-existing strategies. Current work addresses this limitation by introducing an Evolution Symbiont Agent whose purpose is to generate new strategies in real-time (during gameplay) through evolutionary mechanisms using Gene Expression Programming. Experimental results show that the presence of the evolution symbiont agent can use Gene Expression Programming to generate strategies capable of outperforming an opposing strategy.
{"title":"A Gene Expression Programming Inspired Evolution Symbiont Agent for Real-Time Strategy Generation","authors":"S. Sithungu, E. M. Ehlers","doi":"10.1145/3581792.3581801","DOIUrl":"https://doi.org/10.1145/3581792.3581801","url":null,"abstract":"AdaptiveSGA is a method for achieving Adaptive Game Artificial Intelligence-Based Dynamic Difficulty Balancing through the Symbiotic Game Agent Model. Previous work has shown that AdaptiveSGA can achieve Dynamic Difficulty Balancing in simulated soccer by effectively changing a team's strategy based on the opponent's performance. AdaptiveSGA pre-existing strategies and switches between them during runtime to increase the game's replayability by adapting the challenge it poses to the human player. Although this method works, its limitation is that if the human player surpasses the most intelligent strategy of the computer opponent, there is no way for the model to generate a new strategy during runtime that can potentially overcome the human player. AdaptiveSGA can only maintain engagement with the human player if the human player has not overcome the best strategy for the pool of pre-existing strategies. Current work addresses this limitation by introducing an Evolution Symbiont Agent whose purpose is to generate new strategies in real-time (during gameplay) through evolutionary mechanisms using Gene Expression Programming. Experimental results show that the presence of the evolution symbiont agent can use Gene Expression Programming to generate strategies capable of outperforming an opposing strategy.","PeriodicalId":436413,"journal":{"name":"Proceedings of the 2022 5th International Conference on Computational Intelligence and Intelligent Systems","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133318519","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}
Zhe Gu, Yanjing Lei, Sixian Chan, Di Cao, Kongkai Zhang
With the increasing urbanization and the popularity of traffic video surveillance, and the rapid development of object detection algorithms, object detection of traffic events through video analysis has become possible. This paper proposes the design and implementation of a traffic event detection system based on video analysis. Firstly, the video stream is processed, mainly for video access and display, and the compression of neural networks achieves the network acceleration. Secondly, the structured information of vehicles is obtained by nighttime vehicle detection and joint detection and tracking. Finally, the car's driving behavior is analyzed through video calibration and video analysis. The system has been used online in many places in China and has achieved remarkable results.
{"title":"Traffic Incident Detection System Based on Video Analysis","authors":"Zhe Gu, Yanjing Lei, Sixian Chan, Di Cao, Kongkai Zhang","doi":"10.1145/3581792.3581795","DOIUrl":"https://doi.org/10.1145/3581792.3581795","url":null,"abstract":"With the increasing urbanization and the popularity of traffic video surveillance, and the rapid development of object detection algorithms, object detection of traffic events through video analysis has become possible. This paper proposes the design and implementation of a traffic event detection system based on video analysis. Firstly, the video stream is processed, mainly for video access and display, and the compression of neural networks achieves the network acceleration. Secondly, the structured information of vehicles is obtained by nighttime vehicle detection and joint detection and tracking. Finally, the car's driving behavior is analyzed through video calibration and video analysis. The system has been used online in many places in China and has achieved remarkable results.","PeriodicalId":436413,"journal":{"name":"Proceedings of the 2022 5th International Conference on Computational Intelligence and Intelligent Systems","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114608559","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}
Generative Adversarial Networks (GAN) are approaches that are utilized for data augmentation, which facilitates the development of more accurate detection models for unusual or unbalanced datasets. Computer-assisted diagnostic methods may be made more reliable by using synthetic pictures generated by GAN. Generative adversarial networks are challenging to train because too unpredictable training dynamics may occur throughout the learning process, such as model collapse and vanishing gradients. For accurate and faster results the GAN network need to trained in parallel and distributed manner. We enhance the speed and precision of the Deep Convolutional Generative Adversarial Networks (DCGAN) architecture by using its parallelism and executing it on High-Performance Computing platforms. The effective analysis of a DCGAN in Graphic Processing Unit and Tensor Processing Unit platforms in which each layer execution pattern is analyzed. The bottleneck is identified for the GAN structure for each execution platforms. The Central Processing Unit is capable of processing neural network models, but it requires a great deal of time to do it. Graphic Processing Unit in contrast, side, are a hundred times quicker than CPUs for Neural Networks, however, they are prohibitively expensive compared to CPUs. Using the systolic array structure, TPU performs well on neural networks with high batch sizes but in GAN the shift between CPU and TPU is huge so it does not perform well.
{"title":"Single Node Acceleration of Generative Adversarial Networks using HPC for Image Analytics","authors":"A. Ravikumar, H. Sriraman","doi":"10.1145/3581792.3581802","DOIUrl":"https://doi.org/10.1145/3581792.3581802","url":null,"abstract":"Generative Adversarial Networks (GAN) are approaches that are utilized for data augmentation, which facilitates the development of more accurate detection models for unusual or unbalanced datasets. Computer-assisted diagnostic methods may be made more reliable by using synthetic pictures generated by GAN. Generative adversarial networks are challenging to train because too unpredictable training dynamics may occur throughout the learning process, such as model collapse and vanishing gradients. For accurate and faster results the GAN network need to trained in parallel and distributed manner. We enhance the speed and precision of the Deep Convolutional Generative Adversarial Networks (DCGAN) architecture by using its parallelism and executing it on High-Performance Computing platforms. The effective analysis of a DCGAN in Graphic Processing Unit and Tensor Processing Unit platforms in which each layer execution pattern is analyzed. The bottleneck is identified for the GAN structure for each execution platforms. The Central Processing Unit is capable of processing neural network models, but it requires a great deal of time to do it. Graphic Processing Unit in contrast, side, are a hundred times quicker than CPUs for Neural Networks, however, they are prohibitively expensive compared to CPUs. Using the systolic array structure, TPU performs well on neural networks with high batch sizes but in GAN the shift between CPU and TPU is huge so it does not perform well.","PeriodicalId":436413,"journal":{"name":"Proceedings of the 2022 5th International Conference on Computational Intelligence and Intelligent Systems","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122205431","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}
Many methods have been applied to image segmentation, including unsupervised, supervised, and even deep learning-based models. Semantic and instance segmentation are the two most widely researched forms of segmentation. It is of value to use multiple methods to segment an image. In this paper, we present an image segmentation ensemble methodology. Multiple image segmentation methods are applied to an image and merged to create one segmentation using the proposed method. The technique uses the Jaccard index algorithm, sometimes called the Jaccard similarity coefficient and commonly known as Intersection over Union (IoU). This resulted in better segmentation results than the respective individual segmentation methods. This experiment was applied to mathematical expression recognition (MER), with the expressions taken from blackboards with varying degrees of noise, and lighting conditions, from different classroom environments. A summary of empirical results from the segmentation of multiple images is presented in the paper.
{"title":"Jaccard Index in Ensemble Image Segmentation: An Approach","authors":"Daniel Ogwok, E. M. Ehlers","doi":"10.1145/3581792.3581794","DOIUrl":"https://doi.org/10.1145/3581792.3581794","url":null,"abstract":"Many methods have been applied to image segmentation, including unsupervised, supervised, and even deep learning-based models. Semantic and instance segmentation are the two most widely researched forms of segmentation. It is of value to use multiple methods to segment an image. In this paper, we present an image segmentation ensemble methodology. Multiple image segmentation methods are applied to an image and merged to create one segmentation using the proposed method. The technique uses the Jaccard index algorithm, sometimes called the Jaccard similarity coefficient and commonly known as Intersection over Union (IoU). This resulted in better segmentation results than the respective individual segmentation methods. This experiment was applied to mathematical expression recognition (MER), with the expressions taken from blackboards with varying degrees of noise, and lighting conditions, from different classroom environments. A summary of empirical results from the segmentation of multiple images is presented in the paper.","PeriodicalId":436413,"journal":{"name":"Proceedings of the 2022 5th International Conference on Computational Intelligence and Intelligent Systems","volume":"106 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124104394","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}
As a means of transportation, bicycle has brought great convenience for human travel and exercise. With the popularization of bicycle, more and more cross-country time trial bicycle races have begun to rise. Based on this, this paper adopts Pontryagin's Maximum Principles and analytic hierarchy Process respectively to establish mechanical model and terrain analysis model, and evaluates the comprehensive quality of racers based on their race types, while considering the influence of various factors such as weather environment. In this paper, the power distribution of racers in different terrains and time periods is analyzed, and the model is applied to a typical track to obtain the power distribution diagram of racers achieving the best results.
{"title":"Stage-Terrain-Power Model Based on Analytic Hierarchy Process","authors":"Boyu Zang, Jishen Zhao","doi":"10.1145/3581792.3581804","DOIUrl":"https://doi.org/10.1145/3581792.3581804","url":null,"abstract":"As a means of transportation, bicycle has brought great convenience for human travel and exercise. With the popularization of bicycle, more and more cross-country time trial bicycle races have begun to rise. Based on this, this paper adopts Pontryagin's Maximum Principles and analytic hierarchy Process respectively to establish mechanical model and terrain analysis model, and evaluates the comprehensive quality of racers based on their race types, while considering the influence of various factors such as weather environment. In this paper, the power distribution of racers in different terrains and time periods is analyzed, and the model is applied to a typical track to obtain the power distribution diagram of racers achieving the best results.","PeriodicalId":436413,"journal":{"name":"Proceedings of the 2022 5th International Conference on Computational Intelligence and Intelligent Systems","volume":"56 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133792148","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：