Pub Date : 2021-11-01DOI: 10.1109/CONF-SPML54095.2021.00048
Li Yuan
Remote sensing image classification occupies a vital place in earth observation and has many applications in military and civil fields. It can be divided into two typical tasks: high-resolution remote sensing images and hyperspectral image classification. However, high-resolution remote sensing and hyperspectral image classification cannot facilitate all features and achieve good accuracy with traditional methods. As deep learning methods, especially the convolutional neural networks (CNN), are developing rapidly, image classification methods based on CNN can perform well and provide new ideas for remote sensing classification. In this paper, we first review the background of typical remote sensing images and CNN. Then, we provide an overview of the development of the CNN model. After that, we point out some existing problems that we need to overcome for the CNN methods. Finally, the corresponding solutions are provided, and future work is presented with the analysis of some popular methods.
{"title":"Remote Sensing Image Classification Methods Based on CNN: Challenge and Trends","authors":"Li Yuan","doi":"10.1109/CONF-SPML54095.2021.00048","DOIUrl":"https://doi.org/10.1109/CONF-SPML54095.2021.00048","url":null,"abstract":"Remote sensing image classification occupies a vital place in earth observation and has many applications in military and civil fields. It can be divided into two typical tasks: high-resolution remote sensing images and hyperspectral image classification. However, high-resolution remote sensing and hyperspectral image classification cannot facilitate all features and achieve good accuracy with traditional methods. As deep learning methods, especially the convolutional neural networks (CNN), are developing rapidly, image classification methods based on CNN can perform well and provide new ideas for remote sensing classification. In this paper, we first review the background of typical remote sensing images and CNN. Then, we provide an overview of the development of the CNN model. After that, we point out some existing problems that we need to overcome for the CNN methods. Finally, the corresponding solutions are provided, and future work is presented with the analysis of some popular methods.","PeriodicalId":415094,"journal":{"name":"2021 International Conference on Signal Processing and Machine Learning (CONF-SPML)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115267601","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 : 2021-11-01DOI: 10.1109/CONF-SPML54095.2021.00038
Shikun Liu
Music tutor can provide practice advice for musical instrument leaners. The core is the combination of music theory knowledge, machine learning and chord recognition. Chord recognition is the basis of automatic music labeling, and plays an important role in music segmentation and audio matching. Aiming at the problem of low recognition rate of the same chord between different instruments, this paper uses an improved algorithm based on instantaneous frequency to extract Pitch Level Profile (PCP) features. Music instructor makes suggestions and plans for learners based on the mining data of chord recognition (accuracy rate, loudness difference, etc.) It can provide a more reasonable practice plan for beginners to make music teaching efficient.
{"title":"Music Tutor: Application of Chord Recognition in Music Teaching","authors":"Shikun Liu","doi":"10.1109/CONF-SPML54095.2021.00038","DOIUrl":"https://doi.org/10.1109/CONF-SPML54095.2021.00038","url":null,"abstract":"Music tutor can provide practice advice for musical instrument leaners. The core is the combination of music theory knowledge, machine learning and chord recognition. Chord recognition is the basis of automatic music labeling, and plays an important role in music segmentation and audio matching. Aiming at the problem of low recognition rate of the same chord between different instruments, this paper uses an improved algorithm based on instantaneous frequency to extract Pitch Level Profile (PCP) features. Music instructor makes suggestions and plans for learners based on the mining data of chord recognition (accuracy rate, loudness difference, etc.) It can provide a more reasonable practice plan for beginners to make music teaching efficient.","PeriodicalId":415094,"journal":{"name":"2021 International Conference on Signal Processing and Machine Learning (CONF-SPML)","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124771183","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 : 2021-11-01DOI: 10.1109/CONF-SPML54095.2021.00069
Lirui Liu
The purpose of this study was to investigate the ability to achieve self-navigation by robots in an unknown environment. An experiment was set up to collect the data. By installing a visual sensor on the robot, environment data and other crucial information were collected and analyzed efficiently. The results reveal that robots cannot recognize the environmental perception stage due to the limitation of existing computing and storage capabilities. The study findings may serve as a guide for further research on robotic intelligence.
{"title":"Intelligent Patrol Robot Based on Visual Machine Deep Learning","authors":"Lirui Liu","doi":"10.1109/CONF-SPML54095.2021.00069","DOIUrl":"https://doi.org/10.1109/CONF-SPML54095.2021.00069","url":null,"abstract":"The purpose of this study was to investigate the ability to achieve self-navigation by robots in an unknown environment. An experiment was set up to collect the data. By installing a visual sensor on the robot, environment data and other crucial information were collected and analyzed efficiently. The results reveal that robots cannot recognize the environmental perception stage due to the limitation of existing computing and storage capabilities. The study findings may serve as a guide for further research on robotic intelligence.","PeriodicalId":415094,"journal":{"name":"2021 International Conference on Signal Processing and Machine Learning (CONF-SPML)","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128273651","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 : 2021-11-01DOI: 10.1109/CONF-SPML54095.2021.00024
Bin Tan, Yinyin Peng, Jiugen Lin
Q-learning belongs to reinforcement learning and artificial intelligence learning algorithm. Reinforcement learning does not need external guidance; it interacts with the external environment through its own sensors. It maps the state of the external input environment to output action through continuous learning, and makes the corresponding reward value of this action the maxi-mum. In order to make the submersible have the ability to adapt to the environment independently, it can adjust the path automatically through its own learning. This paper proposes to introduce Q-learning mechanism in reinforcement learning to complete the adjustment of fuzzy rule strategy in un-known environment.
{"title":"A Local Path Planning Method Based on Q-Learning","authors":"Bin Tan, Yinyin Peng, Jiugen Lin","doi":"10.1109/CONF-SPML54095.2021.00024","DOIUrl":"https://doi.org/10.1109/CONF-SPML54095.2021.00024","url":null,"abstract":"Q-learning belongs to reinforcement learning and artificial intelligence learning algorithm. Reinforcement learning does not need external guidance; it interacts with the external environment through its own sensors. It maps the state of the external input environment to output action through continuous learning, and makes the corresponding reward value of this action the maxi-mum. In order to make the submersible have the ability to adapt to the environment independently, it can adjust the path automatically through its own learning. This paper proposes to introduce Q-learning mechanism in reinforcement learning to complete the adjustment of fuzzy rule strategy in un-known environment.","PeriodicalId":415094,"journal":{"name":"2021 International Conference on Signal Processing and Machine Learning (CONF-SPML)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129263339","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 : 2021-11-01DOI: 10.1109/CONF-SPML54095.2021.00012
Lingxuan Zhao
Based on the principle of closed-loop fiber optic gyroscope, the research results in the field of interferometric fiber optic gyroscope digital closed-loop system modeling and control were summarized in this paper. The PID control model has a relatively simple structure and has been widely used. The F-PID control model can effectively shorten the adjustment time, reduce the amount of overshoot, and has a strong anti-interference ability. The system identification modeling method of the closed-loop fiber optic gyroscope is simple to implement and can overcome the influence of white noise on the signal amplitude and phase detection. In view of the closed-loop fiber optic gyroscope model, the method of suppressing the dead zone of the fiber optic gyroscope was discussed. Based on the dynamic model of the closed-loop fiber optic gyroscope, the method to improve the angular acceleration tracking ability of the fiber optic gyroscope was analyzed. Finally, combined with the technological progress of optoelectronic devices, the future researches in the field of fiber optic gyroscope modeling and control were prospected.
{"title":"Research on Modeling and Control of Closed-loop Fiber Optic Gyroscope","authors":"Lingxuan Zhao","doi":"10.1109/CONF-SPML54095.2021.00012","DOIUrl":"https://doi.org/10.1109/CONF-SPML54095.2021.00012","url":null,"abstract":"Based on the principle of closed-loop fiber optic gyroscope, the research results in the field of interferometric fiber optic gyroscope digital closed-loop system modeling and control were summarized in this paper. The PID control model has a relatively simple structure and has been widely used. The F-PID control model can effectively shorten the adjustment time, reduce the amount of overshoot, and has a strong anti-interference ability. The system identification modeling method of the closed-loop fiber optic gyroscope is simple to implement and can overcome the influence of white noise on the signal amplitude and phase detection. In view of the closed-loop fiber optic gyroscope model, the method of suppressing the dead zone of the fiber optic gyroscope was discussed. Based on the dynamic model of the closed-loop fiber optic gyroscope, the method to improve the angular acceleration tracking ability of the fiber optic gyroscope was analyzed. Finally, combined with the technological progress of optoelectronic devices, the future researches in the field of fiber optic gyroscope modeling and control were prospected.","PeriodicalId":415094,"journal":{"name":"2021 International Conference on Signal Processing and Machine Learning (CONF-SPML)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129190108","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 : 2021-11-01DOI: 10.1109/CONF-SPML54095.2021.00035
Mingcun Liu, Ce Li, Rui Yan, Yunzhi Xu, Jingyi Qiao, Feng Yang
In urban construction, the defect detection and repair work of drainage pipe-lines are very important, and visual defect detection on pipeline inner surface has become a hot research issue in the application of computer vision and pipeline robot. However, it is still difficult to detect the defects automatically because it is limited by low-quality video and different models of robots. At present, most pipeline detection methods are implemented by pipeline robots equipped with high-definition cameras and manual recognition to find defects frame by frame. To cope with these issues, this paper proposes a method of visual pipeline defect detection enhanced by image restoration. In which, the image restoration using partial convolution is firstly proposed to impair the image that is locally occluded by the haulage rope, then the fast detection using enhanced image data is proposed for pipeline defects. By analyzing the influence of the restoration on the defect detection, the experiment results show that our method has produced significantly improved detection performance by the partial image restoration and it is an efficient method for the application of pipeline robot.
{"title":"Enhanced Visual Pipeline Defect Detection Using Partial Convolution Image Restoration","authors":"Mingcun Liu, Ce Li, Rui Yan, Yunzhi Xu, Jingyi Qiao, Feng Yang","doi":"10.1109/CONF-SPML54095.2021.00035","DOIUrl":"https://doi.org/10.1109/CONF-SPML54095.2021.00035","url":null,"abstract":"In urban construction, the defect detection and repair work of drainage pipe-lines are very important, and visual defect detection on pipeline inner surface has become a hot research issue in the application of computer vision and pipeline robot. However, it is still difficult to detect the defects automatically because it is limited by low-quality video and different models of robots. At present, most pipeline detection methods are implemented by pipeline robots equipped with high-definition cameras and manual recognition to find defects frame by frame. To cope with these issues, this paper proposes a method of visual pipeline defect detection enhanced by image restoration. In which, the image restoration using partial convolution is firstly proposed to impair the image that is locally occluded by the haulage rope, then the fast detection using enhanced image data is proposed for pipeline defects. By analyzing the influence of the restoration on the defect detection, the experiment results show that our method has produced significantly improved detection performance by the partial image restoration and it is an efficient method for the application of pipeline robot.","PeriodicalId":415094,"journal":{"name":"2021 International Conference on Signal Processing and Machine Learning (CONF-SPML)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121193307","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 : 2021-11-01DOI: 10.1109/CONF-SPML54095.2021.00021
Yiao Zhan
As the foundation of collaborative control between MASs, the problem of consensus has attracted the eyes of more and more relevant scholars and has become a vital research topic in the development of frontier theories of control disciplines. According to the remarkable feature of saving communication resource, event-triggered consensus control has been widely studied. This paper gives some researched event-triggered consensus controllers with different dynamics, and the corresponding trigger conditions. Then, through systematic analysis of the design of these consensus control methods, the idea of event-based consensus controller and the corresponding triggering conditions are revealed. Furthermore, consensus stability and Zeno behavior elimination methods are analyzed. Finally, some issues in the research of event-triggered control and show some hot and promising research topics are pointed out to be solved in the future.
{"title":"Research on The Consensus Problem of Multi-agent Systems via Event-Triggered Mechanism","authors":"Yiao Zhan","doi":"10.1109/CONF-SPML54095.2021.00021","DOIUrl":"https://doi.org/10.1109/CONF-SPML54095.2021.00021","url":null,"abstract":"As the foundation of collaborative control between MASs, the problem of consensus has attracted the eyes of more and more relevant scholars and has become a vital research topic in the development of frontier theories of control disciplines. According to the remarkable feature of saving communication resource, event-triggered consensus control has been widely studied. This paper gives some researched event-triggered consensus controllers with different dynamics, and the corresponding trigger conditions. Then, through systematic analysis of the design of these consensus control methods, the idea of event-based consensus controller and the corresponding triggering conditions are revealed. Furthermore, consensus stability and Zeno behavior elimination methods are analyzed. Finally, some issues in the research of event-triggered control and show some hot and promising research topics are pointed out to be solved in the future.","PeriodicalId":415094,"journal":{"name":"2021 International Conference on Signal Processing and Machine Learning (CONF-SPML)","volume":"126 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121915121","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 : 2021-11-01DOI: 10.1109/CONF-SPML54095.2021.00068
Xiangyu Liu
Face recognition has become one of the most popular computer technologies in the last ten years, backed by deep convolutional neural networks. It exploits its wide application in various commercial fields. Face recognition technology is relatively mature nowadays. Scientists and engineers have already implemented the necessary functions like face detection, landmarks extraction, and face identification. This paper will depict the necessary steps of those functions, and some popular face recognition libraries will also be introduced in Chapter 3. The paper aims to discuss the parameter settings of the open-source library face_recognition under real-world scenarios with distinct requirements and limitations. Finally, the paper will also go into two cases to analyze the influence of specific parameters and discuss some appropriate settings under different situations.
{"title":"Applicability of Face Recognition in Real-World Scenarios","authors":"Xiangyu Liu","doi":"10.1109/CONF-SPML54095.2021.00068","DOIUrl":"https://doi.org/10.1109/CONF-SPML54095.2021.00068","url":null,"abstract":"Face recognition has become one of the most popular computer technologies in the last ten years, backed by deep convolutional neural networks. It exploits its wide application in various commercial fields. Face recognition technology is relatively mature nowadays. Scientists and engineers have already implemented the necessary functions like face detection, landmarks extraction, and face identification. This paper will depict the necessary steps of those functions, and some popular face recognition libraries will also be introduced in Chapter 3. The paper aims to discuss the parameter settings of the open-source library face_recognition under real-world scenarios with distinct requirements and limitations. Finally, the paper will also go into two cases to analyze the influence of specific parameters and discuss some appropriate settings under different situations.","PeriodicalId":415094,"journal":{"name":"2021 International Conference on Signal Processing and Machine Learning (CONF-SPML)","volume":"82 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124552499","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 : 2021-11-01DOI: 10.1109/CONF-SPML54095.2021.00047
Yifan Chen
T Targeted at the existing complex structure, numerous switching components and high control difficulty of existing equalization circuit of lithium-ion battery series, this paper proposes an active equalization topology circuit based on multi-input transformer. The equalization circuit is composed of battery module, fly-wheel diode, MOS transistor and transformer. Based on the classification and summary of battery equalization topology, this paper analyzes and studies the principle of active equalization topology based on multi-input transformers. The working principle is simple, with the use of fewer devices. Matlab/Simulink is applied to build a model for simulation analysis, and the simulation results show that switching frequency and series module capacity have an impact on the equalization effects. The equalization comparison rate simulation of the series capacitor module and the single module indicates that the proposed topology has a faster equalization speed for multiple modules. The simulation results verify the validity of the proposed topology in voltage equalization between different modules.
{"title":"Research on Active Equalization Topology Based on the Multi-input Transformer","authors":"Yifan Chen","doi":"10.1109/CONF-SPML54095.2021.00047","DOIUrl":"https://doi.org/10.1109/CONF-SPML54095.2021.00047","url":null,"abstract":"T Targeted at the existing complex structure, numerous switching components and high control difficulty of existing equalization circuit of lithium-ion battery series, this paper proposes an active equalization topology circuit based on multi-input transformer. The equalization circuit is composed of battery module, fly-wheel diode, MOS transistor and transformer. Based on the classification and summary of battery equalization topology, this paper analyzes and studies the principle of active equalization topology based on multi-input transformers. The working principle is simple, with the use of fewer devices. Matlab/Simulink is applied to build a model for simulation analysis, and the simulation results show that switching frequency and series module capacity have an impact on the equalization effects. The equalization comparison rate simulation of the series capacitor module and the single module indicates that the proposed topology has a faster equalization speed for multiple modules. The simulation results verify the validity of the proposed topology in voltage equalization between different modules.","PeriodicalId":415094,"journal":{"name":"2021 International Conference on Signal Processing and Machine Learning (CONF-SPML)","volume":"2001 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128294751","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 : 2021-11-01DOI: 10.1109/CONF-SPML54095.2021.00011
Jizhao Lei, Minghui Li, Yihui Jin, Di Zhao, Huijun Wang, Yunhe Liu, Ruiliang Song, Wenliang Lin, Ke Wang
Research institutions around the world plan to build a simulation platform that links constellation configuration and protocols together to support the design and verification of key technologies in 6G satellite communication systems. An important issue to improve the reliability and efficiency of simulation verification is how to effectively transfer the parameters of link-level simulation and system-level simulation. In this paper, by optimizing the traditional ground-based EESM algorithm, 12 kinds of channels are fitted, and all L2S interface parameter $beta$ values under MCS are obtained, and a MCS is proposed for $beta$ fitting verification, and the fitting effect meets the specified error Required by 3GPP. The wideband CQI value is obtained through the simulation results of all links and based on the subband weighted CQI method. Then specify the MCS-CQI mapping table according to the CQI value, and simulate the link adaptive adjustment process through the mapping table. Finally, the feedback SNR and CQI are used to verify whether the corresponding BLER value meets the requirement of less than 10%.
{"title":"Key Parameter Mapping Method of Signal-To-Noise Ratio from Link Simulation to System Simulation","authors":"Jizhao Lei, Minghui Li, Yihui Jin, Di Zhao, Huijun Wang, Yunhe Liu, Ruiliang Song, Wenliang Lin, Ke Wang","doi":"10.1109/CONF-SPML54095.2021.00011","DOIUrl":"https://doi.org/10.1109/CONF-SPML54095.2021.00011","url":null,"abstract":"Research institutions around the world plan to build a simulation platform that links constellation configuration and protocols together to support the design and verification of key technologies in 6G satellite communication systems. An important issue to improve the reliability and efficiency of simulation verification is how to effectively transfer the parameters of link-level simulation and system-level simulation. In this paper, by optimizing the traditional ground-based EESM algorithm, 12 kinds of channels are fitted, and all L2S interface parameter $beta$ values under MCS are obtained, and a MCS is proposed for $beta$ fitting verification, and the fitting effect meets the specified error Required by 3GPP. The wideband CQI value is obtained through the simulation results of all links and based on the subband weighted CQI method. Then specify the MCS-CQI mapping table according to the CQI value, and simulate the link adaptive adjustment process through the mapping table. Finally, the feedback SNR and CQI are used to verify whether the corresponding BLER value meets the requirement of less than 10%.","PeriodicalId":415094,"journal":{"name":"2021 International Conference on Signal Processing and Machine Learning (CONF-SPML)","volume":"81 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125523159","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：