Pub Date : 2019-05-01DOI: 10.1109/DDCLS.2019.8908843
Shali Yu, Senping Tian
In this paper, based on the Kinetis 60 chip of Lanzhou Electronics, a two-wheeled self-balancing intelligent vehicle is designed. The built-in solid-state gyroscope is used to judge the status in vehicle body system. By using the PID algorithm, the motor can be driven to achieve two-wheel self-balancing function. Moreover, we also can get the speed control function which is up to two point five meters every second.
{"title":"Design and Manufacture of Two-Wheeled Self-Balancing Vehicle Based on 32-Bit Single-Chip Microcomputer Control","authors":"Shali Yu, Senping Tian","doi":"10.1109/DDCLS.2019.8908843","DOIUrl":"https://doi.org/10.1109/DDCLS.2019.8908843","url":null,"abstract":"In this paper, based on the Kinetis 60 chip of Lanzhou Electronics, a two-wheeled self-balancing intelligent vehicle is designed. The built-in solid-state gyroscope is used to judge the status in vehicle body system. By using the PID algorithm, the motor can be driven to achieve two-wheel self-balancing function. Moreover, we also can get the speed control function which is up to two point five meters every second.","PeriodicalId":6699,"journal":{"name":"2019 IEEE 8th Data Driven Control and Learning Systems Conference (DDCLS)","volume":"47 10 1","pages":"175-179"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82767090","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 : 2019-05-01DOI: 10.1109/DDCLS.2019.8908832
Jian Hou, Chengcong Lv, Aihua Zhang, E. Xu
The density peak based clustering algorithm is presented by assuming that cluster centers are local density peaks, and utilizes local density relationship to detect cluster centers. This algorithm has been shown to be effective and efficient in some experiments. However, by studying the clustering mechanism in depth, we find that it may not be appropriate to treat density peaks as cluster centers in some cases. On one hand, the cluster centers obtained this way are often inconsistent with human intuition. On the other hand, local density difference across clusters is likely to influence the cluster center identification result. To relieve this problem, we present centerness as an alternative criterion of cluster center detection. The centerness criterion reflects to which degree the neighborhood of one data is filled with the nearest neighbors evenly, and is calculated with a histogram based method in our approach. By selecting cluster centers from centerness peaks, the clustering can be accomplished in a similar way as density peak algorithm. Our approach relieves the aforementioned problems of density peak algorithm, and performs well in experiments with synthetic and real datasets.
{"title":"Centerness Peak Based Clustering and Image Segmentation","authors":"Jian Hou, Chengcong Lv, Aihua Zhang, E. Xu","doi":"10.1109/DDCLS.2019.8908832","DOIUrl":"https://doi.org/10.1109/DDCLS.2019.8908832","url":null,"abstract":"The density peak based clustering algorithm is presented by assuming that cluster centers are local density peaks, and utilizes local density relationship to detect cluster centers. This algorithm has been shown to be effective and efficient in some experiments. However, by studying the clustering mechanism in depth, we find that it may not be appropriate to treat density peaks as cluster centers in some cases. On one hand, the cluster centers obtained this way are often inconsistent with human intuition. On the other hand, local density difference across clusters is likely to influence the cluster center identification result. To relieve this problem, we present centerness as an alternative criterion of cluster center detection. The centerness criterion reflects to which degree the neighborhood of one data is filled with the nearest neighbors evenly, and is calculated with a histogram based method in our approach. By selecting cluster centers from centerness peaks, the clustering can be accomplished in a similar way as density peak algorithm. Our approach relieves the aforementioned problems of density peak algorithm, and performs well in experiments with synthetic and real datasets.","PeriodicalId":6699,"journal":{"name":"2019 IEEE 8th Data Driven Control and Learning Systems Conference (DDCLS)","volume":"192 1","pages":"266-270"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"82794721","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 : 2019-05-01DOI: 10.1109/DDCLS.2019.8909075
D. Lu, Z. Hou
The current video background image extraction methods mainly obtain the gray background image, and the gray image processing is very sensitive to the interference noise, which brings great difficulty in detecting and tracking of moving target accurately. In order to overcome the above problems, a novel color background image extraction method is proposed using the idea of model free adaptive control method. The method introduces the pseudo-Jacobian matrix of the system and combines RGB three-channel historical data of pixels to establish the color background image extraction and update. The proposed method that under different video conditions is compared with the traditional gray background image extraction methods. The results show that the method can extract the color background image intuitively, and the separated foreground is closer to the ground truth of the video target.
{"title":"MIMO Model-Free Adaptive Control Color Background Image Extraction to Video","authors":"D. Lu, Z. Hou","doi":"10.1109/DDCLS.2019.8909075","DOIUrl":"https://doi.org/10.1109/DDCLS.2019.8909075","url":null,"abstract":"The current video background image extraction methods mainly obtain the gray background image, and the gray image processing is very sensitive to the interference noise, which brings great difficulty in detecting and tracking of moving target accurately. In order to overcome the above problems, a novel color background image extraction method is proposed using the idea of model free adaptive control method. The method introduces the pseudo-Jacobian matrix of the system and combines RGB three-channel historical data of pixels to establish the color background image extraction and update. The proposed method that under different video conditions is compared with the traditional gray background image extraction methods. The results show that the method can extract the color background image intuitively, and the separated foreground is closer to the ground truth of the video target.","PeriodicalId":6699,"journal":{"name":"2019 IEEE 8th Data Driven Control and Learning Systems Conference (DDCLS)","volume":"58 1","pages":"1122-1127"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86773264","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 : 2019-05-01DOI: 10.1109/DDCLS.2019.8909062
Dazi Li, Yu Zheng, Tianheng Song, Q. Jin
Reinforcement learning is considered to be one of the main methods of general artificial intelligence, which can realize self-learning of machines through interaction with the environment. In this paper, a modified version of deep reinforcement learning algorithm based on the Actor-Critic framework is proposed. Unlike traditional updated methods, the algorithm proposed in this paper adopts a special on-policy method, which we called Accelerated Linear Approximation Method in Deep Actor-Critic Framework (ALA-AC). When the network is trained to a certain extent, the networks' parameters of some layers are frozen, and the remaining layers' parameters are trained for better strategy and faster training speed.
强化学习被认为是通用人工智能的主要方法之一，它可以通过与环境的交互实现机器的自学习。本文提出了一种基于Actor-Critic框架的深度强化学习改进算法。与传统的更新方法不同，本文提出的算法采用了一种特殊的on-policy方法，我们称之为Deep actor - critical Framework (ALA-AC)中的加速线性逼近方法。当网络训练到一定程度时，部分层的网络参数被冻结，剩余层的网络参数继续训练，以获得更好的训练策略和更快的训练速度。
{"title":"An Accelerated Linear Approximation Method in Deep Actor-Critic Framework","authors":"Dazi Li, Yu Zheng, Tianheng Song, Q. Jin","doi":"10.1109/DDCLS.2019.8909062","DOIUrl":"https://doi.org/10.1109/DDCLS.2019.8909062","url":null,"abstract":"Reinforcement learning is considered to be one of the main methods of general artificial intelligence, which can realize self-learning of machines through interaction with the environment. In this paper, a modified version of deep reinforcement learning algorithm based on the Actor-Critic framework is proposed. Unlike traditional updated methods, the algorithm proposed in this paper adopts a special on-policy method, which we called Accelerated Linear Approximation Method in Deep Actor-Critic Framework (ALA-AC). When the network is trained to a certain extent, the networks' parameters of some layers are frozen, and the remaining layers' parameters are trained for better strategy and faster training speed.","PeriodicalId":6699,"journal":{"name":"2019 IEEE 8th Data Driven Control and Learning Systems Conference (DDCLS)","volume":"2 1","pages":"87-92"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89091053","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 : 2019-05-01DOI: 10.1109/DDCLS.2019.8908975
Chang Zhao, Haijiang Zhu, Xuejing Wang
Although steel surface defect recognition based on 2D image data has been extensively researched over the last ten years, it is very difficult for the identification of the defects with depth information in these methods. This paper presents a recognition method of steel plate surface defect through the estimated 3D depth information. In this method, the 3D data of the steel plate surface are first reconstructed using structure from motion (SFM). Then 3D points of the defect are segmented from the 3D reconstructed result of the steel plate surface using a region-growing based 3D information segmentation method. Finally, normal map is estimated from the segmented 3D point cloud, and the smoothness threshold in the normal map is optimized to classify the defect region and other regions. In experiment, the steel plate specimens with different hole sizes and the non-injured region are prepared, and the defect region based 3D information is classified. Experimental results show that the proposed method is efficient and feasible.
{"title":"Steel Plate Surface Defect Recognition Method Based on Depth Information","authors":"Chang Zhao, Haijiang Zhu, Xuejing Wang","doi":"10.1109/DDCLS.2019.8908975","DOIUrl":"https://doi.org/10.1109/DDCLS.2019.8908975","url":null,"abstract":"Although steel surface defect recognition based on 2D image data has been extensively researched over the last ten years, it is very difficult for the identification of the defects with depth information in these methods. This paper presents a recognition method of steel plate surface defect through the estimated 3D depth information. In this method, the 3D data of the steel plate surface are first reconstructed using structure from motion (SFM). Then 3D points of the defect are segmented from the 3D reconstructed result of the steel plate surface using a region-growing based 3D information segmentation method. Finally, normal map is estimated from the segmented 3D point cloud, and the smoothness threshold in the normal map is optimized to classify the defect region and other regions. In experiment, the steel plate specimens with different hole sizes and the non-injured region are prepared, and the defect region based 3D information is classified. Experimental results show that the proposed method is efficient and feasible.","PeriodicalId":6699,"journal":{"name":"2019 IEEE 8th Data Driven Control and Learning Systems Conference (DDCLS)","volume":"45 6 1","pages":"322-327"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83028402","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 : 2019-05-01DOI: 10.1109/DDCLS.2019.8908835
Shida Liu, Z. Hou, Yuan Guo, Lei Guo
In this work, a novel robust model free adaptive control (Ro-MFAC) algorithm is proposed for a class of discrete nonlinear systems existing both large time delay and disturbance. The main feather of Ro-MFAC is that the controller is designed only based on the input and output data of the system by using a new dynamic linearization technique with a time-varying parameter termed pseudo gradient. Moreover, by combining a novel augmented pseudo gradient, the Ro-MFAC can effectively suppress the system disturbance, such that the Ro-MFAC has strong robustness. Meanwhile, by using the tracking differentiators, the Ro-MFAC controller can also deal with the time delay existing in the system. Furthermore, the numerical simulation results verify the effectiveness of proposed Ro-MFAC.
{"title":"A Novel Modified Robust Model-Free Adaptive Control Method for a Class of Nonlinear Systems with Time Delay","authors":"Shida Liu, Z. Hou, Yuan Guo, Lei Guo","doi":"10.1109/DDCLS.2019.8908835","DOIUrl":"https://doi.org/10.1109/DDCLS.2019.8908835","url":null,"abstract":"In this work, a novel robust model free adaptive control (Ro-MFAC) algorithm is proposed for a class of discrete nonlinear systems existing both large time delay and disturbance. The main feather of Ro-MFAC is that the controller is designed only based on the input and output data of the system by using a new dynamic linearization technique with a time-varying parameter termed pseudo gradient. Moreover, by combining a novel augmented pseudo gradient, the Ro-MFAC can effectively suppress the system disturbance, such that the Ro-MFAC has strong robustness. Meanwhile, by using the tracking differentiators, the Ro-MFAC controller can also deal with the time delay existing in the system. Furthermore, the numerical simulation results verify the effectiveness of proposed Ro-MFAC.","PeriodicalId":6699,"journal":{"name":"2019 IEEE 8th Data Driven Control and Learning Systems Conference (DDCLS)","volume":"21 1","pages":"1329-1334"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83055404","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 : 2019-05-01DOI: 10.1109/DDCLS.2019.8908998
A. Zhang, Chengcong Lv, Xing Huo, Zhiyong She
Principal component regression (PCR) is not only a kind of multivariate statistical method, but also a type of data-driven method. The improved PCR (IPCR) optimizes the performance of fault detection for Tennessee Eastman process (TEP). IPCR could solve the unsatisfactory detection performance generated by the incomplete sample decomposition. Multiple IPCR (MIPCR) is a novel improved method relative to IPCR. It uses multiple quality variables to detect product quality at the same time. And the results, obtained via MIPCR, are fused. Then screening the variables via the fault performance is done. Simulations for Tennessee Eastman process (TEP) are presented with PCR, IPCR and MIPCR. Via the simulations, the validity and superiority of MIPCR are all verified.
{"title":"A Novel Method of Fault Detection Method for TEP based MIPCR","authors":"A. Zhang, Chengcong Lv, Xing Huo, Zhiyong She","doi":"10.1109/DDCLS.2019.8908998","DOIUrl":"https://doi.org/10.1109/DDCLS.2019.8908998","url":null,"abstract":"Principal component regression (PCR) is not only a kind of multivariate statistical method, but also a type of data-driven method. The improved PCR (IPCR) optimizes the performance of fault detection for Tennessee Eastman process (TEP). IPCR could solve the unsatisfactory detection performance generated by the incomplete sample decomposition. Multiple IPCR (MIPCR) is a novel improved method relative to IPCR. It uses multiple quality variables to detect product quality at the same time. And the results, obtained via MIPCR, are fused. Then screening the variables via the fault performance is done. Simulations for Tennessee Eastman process (TEP) are presented with PCR, IPCR and MIPCR. Via the simulations, the validity and superiority of MIPCR are all verified.","PeriodicalId":6699,"journal":{"name":"2019 IEEE 8th Data Driven Control and Learning Systems Conference (DDCLS)","volume":"184 4 1","pages":"388-393"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81047704","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 : 2019-05-01DOI: 10.1109/DDCLS.2019.8908880
Hui-Min Shao, Jianguo Wang, Yu Wang, Yuan Yao, Junjiang Liu
Emotions are closely related to people's work and life. Emotional analysis and recognition is not only an urgent need to solve certain mental illnesses, but also has broad application prospects in the fields of human-computer interaction, entertainment and medical care. Therefore, it is of great value to classify emotional EEG signals. This paper introduces CNN(Convolutional Neural Networks)into the process of emotional EEG recognition. The innovation of this method is to adjustthe convolution kernel of the CNN to adapt to the input of EEG signals. The classification accuracy of 0.8579 is achieved in the three-classification emotional EEG signal.
{"title":"EEG-Based Emotion Recognition with Deep Convolution Neural Network","authors":"Hui-Min Shao, Jianguo Wang, Yu Wang, Yuan Yao, Junjiang Liu","doi":"10.1109/DDCLS.2019.8908880","DOIUrl":"https://doi.org/10.1109/DDCLS.2019.8908880","url":null,"abstract":"Emotions are closely related to people's work and life. Emotional analysis and recognition is not only an urgent need to solve certain mental illnesses, but also has broad application prospects in the fields of human-computer interaction, entertainment and medical care. Therefore, it is of great value to classify emotional EEG signals. This paper introduces CNN(Convolutional Neural Networks)into the process of emotional EEG recognition. The innovation of this method is to adjustthe convolution kernel of the CNN to adapt to the input of EEG signals. The classification accuracy of 0.8579 is achieved in the three-classification emotional EEG signal.","PeriodicalId":6699,"journal":{"name":"2019 IEEE 8th Data Driven Control and Learning Systems Conference (DDCLS)","volume":"30 1","pages":"1225-1229"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"83386355","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 : 2019-05-01DOI: 10.1109/ddcls.2019.8908939
Jun Zhang, Shengliang Hu, Lingang Wu, Xueman Fan, Qing Yang
In order to cope with the threat of new type anti-ship missiles in active service, an exploratory study on the air-floating corner reflectors is carried out. Firstly, the reasonable placement position of the dilute air-floating corner reflectors is analyzed theoretically. Then, the high resolution range profile of air-floating corner reflectors and warships are obtained by CST simulation. Finally, the similarity of the above two is measured based on the average Euclidean distance. The results show that the five kind of air-floating corner reflectors propounded at the end of the paper have a high similarity to the ship target in high resolution range profile.
{"title":"Air-floating Corner Reflectors Dilution Jamming Placement Position","authors":"Jun Zhang, Shengliang Hu, Lingang Wu, Xueman Fan, Qing Yang","doi":"10.1109/ddcls.2019.8908939","DOIUrl":"https://doi.org/10.1109/ddcls.2019.8908939","url":null,"abstract":"In order to cope with the threat of new type anti-ship missiles in active service, an exploratory study on the air-floating corner reflectors is carried out. Firstly, the reasonable placement position of the dilute air-floating corner reflectors is analyzed theoretically. Then, the high resolution range profile of air-floating corner reflectors and warships are obtained by CST simulation. Finally, the similarity of the above two is measured based on the average Euclidean distance. The results show that the five kind of air-floating corner reflectors propounded at the end of the paper have a high similarity to the ship target in high resolution range profile.","PeriodicalId":6699,"journal":{"name":"2019 IEEE 8th Data Driven Control and Learning Systems Conference (DDCLS)","volume":"7 1","pages":"993-997"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88620038","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 an economic and reliable transportation system, rounding autonomous guided vehicle is widely researched and implemented in logistics. However, higher automation implies less involving of manual control, which makes the unattended workshop prone to malicious attacks. Since the operation of rounding autonomous guided vehicle system largely depends on the accuracy of scheduling strategy, authenticity of rounding autonomous guided vehicle position must be preserved to avoid collision, priority breach, steal, etc. In order to ensure the correctness of positioning, a novel location acquisition and authentication scheme is proposed in this paper, with the help of message authentication code and verifiable threshold secret sharing. According to security and performance analysis, our scheme is resistant against chosen plaintext attack and feasible in rounding autonomous guided vehicle environment.
{"title":"On Authenticity Preservation of Positioning in Rounding Autonomous Guided Vehicle","authors":"Lu Wang, Wenjuan Dong, Xin-Gang Wang, Hongliang Liu, Hongtao Qu, Yudong Xing, Darong Huang","doi":"10.1109/DDCLS.2019.8908962","DOIUrl":"https://doi.org/10.1109/DDCLS.2019.8908962","url":null,"abstract":"As an economic and reliable transportation system, rounding autonomous guided vehicle is widely researched and implemented in logistics. However, higher automation implies less involving of manual control, which makes the unattended workshop prone to malicious attacks. Since the operation of rounding autonomous guided vehicle system largely depends on the accuracy of scheduling strategy, authenticity of rounding autonomous guided vehicle position must be preserved to avoid collision, priority breach, steal, etc. In order to ensure the correctness of positioning, a novel location acquisition and authentication scheme is proposed in this paper, with the help of message authentication code and verifiable threshold secret sharing. According to security and performance analysis, our scheme is resistant against chosen plaintext attack and feasible in rounding autonomous guided vehicle environment.","PeriodicalId":6699,"journal":{"name":"2019 IEEE 8th Data Driven Control and Learning Systems Conference (DDCLS)","volume":"102 1","pages":"24-28"},"PeriodicalIF":0.0,"publicationDate":"2019-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"89281038","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：