Pub Date : 2014-06-23DOI: 10.1109/INISTA.2014.6873613
Veli Bayar, Bora Akar, Uğur Yayan, H. Yavuz, A. Yazıcı
Autonomous mobile vehicles are used in many applications to realize special tasks. These tasks involve obstacle avoidance, target reaching and/or tracking. Such vehicles include the use of artificial intelligence to assist the vehicle's operator. Fuzzy logic can be used in the design of an autonomous vehicle to improve the classical control mechanisms. Classical robot control/decision mechanisms can give imperfect results due to sensor compensation errors or calculation costs. These drawbacks can be eliminated by using a combined fuzzy inference. In this study, we have modified the mobile robot ATEKS, which is an intelligent wheelchair, by introducing three fuzzy inference systems to realize goal reaching, obstacle avoidance and a controller for combined behavior selection. Designed fuzzy control system has been implemented on Robot Operating System (ROS) under Ubuntu 12.04 operating system and tested under Gazebo simulation platform. Simulation results verified faithful behavior outputs of ATEKS.
{"title":"Fuzzy logic based design of classical behaviors for mobile robots in ROS middleware","authors":"Veli Bayar, Bora Akar, Uğur Yayan, H. Yavuz, A. Yazıcı","doi":"10.1109/INISTA.2014.6873613","DOIUrl":"https://doi.org/10.1109/INISTA.2014.6873613","url":null,"abstract":"Autonomous mobile vehicles are used in many applications to realize special tasks. These tasks involve obstacle avoidance, target reaching and/or tracking. Such vehicles include the use of artificial intelligence to assist the vehicle's operator. Fuzzy logic can be used in the design of an autonomous vehicle to improve the classical control mechanisms. Classical robot control/decision mechanisms can give imperfect results due to sensor compensation errors or calculation costs. These drawbacks can be eliminated by using a combined fuzzy inference. In this study, we have modified the mobile robot ATEKS, which is an intelligent wheelchair, by introducing three fuzzy inference systems to realize goal reaching, obstacle avoidance and a controller for combined behavior selection. Designed fuzzy control system has been implemented on Robot Operating System (ROS) under Ubuntu 12.04 operating system and tested under Gazebo simulation platform. Simulation results verified faithful behavior outputs of ATEKS.","PeriodicalId":339652,"journal":{"name":"2014 IEEE International Symposium on Innovations in Intelligent Systems and Applications (INISTA) Proceedings","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121122089","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 : 2014-06-23DOI: 10.1109/INISTA.2014.6873622
Hamid Hadavi, H. Viktor, E. Paquet
Finding correspondences between deformable objects has wide application in many domains. In information retrieval, researchers may be interested in finding similar objects, while computer animation experts may be considering ways to morph shapes. The correspondence problem is especially challenging when the objects under consideration are suspect to non-rigid deformations, noise and/or distortions. In this paper, a novel method using Quantum Particle Swarm Optimization (QPSO) and Genetic Algorithms (GA) is presented to address this issue. In our QPSO-GA algorithm we formulate the problem of correspondence detection as an optimization problem over all possible mapping in between the geodesic distance matrices associated with two sets of point clouds. We proceed to identify the optimal mapping, by first applying Quantum Particle Swarm Optimization to the permutation matrices associated with their geodesic distance matrices and then employing Genetic Algorithms in order to guide the search. Experimental results suggest that our QPSO-GA algorithm is fast, scalable, and robust. Our method accurately identifies the correspondences between objects, even in the presence of noise and distortion.
{"title":"A Quantum Particle Swarm Optimization and Genetic Algorithm approach to the correspondence problem","authors":"Hamid Hadavi, H. Viktor, E. Paquet","doi":"10.1109/INISTA.2014.6873622","DOIUrl":"https://doi.org/10.1109/INISTA.2014.6873622","url":null,"abstract":"Finding correspondences between deformable objects has wide application in many domains. In information retrieval, researchers may be interested in finding similar objects, while computer animation experts may be considering ways to morph shapes. The correspondence problem is especially challenging when the objects under consideration are suspect to non-rigid deformations, noise and/or distortions. In this paper, a novel method using Quantum Particle Swarm Optimization (QPSO) and Genetic Algorithms (GA) is presented to address this issue. In our QPSO-GA algorithm we formulate the problem of correspondence detection as an optimization problem over all possible mapping in between the geodesic distance matrices associated with two sets of point clouds. We proceed to identify the optimal mapping, by first applying Quantum Particle Swarm Optimization to the permutation matrices associated with their geodesic distance matrices and then employing Genetic Algorithms in order to guide the search. Experimental results suggest that our QPSO-GA algorithm is fast, scalable, and robust. Our method accurately identifies the correspondences between objects, even in the presence of noise and distortion.","PeriodicalId":339652,"journal":{"name":"2014 IEEE International Symposium on Innovations in Intelligent Systems and Applications (INISTA) Proceedings","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129429498","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 : 2014-06-23DOI: 10.1109/INISTA.2014.6873590
E. Yesil, A. I. Savran, Cagri Guzay
In this study, an optimization based PID controller tuning method is proposed for load-frequency control (LFC) problem. The proposed Big Bang-Big Crunch 2 (BB-BC2) method is an extended version of the original BB-BC, which has a very fast convergence and less computational time. A two-area power system is modeled in Matlab-Simulink for simulations, and then the original BB-BC and the proposed BB-BC2 optimization methods are firstly compared with each other. Since BB-BC method is originally based on randomness these tests are repeated for 100 times and the benefit of the proposed BB-BC2 is shown. Afterwards, the performance of the proposed BB-BC2 algorithm is compared with three other PID tuning methods from literature. The simulation results verify the advantage of the proposed BB-BC2 algorithm to optimize the PID controllers as the load-frequency controller.
{"title":"Load frequency controller design using new Big Bang - Big Crunch 2 algorithm","authors":"E. Yesil, A. I. Savran, Cagri Guzay","doi":"10.1109/INISTA.2014.6873590","DOIUrl":"https://doi.org/10.1109/INISTA.2014.6873590","url":null,"abstract":"In this study, an optimization based PID controller tuning method is proposed for load-frequency control (LFC) problem. The proposed Big Bang-Big Crunch 2 (BB-BC2) method is an extended version of the original BB-BC, which has a very fast convergence and less computational time. A two-area power system is modeled in Matlab-Simulink for simulations, and then the original BB-BC and the proposed BB-BC2 optimization methods are firstly compared with each other. Since BB-BC method is originally based on randomness these tests are repeated for 100 times and the benefit of the proposed BB-BC2 is shown. Afterwards, the performance of the proposed BB-BC2 algorithm is compared with three other PID tuning methods from literature. The simulation results verify the advantage of the proposed BB-BC2 algorithm to optimize the PID controllers as the load-frequency controller.","PeriodicalId":339652,"journal":{"name":"2014 IEEE International Symposium on Innovations in Intelligent Systems and Applications (INISTA) Proceedings","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126694637","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 : 2014-06-23DOI: 10.1109/INISTA.2014.6873628
N. T. Artug, I. Goker, B. Bolat, Gokalp Tulum, O. Osman, M. Baslo
In this study a new dataset are prepared for neuromuscular diseases using scanning EMG method and four new features are extracted. These features are maximum amplitude, phase duration at the maximum amplitude, maximum amplitude times phase duration, and number of peaks. By using statistical values such as mean and variance, number of features has increased up to eight. This dataset was classified by using multi layer perceptron (MLP), support vector machines (SVM), k-nearest neighbours algorithm (k-NN), and radial basis function networks (RBF). The best accuracy is obtained as 97.78% with SVM algorithm and 3-NN algorithm.
{"title":"Feature extraction and classification of neuromuscular diseases using scanning EMG","authors":"N. T. Artug, I. Goker, B. Bolat, Gokalp Tulum, O. Osman, M. Baslo","doi":"10.1109/INISTA.2014.6873628","DOIUrl":"https://doi.org/10.1109/INISTA.2014.6873628","url":null,"abstract":"In this study a new dataset are prepared for neuromuscular diseases using scanning EMG method and four new features are extracted. These features are maximum amplitude, phase duration at the maximum amplitude, maximum amplitude times phase duration, and number of peaks. By using statistical values such as mean and variance, number of features has increased up to eight. This dataset was classified by using multi layer perceptron (MLP), support vector machines (SVM), k-nearest neighbours algorithm (k-NN), and radial basis function networks (RBF). The best accuracy is obtained as 97.78% with SVM algorithm and 3-NN algorithm.","PeriodicalId":339652,"journal":{"name":"2014 IEEE International Symposium on Innovations in Intelligent Systems and Applications (INISTA) Proceedings","volume":"203 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121433862","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 : 2014-06-23DOI: 10.1109/INISTA.2014.6873619
Sevcan Yilmaz, Y. Oysal
This paper introduces the architecture and learning procedure of dynamic adaptive neuro-fuzzy inference system (DANFIS) for nonlinear dynamical system modeling. In our DANIS model, IF part of the rules are comprised of Gaussian type membership functions and THEN part of the rules are differential equations of linear functions. In order to find optimal model parameters, a gradient based algorithm Broyden-Fletcher-Goldfarb-Shanno (BFGS) method is used. Gradients in this algorithm is calculated by using adjoint sensitivity method. To validate the model, two simulations, Van der Pol oscillator and tunnel diode circuit, are performed. Simulation results are also given to demonstrate the effectiveness of the proposed DANFIS with learning method.
{"title":"Nonlinear system modeling with dynamic adaptive neuro-fuzzy inference system","authors":"Sevcan Yilmaz, Y. Oysal","doi":"10.1109/INISTA.2014.6873619","DOIUrl":"https://doi.org/10.1109/INISTA.2014.6873619","url":null,"abstract":"This paper introduces the architecture and learning procedure of dynamic adaptive neuro-fuzzy inference system (DANFIS) for nonlinear dynamical system modeling. In our DANIS model, IF part of the rules are comprised of Gaussian type membership functions and THEN part of the rules are differential equations of linear functions. In order to find optimal model parameters, a gradient based algorithm Broyden-Fletcher-Goldfarb-Shanno (BFGS) method is used. Gradients in this algorithm is calculated by using adjoint sensitivity method. To validate the model, two simulations, Van der Pol oscillator and tunnel diode circuit, are performed. Simulation results are also given to demonstrate the effectiveness of the proposed DANFIS with learning method.","PeriodicalId":339652,"journal":{"name":"2014 IEEE International Symposium on Innovations in Intelligent Systems and Applications (INISTA) Proceedings","volume":"84 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132126655","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 : 2014-06-23DOI: 10.1109/INISTA.2014.6873626
Mahmut Kaya, H. Ş. Bilge
k nearest neighbor algorithm is a widely used classifier. It benefits from distances among features to classify the data. Classifiers based on distance metrics are affected from irrelevant or redundant features. Especially, it is valid for big datasets. So, some of features can be weighted with higher coefficients to reduce the effect of irrelevant or redundant features. We suggest adaptive weighted k nearest neighbor algorithm to increase classification accuracy. This algorithm uses t test which is one of the feature selection to weight features. Classification accuracy is increased from 74.14% to 86.57% for k=3 neighbors and Euclidean distance metric thanks to the proposed method.
{"title":"Classification of pancreas tumor dataset using adaptive weighted k nearest neighbor algorithm","authors":"Mahmut Kaya, H. Ş. Bilge","doi":"10.1109/INISTA.2014.6873626","DOIUrl":"https://doi.org/10.1109/INISTA.2014.6873626","url":null,"abstract":"k nearest neighbor algorithm is a widely used classifier. It benefits from distances among features to classify the data. Classifiers based on distance metrics are affected from irrelevant or redundant features. Especially, it is valid for big datasets. So, some of features can be weighted with higher coefficients to reduce the effect of irrelevant or redundant features. We suggest adaptive weighted k nearest neighbor algorithm to increase classification accuracy. This algorithm uses t test which is one of the feature selection to weight features. Classification accuracy is increased from 74.14% to 86.57% for k=3 neighbors and Euclidean distance metric thanks to the proposed method.","PeriodicalId":339652,"journal":{"name":"2014 IEEE International Symposium on Innovations in Intelligent Systems and Applications (INISTA) Proceedings","volume":"145 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133588385","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 : 2014-06-23DOI: 10.1109/INISTA.2014.6873632
S. Stubberud, K. Kramer
GPS navigation and guidance has become more prevalent in critical systems such as UAV and shipping. Attacks on GPS are now becoming of greater concern. In this paper, an evidence accrual system is discussed that looks to identify when a GPS navigation system may be compromised. The techniques use a novel fuzzy Kalman filter to drive the evidence generation in conjunction with an image-based correlation technique. The image correlation provides a pattern recognition for complex observations that avoids the identification and development of complex functions. This new evidence accrual system is applied to realistic and complex GPS attack problems.
{"title":"Threat assessment for GPS navigation","authors":"S. Stubberud, K. Kramer","doi":"10.1109/INISTA.2014.6873632","DOIUrl":"https://doi.org/10.1109/INISTA.2014.6873632","url":null,"abstract":"GPS navigation and guidance has become more prevalent in critical systems such as UAV and shipping. Attacks on GPS are now becoming of greater concern. In this paper, an evidence accrual system is discussed that looks to identify when a GPS navigation system may be compromised. The techniques use a novel fuzzy Kalman filter to drive the evidence generation in conjunction with an image-based correlation technique. The image correlation provides a pattern recognition for complex observations that avoids the identification and development of complex functions. This new evidence accrual system is applied to realistic and complex GPS attack problems.","PeriodicalId":339652,"journal":{"name":"2014 IEEE International Symposium on Innovations in Intelligent Systems and Applications (INISTA) Proceedings","volume":"151 ","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114089902","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 : 2014-06-23DOI: 10.1109/INISTA.2014.6873606
Sara Zhalehpour, Z. Akhtar, Ç. Erdem
In this paper we present an effective framework for multimodal emotion recognition based on a novel approach for automatic peak frame selection from audio-visual video sequences. Given a video with an emotional expression, peak frames are the ones at which the emotion is at its apex. The objective of peak frame selection is to make the training process for the automatic emotion recognition system easier by summarizing the expressed emotion over a video sequence. The main steps of the proposed framework consists of extraction of video and audio features based on peak frame selection, unimodal classification and decision level fusion of audio and visual results. We evaluated the performance of our approach on eNTERFACE'05 audio-visual database containing six basic emotional classes. Experimental results demonstrate the effectiveness and superiority of the proposed system over other methods in the literature.
{"title":"Multimodal emotion recognition with automatic peak frame selection","authors":"Sara Zhalehpour, Z. Akhtar, Ç. Erdem","doi":"10.1109/INISTA.2014.6873606","DOIUrl":"https://doi.org/10.1109/INISTA.2014.6873606","url":null,"abstract":"In this paper we present an effective framework for multimodal emotion recognition based on a novel approach for automatic peak frame selection from audio-visual video sequences. Given a video with an emotional expression, peak frames are the ones at which the emotion is at its apex. The objective of peak frame selection is to make the training process for the automatic emotion recognition system easier by summarizing the expressed emotion over a video sequence. The main steps of the proposed framework consists of extraction of video and audio features based on peak frame selection, unimodal classification and decision level fusion of audio and visual results. We evaluated the performance of our approach on eNTERFACE'05 audio-visual database containing six basic emotional classes. Experimental results demonstrate the effectiveness and superiority of the proposed system over other methods in the literature.","PeriodicalId":339652,"journal":{"name":"2014 IEEE International Symposium on Innovations in Intelligent Systems and Applications (INISTA) Proceedings","volume":"318 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116290228","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 : 2014-06-23DOI: 10.1109/INISTA.2014.6873642
I. Aydin, Orhan Yaman, Mehmet Karaköse, S. B. Çelebi
Pantograph-catenary system is the most important component for transmitting the electric energy to the train. If the faults have not detected in an early stage, energy can disrupt the energy and this leads to more serious faults. The arcs occurred in the contact point is the first step of a fault. When they are detected in an early stage, catastrophic faults and accidents can be avoided. In this study, a new approach has been proposed to detect arcs in pantograph-catenary system. The proposed method applies a threshold value to each video frame and the rate of sudden glares are converted to time series. The phase space of the obtained time series is constructed and the arc event is found by using particle swarm optimization. The proposed method is analyzed by using real pantograph-videos and good result have been obtained.
{"title":"Particle swarm based arc detection on time series in pantograph-catenary system","authors":"I. Aydin, Orhan Yaman, Mehmet Karaköse, S. B. Çelebi","doi":"10.1109/INISTA.2014.6873642","DOIUrl":"https://doi.org/10.1109/INISTA.2014.6873642","url":null,"abstract":"Pantograph-catenary system is the most important component for transmitting the electric energy to the train. If the faults have not detected in an early stage, energy can disrupt the energy and this leads to more serious faults. The arcs occurred in the contact point is the first step of a fault. When they are detected in an early stage, catastrophic faults and accidents can be avoided. In this study, a new approach has been proposed to detect arcs in pantograph-catenary system. The proposed method applies a threshold value to each video frame and the rate of sudden glares are converted to time series. The phase space of the obtained time series is constructed and the arc event is found by using particle swarm optimization. The proposed method is analyzed by using real pantograph-videos and good result have been obtained.","PeriodicalId":339652,"journal":{"name":"2014 IEEE International Symposium on Innovations in Intelligent Systems and Applications (INISTA) Proceedings","volume":"68 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121455467","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 : 2014-06-23DOI: 10.1109/INISTA.2014.6873631
YouJun Choi, HeeSung Shin, JaeYeol Lee
Driver's drowsiness and fatigue on driving is one of the most major reasons that causes serious car accidents. This paper suggests smart steering wheel system that have physiological sensors for real automotive application and emergency alarm systems for driver using smart phone. Smart steering wheel implementation method is described briefly for real automotive application. The mobile communication system for driver's emergency situation using smart phone and automatic emergency location alarm system based on google map is also described.
{"title":"Smart steering wheel system for driver's emergency situation using physiological sensors and smart phone","authors":"YouJun Choi, HeeSung Shin, JaeYeol Lee","doi":"10.1109/INISTA.2014.6873631","DOIUrl":"https://doi.org/10.1109/INISTA.2014.6873631","url":null,"abstract":"Driver's drowsiness and fatigue on driving is one of the most major reasons that causes serious car accidents. This paper suggests smart steering wheel system that have physiological sensors for real automotive application and emergency alarm systems for driver using smart phone. Smart steering wheel implementation method is described briefly for real automotive application. The mobile communication system for driver's emergency situation using smart phone and automatic emergency location alarm system based on google map is also described.","PeriodicalId":339652,"journal":{"name":"2014 IEEE International Symposium on Innovations in Intelligent Systems and Applications (INISTA) Proceedings","volume":"155 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-06-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122052310","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：