Pub Date : 2017-09-01DOI: 10.1109/IDAP.2017.8090318
Tunç Gültekin, Aybars Uğur
For deep learning applications, large numbers of samples are essential. If this condition is not met, effective features cannot be generated and overfitting occurs especially for the small datasets such as in medical applications. To address this issue, we propose a new dynamic ensemble merging algorithm that iteratively adjusts the weights of a convolutional neural network (CNN) ensemble's elements in an online manner. For given test instance, the proposed algorithm1, initially assigns equal weights to each of the classifiers and increases the weights of best k ones along iterations. Experiments that we conduct on a small deep learning dataset lead to promising ensemble results compared to its counterparts.
{"title":"An iterative dynamic ensemble weighting approach for deep learning applications","authors":"Tunç Gültekin, Aybars Uğur","doi":"10.1109/IDAP.2017.8090318","DOIUrl":"https://doi.org/10.1109/IDAP.2017.8090318","url":null,"abstract":"For deep learning applications, large numbers of samples are essential. If this condition is not met, effective features cannot be generated and overfitting occurs especially for the small datasets such as in medical applications. To address this issue, we propose a new dynamic ensemble merging algorithm that iteratively adjusts the weights of a convolutional neural network (CNN) ensemble's elements in an online manner. For given test instance, the proposed algorithm1, initially assigns equal weights to each of the classifiers and increases the weights of best k ones along iterations. Experiments that we conduct on a small deep learning dataset lead to promising ensemble results compared to its counterparts.","PeriodicalId":111721,"journal":{"name":"2017 International Artificial Intelligence and Data Processing Symposium (IDAP)","volume":"258 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131034018","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 : 2017-09-01DOI: 10.1109/IDAP.2017.8090168
Necmettin Sezgin, Ö. F. Ertugrul, Ramazan Tekin, M. Tagluk
In this study, two-channel surface electromyogram (sEMG) signals were used to classify hand open/close with fingers. The bispectrum analysis of the sEMG signal recorded with surface electrodes near the region of the muscle bundles on the front and back of the forearm was classified by extreme learning machines (ELM) based on phase matches in the EMG signal. EMG signals belonging to 17 persons, 8 males and 9 females, with an average age of 24 were used in the study. The fingers were classified using ELM algorithm with 94.60% accuracy in average. From the information obtained through this study, it seems possible to control finger movements and hand opening/closing by using muscle activities of the forearm which we hope to lead to control of intelligent prosthesis hands with high degree of freedom.
{"title":"Classification of hand opening/closing and fingers by using two channel surface EMG signal","authors":"Necmettin Sezgin, Ö. F. Ertugrul, Ramazan Tekin, M. Tagluk","doi":"10.1109/IDAP.2017.8090168","DOIUrl":"https://doi.org/10.1109/IDAP.2017.8090168","url":null,"abstract":"In this study, two-channel surface electromyogram (sEMG) signals were used to classify hand open/close with fingers. The bispectrum analysis of the sEMG signal recorded with surface electrodes near the region of the muscle bundles on the front and back of the forearm was classified by extreme learning machines (ELM) based on phase matches in the EMG signal. EMG signals belonging to 17 persons, 8 males and 9 females, with an average age of 24 were used in the study. The fingers were classified using ELM algorithm with 94.60% accuracy in average. From the information obtained through this study, it seems possible to control finger movements and hand opening/closing by using muscle activities of the forearm which we hope to lead to control of intelligent prosthesis hands with high degree of freedom.","PeriodicalId":111721,"journal":{"name":"2017 International Artificial Intelligence and Data Processing Symposium (IDAP)","volume":"26 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133427559","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 : 2017-09-01DOI: 10.1109/IDAP.2017.8090311
Özgür Öztürk, H. Kutucu
The use of computer technology in medical sciences is spreading with technology. The use of computers especially for imaging has become a third eye for physicians. In orthopedic surgeons, after simple roentgenograms for fracture detection, the use of computerized tomography and magnetic resonance has provided great convenience in the detection of fracture, typing, and therefore the appropriate treatment of the patient. The advancing technology has increased the quality of the images in the x-rayograms, reduced artifacts and enabled digital measurements. In this study, image processing and learning techniques were used to diagnose long bone fractures. The proposed artificial neural network has 89% success rate.
{"title":"Detection of bone fractures using image processing techniques and artificial neural networks","authors":"Özgür Öztürk, H. Kutucu","doi":"10.1109/IDAP.2017.8090311","DOIUrl":"https://doi.org/10.1109/IDAP.2017.8090311","url":null,"abstract":"The use of computer technology in medical sciences is spreading with technology. The use of computers especially for imaging has become a third eye for physicians. In orthopedic surgeons, after simple roentgenograms for fracture detection, the use of computerized tomography and magnetic resonance has provided great convenience in the detection of fracture, typing, and therefore the appropriate treatment of the patient. The advancing technology has increased the quality of the images in the x-rayograms, reduced artifacts and enabled digital measurements. In this study, image processing and learning techniques were used to diagnose long bone fractures. The proposed artificial neural network has 89% success rate.","PeriodicalId":111721,"journal":{"name":"2017 International Artificial Intelligence and Data Processing Symposium (IDAP)","volume":"68 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117142002","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 : 2017-09-01DOI: 10.1109/IDAP.2017.8090180
Kazım Hanbay, Sedat Golgiyaz, M. F. Talu
In industrial fabric productions, real time systems are needed to detect the fabric defects. This paper presents a real time defect detection approach which compares the time performances of Matlab and C++ programming languages. In the proposed method, important texture features of the fabric images are extracted using CoHOG method. Artificial neural network is used to classify the fabric defects. The developed method has been applied to detect the knitting fabric defects on a circular knitting machine. An overall defect detection success rate of 93% is achieved for the Matlab and C++ applications. To give an idea to the researches in defect detection area, real time operation speeds of Matlab and C++ codes have been examined. Especially, the number of images that can be processed in one second has been determined. While the Matlab based coding can process 3 images in 1 second, C++/Opencv based coding can process 55 images in 1 second. Previous works have rarely included the practical comparative evaluations of software environments. Therefore, we believe that the results of our industrial experiments will be a valuable resource for future works in this area.
{"title":"Real time fabric defect detection system on Matlab and C++/Opencv platforms","authors":"Kazım Hanbay, Sedat Golgiyaz, M. F. Talu","doi":"10.1109/IDAP.2017.8090180","DOIUrl":"https://doi.org/10.1109/IDAP.2017.8090180","url":null,"abstract":"In industrial fabric productions, real time systems are needed to detect the fabric defects. This paper presents a real time defect detection approach which compares the time performances of Matlab and C++ programming languages. In the proposed method, important texture features of the fabric images are extracted using CoHOG method. Artificial neural network is used to classify the fabric defects. The developed method has been applied to detect the knitting fabric defects on a circular knitting machine. An overall defect detection success rate of 93% is achieved for the Matlab and C++ applications. To give an idea to the researches in defect detection area, real time operation speeds of Matlab and C++ codes have been examined. Especially, the number of images that can be processed in one second has been determined. While the Matlab based coding can process 3 images in 1 second, C++/Opencv based coding can process 55 images in 1 second. Previous works have rarely included the practical comparative evaluations of software environments. Therefore, we believe that the results of our industrial experiments will be a valuable resource for future works in this area.","PeriodicalId":111721,"journal":{"name":"2017 International Artificial Intelligence and Data Processing Symposium (IDAP)","volume":"95 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116276872","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 : 2017-09-01DOI: 10.1109/IDAP.2017.8090345
Ö. F. Ertugrul, Necmettin Sezgin, Abdulkerim Öztekin, M. Tagluk
Estimating short-term power load is a fundamental issue in the power distribution system. Since short-term power load is related to many parameters such as weather conditions, and time. The aim of this study is to determine the relevant parameters in estimating short-term power load not only in order to decrease the computational cost, but also to achieve higher success rates. Furthermore, by using selected features the required memory, equipment and communication costs are also decreased in real time applications. Feature selection by extreme learning machine method was used in determining relevant features. The short-term power loads of two houses (one of them has a power generation capability) were used in tests and achieved results showed lower error rates were obtained by using less number of features.
{"title":"Determining relevant features in estimating short-term power load of a small house via feature selection by extreme learning machine","authors":"Ö. F. Ertugrul, Necmettin Sezgin, Abdulkerim Öztekin, M. Tagluk","doi":"10.1109/IDAP.2017.8090345","DOIUrl":"https://doi.org/10.1109/IDAP.2017.8090345","url":null,"abstract":"Estimating short-term power load is a fundamental issue in the power distribution system. Since short-term power load is related to many parameters such as weather conditions, and time. The aim of this study is to determine the relevant parameters in estimating short-term power load not only in order to decrease the computational cost, but also to achieve higher success rates. Furthermore, by using selected features the required memory, equipment and communication costs are also decreased in real time applications. Feature selection by extreme learning machine method was used in determining relevant features. The short-term power loads of two houses (one of them has a power generation capability) were used in tests and achieved results showed lower error rates were obtained by using less number of features.","PeriodicalId":111721,"journal":{"name":"2017 International Artificial Intelligence and Data Processing Symposium (IDAP)","volume":"140 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121957444","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 : 2017-09-01DOI: 10.1109/IDAP.2017.8090312
Veysel Gündüzalp, Sağlık Bakanlığı, Turker Tuncer, Adli Bilişim Mühendisliği, Mustafa Ulaş, Yazılım Mühendisliği, E. Avci
Nowadays, the using of smartphones has expeditiously increased. The developing of information security applications for smartphones becomes important because of the fact that a clear majority of individuals informations accupy in smartphones. For this reason the developing of ligeweight information security applications becomes vitally important. In this study, a data-hiding schema that runs speedly and whose availability is high is suggested for smartphones. Data-hiding schema should be high capacity, speedy and safe is prioritised.
{"title":"Akilli telefonlar için geliştirilmiş hafif siklet veri gizleme uygulamasi","authors":"Veysel Gündüzalp, Sağlık Bakanlığı, Turker Tuncer, Adli Bilişim Mühendisliği, Mustafa Ulaş, Yazılım Mühendisliği, E. Avci","doi":"10.1109/IDAP.2017.8090312","DOIUrl":"https://doi.org/10.1109/IDAP.2017.8090312","url":null,"abstract":"Nowadays, the using of smartphones has expeditiously increased. The developing of information security applications for smartphones becomes important because of the fact that a clear majority of individuals informations accupy in smartphones. For this reason the developing of ligeweight information security applications becomes vitally important. In this study, a data-hiding schema that runs speedly and whose availability is high is suggested for smartphones. Data-hiding schema should be high capacity, speedy and safe is prioritised.","PeriodicalId":111721,"journal":{"name":"2017 International Artificial Intelligence and Data Processing Symposium (IDAP)","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122110896","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 : 2017-09-01DOI: 10.1109/IDAP.2017.8090249
Ülkü Arslan Aydin, Sinan Kalkan, Cengiz Acartürk
Gaze analysis in dynamic environments has remained an unresolved problem due to the complexities that pertain to the detection and tracking of objects in the visual environment. This study provides a solution to the problem for face-to-face communication, in which the visual objects in the environment are faces. The application that has been developed for this purpose is able to detect and track faces in video steram, and it maps gaze locations to the images, thus allowing the user to detect gaze behavior, such as gaze aversion. The application is also capable of segmentation and diarization of speech syncronously with the vide o stream and eye movement overlay. It allows the user to annotate speech by speech act labels. The pilot studies reveal that the application provides acceptable accuracy values in the analysis, as well as significantly reducing the time for the analyses.
{"title":"Dynamic gaze analysis: An application enviroment for face-to-face communication","authors":"Ülkü Arslan Aydin, Sinan Kalkan, Cengiz Acartürk","doi":"10.1109/IDAP.2017.8090249","DOIUrl":"https://doi.org/10.1109/IDAP.2017.8090249","url":null,"abstract":"Gaze analysis in dynamic environments has remained an unresolved problem due to the complexities that pertain to the detection and tracking of objects in the visual environment. This study provides a solution to the problem for face-to-face communication, in which the visual objects in the environment are faces. The application that has been developed for this purpose is able to detect and track faces in video steram, and it maps gaze locations to the images, thus allowing the user to detect gaze behavior, such as gaze aversion. The application is also capable of segmentation and diarization of speech syncronously with the vide o stream and eye movement overlay. It allows the user to annotate speech by speech act labels. The pilot studies reveal that the application provides acceptable accuracy values in the analysis, as well as significantly reducing the time for the analyses.","PeriodicalId":111721,"journal":{"name":"2017 International Artificial Intelligence and Data Processing Symposium (IDAP)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128375793","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 : 2017-09-01DOI: 10.1109/IDAP.2017.8090253
Hasan Polat, M. Akin, M. S. Özerdem
The aim of this study was to detect sleep stages of human by using EEG signals. In accordance with this purpose, discrete wavelet transforms (DWT) and empirical mode decomposition (EMD) were separately used for feature extraction. Subcomponents of EEG signals obtained by the two methods were assumed as feature vectors. Statistical parameters were used to reduce dimension of feature vectors. The same statistical parameters were used to compare performance of methods related to DWT and EMD. K nearest neighborhood (kNN) algorithm was used in classification final feature vectors that obtained EEG segments related to different sleep stages. The classification accuracies for feature vectors based on DWT and EMD were obtained as 100% and 88.13%, respectively.
{"title":"The comparison of wavelet and empirical mode decomposition method in prediction of sleep stages from EEG signals","authors":"Hasan Polat, M. Akin, M. S. Özerdem","doi":"10.1109/IDAP.2017.8090253","DOIUrl":"https://doi.org/10.1109/IDAP.2017.8090253","url":null,"abstract":"The aim of this study was to detect sleep stages of human by using EEG signals. In accordance with this purpose, discrete wavelet transforms (DWT) and empirical mode decomposition (EMD) were separately used for feature extraction. Subcomponents of EEG signals obtained by the two methods were assumed as feature vectors. Statistical parameters were used to reduce dimension of feature vectors. The same statistical parameters were used to compare performance of methods related to DWT and EMD. K nearest neighborhood (kNN) algorithm was used in classification final feature vectors that obtained EEG segments related to different sleep stages. The classification accuracies for feature vectors based on DWT and EMD were obtained as 100% and 88.13%, respectively.","PeriodicalId":111721,"journal":{"name":"2017 International Artificial Intelligence and Data Processing Symposium (IDAP)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128909919","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 : 2017-09-01DOI: 10.1109/IDAP.2017.8090191
Aykut Beke, Ahmet Arda Yuceler, T. Kumbasar
In this study, we will present a rule based fuzzy gesture recognition system where a user will interact with a spherical robot with hand gestures performed with a smart phone and the droid will respond by imitating this movements. In this context, we will take up the Gesture Recognition, Fuzzy Logic and Internet of Things (IoT) frameworks to construct such a Human-Machine Interface (HMI). In the proposed structure, the IoT collect the necessary IMU data from the smart phone for classification purposes while also providing the necessary data to the Sphero 2.0 droid. To recognize/classify the hand gestures performed with a smart phone, we will use and train fuzzy classifier. For proof of concept purposes, we have defined two hand gesture movements which are circular and linear gesture movement. The presented results clearly show that the performance of the fuzzy classifier is satisfactory even though each user has unique gesture characteristic (different magnitudes and velocities). Finally, we have also tested the proposed system in real-time with a user from whom we have not collected any IMU data. The presented results of the paper will show that the performance fuzzy logic based gesture recognition and interaction system is satisfactory.
{"title":"A rule based fuzzy gesture recognition system to interact with Sphero 2.0 using a smart phone","authors":"Aykut Beke, Ahmet Arda Yuceler, T. Kumbasar","doi":"10.1109/IDAP.2017.8090191","DOIUrl":"https://doi.org/10.1109/IDAP.2017.8090191","url":null,"abstract":"In this study, we will present a rule based fuzzy gesture recognition system where a user will interact with a spherical robot with hand gestures performed with a smart phone and the droid will respond by imitating this movements. In this context, we will take up the Gesture Recognition, Fuzzy Logic and Internet of Things (IoT) frameworks to construct such a Human-Machine Interface (HMI). In the proposed structure, the IoT collect the necessary IMU data from the smart phone for classification purposes while also providing the necessary data to the Sphero 2.0 droid. To recognize/classify the hand gestures performed with a smart phone, we will use and train fuzzy classifier. For proof of concept purposes, we have defined two hand gesture movements which are circular and linear gesture movement. The presented results clearly show that the performance of the fuzzy classifier is satisfactory even though each user has unique gesture characteristic (different magnitudes and velocities). Finally, we have also tested the proposed system in real-time with a user from whom we have not collected any IMU data. The presented results of the paper will show that the performance fuzzy logic based gesture recognition and interaction system is satisfactory.","PeriodicalId":111721,"journal":{"name":"2017 International Artificial Intelligence and Data Processing Symposium (IDAP)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130824970","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 : 2017-09-01DOI: 10.1109/IDAP.2017.8090272
Bilal Şenol
FGATool is a MATLAB tool for graphical analysis of systems represented with transfer functions having orders of integer and fractional numbers. It offers easy-to-use tools for students and researchers working in the field of system analysis. This paper presents the motivation of its development, an overview of the uncertainty module of the toolbox and the relation with existing tools concerned to system analysis. One of the two main modules of the toolbox is introduced which deals with systems including parametric uncertainties. Analysis tools such as step response, Bode and Nyquist diagrams, interlacing property, root analysis on the first Riemann sheet and value set analysis have been studied overall the toolbox. Main motivation of FGATool lays on its ease of use without much knowledge on mathematical background and its user friendly graphical interface. It also brings more easiness and attraction on fractional order system analysis.
{"title":"FGATool for time and frequency analysis of systems with uncertainties","authors":"Bilal Şenol","doi":"10.1109/IDAP.2017.8090272","DOIUrl":"https://doi.org/10.1109/IDAP.2017.8090272","url":null,"abstract":"FGATool is a MATLAB tool for graphical analysis of systems represented with transfer functions having orders of integer and fractional numbers. It offers easy-to-use tools for students and researchers working in the field of system analysis. This paper presents the motivation of its development, an overview of the uncertainty module of the toolbox and the relation with existing tools concerned to system analysis. One of the two main modules of the toolbox is introduced which deals with systems including parametric uncertainties. Analysis tools such as step response, Bode and Nyquist diagrams, interlacing property, root analysis on the first Riemann sheet and value set analysis have been studied overall the toolbox. Main motivation of FGATool lays on its ease of use without much knowledge on mathematical background and its user friendly graphical interface. It also brings more easiness and attraction on fractional order system analysis.","PeriodicalId":111721,"journal":{"name":"2017 International Artificial Intelligence and Data Processing Symposium (IDAP)","volume":"92 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127903410","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：