In this work, advanced learning and moving window-based methods have been used for epileptic seizure detection. Epilepsy is a disorder of the central nervous system and roughly affects 50 million people worldwide. The most common non-invasive tool for studying the brain activity of an epileptic patient is the electroencephalogram. Accurate detection of seizure onset is still an elusive work. Electroencephalogram signals belonging to pediatric patients from Children’s Hospital Boston, Massachusetts Institute of Technology have been used in this work to validate the proposed method. For determining between seizure and non-seizure signals, feature extraction techniques based on time-domain, frequency domain, time-frequency domain have been used. Four different methods (decision tree, random forest, artificial neural network, and ensemble learning) have been studied and their performances have been compared using different statistical measures. The test sample technique has been used for the validation of all seizure detection methods. The results show better performance by random forest among all the four classifiers with an accuracy, sensitivity, and specificity of 91.9%, 94.1%, and 89.7% respectively. The proposed method is suggested as an improved method because it is not channel specific, not patient specific and has a promising accuracy in detecting epileptic seizure.
{"title":"An improved method for recognizing pediatric epileptic seizures based on advanced learning and moving window technique","authors":"Satarupa Chakrabarti, A. Swetapadma, P. Pattnaik","doi":"10.3233/ais-210042","DOIUrl":"https://doi.org/10.3233/ais-210042","url":null,"abstract":"In this work, advanced learning and moving window-based methods have been used for epileptic seizure detection. Epilepsy is a disorder of the central nervous system and roughly affects 50 million people worldwide. The most common non-invasive tool for studying the brain activity of an epileptic patient is the electroencephalogram. Accurate detection of seizure onset is still an elusive work. Electroencephalogram signals belonging to pediatric patients from Children’s Hospital Boston, Massachusetts Institute of Technology have been used in this work to validate the proposed method. For determining between seizure and non-seizure signals, feature extraction techniques based on time-domain, frequency domain, time-frequency domain have been used. Four different methods (decision tree, random forest, artificial neural network, and ensemble learning) have been studied and their performances have been compared using different statistical measures. The test sample technique has been used for the validation of all seizure detection methods. The results show better performance by random forest among all the four classifiers with an accuracy, sensitivity, and specificity of 91.9%, 94.1%, and 89.7% respectively. The proposed method is suggested as an improved method because it is not channel specific, not patient specific and has a promising accuracy in detecting epileptic seizure.","PeriodicalId":49316,"journal":{"name":"Journal of Ambient Intelligence and Smart Environments","volume":"25 1","pages":"39-59"},"PeriodicalIF":1.7,"publicationDate":"2021-12-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81717358","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Epilepsy is a chronic brain disease resulted from the central nervous system lesion, which leads to repeated seizure occurs for the patients. Automatic seizure detection with Electroencephalogram (EEG) has witnessed great progress. However, existing methods paid little attention to the topological relationships of different EEG electrodes. Latest neuroscience researches have demonstrated the connectivity between different brain regions. Besides, class-imbalance is a common problem in EEG based seizure detection. The duration of epileptic EEG signals is much shorter than that of normal signals. In order to deal with the above mentioned two challenges, we propose to model the multi-channel EEG data using the Attention-based Graph ResNet (AGRN). In particular, each channel of the EEG signal represents a node of the graph and the inter-channel relations are modeled via the adjacency matrix in the graph. The loss function of the ARGN model is re-designed using focal loss to cope with the class-imbalance problem. The proposed ARGN with focal model could learn discriminative features from the raw EEG data. Experiments are carried out on the CHB-MIT dataset. The proposed model achieves an average accuracy of 98.70%, a sensitivity of 97.94%, a specificity of 98.66% and a precision of 98.62%. The Area Under the ROC Curve (AUC) is 98.69%.
{"title":"Attention-based Graph ResNet with focal loss for epileptic seizure detection","authors":"Changxu Dong, Yanna Zhao, Gaobo Zhang, Mingrui Xue, Dengyu Chu, Jiatong He, Xinting Ge","doi":"10.3233/ais-210086","DOIUrl":"https://doi.org/10.3233/ais-210086","url":null,"abstract":"Epilepsy is a chronic brain disease resulted from the central nervous system lesion, which leads to repeated seizure occurs for the patients. Automatic seizure detection with Electroencephalogram (EEG) has witnessed great progress. However, existing methods paid little attention to the topological relationships of different EEG electrodes. Latest neuroscience researches have demonstrated the connectivity between different brain regions. Besides, class-imbalance is a common problem in EEG based seizure detection. The duration of epileptic EEG signals is much shorter than that of normal signals. In order to deal with the above mentioned two challenges, we propose to model the multi-channel EEG data using the Attention-based Graph ResNet (AGRN). In particular, each channel of the EEG signal represents a node of the graph and the inter-channel relations are modeled via the adjacency matrix in the graph. The loss function of the ARGN model is re-designed using focal loss to cope with the class-imbalance problem. The proposed ARGN with focal model could learn discriminative features from the raw EEG data. Experiments are carried out on the CHB-MIT dataset. The proposed model achieves an average accuracy of 98.70%, a sensitivity of 97.94%, a specificity of 98.66% and a precision of 98.62%. The Area Under the ROC Curve (AUC) is 98.69%.","PeriodicalId":49316,"journal":{"name":"Journal of Ambient Intelligence and Smart Environments","volume":"186 6 1","pages":"61-73"},"PeriodicalIF":1.7,"publicationDate":"2021-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81085772","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Vincent Tam,Hamid Aghajan,Juan Carlos Augusto,Andrés Muñoz
{"title":"Preface to JAISE 13(6)","authors":"Vincent Tam,Hamid Aghajan,Juan Carlos Augusto,Andrés Muñoz","doi":"10.3233/ais-210613","DOIUrl":"https://doi.org/10.3233/ais-210613","url":null,"abstract":"","PeriodicalId":49316,"journal":{"name":"Journal of Ambient Intelligence and Smart Environments","volume":"6 6","pages":""},"PeriodicalIF":1.7,"publicationDate":"2021-11-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138513281","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Peeraya Sripian, M. N. Anuardi, Teppei Ito, Y. Tobe, M. Sugaya
An important part of nursing care is the physiotherapist’s physical exercise recovery training (for instance, walking), which is aimed at restoring athletic ability, known as rehabilitation (rehab). In rehab, the big problem is that it is difficult to maintain motivation. Therapies using robots have been proposed, such as animalistic robots that have positive psychological, physiological, and social effects on the patient. These also have an important effect in reducing the on-site human workload. However, the problem with these robots is that they do not actually understand what emotions the user is currently feeling. Some studies have been successful in estimating a person’s emotions. As for non-cognitive approaches, there is an emotional estimation of non-verbal information. In this study, we focus on the characteristics of real-time sensing of emotion through heart rates – unconsciously evaluating what a person experiences – and applying it to select the appropriate turn of phrase by a voice-casting robot. We developed a robot to achieve this purpose. As a result, we were able to confirm the effectiveness of a real-time emotion-sensitive voice-casting robot that performs supportive actions significantly different from non-voice casting robots.
{"title":"Emotion-sensitive voice-casting care robot in rehabilitation using real-time sensing and analysis of biometric information","authors":"Peeraya Sripian, M. N. Anuardi, Teppei Ito, Y. Tobe, M. Sugaya","doi":"10.3233/ais-210614","DOIUrl":"https://doi.org/10.3233/ais-210614","url":null,"abstract":"An important part of nursing care is the physiotherapist’s physical exercise recovery training (for instance, walking), which is aimed at restoring athletic ability, known as rehabilitation (rehab). In rehab, the big problem is that it is difficult to maintain motivation. Therapies using robots have been proposed, such as animalistic robots that have positive psychological, physiological, and social effects on the patient. These also have an important effect in reducing the on-site human workload. However, the problem with these robots is that they do not actually understand what emotions the user is currently feeling. Some studies have been successful in estimating a person’s emotions. As for non-cognitive approaches, there is an emotional estimation of non-verbal information. In this study, we focus on the characteristics of real-time sensing of emotion through heart rates – unconsciously evaluating what a person experiences – and applying it to select the appropriate turn of phrase by a voice-casting robot. We developed a robot to achieve this purpose. As a result, we were able to confirm the effectiveness of a real-time emotion-sensitive voice-casting robot that performs supportive actions significantly different from non-voice casting robots.","PeriodicalId":49316,"journal":{"name":"Journal of Ambient Intelligence and Smart Environments","volume":"12 1","pages":"413-431"},"PeriodicalIF":1.7,"publicationDate":"2021-11-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80593623","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Smart parking is becoming more and more an integral part of smart city initiatives. Utilizing and managing parking areas is a challenging task as space is often limited, finding empty spaces are hard and citizens want to park their vehicles close to their preferred places. This becomes worse in important/posh areas of major metropolitan cities during rush hour. Due to unavailability of proper parking management system, citizens have to roam around a lot in order to find a suitable parking area. This leads to the wastage of valuable time, unnecessary fuel consumption and environmental pollution. This paper proposes a smart parking management system (SPMS) based on multiple criteria based parking space reservation algorithm (MCPR) that allows the driver/owner of vehicles to find and reserve most appropriate parking space from anywhere at any time. The system also considers the concept of dynamic pricing strategy for calculating parking charge in order to gain more revenue by the government agencies as well as private investors. The system employs sensors to calculate concentration index, average inter-arrival time of vehicles of a parking area for better parking management and planning. The simulation results show that proposed system reduces the average extra driving required by the users to find a parking area and hence it will reduce traffic congestion, which in turn reduces air pollution caused by unnecessary driving to find a proper parking area.
{"title":"Smart parking management system with dynamic pricing","authors":"Md Ashifuddin Mondal, Z. Rehena, M. Janssen","doi":"10.3233/ais-210615","DOIUrl":"https://doi.org/10.3233/ais-210615","url":null,"abstract":"Smart parking is becoming more and more an integral part of smart city initiatives. Utilizing and managing parking areas is a challenging task as space is often limited, finding empty spaces are hard and citizens want to park their vehicles close to their preferred places. This becomes worse in important/posh areas of major metropolitan cities during rush hour. Due to unavailability of proper parking management system, citizens have to roam around a lot in order to find a suitable parking area. This leads to the wastage of valuable time, unnecessary fuel consumption and environmental pollution. This paper proposes a smart parking management system (SPMS) based on multiple criteria based parking space reservation algorithm (MCPR) that allows the driver/owner of vehicles to find and reserve most appropriate parking space from anywhere at any time. The system also considers the concept of dynamic pricing strategy for calculating parking charge in order to gain more revenue by the government agencies as well as private investors. The system employs sensors to calculate concentration index, average inter-arrival time of vehicles of a parking area for better parking management and planning. The simulation results show that proposed system reduces the average extra driving required by the users to find a parking area and hence it will reduce traffic congestion, which in turn reduces air pollution caused by unnecessary driving to find a proper parking area.","PeriodicalId":49316,"journal":{"name":"Journal of Ambient Intelligence and Smart Environments","volume":"48 1","pages":"473-494"},"PeriodicalIF":1.7,"publicationDate":"2021-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86924200","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Rafik Belloum, Amel Yaddaden, M. Lussier, N. Bier, C. Consel
Older adults often need some level of assistance in performing daily living activities. Even though these activities are common to the vast majority of individuals (e.g., eating, bathing, dressing), the way they are performed varies across individuals. Supporting older people in performing their everyday activities is a major avenue of research in smart homes. However, because of its early stage, this line of work has paid little attention on customizing assistive computing support with respect to the specific needs of each older adult towards improving its effectiveness and acceptability. We propose a tool-based approach to allowing caregivers to define services in the area of home daily living, leveraging their knowledge and expertise on the older adult they care for. This approach consists of two stages: 1) a wizard allows caregivers to define an assistive service, which supports aspects of a daily activity that are specific to an older adult; 2) the wizard-generated service is uploaded in an existing smart home platform and interpreted by a dedicated component, carrying out the caregiver-defined service. Our approach has been implemented. Our wizard has been successfully used to define existing manually-programmed, activity-supporting services. The resulting services have been deployed and executed by an existing assisted living platform deployed in the home of community-dwelling individuals. They have been shown to be equivalent to their manually-programmed counterparts. We also conducted an ergonomics study involving five occupational therapists, who tested our wizard with clinical vignettes describing fictitious patients. Participants were able to successfully define services while revealing an ease of use of our wizard.
{"title":"Caregiver development of activity-supporting services for smart homes","authors":"Rafik Belloum, Amel Yaddaden, M. Lussier, N. Bier, C. Consel","doi":"10.3233/ais-210616","DOIUrl":"https://doi.org/10.3233/ais-210616","url":null,"abstract":"Older adults often need some level of assistance in performing daily living activities. Even though these activities are common to the vast majority of individuals (e.g., eating, bathing, dressing), the way they are performed varies across individuals. Supporting older people in performing their everyday activities is a major avenue of research in smart homes. However, because of its early stage, this line of work has paid little attention on customizing assistive computing support with respect to the specific needs of each older adult towards improving its effectiveness and acceptability. We propose a tool-based approach to allowing caregivers to define services in the area of home daily living, leveraging their knowledge and expertise on the older adult they care for. This approach consists of two stages: 1) a wizard allows caregivers to define an assistive service, which supports aspects of a daily activity that are specific to an older adult; 2) the wizard-generated service is uploaded in an existing smart home platform and interpreted by a dedicated component, carrying out the caregiver-defined service. Our approach has been implemented. Our wizard has been successfully used to define existing manually-programmed, activity-supporting services. The resulting services have been deployed and executed by an existing assisted living platform deployed in the home of community-dwelling individuals. They have been shown to be equivalent to their manually-programmed counterparts. We also conducted an ergonomics study involving five occupational therapists, who tested our wizard with clinical vignettes describing fictitious patients. Participants were able to successfully define services while revealing an ease of use of our wizard.","PeriodicalId":49316,"journal":{"name":"Journal of Ambient Intelligence and Smart Environments","volume":"70 1","pages":"453-471"},"PeriodicalIF":1.7,"publicationDate":"2021-11-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80287866","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Gabriele Civitarese, Juan Ye, Matteo Zampatti, C. Bettini
One of the major challenges in Human Activity Recognition (HAR) based on machine learning is the scarcity of labeled data. Indeed, collecting a sufficient amount of training data to build a reliable recognition problem is often prohibitive. Among the many solutions in the literature to mitigate this issue, collaborative learning is emerging as a promising direction to distribute the annotation burden over multiple users that cooperate to build a shared recognition model. One of the major issues of existing methods is that they assume a static activity model with a fixed set of target activities. In this paper, we propose a novel approach that is based on Growing When Required (GWR) neural networks. A GWR network continuously adapts itself according to the input training data, and hence it is particularly suited when the users share heterogeneous sets of activities. Like in federated learning, for the sake of privacy preservation, each user contributes to the global activity classifier by sharing personal model parameters, and not by directly sharing data. In order to further mitigate privacy threats, we implement a strategy to avoid releasing model parameters that may indirectly reveal information about activities that the user specifically marked as private. Our results on two well-known publicly available datasets show the effectiveness and the flexibility of our approach.
{"title":"Collaborative activity recognition with heterogeneous activity sets and privacy preferences","authors":"Gabriele Civitarese, Juan Ye, Matteo Zampatti, C. Bettini","doi":"10.3233/ais-210018","DOIUrl":"https://doi.org/10.3233/ais-210018","url":null,"abstract":"One of the major challenges in Human Activity Recognition (HAR) based on machine learning is the scarcity of labeled data. Indeed, collecting a sufficient amount of training data to build a reliable recognition problem is often prohibitive. Among the many solutions in the literature to mitigate this issue, collaborative learning is emerging as a promising direction to distribute the annotation burden over multiple users that cooperate to build a shared recognition model. One of the major issues of existing methods is that they assume a static activity model with a fixed set of target activities. In this paper, we propose a novel approach that is based on Growing When Required (GWR) neural networks. A GWR network continuously adapts itself according to the input training data, and hence it is particularly suited when the users share heterogeneous sets of activities. Like in federated learning, for the sake of privacy preservation, each user contributes to the global activity classifier by sharing personal model parameters, and not by directly sharing data. In order to further mitigate privacy threats, we implement a strategy to avoid releasing model parameters that may indirectly reveal information about activities that the user specifically marked as private. Our results on two well-known publicly available datasets show the effectiveness and the flexibility of our approach.","PeriodicalId":49316,"journal":{"name":"Journal of Ambient Intelligence and Smart Environments","volume":"71 1","pages":"433-452"},"PeriodicalIF":1.7,"publicationDate":"2021-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75135397","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Andrés Muñoz, J. Augusto, V. W. L. Tam, H. Aghajan
Andrés Muñoz a, Juan Carlos Augusto b, Vincent Tam c and Hamid Aghajan d a Polytechnic School, Catholic University of Murcia, Spain b Department of Computer Science and Research Group on Development of Intelligent Environments, Middlesex University, UK c Department of Electrical and Electronic Engineering, Faculty of Engineering, the University of Hong Kong, China d imec, IPI, Department of Telecommunications and Information Processing, Gent University, Belgium
andrs Muñoz a、Juan Carlos Augusto b、Vincent Tam c和Hamid Aghajan d a西班牙天主教大学穆西亚理工学院b英国米德尔塞克斯大学计算机科学与智能环境发展研究小组c中国香港大学工程学院电气与电子工程系d c比利时根特大学电信与信息处理系IPI
{"title":"Preface to JAISE 13(5)","authors":"Andrés Muñoz, J. Augusto, V. W. L. Tam, H. Aghajan","doi":"10.3233/AIS-210608","DOIUrl":"https://doi.org/10.3233/AIS-210608","url":null,"abstract":"Andrés Muñoz a, Juan Carlos Augusto b, Vincent Tam c and Hamid Aghajan d a Polytechnic School, Catholic University of Murcia, Spain b Department of Computer Science and Research Group on Development of Intelligent Environments, Middlesex University, UK c Department of Electrical and Electronic Engineering, Faculty of Engineering, the University of Hong Kong, China d imec, IPI, Department of Telecommunications and Information Processing, Gent University, Belgium","PeriodicalId":49316,"journal":{"name":"Journal of Ambient Intelligence and Smart Environments","volume":"1 1","pages":"345-346"},"PeriodicalIF":1.7,"publicationDate":"2021-09-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"87064640","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Yu Wang, G. Rajesh, X. M. Raajini, N. Kritika, A. Kavinkumar, Syed Bilal Hussain Shah
{"title":"Machine learning-based ship detection and tracking using satellite images for maritime surveillance","authors":"Yu Wang, G. Rajesh, X. M. Raajini, N. Kritika, A. Kavinkumar, Syed Bilal Hussain Shah","doi":"10.3233/AIS-210610","DOIUrl":"https://doi.org/10.3233/AIS-210610","url":null,"abstract":"","PeriodicalId":49316,"journal":{"name":"Journal of Ambient Intelligence and Smart Environments","volume":"39 1","pages":"361-371"},"PeriodicalIF":1.7,"publicationDate":"2021-08-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"75412563","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Marcelo Orenes-Vera, Fernando Terroso-Sáenz, M. Valdés-Vela
{"title":"RECITE: A framework for user trajectory analysis in cultural sites","authors":"Marcelo Orenes-Vera, Fernando Terroso-Sáenz, M. Valdés-Vela","doi":"10.3233/AIS-210612","DOIUrl":"https://doi.org/10.3233/AIS-210612","url":null,"abstract":"","PeriodicalId":49316,"journal":{"name":"Journal of Ambient Intelligence and Smart Environments","volume":"32 1","pages":"389-409"},"PeriodicalIF":1.7,"publicationDate":"2021-08-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86332600","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","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：