Pub Date : 2017-07-01DOI: 10.1109/HSI.2017.8005015
Howard J. Carey, Kasun Amarasinghe, M. Manic
Epileptic seizure source identification involves neurologists combing through a substantial amount of data manually, which sometimes takes weeks per patient. This paper presents a methodology for minimizing the amount of data a neurologist has to analyze to identify the seizure focus. The method keeps the neurologist as the final decision maker and aids in the decision making process. It has to be noted that the primary focus of the work was not improving the accuracy of interictal spike detection but reduction of the volume of data. The presented methodology is based on Artificial Neural Networks (ANN) and is implemented on EEG data collected on 5 patients using a dense array EEG reader. As a baseline, a simple template matching was implemented on the same dataset. Experimental results showed that the ANN based methodology was able to reduce the dataset by 98%, a significant improvement on the template matching method.
{"title":"Reduction of massive EEG datasets for epilepsy analysis using Artificial Neural Networks","authors":"Howard J. Carey, Kasun Amarasinghe, M. Manic","doi":"10.1109/HSI.2017.8005015","DOIUrl":"https://doi.org/10.1109/HSI.2017.8005015","url":null,"abstract":"Epileptic seizure source identification involves neurologists combing through a substantial amount of data manually, which sometimes takes weeks per patient. This paper presents a methodology for minimizing the amount of data a neurologist has to analyze to identify the seizure focus. The method keeps the neurologist as the final decision maker and aids in the decision making process. It has to be noted that the primary focus of the work was not improving the accuracy of interictal spike detection but reduction of the volume of data. The presented methodology is based on Artificial Neural Networks (ANN) and is implemented on EEG data collected on 5 patients using a dense array EEG reader. As a baseline, a simple template matching was implemented on the same dataset. Experimental results showed that the ANN based methodology was able to reduce the dataset by 98%, a significant improvement on the template matching method.","PeriodicalId":355011,"journal":{"name":"2017 10th International Conference on Human System Interactions (HSI)","volume":"671 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115120292","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}
In this paper, we presented a low cost assistive device of an exoskeleton robot, to assist the lower limb muscle by following the gait pattern generation. The paper presents the technique how to duplicate the natural gait motion pattern based robotic platform from the neutral person motion as data pattern generation, to control the positioning of foot trajectory by following the data pattern generation which is performed by the embedded system. The distributed control is applied with four slave controllers and a master controller. Four slave controllers are performed to control the four dc motors for the joint revolute of hip and knee of both leg with the PID control technique of each joint. A master controller is to compute the data parameterized trajectories and the positioning of trajectory pattern. Our approach is successfully generated motion of the gait pattern and positioning control of the lower limp exoskeleton. The experimental results are demonstrated the gait pattern generation and robot locomotion.
{"title":"Design and development of low-cost assistive device for lower limb exoskeleton robot","authors":"Wanayuth Sanngoen, Setawichock Nillnawarad, Sema Patchim","doi":"10.1109/HSI.2017.8005017","DOIUrl":"https://doi.org/10.1109/HSI.2017.8005017","url":null,"abstract":"In this paper, we presented a low cost assistive device of an exoskeleton robot, to assist the lower limb muscle by following the gait pattern generation. The paper presents the technique how to duplicate the natural gait motion pattern based robotic platform from the neutral person motion as data pattern generation, to control the positioning of foot trajectory by following the data pattern generation which is performed by the embedded system. The distributed control is applied with four slave controllers and a master controller. Four slave controllers are performed to control the four dc motors for the joint revolute of hip and knee of both leg with the PID control technique of each joint. A master controller is to compute the data parameterized trajectories and the positioning of trajectory pattern. Our approach is successfully generated motion of the gait pattern and positioning control of the lower limp exoskeleton. The experimental results are demonstrated the gait pattern generation and robot locomotion.","PeriodicalId":355011,"journal":{"name":"2017 10th International Conference on Human System Interactions (HSI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121572789","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 : 2017-07-01DOI: 10.1109/HSI.2017.8005022
Daisuke Yamazaki, M. Niitsuma
Industrial robots are introduced in not only large enterprises but also small and medium enterprises (SMEs). Professional engineers are required when introducing and maintaining industrial robots. However, sometimes it is difficult for SMEs to do this by themselves because of economical limitations. Therefore, in many cases, they need to ask the outside for the support. To assist this situation, an aiding system for remote operation of industrial robots has been studied. This system provides information of the local site to an operator who is in the remote site using auditory and visual information. From this, the operator is able to perceive the working situation of the robot remotely. However, when several kinds of auditory information are presented at same time, recognition of the information becomes difficult. In addition, if too many kinds of visual information are presented, it is also difficult for the operator to pay attention appropriately. To solve the problem, we have proposed vibrotactile interfaces to assist information presentation for aiding remote operation of an industrial robot. In this paper, we attempt to present contact information using a vibrotactile glove when contact between an end-effector of a robot and an object occurs. We proposed two types of vibration stimuli to present the contact information. We investigate how human subjects correctly perceive the contact information through the vibration-based presentations compared with a visual based presentation. Subjects? performance of the contact information perception is evaluated based on perceived time, cognitive time and correct answer rate of the contact information.
{"title":"Presentation of contact information of industrial robot's end-effector using vibrotactile sensation","authors":"Daisuke Yamazaki, M. Niitsuma","doi":"10.1109/HSI.2017.8005022","DOIUrl":"https://doi.org/10.1109/HSI.2017.8005022","url":null,"abstract":"Industrial robots are introduced in not only large enterprises but also small and medium enterprises (SMEs). Professional engineers are required when introducing and maintaining industrial robots. However, sometimes it is difficult for SMEs to do this by themselves because of economical limitations. Therefore, in many cases, they need to ask the outside for the support. To assist this situation, an aiding system for remote operation of industrial robots has been studied. This system provides information of the local site to an operator who is in the remote site using auditory and visual information. From this, the operator is able to perceive the working situation of the robot remotely. However, when several kinds of auditory information are presented at same time, recognition of the information becomes difficult. In addition, if too many kinds of visual information are presented, it is also difficult for the operator to pay attention appropriately. To solve the problem, we have proposed vibrotactile interfaces to assist information presentation for aiding remote operation of an industrial robot. In this paper, we attempt to present contact information using a vibrotactile glove when contact between an end-effector of a robot and an object occurs. We proposed two types of vibration stimuli to present the contact information. We investigate how human subjects correctly perceive the contact information through the vibration-based presentations compared with a visual based presentation. Subjects? performance of the contact information perception is evaluated based on perceived time, cognitive time and correct answer rate of the contact information.","PeriodicalId":355011,"journal":{"name":"2017 10th International Conference on Human System Interactions (HSI)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133411535","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 : 2017-07-01DOI: 10.1109/HSI.2017.8005029
Heeryon Cho, S. Yoon
While the performance of sentiment classification has steadily risen through the introduction of various feature-based methods and distributed representation-based approaches, less attention was given to the qualitative aspect of classification, for instance, the identification of useful words in individual opinion texts. We present an approach using set operations for identifying useful words for sentiment classification, and employ truncated singular value decomposition (SVD), a classic low-rank matrix decomposition technique for document retrieval, in order to tackle the issue of both synonymy and noise removal. The sentiment classification performance of our approach, which concatenates three kinds of features, outperforms the existing word-based and distributed word representation-based methods and is comparable to the existing state of the art distributed document representation-based approaches.
{"title":"Improving sentiment classification through distinct word selection","authors":"Heeryon Cho, S. Yoon","doi":"10.1109/HSI.2017.8005029","DOIUrl":"https://doi.org/10.1109/HSI.2017.8005029","url":null,"abstract":"While the performance of sentiment classification has steadily risen through the introduction of various feature-based methods and distributed representation-based approaches, less attention was given to the qualitative aspect of classification, for instance, the identification of useful words in individual opinion texts. We present an approach using set operations for identifying useful words for sentiment classification, and employ truncated singular value decomposition (SVD), a classic low-rank matrix decomposition technique for document retrieval, in order to tackle the issue of both synonymy and noise removal. The sentiment classification performance of our approach, which concatenates three kinds of features, outperforms the existing word-based and distributed word representation-based methods and is comparable to the existing state of the art distributed document representation-based approaches.","PeriodicalId":355011,"journal":{"name":"2017 10th International Conference on Human System Interactions (HSI)","volume":"91 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130579946","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 : 2017-07-01DOI: 10.1109/HSI.2017.8005035
Van-Thanh Hoang, K. Jo
This paper tackles the problem of reconstructing 3D human poses from 2D landmarks, which is still an ill-posed problem. A widely-used approach is active shape model (ASM) which considers an unknown 3D shape as a linear combination of predefined basis shapes. The existing methods often resolve an optimization problem to reckon the weights and viewpoints of basis shapes, but they could fall into a locally-optimal and/or not use in the real-time system. In this paper, we propose an improved method by doing categorize database into subspaces to reduce execution time and make reconstruction accuracy better in four steps: (i) Separating 3D shapes in training database into subspaces based on their features. (ii) Learning predefined basis shapes of each subspace. (iii) Reconstructing 3D human poses from basis shapes of all subspaces. (iv) Picking out the best shape among them as the final result.
{"title":"An improved method for 3D shape estimation using active shape model","authors":"Van-Thanh Hoang, K. Jo","doi":"10.1109/HSI.2017.8005035","DOIUrl":"https://doi.org/10.1109/HSI.2017.8005035","url":null,"abstract":"This paper tackles the problem of reconstructing 3D human poses from 2D landmarks, which is still an ill-posed problem. A widely-used approach is active shape model (ASM) which considers an unknown 3D shape as a linear combination of predefined basis shapes. The existing methods often resolve an optimization problem to reckon the weights and viewpoints of basis shapes, but they could fall into a locally-optimal and/or not use in the real-time system. In this paper, we propose an improved method by doing categorize database into subspaces to reduce execution time and make reconstruction accuracy better in four steps: (i) Separating 3D shapes in training database into subspaces based on their features. (ii) Learning predefined basis shapes of each subspace. (iii) Reconstructing 3D human poses from basis shapes of all subspaces. (iv) Picking out the best shape among them as the final result.","PeriodicalId":355011,"journal":{"name":"2017 10th International Conference on Human System Interactions (HSI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126984283","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 : 2017-07-01DOI: 10.1109/HSI.2017.8004999
Geun-Hoo Lee, Gyuyeong Kim, Jong-Gwan Song, O. F. Ince, Jangsik Park
This paper is an approach for pedestrian detection and tracking with infrared imagery. The detection phase is performed by AdaBoost algorithm based on Haar-like features. AdaBoost classifier is trained with datasets generated from infrared images. The number of negative images used for training with AdaBoost algorithm is 3000. For positive training, 1000 samples are used After detecting the pedestrian with AdaBoost classifier, we proposed the Tracking-Learning-Detection (TLD) frameworks tracking strategies. TLD frameworks are preferred in this study because of its high accuracy rate and computation speed Tracking performance comparison is made between TLD and particle filtering. Results prove that TLD performs a higher tracking rate than particle filtering.
{"title":"Video based pedestrian detection and tracking at night-time","authors":"Geun-Hoo Lee, Gyuyeong Kim, Jong-Gwan Song, O. F. Ince, Jangsik Park","doi":"10.1109/HSI.2017.8004999","DOIUrl":"https://doi.org/10.1109/HSI.2017.8004999","url":null,"abstract":"This paper is an approach for pedestrian detection and tracking with infrared imagery. The detection phase is performed by AdaBoost algorithm based on Haar-like features. AdaBoost classifier is trained with datasets generated from infrared images. The number of negative images used for training with AdaBoost algorithm is 3000. For positive training, 1000 samples are used After detecting the pedestrian with AdaBoost classifier, we proposed the Tracking-Learning-Detection (TLD) frameworks tracking strategies. TLD frameworks are preferred in this study because of its high accuracy rate and computation speed Tracking performance comparison is made between TLD and particle filtering. Results prove that TLD performs a higher tracking rate than particle filtering.","PeriodicalId":355011,"journal":{"name":"2017 10th International Conference on Human System Interactions (HSI)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126028170","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 : 2017-07-01DOI: 10.1109/HSI.2017.8005023
Karam Dad, Jie Wang, S. Abbasi, Min-Cheol Lee
In this paper, proposed a reaction force estimation and bilateral control of master slave manipulation in hydraulic servo system based on Sliding mode control with sliding perturbation observer (SMCSPO). The reaction force is estimated by sliding perturbation observer (SPO) without using any force sensor. The estimated reaction force without force sensor is transmitted to the master device using the impedance model controller. Sliding mode control (SMC) is used to a bilateral controller for the position and force tracking control of a slave. This study proves in experiment that the slaver of a hydraulic servo system can follow the trajectory of the master device (Human Command) using the bilateral control scheme.
{"title":"Reaction force estimation and bilateral control of master slave manipulation using a robust controller","authors":"Karam Dad, Jie Wang, S. Abbasi, Min-Cheol Lee","doi":"10.1109/HSI.2017.8005023","DOIUrl":"https://doi.org/10.1109/HSI.2017.8005023","url":null,"abstract":"In this paper, proposed a reaction force estimation and bilateral control of master slave manipulation in hydraulic servo system based on Sliding mode control with sliding perturbation observer (SMCSPO). The reaction force is estimated by sliding perturbation observer (SPO) without using any force sensor. The estimated reaction force without force sensor is transmitted to the master device using the impedance model controller. Sliding mode control (SMC) is used to a bilateral controller for the position and force tracking control of a slave. This study proves in experiment that the slaver of a hydraulic servo system can follow the trajectory of the master device (Human Command) using the bilateral control scheme.","PeriodicalId":355011,"journal":{"name":"2017 10th International Conference on Human System Interactions (HSI)","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129176292","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 : 2017-07-01DOI: 10.1109/HSI.2017.8005027
Duc Cong Dang, Y. Suh
An algorithm for estimating the walking stick movement information is proposed using an inertial sensor attached on the stick. A standard inertial navigation algorithm using an indirect Kalman filter is applied to update velocity and position of the walking stick during movement. The proposed algorithm is verified with three-meter walking experiments.
{"title":"Pedestrian navigation algorithm using inertial-based walking stick","authors":"Duc Cong Dang, Y. Suh","doi":"10.1109/HSI.2017.8005027","DOIUrl":"https://doi.org/10.1109/HSI.2017.8005027","url":null,"abstract":"An algorithm for estimating the walking stick movement information is proposed using an inertial sensor attached on the stick. A standard inertial navigation algorithm using an indirect Kalman filter is applied to update velocity and position of the walking stick during movement. The proposed algorithm is verified with three-meter walking experiments.","PeriodicalId":355011,"journal":{"name":"2017 10th International Conference on Human System Interactions (HSI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129555890","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 : 2017-07-01DOI: 10.1109/HSI.2017.8005020
A. Vo, Hee-Jun Kang, V. Nguyen
In this paper, a novel output feedback tracking control scheme based on neural sliding mode without joint velocity measurement and the high order sliding mode observer for the uncertainty of robot manipulators are presented. Two second-order sliding mode observers are designed to estimate joint velocities and dynamic uncertainties of the robot manipulator, respectively. The first-second order sliding mode observer is used to estimate the state vector in a finite time without filtration. To estimate the uncertainties without filtration, the second second-order sliding mode nonlinear observer is designed. By integrating two observers, the resulting observer can theoretically obtain exact estimations of both joint velocities and dynamic uncertainties. They are used to design an output feedback tracking control scheme based on neural sliding mode controller. This proposed control scheme can reduce chattering and improves tracking performances. Finally, the simulation for a 2-DOF robot manipulator is given to show the effectiveness of this control strategy.
{"title":"An output feedback tracking control based on neural sliding mode and high order sliding mode observer","authors":"A. Vo, Hee-Jun Kang, V. Nguyen","doi":"10.1109/HSI.2017.8005020","DOIUrl":"https://doi.org/10.1109/HSI.2017.8005020","url":null,"abstract":"In this paper, a novel output feedback tracking control scheme based on neural sliding mode without joint velocity measurement and the high order sliding mode observer for the uncertainty of robot manipulators are presented. Two second-order sliding mode observers are designed to estimate joint velocities and dynamic uncertainties of the robot manipulator, respectively. The first-second order sliding mode observer is used to estimate the state vector in a finite time without filtration. To estimate the uncertainties without filtration, the second second-order sliding mode nonlinear observer is designed. By integrating two observers, the resulting observer can theoretically obtain exact estimations of both joint velocities and dynamic uncertainties. They are used to design an output feedback tracking control scheme based on neural sliding mode controller. This proposed control scheme can reduce chattering and improves tracking performances. Finally, the simulation for a 2-DOF robot manipulator is given to show the effectiveness of this control strategy.","PeriodicalId":355011,"journal":{"name":"2017 10th International Conference on Human System Interactions (HSI)","volume":"195 ","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114005196","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 : 2017-07-01DOI: 10.1109/HSI.2017.8005041
Jimin Pi, Bertram E. Shi
Requiring a dwell time before selection is a common way to solve “Midas-touch problem” in gaze-based interaction. Choosing the dwell time involves a tradeoff between unintentional selection for short dwell times and slow text entry for long dwell times. We propose a probabilistic model for gaze based selection, which adjusts the dwell time based on the probability of each letter based on the past letters selected. By reformulating the entire problem of gaze-based selection probabilistically, we can naturally integrate the probability of each character naturally and with very few prior assumptions and very few free parameters. It automatically assigns shorter dwell times to more likely characters and longer dwell times to less likely characters. Our experimental results demonstrate that the proposed technique speeds up typing without loss in accuracy. The concept of this can be generalized to other dwell-based applications, leading to more efficient gaze system interaction.
{"title":"Probabilistic adjustment of dwell time for eye typing","authors":"Jimin Pi, Bertram E. Shi","doi":"10.1109/HSI.2017.8005041","DOIUrl":"https://doi.org/10.1109/HSI.2017.8005041","url":null,"abstract":"Requiring a dwell time before selection is a common way to solve “Midas-touch problem” in gaze-based interaction. Choosing the dwell time involves a tradeoff between unintentional selection for short dwell times and slow text entry for long dwell times. We propose a probabilistic model for gaze based selection, which adjusts the dwell time based on the probability of each letter based on the past letters selected. By reformulating the entire problem of gaze-based selection probabilistically, we can naturally integrate the probability of each character naturally and with very few prior assumptions and very few free parameters. It automatically assigns shorter dwell times to more likely characters and longer dwell times to less likely characters. Our experimental results demonstrate that the proposed technique speeds up typing without loss in accuracy. The concept of this can be generalized to other dwell-based applications, leading to more efficient gaze system interaction.","PeriodicalId":355011,"journal":{"name":"2017 10th International Conference on Human System Interactions (HSI)","volume":"75 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2017-07-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122801047","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：