Pub Date : 2021-12-17DOI: 10.1109/PIC53636.2021.9687047
H. Shah, R. Mariescu-Istodor, P. Fränti
We present a supervised method for keyword extraction from webpages. The method divides the HTML page into meaningful segments using document object model (DOM) and calculates a language independent feature vector for each word. Based on these, we generate a classification model that gives a likelihood for a word to be a keyword. The most likely words are then selected. We analyze the usefulness of the features on different datasets (news articles and service web pages) and compare different classification methods for the task. Results show that random forest performs best and provides up to 27.8 %- unit improvement compared to the best existing method.
{"title":"WebRank: Language-Independent Extraction of Keywords from Webpages","authors":"H. Shah, R. Mariescu-Istodor, P. Fränti","doi":"10.1109/PIC53636.2021.9687047","DOIUrl":"https://doi.org/10.1109/PIC53636.2021.9687047","url":null,"abstract":"We present a supervised method for keyword extraction from webpages. The method divides the HTML page into meaningful segments using document object model (DOM) and calculates a language independent feature vector for each word. Based on these, we generate a classification model that gives a likelihood for a word to be a keyword. The most likely words are then selected. We analyze the usefulness of the features on different datasets (news articles and service web pages) and compare different classification methods for the task. Results show that random forest performs best and provides up to 27.8 %- unit improvement compared to the best existing method.","PeriodicalId":297239,"journal":{"name":"2021 IEEE International Conference on Progress in Informatics and Computing (PIC)","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124020312","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 : 2021-12-17DOI: 10.1109/PIC53636.2021.9687080
Shenghan Zhang, Binyi Zou, Binquan Xu, Jionglong Su, Huafeng Hu
Since the outbreak of COVID-19 in 2019, more than 200 million individuals have been infected worldwide, resulting in over four million deaths. Although large-scale nucleic acid test is an effective way to diagnose COVID-19, the possibility of false positives or false negatives means that the chest CT scan remains a necessary tool in COVID-19 diagnosis for cross-validation. A lot of research has been carried out using deep learning methods for COVID-19 diagnosis using CT scans. However, privacy concerns result in very limited datasets being publicly available. In this research, we propose a novel framework based on the centripetal contrastive learning of visual representations (CeCLR) method with stacking ensemble learning to represent features more efficiently so as to achieve better performance on a limited COVID-19 dataset. Experimental results demonstrate that our deep learning system is superior to other baseline models. Our method achieves an F1 score of 0.914, AUC of 0.952, and accuracy of 0.909 when diagnosing COVID-19 on CT scans.
{"title":"An Efficient Deep Learning Framework of COVID-19 CT Scans Using Contrastive Learning and Ensemble Strategy","authors":"Shenghan Zhang, Binyi Zou, Binquan Xu, Jionglong Su, Huafeng Hu","doi":"10.1109/PIC53636.2021.9687080","DOIUrl":"https://doi.org/10.1109/PIC53636.2021.9687080","url":null,"abstract":"Since the outbreak of COVID-19 in 2019, more than 200 million individuals have been infected worldwide, resulting in over four million deaths. Although large-scale nucleic acid test is an effective way to diagnose COVID-19, the possibility of false positives or false negatives means that the chest CT scan remains a necessary tool in COVID-19 diagnosis for cross-validation. A lot of research has been carried out using deep learning methods for COVID-19 diagnosis using CT scans. However, privacy concerns result in very limited datasets being publicly available. In this research, we propose a novel framework based on the centripetal contrastive learning of visual representations (CeCLR) method with stacking ensemble learning to represent features more efficiently so as to achieve better performance on a limited COVID-19 dataset. Experimental results demonstrate that our deep learning system is superior to other baseline models. Our method achieves an F1 score of 0.914, AUC of 0.952, and accuracy of 0.909 when diagnosing COVID-19 on CT scans.","PeriodicalId":297239,"journal":{"name":"2021 IEEE International Conference on Progress in Informatics and Computing (PIC)","volume":"103 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117311172","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}
With the development of education data mining and the data of academic affairs accumulated, the performance of students in school could be analyzed from different views and explore more precious aspects which influence the grades of students. Our research conducts data mining on student basic courses information, learning behavior information and admission information, which will help to find the relationship between them. This work mainly focus on exploring the key features that take the important roles in student academic performance. Then the work takes the consider of identifying the relationship between student behaviors and their grades. By using the advanced machine learning methods and feature analysis methods, LASSO, the work rated the most important features of student behaviors. We found several key relationships between student behaviors and their grades, for example, the more books one borrows, the better grade he/she will get. This work would help the educators and students to better understand the relationship between connotative factors and the student achievement.
{"title":"Identifying Key Features in Student Grade Prediction","authors":"Jiaqi Cui, Yupei Zhang, Rui An, Yue Yun, Huan Dai, Xuequn Shang","doi":"10.1109/PIC53636.2021.9687042","DOIUrl":"https://doi.org/10.1109/PIC53636.2021.9687042","url":null,"abstract":"With the development of education data mining and the data of academic affairs accumulated, the performance of students in school could be analyzed from different views and explore more precious aspects which influence the grades of students. Our research conducts data mining on student basic courses information, learning behavior information and admission information, which will help to find the relationship between them. This work mainly focus on exploring the key features that take the important roles in student academic performance. Then the work takes the consider of identifying the relationship between student behaviors and their grades. By using the advanced machine learning methods and feature analysis methods, LASSO, the work rated the most important features of student behaviors. We found several key relationships between student behaviors and their grades, for example, the more books one borrows, the better grade he/she will get. This work would help the educators and students to better understand the relationship between connotative factors and the student achievement.","PeriodicalId":297239,"journal":{"name":"2021 IEEE International Conference on Progress in Informatics and Computing (PIC)","volume":"4 4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123264339","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 : 2021-12-17DOI: 10.1109/pic53636.2021.9687012
{"title":"[Copyright notice]","authors":"","doi":"10.1109/pic53636.2021.9687012","DOIUrl":"https://doi.org/10.1109/pic53636.2021.9687012","url":null,"abstract":"","PeriodicalId":297239,"journal":{"name":"2021 IEEE International Conference on Progress in Informatics and Computing (PIC)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123886884","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 : 2021-12-17DOI: 10.1109/PIC53636.2021.9687086
Bin Zhang, Junjie Moh, Hun-ok Lim
In this research, an automatic navigation system for a bipedal humanoid robot is proposed. The robot firstly moves around in the working space to build a 3D map by using SLAM (Simultaneous Localization and Mapping), and then move toward its destination according to the generated global and local path by using Dijkstra's algorithm and Dynamics Window Approach separately. The effectiveness of the proposed system is proven by simulation experiments.
本文提出了一种双足仿人机器人的自动导航系统。机器人首先在工作空间内移动，利用SLAM (Simultaneous Localization and Mapping)方法构建三维地图，然后分别利用Dijkstra算法和Dynamics Window方法根据生成的全局路径和局部路径向目的地移动。仿真实验证明了该系统的有效性。
{"title":"Research on Automatic Navigation for a Bipedal Humanoid Robot","authors":"Bin Zhang, Junjie Moh, Hun-ok Lim","doi":"10.1109/PIC53636.2021.9687086","DOIUrl":"https://doi.org/10.1109/PIC53636.2021.9687086","url":null,"abstract":"In this research, an automatic navigation system for a bipedal humanoid robot is proposed. The robot firstly moves around in the working space to build a 3D map by using SLAM (Simultaneous Localization and Mapping), and then move toward its destination according to the generated global and local path by using Dijkstra's algorithm and Dynamics Window Approach separately. The effectiveness of the proposed system is proven by simulation experiments.","PeriodicalId":297239,"journal":{"name":"2021 IEEE International Conference on Progress in Informatics and Computing (PIC)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121724654","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 : 2021-12-17DOI: 10.1109/PIC53636.2021.9687085
Shunxian Gu, Xinning Song
Epilepsy is one of the most common neurological diseases worldwide as a common mental disorder. Seizure prediction plays a vital role in improving a patient’s quality of life. This paper proposes a patient-specific seizure prediction method based on multi-scale feature fusion. This study aims at developing an efficient and automatic seizure prediction technique by raw scalp EEG signals with reduced channels. The proposed approach utilizes the deep convolutional neural network in noise handling and the recurrent neural network in establishing contextual correlation. Not any manual feature engineering is performed on the raw EEG data. A multi-scale fusion approach based on the downsampling technique is introduced to compensate for the performance degradation problem caused by reduced channels. 2 is proven to be the best view number. Our proposed C-Bi-LSTM model with multi-views provides the highest overall accuracy of 99.597% and the lowest false positive rate of 0.004 per hour by comparing the classification results.
{"title":"An Efficient Seizure Prediction Method Based on Multi-scale Feature Fusion with Reduced Channels","authors":"Shunxian Gu, Xinning Song","doi":"10.1109/PIC53636.2021.9687085","DOIUrl":"https://doi.org/10.1109/PIC53636.2021.9687085","url":null,"abstract":"Epilepsy is one of the most common neurological diseases worldwide as a common mental disorder. Seizure prediction plays a vital role in improving a patient’s quality of life. This paper proposes a patient-specific seizure prediction method based on multi-scale feature fusion. This study aims at developing an efficient and automatic seizure prediction technique by raw scalp EEG signals with reduced channels. The proposed approach utilizes the deep convolutional neural network in noise handling and the recurrent neural network in establishing contextual correlation. Not any manual feature engineering is performed on the raw EEG data. A multi-scale fusion approach based on the downsampling technique is introduced to compensate for the performance degradation problem caused by reduced channels. 2 is proven to be the best view number. Our proposed C-Bi-LSTM model with multi-views provides the highest overall accuracy of 99.597% and the lowest false positive rate of 0.004 per hour by comparing the classification results.","PeriodicalId":297239,"journal":{"name":"2021 IEEE International Conference on Progress in Informatics and Computing (PIC)","volume":"77 4 Pt 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115041558","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 : 2021-12-17DOI: 10.1109/PIC53636.2021.9687008
Jinshuo Zhang, Zhicheng Wang, Songyan Zhang, Gang Wei, Z. Xiong, Meng Yang
To enhance the performance of existing deep neural networks in semantic segmentation while preserving efficiency at the same time, a semantic segmentation network with the help of GAN (Generative Adversarial Networks) is proposed. The method consists of a generator and a discriminator. The segmentation results obtained from the generator are encoded and then fed into the discriminator to obtain the pixel-wise uncertainty values. Such uncertainty values are taken as weights for the calculation of CEGU (Cross-Entropy with GAN Uncertainty) to help the optimization of the generator. The discriminator is removed after training. Experiment results show that the mean IoU (Intersection over Union) scores of the segmentation results grow by 4.7% and 3.2% respectively on ResNet-50 and ResNet18, after using the GAN auxiliary method along with the CEGU. It shows that such a GAN auxiliary network can significantly improve the performance of basic end-to-end methods with various backbones on the semantic segmentation task, without introducing extra computation cost in the test phase.
为了提高现有深度神经网络在语义分割方面的性能，同时保持效率，提出了一种基于生成式对抗网络(GAN)的语义分割网络。该方法由一个生成器和一个鉴别器组成。对从生成器获得的分割结果进行编码，然后将其输入鉴别器以获得逐像素的不确定性值。将这些不确定性值作为权重计算CEGU (Cross-Entropy with GAN uncertainty)，以帮助优化发电机。训练后去除鉴别器。实验结果表明，在ResNet-50和ResNet18上，GAN辅助方法与CEGU结合使用后，分割结果的平均IoU分数分别提高了4.7%和3.2%。实验结果表明，该GAN辅助网络在不增加测试阶段额外计算成本的情况下，可以显著提高具有不同主干的端到端基本语义分割方法的性能。
{"title":"Image Semantic Segmentation Based on the GAN Auxiliary Network","authors":"Jinshuo Zhang, Zhicheng Wang, Songyan Zhang, Gang Wei, Z. Xiong, Meng Yang","doi":"10.1109/PIC53636.2021.9687008","DOIUrl":"https://doi.org/10.1109/PIC53636.2021.9687008","url":null,"abstract":"To enhance the performance of existing deep neural networks in semantic segmentation while preserving efficiency at the same time, a semantic segmentation network with the help of GAN (Generative Adversarial Networks) is proposed. The method consists of a generator and a discriminator. The segmentation results obtained from the generator are encoded and then fed into the discriminator to obtain the pixel-wise uncertainty values. Such uncertainty values are taken as weights for the calculation of CEGU (Cross-Entropy with GAN Uncertainty) to help the optimization of the generator. The discriminator is removed after training. Experiment results show that the mean IoU (Intersection over Union) scores of the segmentation results grow by 4.7% and 3.2% respectively on ResNet-50 and ResNet18, after using the GAN auxiliary method along with the CEGU. It shows that such a GAN auxiliary network can significantly improve the performance of basic end-to-end methods with various backbones on the semantic segmentation task, without introducing extra computation cost in the test phase.","PeriodicalId":297239,"journal":{"name":"2021 IEEE International Conference on Progress in Informatics and Computing (PIC)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124704528","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 : 2021-12-17DOI: 10.1109/PIC53636.2021.9687065
Xing Wu, Yangyang Qi, Bin Tang, Hairan Liu
Scene Text Detection (STD) is important for developing many popular technologies, such as Security and Automatic Driving. However, the existing text detection models are based on unified text shape and single background, which does not accord with the text characteristics in the natural scene. To detect arbitrarily shaped text with a complex background, we proposed a method based on deformable attention mechanism and named DA-STD. At first, a feature enhancement module named FPEM is applied to enhance the image’s ability of representation learning. In addition, unlike the attention in the vanilla Transformer, our method adopts the deformable attention module interested in the pixels around the sampling points rather than the global features to make relational modeling. Experiments show that not only can we effectively improve the performance of the model but also greatly save the computational cost in this way.
{"title":"DA-STD: Deformable Attention-Based Scene Text Detection in Arbitrary Shape","authors":"Xing Wu, Yangyang Qi, Bin Tang, Hairan Liu","doi":"10.1109/PIC53636.2021.9687065","DOIUrl":"https://doi.org/10.1109/PIC53636.2021.9687065","url":null,"abstract":"Scene Text Detection (STD) is important for developing many popular technologies, such as Security and Automatic Driving. However, the existing text detection models are based on unified text shape and single background, which does not accord with the text characteristics in the natural scene. To detect arbitrarily shaped text with a complex background, we proposed a method based on deformable attention mechanism and named DA-STD. At first, a feature enhancement module named FPEM is applied to enhance the image’s ability of representation learning. In addition, unlike the attention in the vanilla Transformer, our method adopts the deformable attention module interested in the pixels around the sampling points rather than the global features to make relational modeling. Experiments show that not only can we effectively improve the performance of the model but also greatly save the computational cost in this way.","PeriodicalId":297239,"journal":{"name":"2021 IEEE International Conference on Progress in Informatics and Computing (PIC)","volume":"133 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128524468","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 : 2021-12-17DOI: 10.1109/PIC53636.2021.9687074
Nizam Kuxdorf-Alkirata, D. Brückmann
Indoor localization is a research field that has drawn the attention of many researchers over the last years. In some application scenarios, for example when assisting visually impaired persons with finding their way around within indoor environments, the aspect of dynamic obstacle detection plays an important role. In this work, an optimized localization algorithm based on field strength measurements is presented. Furthermore, methods for dynamic obstacle detection are developed and evaluated. For this purpose, a low-cost infrared array sensor is used. Since most of the encountered dynamic obstacles in indoor environments are generally persons, the major advantage of the proposed concept is that the anonymity of the detected persons is preserved and there are no conflicts with data protection regulations. It will be shown that reliable and accurate indoor localization based on field strength measurements within a wireless mesh network can be carried out. Also the detection of moving persons is possible and even the movement patterns of two persons simultaneously crossing the field of view of the sensor can be displayed. The achieved results are verified by extensive measurements and descriptive statistics.
{"title":"An Optimized Algorithm for Indoor Localization and Concepts for Anonymous Dynamic Obstacle Detection","authors":"Nizam Kuxdorf-Alkirata, D. Brückmann","doi":"10.1109/PIC53636.2021.9687074","DOIUrl":"https://doi.org/10.1109/PIC53636.2021.9687074","url":null,"abstract":"Indoor localization is a research field that has drawn the attention of many researchers over the last years. In some application scenarios, for example when assisting visually impaired persons with finding their way around within indoor environments, the aspect of dynamic obstacle detection plays an important role. In this work, an optimized localization algorithm based on field strength measurements is presented. Furthermore, methods for dynamic obstacle detection are developed and evaluated. For this purpose, a low-cost infrared array sensor is used. Since most of the encountered dynamic obstacles in indoor environments are generally persons, the major advantage of the proposed concept is that the anonymity of the detected persons is preserved and there are no conflicts with data protection regulations. It will be shown that reliable and accurate indoor localization based on field strength measurements within a wireless mesh network can be carried out. Also the detection of moving persons is possible and even the movement patterns of two persons simultaneously crossing the field of view of the sensor can be displayed. The achieved results are verified by extensive measurements and descriptive statistics.","PeriodicalId":297239,"journal":{"name":"2021 IEEE International Conference on Progress in Informatics and Computing (PIC)","volume":"141 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133014795","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 : 2021-12-17DOI: 10.1109/PIC53636.2021.9687048
Yufeng Liu, Fan Yang
Graph grammar is a two-dimensional formal method, providing an intuitive yet formal tool for graphical models. However, existing graph grammar formalisms either ignore the specification of edge semantics or lack the parsing ability. To handle these problems, this paper improves the edge processing of graph grammar by introducing curvatures and bend-directions into the formalism of graph grammar. With an entire update of the theoretical framework and grammatical operations, the expressive power and application scope of graph grammar are both increased. Moreover, an example on simple pattern design is given to illustrate the application of the improved formalism.
{"title":"An Enhancement to Graph Grammar for the Specification of Edge Semantics","authors":"Yufeng Liu, Fan Yang","doi":"10.1109/PIC53636.2021.9687048","DOIUrl":"https://doi.org/10.1109/PIC53636.2021.9687048","url":null,"abstract":"Graph grammar is a two-dimensional formal method, providing an intuitive yet formal tool for graphical models. However, existing graph grammar formalisms either ignore the specification of edge semantics or lack the parsing ability. To handle these problems, this paper improves the edge processing of graph grammar by introducing curvatures and bend-directions into the formalism of graph grammar. With an entire update of the theoretical framework and grammatical operations, the expressive power and application scope of graph grammar are both increased. Moreover, an example on simple pattern design is given to illustrate the application of the improved formalism.","PeriodicalId":297239,"journal":{"name":"2021 IEEE International Conference on Progress in Informatics and Computing (PIC)","volume":"325 Pt A 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131221464","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：