Pub Date : 2023-04-21DOI: 10.1109/ICASI57738.2023.10179542
Yu-Wei Chou, Chen-Wei Liao, Jin-Ruei Shih, Jui-Huan Kuo, Kai-Yi Wong
This research designed and developed an interactive chess board capable of playing Quarto game against humans. The designed interactive chess board utilizes CoreXY mechanism to manipulate the electromagnet to achieve two-dimensional movement under the chess board. Furthermore, the designed interactive chess board employs a depth camera with the YOLOv5 algorithm to identify the features and position of each chess piece. Finally, the game strategy mechanics of the Quarto game are combined to the system for the chess board.
{"title":"Design and Development of an Interactive Chess Board for Quarto","authors":"Yu-Wei Chou, Chen-Wei Liao, Jin-Ruei Shih, Jui-Huan Kuo, Kai-Yi Wong","doi":"10.1109/ICASI57738.2023.10179542","DOIUrl":"https://doi.org/10.1109/ICASI57738.2023.10179542","url":null,"abstract":"This research designed and developed an interactive chess board capable of playing Quarto game against humans. The designed interactive chess board utilizes CoreXY mechanism to manipulate the electromagnet to achieve two-dimensional movement under the chess board. Furthermore, the designed interactive chess board employs a depth camera with the YOLOv5 algorithm to identify the features and position of each chess piece. Finally, the game strategy mechanics of the Quarto game are combined to the system for the chess board.","PeriodicalId":281254,"journal":{"name":"2023 9th International Conference on Applied System Innovation (ICASI)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115438352","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 : 2023-04-21DOI: 10.1109/ICASI57738.2023.10179539
Ping-Chen Wu, Pei-Fang Li, Zong-Tai Wu, J. Hung
State-of-the-art speech enhancement techniques use deep neural networks to improve distorted speech signals. These networks employ an encoder-decoder framework, with the encoder extracting features from the input signal. Our research suggests using discrete wavelet transform (DWT) features as an alternative to existing methods. DWT features work well with time-domain features and improve performance in the adaptive FullSubNet+ framework. This study proposes using wavelet packet decomposition (WPD) to extract features and discarding sub-band WPD features that harm performance. Our method outperforms the original A-FSN in objective speech metrics, making it a promising speech enhancement framework.
{"title":"The Study of Improving the Adaptive FullSubNet+ Speech Enhancement Framework with Selective Wavelet Packet Decomposition Sub-Band Features","authors":"Ping-Chen Wu, Pei-Fang Li, Zong-Tai Wu, J. Hung","doi":"10.1109/ICASI57738.2023.10179539","DOIUrl":"https://doi.org/10.1109/ICASI57738.2023.10179539","url":null,"abstract":"State-of-the-art speech enhancement techniques use deep neural networks to improve distorted speech signals. These networks employ an encoder-decoder framework, with the encoder extracting features from the input signal. Our research suggests using discrete wavelet transform (DWT) features as an alternative to existing methods. DWT features work well with time-domain features and improve performance in the adaptive FullSubNet+ framework. This study proposes using wavelet packet decomposition (WPD) to extract features and discarding sub-band WPD features that harm performance. Our method outperforms the original A-FSN in objective speech metrics, making it a promising speech enhancement framework.","PeriodicalId":281254,"journal":{"name":"2023 9th International Conference on Applied System Innovation (ICASI)","volume":"53 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115681476","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 : 2023-04-21DOI: 10.1109/ICASI57738.2023.10179585
Chao‐Ming Lin
This study is based on the thermal image measurement technology, aiming at the experimental record of the transient process of heat generation, heat dissipation and heat stability of the conductive ball’s resistance through current conduction for the Anisotropic Conductive Film (ACF) assembly specimen after the bending load. The test vehicle of flexible printed circuit (FPC) is conducted by the thermos-compression bonding of the flexible circuit and the transparent substrate (PET / coated ITO) using ACF. The conductive balls in the ACF will be compressed and rupture during the thermos-compression process, and then play the role of electrical conduction. However, after the FPC assembly are subjected to different bending loads, the conductive balls may cause severe cracking or crushing, which will lead to an increase in the resistance of the conductive balls. The thermal image records of this research can be used to obtain the resistance variations before and after loading. Finally, the bending resistance and electrical conduction quality of the ACF can be evaluated by the temperature distributions and average temperature values after the conductive joints resistances have stabilized heat dissipation.
{"title":"Thermal Image Analysis of Conductive Joints of Flexible Printed Circuit (FPC) using Anisotropic Conductive Films (ACF) Bonding","authors":"Chao‐Ming Lin","doi":"10.1109/ICASI57738.2023.10179585","DOIUrl":"https://doi.org/10.1109/ICASI57738.2023.10179585","url":null,"abstract":"This study is based on the thermal image measurement technology, aiming at the experimental record of the transient process of heat generation, heat dissipation and heat stability of the conductive ball’s resistance through current conduction for the Anisotropic Conductive Film (ACF) assembly specimen after the bending load. The test vehicle of flexible printed circuit (FPC) is conducted by the thermos-compression bonding of the flexible circuit and the transparent substrate (PET / coated ITO) using ACF. The conductive balls in the ACF will be compressed and rupture during the thermos-compression process, and then play the role of electrical conduction. However, after the FPC assembly are subjected to different bending loads, the conductive balls may cause severe cracking or crushing, which will lead to an increase in the resistance of the conductive balls. The thermal image records of this research can be used to obtain the resistance variations before and after loading. Finally, the bending resistance and electrical conduction quality of the ACF can be evaluated by the temperature distributions and average temperature values after the conductive joints resistances have stabilized heat dissipation.","PeriodicalId":281254,"journal":{"name":"2023 9th International Conference on Applied System Innovation (ICASI)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116647075","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 : 2023-04-21DOI: 10.1109/ICASI57738.2023.10179520
Shih-Yung Hsu, Yi-Hsuan Lee, Jing-Wei Huang
As Neural Networks have achieved excellent results in many fields, researchers attempt to use Neural Networks to solve graph processing tasks such as node classification, link prediction, and graph classification. Graph Neural Network (GNN) is a machine-learning model that takes graphs as input. In this article, we select active users on a Twitter page and predict their retweet behaviors using Graph Attention Network (GAT). Negative sampling is also applied due to the imbalanced dataset. Experimental results show that GAT well predicts the retweet behavior and tweet count.
{"title":"GNN-based Approach for User Retweet Behavior Prediction","authors":"Shih-Yung Hsu, Yi-Hsuan Lee, Jing-Wei Huang","doi":"10.1109/ICASI57738.2023.10179520","DOIUrl":"https://doi.org/10.1109/ICASI57738.2023.10179520","url":null,"abstract":"As Neural Networks have achieved excellent results in many fields, researchers attempt to use Neural Networks to solve graph processing tasks such as node classification, link prediction, and graph classification. Graph Neural Network (GNN) is a machine-learning model that takes graphs as input. In this article, we select active users on a Twitter page and predict their retweet behaviors using Graph Attention Network (GAT). Negative sampling is also applied due to the imbalanced dataset. Experimental results show that GAT well predicts the retweet behavior and tweet count.","PeriodicalId":281254,"journal":{"name":"2023 9th International Conference on Applied System Innovation (ICASI)","volume":"16 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126075545","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 : 2023-04-21DOI: 10.1109/ICASI57738.2023.10179495
Chia Dai, Wan-Ling Zeng, Jia-Xuan Zeng, J. Hung
Conformer-based MetricGAN (CMGAN) is a deep neural network (DNN)-based speech enhancement (SE) method that uses time-frequency (TF) domain features to learn a novel conformer-wise generative network, and it has demonstrated excellent SE performance in terms of various perceptual evaluation metrics.In this study, we propose to revise CMGAN along three directions. To begin, we incorporate phone-fortified perceptual loss (PFPL) into its loss function. The PFPL is calculated using latent representations of speech from the wav2vec module. With PFPL as part of the loss function can effectively use perceptual and linguistic speech information to direct CMGAN model training. Next, we revise the discriminator output by adding the STOI values. The original discriminator is trained to estimate the enhanced PESQ score by taking both clean and enhanced spectrum as inputs as well as the associated PESQ label. In other words, the initial discriminator only takes into account the PESQ score. By further considering STOI, we expect to improve the discriminator. Finally, we add noise label estimation to the entire CMGAN framework. The original CMGAN only calculates the disparity between the estimated value provided by the model and the clean target with clean labels. Instead, we further take into account noise estimation loss, which can show the discrepancy between the predicted noise and the noise label.The Voicebank-Demand dataset is used for the evaluation experiments. According to the experimental results, the revised CMGAN outperforms the original by gaining greater scores on objective perceptual metrics including PESQ and STOI. As a result, we confirm the success of the presented revisions in CMGAN.
{"title":"Leveraging the Objective Intelligibility and Noise Estimation to Improve Conformer-Based MetricGAN","authors":"Chia Dai, Wan-Ling Zeng, Jia-Xuan Zeng, J. Hung","doi":"10.1109/ICASI57738.2023.10179495","DOIUrl":"https://doi.org/10.1109/ICASI57738.2023.10179495","url":null,"abstract":"Conformer-based MetricGAN (CMGAN) is a deep neural network (DNN)-based speech enhancement (SE) method that uses time-frequency (TF) domain features to learn a novel conformer-wise generative network, and it has demonstrated excellent SE performance in terms of various perceptual evaluation metrics.In this study, we propose to revise CMGAN along three directions. To begin, we incorporate phone-fortified perceptual loss (PFPL) into its loss function. The PFPL is calculated using latent representations of speech from the wav2vec module. With PFPL as part of the loss function can effectively use perceptual and linguistic speech information to direct CMGAN model training. Next, we revise the discriminator output by adding the STOI values. The original discriminator is trained to estimate the enhanced PESQ score by taking both clean and enhanced spectrum as inputs as well as the associated PESQ label. In other words, the initial discriminator only takes into account the PESQ score. By further considering STOI, we expect to improve the discriminator. Finally, we add noise label estimation to the entire CMGAN framework. The original CMGAN only calculates the disparity between the estimated value provided by the model and the clean target with clean labels. Instead, we further take into account noise estimation loss, which can show the discrepancy between the predicted noise and the noise label.The Voicebank-Demand dataset is used for the evaluation experiments. According to the experimental results, the revised CMGAN outperforms the original by gaining greater scores on objective perceptual metrics including PESQ and STOI. As a result, we confirm the success of the presented revisions in CMGAN.","PeriodicalId":281254,"journal":{"name":"2023 9th International Conference on Applied System Innovation (ICASI)","volume":"107 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114899156","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 : 2023-04-21DOI: 10.1109/ICASI57738.2023.10179522
Guan-Ting Liu, Ching-Hu Lu
Nowadays, good hand detection has been proven helpful for a smart assembly factory to improve work efficiency. Particularly, an assembly line for an Industry 4.0 factory needs to manufacture a diverse range of products, its assemblers must acquire knowledge of distinct assembly processes and inspection procedures. Therefore, hand detection via cameras has become a prevalent method of aiding the assembly process in smart factories. However, existing hand detection in a smart factory still relies on a powerful back-end server for image processing due to the limited computing power of a camera. To address this issue, we propose a “Lightweight Anchor-Free Hand-detection Model” (LAFHDM), and the resultant deep neural networks (DNNs) can directly fit into a smart camera to detect assemblers’ hand positions to verify the correctness of assembly steps. The proposal is also in accordance with the inevitable trends of edge computing and the Internet of Things. The experimental results show that the inference speed of the LAFHDM is at least 40 times faster, the accuracy can be 27.41% higher than that of previous models. Moreover, the inference speed of an edge camera is improved approximately three times.
{"title":"Anchor-free Hand-detection with Lightweight Design for Smart Factories","authors":"Guan-Ting Liu, Ching-Hu Lu","doi":"10.1109/ICASI57738.2023.10179522","DOIUrl":"https://doi.org/10.1109/ICASI57738.2023.10179522","url":null,"abstract":"Nowadays, good hand detection has been proven helpful for a smart assembly factory to improve work efficiency. Particularly, an assembly line for an Industry 4.0 factory needs to manufacture a diverse range of products, its assemblers must acquire knowledge of distinct assembly processes and inspection procedures. Therefore, hand detection via cameras has become a prevalent method of aiding the assembly process in smart factories. However, existing hand detection in a smart factory still relies on a powerful back-end server for image processing due to the limited computing power of a camera. To address this issue, we propose a “Lightweight Anchor-Free Hand-detection Model” (LAFHDM), and the resultant deep neural networks (DNNs) can directly fit into a smart camera to detect assemblers’ hand positions to verify the correctness of assembly steps. The proposal is also in accordance with the inevitable trends of edge computing and the Internet of Things. The experimental results show that the inference speed of the LAFHDM is at least 40 times faster, the accuracy can be 27.41% higher than that of previous models. Moreover, the inference speed of an edge camera is improved approximately three times.","PeriodicalId":281254,"journal":{"name":"2023 9th International Conference on Applied System Innovation (ICASI)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129097103","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 : 2023-04-21DOI: 10.1109/icasi57738.2023.10179561
{"title":"Pre-Conference Schedule","authors":"","doi":"10.1109/icasi57738.2023.10179561","DOIUrl":"https://doi.org/10.1109/icasi57738.2023.10179561","url":null,"abstract":"","PeriodicalId":281254,"journal":{"name":"2023 9th International Conference on Applied System Innovation (ICASI)","volume":"59 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123523470","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 : 2023-04-21DOI: 10.1109/ICASI57738.2023.10179586
Jeng-Dao Lee, Cheng-Yen Chang, Kuan-Wei Chen, Lin-Yin Chen, Yu-Rou Tu
Smart agriculture has become a very hot topic in recent years. Since the robot technology required for each type of agriculture is different, how to design a suitable robot is a big challenge. For the research results to be widely used in agriculture, a general-purpose robot for watering and fertilizing actions has been proposed in this study. This study completes the modification of the electric car body for agriculture, the ROS control platform, the dispatch of agricultural robots, and automatic spraying actions. Finally, the relevant experimental results will be realized in the outdoor field.
{"title":"Development and Implementation of Automatic Agricultural Spraying Robot","authors":"Jeng-Dao Lee, Cheng-Yen Chang, Kuan-Wei Chen, Lin-Yin Chen, Yu-Rou Tu","doi":"10.1109/ICASI57738.2023.10179586","DOIUrl":"https://doi.org/10.1109/ICASI57738.2023.10179586","url":null,"abstract":"Smart agriculture has become a very hot topic in recent years. Since the robot technology required for each type of agriculture is different, how to design a suitable robot is a big challenge. For the research results to be widely used in agriculture, a general-purpose robot for watering and fertilizing actions has been proposed in this study. This study completes the modification of the electric car body for agriculture, the ROS control platform, the dispatch of agricultural robots, and automatic spraying actions. Finally, the relevant experimental results will be realized in the outdoor field.","PeriodicalId":281254,"journal":{"name":"2023 9th International Conference on Applied System Innovation (ICASI)","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125702124","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 : 2023-04-21DOI: 10.1109/ICASI57738.2023.10179556
Yu-Ting Huang, Yi-Chin Fang, Sheng-Feng Lin
The remote-sensing instrument (RSI) applications are essential to capture images within specific spectral bands. And, to classify the targeted information, it is crucial to choose the appropriate atmospheric windows based on the apparent spectral zone. That helps to overcome challenges related to complicated physical limitations to achieve the crucial applications of RSI. This study aims to design a near-infrared (NIR) telescope equipped with an indium gallium arsenide (InGaAs) image sensor for a 2U CubeSat RSI. The telescope has been designed to operate within specific spectral ranges within the NIR spectrum. The estimated modulation transfer function (MTF) of the NIR telescope exhibits a performance greater than 0.25 per 10 $mu$m pixel pitch (50lp/mm) of the InGaAs image sensor, resulting in a ground sampling distance (GSD) of 16 m and a swath width of20.48 km when the NIR telescope is positioned at a flight height of 480 km.
{"title":"Optical Design of Near-Infrared Telescope for CubeSat Remote-Sensing Instrument with InGaAs Image Sensor","authors":"Yu-Ting Huang, Yi-Chin Fang, Sheng-Feng Lin","doi":"10.1109/ICASI57738.2023.10179556","DOIUrl":"https://doi.org/10.1109/ICASI57738.2023.10179556","url":null,"abstract":"The remote-sensing instrument (RSI) applications are essential to capture images within specific spectral bands. And, to classify the targeted information, it is crucial to choose the appropriate atmospheric windows based on the apparent spectral zone. That helps to overcome challenges related to complicated physical limitations to achieve the crucial applications of RSI. This study aims to design a near-infrared (NIR) telescope equipped with an indium gallium arsenide (InGaAs) image sensor for a 2U CubeSat RSI. The telescope has been designed to operate within specific spectral ranges within the NIR spectrum. The estimated modulation transfer function (MTF) of the NIR telescope exhibits a performance greater than 0.25 per 10 $mu$m pixel pitch (50lp/mm) of the InGaAs image sensor, resulting in a ground sampling distance (GSD) of 16 m and a swath width of20.48 km when the NIR telescope is positioned at a flight height of 480 km.","PeriodicalId":281254,"journal":{"name":"2023 9th International Conference on Applied System Innovation (ICASI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130023734","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 : 2023-04-21DOI: 10.1109/ICASI57738.2023.10179576
Chien-Hsuan Chen, Huaijie Huang
With the explosive growth of 5G applications, the scale and complexity of network operation, management, and maintenance have increased for telecommunications operators in the B5G era. The 5G specifications defined by 3GPP have established network data analytics functions (NWDAF) and their interfaces, allowing various network functions to obtain AI model inference through subscription to NWDAF, thus achieving intelligent and autonomous management of the 5G core network. This study will use cloud services to implement a cloud-based multi-model architecture for NWDAF.
{"title":"C-NWDAF: Designing a Cloud-based Multi-Model Architecture for Network Data Analytics Function","authors":"Chien-Hsuan Chen, Huaijie Huang","doi":"10.1109/ICASI57738.2023.10179576","DOIUrl":"https://doi.org/10.1109/ICASI57738.2023.10179576","url":null,"abstract":"With the explosive growth of 5G applications, the scale and complexity of network operation, management, and maintenance have increased for telecommunications operators in the B5G era. The 5G specifications defined by 3GPP have established network data analytics functions (NWDAF) and their interfaces, allowing various network functions to obtain AI model inference through subscription to NWDAF, thus achieving intelligent and autonomous management of the 5G core network. This study will use cloud services to implement a cloud-based multi-model architecture for NWDAF.","PeriodicalId":281254,"journal":{"name":"2023 9th International Conference on Applied System Innovation (ICASI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-04-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131542435","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：