Multimedia data especially video traffic becomes increasingly popular in Internet traffic. How to extract effective features from video streams for fine-grained classification is a huge challenge. This paper collected 6 kinds of typical online video streams from the real network, analyzes and proposes a new set of features, e.g. the statistics of valid main protocol values in the flow to remove useless information in getting valid values. Experimental results show that these new features perform better in fine grained video traffic classification in comparison with an existing method.
{"title":"Feature Mining for Internet Video Traffic Classification","authors":"Lingyun Yang, Yu-ning Dong, Zheng Wu, Pingping Tang, You-hong Feng","doi":"10.1109/ICNIDC.2018.8525805","DOIUrl":"https://doi.org/10.1109/ICNIDC.2018.8525805","url":null,"abstract":"Multimedia data especially video traffic becomes increasingly popular in Internet traffic. How to extract effective features from video streams for fine-grained classification is a huge challenge. This paper collected 6 kinds of typical online video streams from the real network, analyzes and proposes a new set of features, e.g. the statistics of valid main protocol values in the flow to remove useless information in getting valid values. Experimental results show that these new features perform better in fine grained video traffic classification in comparison with an existing method.","PeriodicalId":256992,"journal":{"name":"2018 International Conference on Network Infrastructure and Digital Content (IC-NIDC)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124823152","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 : 2018-08-01DOI: 10.1109/ICNIDC.2018.8525768
Zhihan Yao, Zhilin Yang, Tianhao Wu, Liyang Chen, Konglin Zhu, Lin Zhang, Sixi Su
Intelligent transportation systems that designed to provide safer, more comfortable driving and traffic efficiency have developed rapidly in recent years. 802.11p and LTE-V are the major communications technologies used in V2X systems. Several studies have conducted extensive research and evaluation on the performance and application of 802.11p and LTE-V through modeling and simulation. However, V2X cloud collaboration systems based on LTE-V technology are rare. In most cases, V2X applications are safety-related, the performance of communication is very important. Especially in some emergencies, delay time may cause fatal accidents. Therefore, this paper proposes a collaborative cloud platform application architecture based on LTE-V technology. By real road environment tests on typical V2V and V2I scenes, we can see that the collaborative cloud platform system has excellent performance in assisting driver driving and road traffic control.
{"title":"Implementing ITS Applications by LTE-V2X Equipment-challenges and opportunities","authors":"Zhihan Yao, Zhilin Yang, Tianhao Wu, Liyang Chen, Konglin Zhu, Lin Zhang, Sixi Su","doi":"10.1109/ICNIDC.2018.8525768","DOIUrl":"https://doi.org/10.1109/ICNIDC.2018.8525768","url":null,"abstract":"Intelligent transportation systems that designed to provide safer, more comfortable driving and traffic efficiency have developed rapidly in recent years. 802.11p and LTE-V are the major communications technologies used in V2X systems. Several studies have conducted extensive research and evaluation on the performance and application of 802.11p and LTE-V through modeling and simulation. However, V2X cloud collaboration systems based on LTE-V technology are rare. In most cases, V2X applications are safety-related, the performance of communication is very important. Especially in some emergencies, delay time may cause fatal accidents. Therefore, this paper proposes a collaborative cloud platform application architecture based on LTE-V technology. By real road environment tests on typical V2V and V2I scenes, we can see that the collaborative cloud platform system has excellent performance in assisting driver driving and road traffic control.","PeriodicalId":256992,"journal":{"name":"2018 International Conference on Network Infrastructure and Digital Content (IC-NIDC)","volume":"414 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116228153","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 : 2018-08-01DOI: 10.1109/ICNIDC.2018.8525822
Yipeng Jiang, Fang Liu, Qing Yan, Zhengxiang Ke
Funnel analysis is used to describe the conversation rate between user behavior. However, the funnel analysis method widely used currently has low-performance in process time. This paper presents an improved funnel analysis method based on the funnel analysis method. The method improvement includes presenting an improved funnel analysis algorithm having constant space complexity and linear time complexity, and utilizing the Spark framework to replace the Hive framework of the original method. The improvement method can be applied to analyze a large amount of data and real-time streaming data. The experimental results show that the performance of the improved method and the improved algorithm are efficient.
{"title":"An Improved Method for Orderly Funnel Analysis of Massive User Behavior Data","authors":"Yipeng Jiang, Fang Liu, Qing Yan, Zhengxiang Ke","doi":"10.1109/ICNIDC.2018.8525822","DOIUrl":"https://doi.org/10.1109/ICNIDC.2018.8525822","url":null,"abstract":"Funnel analysis is used to describe the conversation rate between user behavior. However, the funnel analysis method widely used currently has low-performance in process time. This paper presents an improved funnel analysis method based on the funnel analysis method. The method improvement includes presenting an improved funnel analysis algorithm having constant space complexity and linear time complexity, and utilizing the Spark framework to replace the Hive framework of the original method. The improvement method can be applied to analyze a large amount of data and real-time streaming data. The experimental results show that the performance of the improved method and the improved algorithm are efficient.","PeriodicalId":256992,"journal":{"name":"2018 International Conference on Network Infrastructure and Digital Content (IC-NIDC)","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128273327","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 : 2018-08-01DOI: 10.1109/ICNIDC.2018.8525597
Jaehun Kim, Kyoungin Noh, Jaeha Kim, Joon‐Hyuk Chang
This paper presents a real environment sound event detection method based on pre-processing technology. Our goal is to improve the performance of the sound event detection using a pre-processing module called parameterized multi-channel non-causal Wiener filter (PMWF). First, we convert the existing 1 channel data to 2 channels through the Room impulse response generator (RIR) module. The reason for 2-channel conversion is that PMWF requires multiple channels for beamforming. Noise cancellation is performed through PMWF and the results are derived through the proposed convolutional neural network model. As a result, we found that this method has a good effect on real-time sound event detection, and we found that peak normalization and median filter also have a good effect.
{"title":"Sound Event Detection Based on Beamformed Convolutional Neural Network Using Multi-Microphones","authors":"Jaehun Kim, Kyoungin Noh, Jaeha Kim, Joon‐Hyuk Chang","doi":"10.1109/ICNIDC.2018.8525597","DOIUrl":"https://doi.org/10.1109/ICNIDC.2018.8525597","url":null,"abstract":"This paper presents a real environment sound event detection method based on pre-processing technology. Our goal is to improve the performance of the sound event detection using a pre-processing module called parameterized multi-channel non-causal Wiener filter (PMWF). First, we convert the existing 1 channel data to 2 channels through the Room impulse response generator (RIR) module. The reason for 2-channel conversion is that PMWF requires multiple channels for beamforming. Noise cancellation is performed through PMWF and the results are derived through the proposed convolutional neural network model. As a result, we found that this method has a good effect on real-time sound event detection, and we found that peak normalization and median filter also have a good effect.","PeriodicalId":256992,"journal":{"name":"2018 International Conference on Network Infrastructure and Digital Content (IC-NIDC)","volume":"86 1-4","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114009067","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}
Bone tumor is a kind of harmful tumor which mostly occurs in adolescents. In this paper, we present a support vector machine (SVM) based bone tumor detector by using the texture feature of x-ray images. Due to the low incidence of bone tumor, it is hard to acquire dataset on a large scale, we use linear kernel function of SVM and cross validation to reach a more stable result. According to the characteristic of bone tumor x-ray images, we extract the texture features such as the angular second moment, correlation, entropy, homogeneity, contrast, dissimilarity from the x-ray images based on gray level co-occurrence matrix (GLCM). These features are used as input for the support vector machine classifier. And according to the scale of the dataset, a 5-fold cross validation test is performed in this paper. The highest accuracy of this detector can reach 99%.
{"title":"SVM-Based Bone Tumor Detection by Using the Texture Features of X-Ray Image","authors":"Chuli Xia, K. Niu, Zhiqiang He, Shun Tang, Jichuan Wang, Yidan Zhang, Zhiqing Zhao, Wei Guo","doi":"10.1109/ICNIDC.2018.8525806","DOIUrl":"https://doi.org/10.1109/ICNIDC.2018.8525806","url":null,"abstract":"Bone tumor is a kind of harmful tumor which mostly occurs in adolescents. In this paper, we present a support vector machine (SVM) based bone tumor detector by using the texture feature of x-ray images. Due to the low incidence of bone tumor, it is hard to acquire dataset on a large scale, we use linear kernel function of SVM and cross validation to reach a more stable result. According to the characteristic of bone tumor x-ray images, we extract the texture features such as the angular second moment, correlation, entropy, homogeneity, contrast, dissimilarity from the x-ray images based on gray level co-occurrence matrix (GLCM). These features are used as input for the support vector machine classifier. And according to the scale of the dataset, a 5-fold cross validation test is performed in this paper. The highest accuracy of this detector can reach 99%.","PeriodicalId":256992,"journal":{"name":"2018 International Conference on Network Infrastructure and Digital Content (IC-NIDC)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132944084","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 : 2018-08-01DOI: 10.1109/ICNIDC.2018.8525524
Chen Lu, D. Liang, Shan Wang, Lili Zeng, Yilin Zhao
In this paper, a novel approach to the $k$-Nearest Neighbors ($ktext{NN}$) algorithm is proposed. As one of the ten classical algorithms of data mining, KNN algorithm has a very good performance in classification problems such as pattern recognition. However, it undergoes an undeniable weakness that is high complexity, especially when the training set is huge. The motivation behind this proposed algorithm is to increase the computational efficiency of the traditional $ktext{NN}$ algorithm, without sacrificing the accuracy, or even improve it. This key idea of the proposed algorithm is to pre-cut the comparison procedure of distance comparison through a predefined threshold. The experimental results reveal that this improved pre-cut $k$ NN algorithm, based on the threshold value of the smallest $k$ distance, greatly increases computational efficiency, and do not cause any precision deduction, even improve an amount of accuracy. It can be concluded that this proposed algorithm achieves superior computational efficiency compared to the traditional $ktext{NN}$ and previously proposed $mathrm{F}ktext{NN}$ algorithm, especially when the data set is very large.
{"title":"Pre-cut kNN Algorithm Based on Threshold of Distance","authors":"Chen Lu, D. Liang, Shan Wang, Lili Zeng, Yilin Zhao","doi":"10.1109/ICNIDC.2018.8525524","DOIUrl":"https://doi.org/10.1109/ICNIDC.2018.8525524","url":null,"abstract":"In this paper, a novel approach to the $k$-Nearest Neighbors ($ktext{NN}$) algorithm is proposed. As one of the ten classical algorithms of data mining, KNN algorithm has a very good performance in classification problems such as pattern recognition. However, it undergoes an undeniable weakness that is high complexity, especially when the training set is huge. The motivation behind this proposed algorithm is to increase the computational efficiency of the traditional $ktext{NN}$ algorithm, without sacrificing the accuracy, or even improve it. This key idea of the proposed algorithm is to pre-cut the comparison procedure of distance comparison through a predefined threshold. The experimental results reveal that this improved pre-cut $k$ NN algorithm, based on the threshold value of the smallest $k$ distance, greatly increases computational efficiency, and do not cause any precision deduction, even improve an amount of accuracy. It can be concluded that this proposed algorithm achieves superior computational efficiency compared to the traditional $ktext{NN}$ and previously proposed $mathrm{F}ktext{NN}$ algorithm, especially when the data set is very large.","PeriodicalId":256992,"journal":{"name":"2018 International Conference on Network Infrastructure and Digital Content (IC-NIDC)","volume":"154 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133005834","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 : 2018-08-01DOI: 10.1109/ICNIDC.2018.8525629
Jianbo Zhao, Mingzheng Li, Weijie Liu, Si Li, Zhiqing Lin
With the rapid development of China, more and more non-native Chinese speakers begin to learn Chinese. Therefore, the task of detecting Chinese grammatical error has got more and more attention. However, most current detection methods focus on building more complex detection models and adding artificial features, ignore the effect of polysemic words in Chinese text. In this paper, we propose a Chinese grammatical error detection model to handle the ambiguity problems of Chinese words. Compared with the baseline model, our model achieves better results on accuracy, MRR, HIT@2 and HIT@20%.
{"title":"Detection of Chinese Grammatical Errors with Context Representation","authors":"Jianbo Zhao, Mingzheng Li, Weijie Liu, Si Li, Zhiqing Lin","doi":"10.1109/ICNIDC.2018.8525629","DOIUrl":"https://doi.org/10.1109/ICNIDC.2018.8525629","url":null,"abstract":"With the rapid development of China, more and more non-native Chinese speakers begin to learn Chinese. Therefore, the task of detecting Chinese grammatical error has got more and more attention. However, most current detection methods focus on building more complex detection models and adding artificial features, ignore the effect of polysemic words in Chinese text. In this paper, we propose a Chinese grammatical error detection model to handle the ambiguity problems of Chinese words. Compared with the baseline model, our model achieves better results on accuracy, MRR, HIT@2 and HIT@20%.","PeriodicalId":256992,"journal":{"name":"2018 International Conference on Network Infrastructure and Digital Content (IC-NIDC)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133313337","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 : 2018-08-01DOI: 10.1109/ICNIDC.2018.8525600
Yujiao Du, Bo Xiao, Wenchao Xu, Desheng Cui, Qianfang Xu, Liping Yan
Bike-sharing system has been very popular all over the world as it provides benefits like healthy lifestyle and convenience for users. For better dispatching these sharing bikes to the most needed places at any time, a precise prediction of the destination is needed. Unfortunately, existing approaches for destination prediction are used in systems with fixed stations or taxi scenarios. But in our scenario, people can pick up or drop off bikes at any places, which increases the predicting difficulty. In this paper, a data-driven approach is proposed to predict destinations based on large-scale bike trip data. We first formulate destination prediction as a binary classification problem and introduce two different approaches to construct our dataset. After that, different strategies are presented to generate potential candidates and extract multi-view features from historical data. Finally, we train a classifier and returns potential destinations ranked by their probability decreasingly. Experiments conducted on the real-world bike-sharing system dataset demonstrate the effectiveness of the proposed method.
{"title":"Destination Prediction for Sharing-Bikes' Trips","authors":"Yujiao Du, Bo Xiao, Wenchao Xu, Desheng Cui, Qianfang Xu, Liping Yan","doi":"10.1109/ICNIDC.2018.8525600","DOIUrl":"https://doi.org/10.1109/ICNIDC.2018.8525600","url":null,"abstract":"Bike-sharing system has been very popular all over the world as it provides benefits like healthy lifestyle and convenience for users. For better dispatching these sharing bikes to the most needed places at any time, a precise prediction of the destination is needed. Unfortunately, existing approaches for destination prediction are used in systems with fixed stations or taxi scenarios. But in our scenario, people can pick up or drop off bikes at any places, which increases the predicting difficulty. In this paper, a data-driven approach is proposed to predict destinations based on large-scale bike trip data. We first formulate destination prediction as a binary classification problem and introduce two different approaches to construct our dataset. After that, different strategies are presented to generate potential candidates and extract multi-view features from historical data. Finally, we train a classifier and returns potential destinations ranked by their probability decreasingly. Experiments conducted on the real-world bike-sharing system dataset demonstrate the effectiveness of the proposed method.","PeriodicalId":256992,"journal":{"name":"2018 International Conference on Network Infrastructure and Digital Content (IC-NIDC)","volume":"195 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132583612","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 : 2018-08-01DOI: 10.1109/ICNIDC.2018.8525618
Kaili Ni, Meixia Fu, Zhongjie Huang, Songlin Sun
Nowadays convolutional neural network(CNN) has been successfully applied in image processing. At the same time license plate recognition is more and more universal. Before recognition with deep learning, we need to collect enough images to train the network. The quality of data is very important. The current methods of getting license plate based on deep learning are increasingly various, however, there are still many images where illumination, size and blurriness make it is extremely difficult to recognize. As a result, images with low quality eventually affect the accuracy of recognition. Therefore, license plate classification is essential to eliminate low quality images so that improve the quality of the dataset. In this paper, a method based on CNN is proposed to deal with license plate classification. We use a seven layers CNN and ultimately the best result reached 98.79%.
{"title":"A Proposed License Plate Classification Method Based on Convolutional Neural Network","authors":"Kaili Ni, Meixia Fu, Zhongjie Huang, Songlin Sun","doi":"10.1109/ICNIDC.2018.8525618","DOIUrl":"https://doi.org/10.1109/ICNIDC.2018.8525618","url":null,"abstract":"Nowadays convolutional neural network(CNN) has been successfully applied in image processing. At the same time license plate recognition is more and more universal. Before recognition with deep learning, we need to collect enough images to train the network. The quality of data is very important. The current methods of getting license plate based on deep learning are increasingly various, however, there are still many images where illumination, size and blurriness make it is extremely difficult to recognize. As a result, images with low quality eventually affect the accuracy of recognition. Therefore, license plate classification is essential to eliminate low quality images so that improve the quality of the dataset. In this paper, a method based on CNN is proposed to deal with license plate classification. We use a seven layers CNN and ultimately the best result reached 98.79%.","PeriodicalId":256992,"journal":{"name":"2018 International Conference on Network Infrastructure and Digital Content (IC-NIDC)","volume":"108 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124145523","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 : 2018-08-01DOI: 10.1109/ICNIDC.2018.8525830
Yanbiao Li, Zeyuan Zhao, Ke Yu, Xiaofei Wu
Nowadays, the number of features for machine learning is increasing rapidly, which adversely affects the memory used and the time consumed during learning. Lots of feature selection methods, including Filter, Wrapper and Embedded methods, have been proposed and successfully applied to real applications. This paper proposes an ensemble method which integrates the existing classical methods for feature selection, named Ensemble Feature Selection Method Based on Adaptive Weights (EAW). According to different data sets and application scenarios, the EAW method adjusts weights automatically for the three basic feature selection methods, i.e. Mutual Information-based, ReliefF and K-means-based method. Experiments for different application scenarios show that our EAW method performs better in accuracy by using less memory and less time.
{"title":"Ensemble Feature Selection Method Based on Adaptive Weights","authors":"Yanbiao Li, Zeyuan Zhao, Ke Yu, Xiaofei Wu","doi":"10.1109/ICNIDC.2018.8525830","DOIUrl":"https://doi.org/10.1109/ICNIDC.2018.8525830","url":null,"abstract":"Nowadays, the number of features for machine learning is increasing rapidly, which adversely affects the memory used and the time consumed during learning. Lots of feature selection methods, including Filter, Wrapper and Embedded methods, have been proposed and successfully applied to real applications. This paper proposes an ensemble method which integrates the existing classical methods for feature selection, named Ensemble Feature Selection Method Based on Adaptive Weights (EAW). According to different data sets and application scenarios, the EAW method adjusts weights automatically for the three basic feature selection methods, i.e. Mutual Information-based, ReliefF and K-means-based method. Experiments for different application scenarios show that our EAW method performs better in accuracy by using less memory and less time.","PeriodicalId":256992,"journal":{"name":"2018 International Conference on Network Infrastructure and Digital Content (IC-NIDC)","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2018-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126158563","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：