This paper is concerned with secure consensus of second-order discrete-time multi-agent systems under replay attacks. State information is transmitted over a communication network and each agent may be attacked by an adversary who is able to replay the state information sent from its neighbors maliciously. A consensus protocol based on distributed model predictive control is developed in the presence of replay attacks. The sufficient conditions for multi-agent systems to achieve secure consensus under replay attacks is derived. The effectiveness of the consensus protocol based on distributed model predictive control is illustrated through numerical examples.
{"title":"Distributed Secure Consensus for Second-Order Multi-Agent Systems under Replay Attacks","authors":"Ling Wang, Zhihai Wu","doi":"10.1145/3457682.3457722","DOIUrl":"https://doi.org/10.1145/3457682.3457722","url":null,"abstract":"This paper is concerned with secure consensus of second-order discrete-time multi-agent systems under replay attacks. State information is transmitted over a communication network and each agent may be attacked by an adversary who is able to replay the state information sent from its neighbors maliciously. A consensus protocol based on distributed model predictive control is developed in the presence of replay attacks. The sufficient conditions for multi-agent systems to achieve secure consensus under replay attacks is derived. The effectiveness of the consensus protocol based on distributed model predictive control is illustrated through numerical examples.","PeriodicalId":142045,"journal":{"name":"2021 13th International Conference on Machine Learning and Computing","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-02-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133798397","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}
Genxuan Hong, Zhanquan Wang, Fuchen Gao, Hengming Ji
Intelligent transportation is an important part of a smart city. Due to the traffic flow sequence has characteristics of periodicity, nonlinearity and easily affected by external factors, improving the accuracy of traffic flow prediction in traffic hub network is important research content of intelligent transportation. For traffic flow prediction problem, an end-to-end framework called DeepTFP is proposed. Specifically, extracting spatiotemporal characteristics of traffic flow data as input of the model through spatiotemporal analysis. Then, a cross-entropy loss function based on error updating for the encoder-decoder network is designed to generate traffic flow predictions, encoder using Bi-direction long-short term memory(BiLSTM), decoder using long-short term memory(LSTM). We conducted extensive experiments on real datasets. The experiment results show that DeepTFP outperforms the other traffic flow prediction methods in terms of prediction error.
{"title":"Traffic Flow Prediction Using Spatiotemporal Analysis and Encoder-Decoder Network","authors":"Genxuan Hong, Zhanquan Wang, Fuchen Gao, Hengming Ji","doi":"10.1145/3457682.3457726","DOIUrl":"https://doi.org/10.1145/3457682.3457726","url":null,"abstract":"Intelligent transportation is an important part of a smart city. Due to the traffic flow sequence has characteristics of periodicity, nonlinearity and easily affected by external factors, improving the accuracy of traffic flow prediction in traffic hub network is important research content of intelligent transportation. For traffic flow prediction problem, an end-to-end framework called DeepTFP is proposed. Specifically, extracting spatiotemporal characteristics of traffic flow data as input of the model through spatiotemporal analysis. Then, a cross-entropy loss function based on error updating for the encoder-decoder network is designed to generate traffic flow predictions, encoder using Bi-direction long-short term memory(BiLSTM), decoder using long-short term memory(LSTM). We conducted extensive experiments on real datasets. The experiment results show that DeepTFP outperforms the other traffic flow prediction methods in terms of prediction error.","PeriodicalId":142045,"journal":{"name":"2021 13th International Conference on Machine Learning and Computing","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-02-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134122282","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 order to characterize causal relation, different scholars have studied it from multiple perspectives. In the field of logic, the causal theory proposed by Alexander elaborated the causal relationship from the perspective of nonmonotonic reasoning. The Horn causal theory and the concept of equivalence relationship are defined in his article, but the author did not give the determination method of equivalence relationship. In order to make up for this deficiency, this paper introduces the concept of bisimulation to describe the equivalence relation between Horn causal theories and proves the consistency between bisimulation relation and the equivalence of models. Then the corresponding algorithm is proposed to determine the equivalence. An example is also given to illustrate the application of this method in determining equivalence relationship.
{"title":"The Determination of the Equivalence of Causal Theories","authors":"Yu Wang, Jin-Jie Zhang","doi":"10.1145/3457682.3457757","DOIUrl":"https://doi.org/10.1145/3457682.3457757","url":null,"abstract":"In order to characterize causal relation, different scholars have studied it from multiple perspectives. In the field of logic, the causal theory proposed by Alexander elaborated the causal relationship from the perspective of nonmonotonic reasoning. The Horn causal theory and the concept of equivalence relationship are defined in his article, but the author did not give the determination method of equivalence relationship. In order to make up for this deficiency, this paper introduces the concept of bisimulation to describe the equivalence relation between Horn causal theories and proves the consistency between bisimulation relation and the equivalence of models. Then the corresponding algorithm is proposed to determine the equivalence. An example is also given to illustrate the application of this method in determining equivalence relationship.","PeriodicalId":142045,"journal":{"name":"2021 13th International Conference on Machine Learning and Computing","volume":"10 1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-02-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134317722","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}
Zhizhong Su, Yaoyi Xi, Rong Cao, Huifeng Tang, Hangyu Pan
Timely identification of Chinese Microblogs users' stance and tendency is of great significance for social managers to understand the trends of online public opinion. Traditional stance detection methods underutilize target information, which affects the detection effect. This paper proposes to integrate the target subject information into a Chinese Microblogs stance detection method based on a generalized autoregressive pretraining language model, and use the advantages of the generalized autoregressive model to extract deep semantics to weaken the high randomness of Microblogs self-media text language and lack of grammar. The impact of norms on text modeling. First carry out microblog data preprocessing to reduce the influence of noise data on the detection effect; then connect the target subject information and the text sequence to be tested into the XLNet network for fine-tuning training; Finally, the fine-tuned XLNet network is combined with the Softmax regression model for stance classification. The experimental results show that the value of the proposed method in the NLPCC2016 Chinese Microblogs detection and evaluation task reaches 0.75, which is better than the existing public model, and the effect is improved significantly.
{"title":"A Stance Detection Approach Based on Generalized Autoregressive pretrained Language Model in Chinese Microblogs","authors":"Zhizhong Su, Yaoyi Xi, Rong Cao, Huifeng Tang, Hangyu Pan","doi":"10.1145/3457682.3457717","DOIUrl":"https://doi.org/10.1145/3457682.3457717","url":null,"abstract":"Timely identification of Chinese Microblogs users' stance and tendency is of great significance for social managers to understand the trends of online public opinion. Traditional stance detection methods underutilize target information, which affects the detection effect. This paper proposes to integrate the target subject information into a Chinese Microblogs stance detection method based on a generalized autoregressive pretraining language model, and use the advantages of the generalized autoregressive model to extract deep semantics to weaken the high randomness of Microblogs self-media text language and lack of grammar. The impact of norms on text modeling. First carry out microblog data preprocessing to reduce the influence of noise data on the detection effect; then connect the target subject information and the text sequence to be tested into the XLNet network for fine-tuning training; Finally, the fine-tuned XLNet network is combined with the Softmax regression model for stance classification. The experimental results show that the value of the proposed method in the NLPCC2016 Chinese Microblogs detection and evaluation task reaches 0.75, which is better than the existing public model, and the effect is improved significantly.","PeriodicalId":142045,"journal":{"name":"2021 13th International Conference on Machine Learning and Computing","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-02-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125203801","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, an Intelligent Hierarchical Conditional Random Field based Attention Mechanism (HCRF-AM) model is proposed, which can be applied to the Gastric Histopathology Image Classification (GHIC) tasks to assist pathologists in medical diagnosis. However, there exists redundant information in a weakly supervised learning mission. Thus, designing the network that can extract effective distinguishing features has become the focus of research. The HCRF-AM model consists of attention mechanism (AM) module and image classification (IC) module. First, in the AM module, an HCRF model is built to extract attention areas. Then, a convolutional neural network (CNN) model is trained with the attention region selected. Thirdly, an algorithm called classification probability based Ensemble Learning (EL) is used to obtain the image-level result from patch-level output of the CNN. In the experiment, a classification specificity of 96.67% is achieved on a gastric histopathological dataset with 700 images.
本文提出了一种基于智能分层条件随机场的注意机制(HCRF-AM)模型，该模型可用于胃组织病理学图像分类(GHIC)任务，以辅助病理医师进行医学诊断。然而，弱监督学习任务中存在冗余信息。因此，设计能够有效提取识别特征的网络成为研究的重点。HCRF-AM模型包括注意机制(AM)模块和图像分类(IC)模块。首先，在AM模块中，建立HCRF模型提取注意区域。然后，用选择的注意区域训练卷积神经网络(CNN)模型。第三，采用基于分类概率的集成学习(classification probability based Ensemble Learning, EL)算法，从CNN的patch级输出中获得图像级结果。在实验中，对700张胃组织病理学数据集的分类特异性达到96.67%。
{"title":"Intelligent Gastric Histopathology Image Classification Using Hierarchical Conditional Random Field based Attention Mechanism","authors":"Yixin Li, Xinran Wu, Chen Li, Changhao Sun, Xiaoyan Li, M. Rahaman, Yong Zhang","doi":"10.1145/3457682.3457733","DOIUrl":"https://doi.org/10.1145/3457682.3457733","url":null,"abstract":"In this paper, an Intelligent Hierarchical Conditional Random Field based Attention Mechanism (HCRF-AM) model is proposed, which can be applied to the Gastric Histopathology Image Classification (GHIC) tasks to assist pathologists in medical diagnosis. However, there exists redundant information in a weakly supervised learning mission. Thus, designing the network that can extract effective distinguishing features has become the focus of research. The HCRF-AM model consists of attention mechanism (AM) module and image classification (IC) module. First, in the AM module, an HCRF model is built to extract attention areas. Then, a convolutional neural network (CNN) model is trained with the attention region selected. Thirdly, an algorithm called classification probability based Ensemble Learning (EL) is used to obtain the image-level result from patch-level output of the CNN. In the experiment, a classification specificity of 96.67% is achieved on a gastric histopathological dataset with 700 images.","PeriodicalId":142045,"journal":{"name":"2021 13th International Conference on Machine Learning and Computing","volume":"92 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-02-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130405209","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 recent years, the research of neural networks has brought new solutions to machine translation. The application of sequence-tosequence model has made a qualitative leap in the performance of machine translation. The training of neural machine translation model depends on large-scale bilingual parallel corpus, the size of corpus directly affects the performance of neural machine translation. Under the guidance of BERT (Bidirectional Encoder) model to calculate the semantic similarity degree for the extension of training corpus in this paper. The scores of two sentences were calculated by using dot product and cosine similarity, and then the sentences with high scores were expanded to the training corpus with a scale of 540,000 sentence pairs. Finally, Transformer was used to train the Mongolian and Chinese neural machine translation system, which was 0.91 percentage points higher than the BLEU value in the baseline experiment.
{"title":"Research on the Application of BERT in Mongolian-Chinese Neural Machine Translation","authors":"Xiu Zhi, Siriguleng Wang","doi":"10.1145/3457682.3457744","DOIUrl":"https://doi.org/10.1145/3457682.3457744","url":null,"abstract":"In recent years, the research of neural networks has brought new solutions to machine translation. The application of sequence-tosequence model has made a qualitative leap in the performance of machine translation. The training of neural machine translation model depends on large-scale bilingual parallel corpus, the size of corpus directly affects the performance of neural machine translation. Under the guidance of BERT (Bidirectional Encoder) model to calculate the semantic similarity degree for the extension of training corpus in this paper. The scores of two sentences were calculated by using dot product and cosine similarity, and then the sentences with high scores were expanded to the training corpus with a scale of 540,000 sentence pairs. Finally, Transformer was used to train the Mongolian and Chinese neural machine translation system, which was 0.91 percentage points higher than the BLEU value in the baseline experiment.","PeriodicalId":142045,"journal":{"name":"2021 13th International Conference on Machine Learning and Computing","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-02-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121095285","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}
Rapid development in deep learning is making it easier to create fake videos known as “deepfake” videos in which human faces are swapped. Since deepfake videos are difficult to recognize by human eyes, it becomes important to automatically detect these forgeries and prevent their abuse. In this paper, we propose a deep neural network model to detect deepfake videos using a convolutional neural network (CNN) to extract frame-level features. These features are then used to train a convolutional GRU that learns to distinguish between fake and real videos. Evaluation is performed on the recently released Celeb-DF(v2)datasets where a state-of-art AUC score was achieved.
{"title":"Deepfake Video Detection by Using Convolutional Gated Recurrent Unit","authors":"Yifeng Tu, Yang Liu, Xueming Li","doi":"10.1145/3457682.3457736","DOIUrl":"https://doi.org/10.1145/3457682.3457736","url":null,"abstract":"Rapid development in deep learning is making it easier to create fake videos known as “deepfake” videos in which human faces are swapped. Since deepfake videos are difficult to recognize by human eyes, it becomes important to automatically detect these forgeries and prevent their abuse. In this paper, we propose a deep neural network model to detect deepfake videos using a convolutional neural network (CNN) to extract frame-level features. These features are then used to train a convolutional GRU that learns to distinguish between fake and real videos. Evaluation is performed on the recently released Celeb-DF(v2)datasets where a state-of-art AUC score was achieved.","PeriodicalId":142045,"journal":{"name":"2021 13th International Conference on Machine Learning and Computing","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-02-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122580937","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 recent years, with the rapid development of the Internet, complex and diverse applications and network traffic have been generated. At the same time, network encryption technologies and various new network traffic have emerged, which affects the efficiency of the original traffic classification technology. In order to improve the efficiency of traffic classification and reduce the classification time, this paper proposes a network traffic classification model (Cosine similarity and decision tree classification model, CSDT) based on cosine similarity and decision tree algorithm to identify and classify traffic. First, the cosine similarity algorithm is used to judge the similarity of adjacent network traffic, and the network traffic with higher similarity is labeled with a known classification and forwarded. For network traffic with low similarity, the decision tree algorithm is used to classify the related feature values. This model utilizes the characteristics of high similarity in adjacent data streams, and uses similarity algorithms to preprocess network traffic to reduce classification time. The Moore data set publicly available in the field of network traffic classification is used for training and testing, and the results are compared with various machine learning algorithms on the Weka platform. The experimental results show that the model has a good classification accuracy, which greatly reduces the classification time and improves the classification efficiency of network traffic is improved.
{"title":"Research on Flow Classification Model Based on Similarity and Machine Learning Algorithm","authors":"Meigen Huang, Lingling Wu, Xuewang Yuan","doi":"10.1145/3457682.3457687","DOIUrl":"https://doi.org/10.1145/3457682.3457687","url":null,"abstract":"In recent years, with the rapid development of the Internet, complex and diverse applications and network traffic have been generated. At the same time, network encryption technologies and various new network traffic have emerged, which affects the efficiency of the original traffic classification technology. In order to improve the efficiency of traffic classification and reduce the classification time, this paper proposes a network traffic classification model (Cosine similarity and decision tree classification model, CSDT) based on cosine similarity and decision tree algorithm to identify and classify traffic. First, the cosine similarity algorithm is used to judge the similarity of adjacent network traffic, and the network traffic with higher similarity is labeled with a known classification and forwarded. For network traffic with low similarity, the decision tree algorithm is used to classify the related feature values. This model utilizes the characteristics of high similarity in adjacent data streams, and uses similarity algorithms to preprocess network traffic to reduce classification time. The Moore data set publicly available in the field of network traffic classification is used for training and testing, and the results are compared with various machine learning algorithms on the Weka platform. The experimental results show that the model has a good classification accuracy, which greatly reduces the classification time and improves the classification efficiency of network traffic is improved.","PeriodicalId":142045,"journal":{"name":"2021 13th International Conference on Machine Learning and Computing","volume":"32 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-02-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130646591","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}
We have known that reinforcement learning, deep learning, and deep reinforcement learning effectively acquire action rules for the autonomous motion of objects. However, it is known that these learning processes require a large amount of learning time. Besides, we should consider the similarity of the environment between the training target and the test target. In actual autonomous driving, there is no such thing as driving only on a course that has been learned in advance. In this study, the autonomous driving of a model car is used as the experimental object. The training target for acquiring the learning model and the actual driving courses are changed. In this study, we report on the effectiveness of transfer learning using a model car as the basis for a learning model acquired by reinforcement learning.
{"title":"Effectiveness of Transfer Learning in Autonomous Driving using Model Car","authors":"Shohei Chiba, Hisayuki Sasaoka","doi":"10.1145/3457682.3457773","DOIUrl":"https://doi.org/10.1145/3457682.3457773","url":null,"abstract":"We have known that reinforcement learning, deep learning, and deep reinforcement learning effectively acquire action rules for the autonomous motion of objects. However, it is known that these learning processes require a large amount of learning time. Besides, we should consider the similarity of the environment between the training target and the test target. In actual autonomous driving, there is no such thing as driving only on a course that has been learned in advance. In this study, the autonomous driving of a model car is used as the experimental object. The training target for acquiring the learning model and the actual driving courses are changed. In this study, we report on the effectiveness of transfer learning using a model car as the basis for a learning model acquired by reinforcement learning.","PeriodicalId":142045,"journal":{"name":"2021 13th International Conference on Machine Learning and Computing","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-02-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123169758","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}
Haiming Ye, Weiwen Zhang, Mengna Nie, Depei Wang, Lianglun Cheng
While there is an ever increasing collection of domain-specific news, it is difficult for people to identify the important ones from massive information. The challenge lies in that users’ information, e.g., comments and CTR (Click-Through-Rate), may not be available in those professional news articles. In this paper, we develop a deep learning model for important news push service, referred to as HMA, which consists of a Hierarchical attention network and a Multi-head Attention mechanism for non-linear text regression. We conduct the experiments with a dataset of marine industry news to evaluate the performance of the proposed deep learning model. The experiment results show that HMA outperforms other alternative deep learning models due to the hierarchical structure and multi-head attention mechanism. Moreover, the execution time of inference by HMA is less than the computation of TF-IDF when adding the news articles into the news repository. Therefore, the proposed method has the potential for efficiently pushing the important domain-specific news articles without users’ information.
{"title":"Efficient Domain-Specific News Push Service Using Deep Learning Based Text Regression without Users’ Information","authors":"Haiming Ye, Weiwen Zhang, Mengna Nie, Depei Wang, Lianglun Cheng","doi":"10.1145/3457682.3457684","DOIUrl":"https://doi.org/10.1145/3457682.3457684","url":null,"abstract":"While there is an ever increasing collection of domain-specific news, it is difficult for people to identify the important ones from massive information. The challenge lies in that users’ information, e.g., comments and CTR (Click-Through-Rate), may not be available in those professional news articles. In this paper, we develop a deep learning model for important news push service, referred to as HMA, which consists of a Hierarchical attention network and a Multi-head Attention mechanism for non-linear text regression. We conduct the experiments with a dataset of marine industry news to evaluate the performance of the proposed deep learning model. The experiment results show that HMA outperforms other alternative deep learning models due to the hierarchical structure and multi-head attention mechanism. Moreover, the execution time of inference by HMA is less than the computation of TF-IDF when adding the news articles into the news repository. Therefore, the proposed method has the potential for efficiently pushing the important domain-specific news articles without users’ information.","PeriodicalId":142045,"journal":{"name":"2021 13th International Conference on Machine Learning and Computing","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-02-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115421744","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：