Collaborative filtering is widely used in recommendation systems. Hybrid approach has been proposed since the collaborative-based method is susceptible to problems such as sparsity and cold start. Recently, the related methods have pointed out that it is very effective to alleviate the above problem by inferring the stochastic distribution of the latent variables for item's auxiliary information. Usually, item boasts more than one kind of auxiliary information. How do we infer the stochastic distribution of the latent variables with multiple auxiliary information? In this paper, we proposed a collaborative multi-auxiliary information autoencoder that can simultaneously consider multiple types of auxiliary information correspondingly. On the one hand, we can successfully accomplish the above issues via the improvement of variational autoencoder. On the other hand, we demonstrated the effectiveness of our method through experiments on real datasets.
{"title":"Collaborative Multi-Auxiliary Information Variational Autoencoder for Recommender Systems","authors":"Jin-Bo Bai, Zhijie Ban","doi":"10.1145/3318299.3318336","DOIUrl":"https://doi.org/10.1145/3318299.3318336","url":null,"abstract":"Collaborative filtering is widely used in recommendation systems. Hybrid approach has been proposed since the collaborative-based method is susceptible to problems such as sparsity and cold start. Recently, the related methods have pointed out that it is very effective to alleviate the above problem by inferring the stochastic distribution of the latent variables for item's auxiliary information. Usually, item boasts more than one kind of auxiliary information. How do we infer the stochastic distribution of the latent variables with multiple auxiliary information? In this paper, we proposed a collaborative multi-auxiliary information autoencoder that can simultaneously consider multiple types of auxiliary information correspondingly. On the one hand, we can successfully accomplish the above issues via the improvement of variational autoencoder. On the other hand, we demonstrated the effectiveness of our method through experiments on real datasets.","PeriodicalId":164987,"journal":{"name":"International Conference on Machine Learning and Computing","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127140169","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}
Visual Question Answering (VQA) is the multitask research field of computer vision and natural language processing and is one of the most intelligent applications among machine learning applications at present. It firstly analyzes and copes with the problem sentences to extract the core key words as well as then seeking out the answers from the figure. In our research, it extracts characteristic values from problem sentences and images by adopting the BI-LSTM and VGG_19 algorithms. Then, after integrating the values into new feature vectors, the paper correlates them into the attention through the attention mechanism and finally predicts the answers finally. Also, the VQA1.0 data set is adopted to train the model. After conducting the training, the accuracy of the test by using the test set reached up to 54.8%.
{"title":"Feature Fusion Attention Visual Question Answering","authors":"Chunlin Wang, Jianyong Sun, Xiaolin Chen","doi":"10.1145/3318299.3318305","DOIUrl":"https://doi.org/10.1145/3318299.3318305","url":null,"abstract":"Visual Question Answering (VQA) is the multitask research field of computer vision and natural language processing and is one of the most intelligent applications among machine learning applications at present. It firstly analyzes and copes with the problem sentences to extract the core key words as well as then seeking out the answers from the figure. In our research, it extracts characteristic values from problem sentences and images by adopting the BI-LSTM and VGG_19 algorithms. Then, after integrating the values into new feature vectors, the paper correlates them into the attention through the attention mechanism and finally predicts the answers finally. Also, the VQA1.0 data set is adopted to train the model. After conducting the training, the accuracy of the test by using the test set reached up to 54.8%.","PeriodicalId":164987,"journal":{"name":"International Conference on Machine Learning and Computing","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131683638","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}
Younas Khan, Usman Qamar, Nazish Yousaf, Aimal Khan
Heart Failure (HF) has been proven one of the leading causes of death that is why an accurate and timely prediction of HF risks is extremely essential. Clinical methods, for instance, angiography is the best and most effective way of diagnosing HF, however, studies show that it is not only costly but has side effects as well. Lately, machine learning techniques have been used for the stated purpose. This survey paper aims to present a systematic literature review based on 35 journal articles published since 2012, where state of the art machine learning classification techniques have been implemented on heart disease datasets. This study critically analyzes the selected papers and finds gaps in the existing literature and is assistive for researchers who intend to apply machine learning in medical domains, particularly on heart disease datasets. The survey finds out that the most popular classification techniques are Support Vector Machine, Neural Networks, and ensemble classifiers.
{"title":"Machine Learning Techniques for Heart Disease Datasets: A Survey","authors":"Younas Khan, Usman Qamar, Nazish Yousaf, Aimal Khan","doi":"10.1145/3318299.3318343","DOIUrl":"https://doi.org/10.1145/3318299.3318343","url":null,"abstract":"Heart Failure (HF) has been proven one of the leading causes of death that is why an accurate and timely prediction of HF risks is extremely essential. Clinical methods, for instance, angiography is the best and most effective way of diagnosing HF, however, studies show that it is not only costly but has side effects as well. Lately, machine learning techniques have been used for the stated purpose. This survey paper aims to present a systematic literature review based on 35 journal articles published since 2012, where state of the art machine learning classification techniques have been implemented on heart disease datasets. This study critically analyzes the selected papers and finds gaps in the existing literature and is assistive for researchers who intend to apply machine learning in medical domains, particularly on heart disease datasets. The survey finds out that the most popular classification techniques are Support Vector Machine, Neural Networks, and ensemble classifiers.","PeriodicalId":164987,"journal":{"name":"International Conference on Machine Learning and Computing","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133058276","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}
Deep Learning (DL) based methods have recently been receiving attention in Human Activity Recognition (HAR) for their strong capability of nonlinear mapping. However, these methods suffer from high time consumption during training process due to enormous network parameters. Moreover, the DL-based scheme is less capable of incremental learning which is important for some online human activity recognition applications. In this paper, the Broad Learning System (BLS) known as a promising alternative to DL-based methods is introduced to the classification of human activities. Both the online and offline BLS-based recognition frameworks are proposed to enhance the system flexibility. Specifically, during the online training stage, the artificial hyperspherical data generation model is incorporated into the incremental BLS, enabling it to update the model to accommodate new incoming data more efficiently. Experiments are made towards the proposed BLS network based upon two public human activity datasets, namely, HART and WISDM. The results demonstrate the advantage of the proposed BLS-based scheme over the classic DL-based approaches in terms of the training speed and prediction accuracy.
{"title":"A Flexible Approach for Human Activity Recognition Based on Broad Learning System","authors":"Zhidi Lin, Haipeng Chen, Qi Yang, Xuemin Hong","doi":"10.1145/3318299.3318318","DOIUrl":"https://doi.org/10.1145/3318299.3318318","url":null,"abstract":"Deep Learning (DL) based methods have recently been receiving attention in Human Activity Recognition (HAR) for their strong capability of nonlinear mapping. However, these methods suffer from high time consumption during training process due to enormous network parameters. Moreover, the DL-based scheme is less capable of incremental learning which is important for some online human activity recognition applications. In this paper, the Broad Learning System (BLS) known as a promising alternative to DL-based methods is introduced to the classification of human activities. Both the online and offline BLS-based recognition frameworks are proposed to enhance the system flexibility. Specifically, during the online training stage, the artificial hyperspherical data generation model is incorporated into the incremental BLS, enabling it to update the model to accommodate new incoming data more efficiently. Experiments are made towards the proposed BLS network based upon two public human activity datasets, namely, HART and WISDM. The results demonstrate the advantage of the proposed BLS-based scheme over the classic DL-based approaches in terms of the training speed and prediction accuracy.","PeriodicalId":164987,"journal":{"name":"International Conference on Machine Learning and Computing","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114774444","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}
Smart end-user devices are connected to the global ecosystem explosively and producing an enormous amount of network traffic at the backhaul. Moreover, Real-time applications such as remote surgery, self-driving cars, and other new technologies required high quality of user experience. To address the challenges Cloud Computing is extended to a new paradigm known as Dew Computing which brings cloud services and capabilities closer to end user devices based on proximity through a decentralized exchange of data and information. However, there is still a user requirement for Ultra-low latency and reliability so that, we introduced Cloud-Edge-Dew architecture to form adaptive local resource utilization and computational offloading during unreliable network to facilitate the collaboration between the various layer in the hierarchy. Moreover, smart end-user devices establish a peer communication or accessing the micro-services which are delivered from Dew Servers and Edge Server. As a result, our scheme provides a decentralize local computation which is more efficient in response time, availability and storage.
{"title":"Decentralized Adaptive Latency-Aware Cloud-Edge-Dew Architecture for Unreliable Network","authors":"Getenet Tefera, Kun She, F. Deeba","doi":"10.1145/3318299.3318380","DOIUrl":"https://doi.org/10.1145/3318299.3318380","url":null,"abstract":"Smart end-user devices are connected to the global ecosystem explosively and producing an enormous amount of network traffic at the backhaul. Moreover, Real-time applications such as remote surgery, self-driving cars, and other new technologies required high quality of user experience. To address the challenges Cloud Computing is extended to a new paradigm known as Dew Computing which brings cloud services and capabilities closer to end user devices based on proximity through a decentralized exchange of data and information. However, there is still a user requirement for Ultra-low latency and reliability so that, we introduced Cloud-Edge-Dew architecture to form adaptive local resource utilization and computational offloading during unreliable network to facilitate the collaboration between the various layer in the hierarchy. Moreover, smart end-user devices establish a peer communication or accessing the micro-services which are delivered from Dew Servers and Edge Server. As a result, our scheme provides a decentralize local computation which is more efficient in response time, availability and storage.","PeriodicalId":164987,"journal":{"name":"International Conference on Machine Learning and Computing","volume":"694 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114822721","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}
Imbalanced data widely exists in real life, while the traditional classification method usually takes accuracy as the classification criterion, which is not suitable for the classification of imbalanced data. Resampling is an important method to deal with imbalanced data classification. In this paper, a margin based random over-sampling (MRO) method is proposed, and then MROBoost algorithm is proposed by combining the AdaBoost algorithm. Experimental results on the UCI dataset show that the MROBoost algorithm is superior to AdaBoost for imbalanced data classification problem.
{"title":"An Over-sampling Method Based on Margin Theory","authors":"Zongtang Zhang, Zhe Chen, Weiguo Dai, Yusheng Cheng","doi":"10.1145/3318299.3318337","DOIUrl":"https://doi.org/10.1145/3318299.3318337","url":null,"abstract":"Imbalanced data widely exists in real life, while the traditional classification method usually takes accuracy as the classification criterion, which is not suitable for the classification of imbalanced data. Resampling is an important method to deal with imbalanced data classification. In this paper, a margin based random over-sampling (MRO) method is proposed, and then MROBoost algorithm is proposed by combining the AdaBoost algorithm. Experimental results on the UCI dataset show that the MROBoost algorithm is superior to AdaBoost for imbalanced data classification problem.","PeriodicalId":164987,"journal":{"name":"International Conference on Machine Learning and Computing","volume":"11 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123724482","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}
This paper proposes a neural network model based on K-means to process the problem of data missing. The method first clusters the samples according to the attributes without missing values to get several clusters, and then puts these clusters into different neural networks to predict the missing values. In this paper, the data can be divided into two types: the continuous numerical type and the discrete numerical type. At the same time, corresponding neural network models are established for these two types. We conduct experiments on the dataset called Human Development Index and Its Components, showing our method to be feasible and superior.
{"title":"Missing Data Processing Based on Deep Neural Network Enhanced by K-Means","authors":"Bin Yu, Chen Zhang, Z. Tang","doi":"10.1145/3318299.3318391","DOIUrl":"https://doi.org/10.1145/3318299.3318391","url":null,"abstract":"This paper proposes a neural network model based on K-means to process the problem of data missing. The method first clusters the samples according to the attributes without missing values to get several clusters, and then puts these clusters into different neural networks to predict the missing values. In this paper, the data can be divided into two types: the continuous numerical type and the discrete numerical type. At the same time, corresponding neural network models are established for these two types. We conduct experiments on the dataset called Human Development Index and Its Components, showing our method to be feasible and superior.","PeriodicalId":164987,"journal":{"name":"International Conference on Machine Learning and Computing","volume":"93 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129335954","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, the defect simulator for high voltage sulfur hexafluoride gas insulated composite electrical apparatus is developed. The device consists of four parts: sulfur hexafluoride gas chamber, solid insulator, defect simulator, observation and measurement device. The defect simulator can effectively simulate free metal particle discharge, tip discharge, suspension discharge and air gap discharge. A real-type integrated defect simulator based on GIS is developed, and the partial discharge signal is tested on the simulator, the change trend of decomposed gas with time is detected. Based on this, an artificial intelligence classification method combining fuzzy ISODATA algorithm and ant colony algorithm is proposed, and the structure parameters of the two algorithms are optimized by PSO algorithm. The field application results of HV combined electrical appliances show that the proposed method is effective. The fault type diagnosis method can effectively judge the fault mode intelligently according to time series of SF6 micro-decomposition gas and typical micro-decomposition gas. This paper not only collects the original classification data from the hardware platform of the defect simulator, but also develops an artificial intelligence classification algorithm software system which is easy to be programmed. It can be directly and effectively used to diagnose and evaluate the type of insulation defect in the field practical engineering of GIS. It has certain theoretical guidance value for GIS equipment fault diagnosis and pattern recognition.
{"title":"Discharge Fault Simulation System for High Voltage SF6 Gas Insulated Switch-gear and Its Intelligent Pattern Recognition","authors":"Shiling Zhang","doi":"10.1145/3318299.3318334","DOIUrl":"https://doi.org/10.1145/3318299.3318334","url":null,"abstract":"In this paper, the defect simulator for high voltage sulfur hexafluoride gas insulated composite electrical apparatus is developed. The device consists of four parts: sulfur hexafluoride gas chamber, solid insulator, defect simulator, observation and measurement device. The defect simulator can effectively simulate free metal particle discharge, tip discharge, suspension discharge and air gap discharge. A real-type integrated defect simulator based on GIS is developed, and the partial discharge signal is tested on the simulator, the change trend of decomposed gas with time is detected. Based on this, an artificial intelligence classification method combining fuzzy ISODATA algorithm and ant colony algorithm is proposed, and the structure parameters of the two algorithms are optimized by PSO algorithm. The field application results of HV combined electrical appliances show that the proposed method is effective. The fault type diagnosis method can effectively judge the fault mode intelligently according to time series of SF6 micro-decomposition gas and typical micro-decomposition gas. This paper not only collects the original classification data from the hardware platform of the defect simulator, but also develops an artificial intelligence classification algorithm software system which is easy to be programmed. It can be directly and effectively used to diagnose and evaluate the type of insulation defect in the field practical engineering of GIS. It has certain theoretical guidance value for GIS equipment fault diagnosis and pattern recognition.","PeriodicalId":164987,"journal":{"name":"International Conference on Machine Learning and Computing","volume":"89 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122024699","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}
Asif Ahmed Neloy, H. M. Sadman Haque, Md. Mahmud Ul Islam
Apartment rental prices are influenced by various factors. The aim of this study is to analyze the different features of an apartment and predict the rental price of it based on multiple factors. An ensemble learning based prediction model is created to reach the goal. We have used a dataset from bProperty.com which includes the rental price and different features of apartments in the city of Dhaka, Bangladesh. The results show the accuracy and prediction of the rent of an apartment, also indicates the different types of categorical values that affect the machine learning models. Another purpose of the study is to find out the factors that signify the apartment rental price in Dhaka. To help our prediction we take on the Advance Regression Techniques (ART) and compare to different features of an apartment for establishing an acceptable model. The following algorithms are selected as the base predictors -- Advance Linear Regression, Neural Network, Random Forest, Support Vector Machine (SVM) and Decision Tree Regressor. The Ensemble learning is stacked of following algorithms -- Ensemble AdaBoosting Regressor, Ensemble Gradient Boosting Regressor, Ensemble XGBoost. Also, Ridge Regression, Lasso Regression, and Elastic Net Regression has been used to combine the advance regression techniques. Tree-based algorithms generate a decision tree from categorical 'YES' and 'NO' values, Ensemble methods to boosting up the learning and prediction accuracy, Support Vector Machine to extend the model for both classification and regression approach and lastly advance linear regression to predict the house price with different features values.
{"title":"Ensemble Learning Based Rental Apartment Price Prediction Model by Categorical Features Factoring","authors":"Asif Ahmed Neloy, H. M. Sadman Haque, Md. Mahmud Ul Islam","doi":"10.1145/3318299.3318377","DOIUrl":"https://doi.org/10.1145/3318299.3318377","url":null,"abstract":"Apartment rental prices are influenced by various factors. The aim of this study is to analyze the different features of an apartment and predict the rental price of it based on multiple factors. An ensemble learning based prediction model is created to reach the goal. We have used a dataset from bProperty.com which includes the rental price and different features of apartments in the city of Dhaka, Bangladesh. The results show the accuracy and prediction of the rent of an apartment, also indicates the different types of categorical values that affect the machine learning models. Another purpose of the study is to find out the factors that signify the apartment rental price in Dhaka. To help our prediction we take on the Advance Regression Techniques (ART) and compare to different features of an apartment for establishing an acceptable model. The following algorithms are selected as the base predictors -- Advance Linear Regression, Neural Network, Random Forest, Support Vector Machine (SVM) and Decision Tree Regressor. The Ensemble learning is stacked of following algorithms -- Ensemble AdaBoosting Regressor, Ensemble Gradient Boosting Regressor, Ensemble XGBoost. Also, Ridge Regression, Lasso Regression, and Elastic Net Regression has been used to combine the advance regression techniques. Tree-based algorithms generate a decision tree from categorical 'YES' and 'NO' values, Ensemble methods to boosting up the learning and prediction accuracy, Support Vector Machine to extend the model for both classification and regression approach and lastly advance linear regression to predict the house price with different features values.","PeriodicalId":164987,"journal":{"name":"International Conference on Machine Learning and Computing","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116451397","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}
Honeycomb tori are attractive alternatives to torus due to the smaller node degree, leading to lower complexity and lower implementation cost. The honeycomb networks are Cayley graphs with excellent topological properties. However, some topological properties of the honeycomb rhombic tori, such as internode distance, routing algorithm and broadcasting algorithm, are not developed. In this paper, we analyze the distance between any two nodes in the honeycomb rhombic tori and present an optimal routing algorithm for this class of networks. The algorithm is fully distributed, which can construct the shortest path between any pair of vertices. A broadcasting algorithm is also presented.
{"title":"Some Topological Properties of the Honeycomb Rhombic Torus Based on Cayley Graph","authors":"Yue-ying Lin, Sihao Xu, Zhen Zhang","doi":"10.1145/3318299.3318357","DOIUrl":"https://doi.org/10.1145/3318299.3318357","url":null,"abstract":"Honeycomb tori are attractive alternatives to torus due to the smaller node degree, leading to lower complexity and lower implementation cost. The honeycomb networks are Cayley graphs with excellent topological properties. However, some topological properties of the honeycomb rhombic tori, such as internode distance, routing algorithm and broadcasting algorithm, are not developed. In this paper, we analyze the distance between any two nodes in the honeycomb rhombic tori and present an optimal routing algorithm for this class of networks. The algorithm is fully distributed, which can construct the shortest path between any pair of vertices. A broadcasting algorithm is also presented.","PeriodicalId":164987,"journal":{"name":"International Conference on Machine Learning and Computing","volume":"69 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123800178","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：