Pub Date : 2021-05-21DOI: 10.1109/ICIST52614.2021.9440653
Xiaoxiao Lv, Jinde Cao
Under the distributed impulsive control with actuator saturation, the local leader-following consensus problem of linear multi-agent systems with fixed topology is considered in this paper. Based on Lyapunov stability theory, average impulsive interval method and contradiction approach, a developed sufficient condition is obtained. In addition, optimization problem constrained by local leader-following consensus criterion is established in the form of linear matrix inequalities, and solved them by YALMIP to obtain the largest domain of attraction. Finally, a numerical example is proposed to demonstrate the feasibility of the obtained results.
{"title":"Impulsive Local Leader-following Consensus and Estimation of Domain of Attraction of Multi-agent Systems with Actuator Saturation","authors":"Xiaoxiao Lv, Jinde Cao","doi":"10.1109/ICIST52614.2021.9440653","DOIUrl":"https://doi.org/10.1109/ICIST52614.2021.9440653","url":null,"abstract":"Under the distributed impulsive control with actuator saturation, the local leader-following consensus problem of linear multi-agent systems with fixed topology is considered in this paper. Based on Lyapunov stability theory, average impulsive interval method and contradiction approach, a developed sufficient condition is obtained. In addition, optimization problem constrained by local leader-following consensus criterion is established in the form of linear matrix inequalities, and solved them by YALMIP to obtain the largest domain of attraction. Finally, a numerical example is proposed to demonstrate the feasibility of the obtained results.","PeriodicalId":371599,"journal":{"name":"2021 11th International Conference on Information Science and Technology (ICIST)","volume":"9 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115590730","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-05-21DOI: 10.1109/ICIST52614.2021.9440631
Liyan Zhu, Tie-shan Li
This paper studies the problem of autopilot heading control of intelligent ship with unknown yaw rate and state constraint. For the cases of adaptive fuzzy control, fuzzy logic system (FLS) is adopted to establish the unknown nonlinear function, a fuzzy state observer is constructed to obtain the unknown yaw rate, barrier Lyapunov function ensures that the tracking error is restricted. In the process of designing rudder controller, fuzzy state observer, state constraint are taken into account. Compared with traditional output feedback scheme, the observer-based state constraint control strategy can save more resource effectively. Based on Lyapunov stability theory, adaptive fuzzy approach is proposed to guarantee the desired control objective. Meanwhile, autopilot constrained requirement are also ensured. Finally, the simulation results are provided to illustrate the effectiveness of the proposed methods.
{"title":"Observer-Based Adaptive Fuzzy Control for Intelligent Ship Autopilot with State Constraint*","authors":"Liyan Zhu, Tie-shan Li","doi":"10.1109/ICIST52614.2021.9440631","DOIUrl":"https://doi.org/10.1109/ICIST52614.2021.9440631","url":null,"abstract":"This paper studies the problem of autopilot heading control of intelligent ship with unknown yaw rate and state constraint. For the cases of adaptive fuzzy control, fuzzy logic system (FLS) is adopted to establish the unknown nonlinear function, a fuzzy state observer is constructed to obtain the unknown yaw rate, barrier Lyapunov function ensures that the tracking error is restricted. In the process of designing rudder controller, fuzzy state observer, state constraint are taken into account. Compared with traditional output feedback scheme, the observer-based state constraint control strategy can save more resource effectively. Based on Lyapunov stability theory, adaptive fuzzy approach is proposed to guarantee the desired control objective. Meanwhile, autopilot constrained requirement are also ensured. Finally, the simulation results are provided to illustrate the effectiveness of the proposed methods.","PeriodicalId":371599,"journal":{"name":"2021 11th International Conference on Information Science and Technology (ICIST)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115732733","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-05-21DOI: 10.1109/icist52614.2021.9440643
Zipeng Huang, Lu Liu, Dan Wang, Haoliang Wang, Zhouhua Peng
This paper addresses the collision-free guidance law design for cooperative path following of multiple unmanned surface vehicles in the presence of static and dynamic obstacles. Specially, collision-free cooperative guidance laws are designed at the kinematic level, and a collision avoidance term is introduced into the desired yaw rate. A synchronized formation can be achieved by multiple unmanned surface vehicles, and at the same time the obstacles can be avoided. Theoretical analysis proves that by using presented cooperative guidance laws, the closed-loop system is globally uniformly asymptotically stable and collision can be avoided. Simulation results substantiate the effectiveness of the proposed method.
{"title":"Collision-free Cooperative Kinematic Guidance Laws for Multiple Unmanned Surface Vehicles Subject to Static and Dynamic Obstacles","authors":"Zipeng Huang, Lu Liu, Dan Wang, Haoliang Wang, Zhouhua Peng","doi":"10.1109/icist52614.2021.9440643","DOIUrl":"https://doi.org/10.1109/icist52614.2021.9440643","url":null,"abstract":"This paper addresses the collision-free guidance law design for cooperative path following of multiple unmanned surface vehicles in the presence of static and dynamic obstacles. Specially, collision-free cooperative guidance laws are designed at the kinematic level, and a collision avoidance term is introduced into the desired yaw rate. A synchronized formation can be achieved by multiple unmanned surface vehicles, and at the same time the obstacles can be avoided. Theoretical analysis proves that by using presented cooperative guidance laws, the closed-loop system is globally uniformly asymptotically stable and collision can be avoided. Simulation results substantiate the effectiveness of the proposed method.","PeriodicalId":371599,"journal":{"name":"2021 11th International Conference on Information Science and Technology (ICIST)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125825157","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-05-21DOI: 10.1109/ICIST52614.2021.9440562
Yuchao Guo, Y. Fan, Gaofeng Pan, C. Song
Visual SLAM based on ORB features will increase the computational pressure of SLAM system due to the large amount of feature extraction and matching computation and the need to screen a large number of mismatched point pairs. It cannot completely eliminate the mismatched point pairs, which will affect the camera positioning accuracy of visual SLAM system to a certain extent. To solve the two questions, the PROSAC algorithm is used, screening point of mismatch on, all matching points by calculation of evaluation function, selection to match point to build the model with the highest quality, through continuous to join interior point, build the final model, screening point pairs of mismatch. Provide high quality data for camera pose estimation and back end optimization of SLAM system. Through the comparison of RANSAC algorithm and PROSAC algorithm false match screening time, as well as tracking error. PROSAC algorithm effectively reduced the time of mismatching screening, with a maximum improvement of 100 times. The tracking error has also improved significantly.
{"title":"A Visual SLAM Image Mismatching Filter Algorithm Based on Progressive Aample Consensus","authors":"Yuchao Guo, Y. Fan, Gaofeng Pan, C. Song","doi":"10.1109/ICIST52614.2021.9440562","DOIUrl":"https://doi.org/10.1109/ICIST52614.2021.9440562","url":null,"abstract":"Visual SLAM based on ORB features will increase the computational pressure of SLAM system due to the large amount of feature extraction and matching computation and the need to screen a large number of mismatched point pairs. It cannot completely eliminate the mismatched point pairs, which will affect the camera positioning accuracy of visual SLAM system to a certain extent. To solve the two questions, the PROSAC algorithm is used, screening point of mismatch on, all matching points by calculation of evaluation function, selection to match point to build the model with the highest quality, through continuous to join interior point, build the final model, screening point pairs of mismatch. Provide high quality data for camera pose estimation and back end optimization of SLAM system. Through the comparison of RANSAC algorithm and PROSAC algorithm false match screening time, as well as tracking error. PROSAC algorithm effectively reduced the time of mismatching screening, with a maximum improvement of 100 times. The tracking error has also improved significantly.","PeriodicalId":371599,"journal":{"name":"2021 11th International Conference on Information Science and Technology (ICIST)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122336930","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}
Shared umbrella can bring us convenience in rain and snow. But uncertainty umbrella demand and the weather may cause the unbalance for a shared umbrella station. According to the information of the rainfall, temperature and so on, this paper proposed an efficient BP neural network to construct a prediction model for predicting the demand of the shared umbrella. Taking Wuhan city as an example, the experimental results show that the proposed method can improve the prediction accuracy of the demand.
{"title":"Demand Forecasting for Shared Umbrella using BP Neural Network","authors":"Jiayi Zeng, Liping Zhang, Shangwen Peng, Junjie Wang, Qiuhua Tang","doi":"10.1109/ICIST52614.2021.9440556","DOIUrl":"https://doi.org/10.1109/ICIST52614.2021.9440556","url":null,"abstract":"Shared umbrella can bring us convenience in rain and snow. But uncertainty umbrella demand and the weather may cause the unbalance for a shared umbrella station. According to the information of the rainfall, temperature and so on, this paper proposed an efficient BP neural network to construct a prediction model for predicting the demand of the shared umbrella. Taking Wuhan city as an example, the experimental results show that the proposed method can improve the prediction accuracy of the demand.","PeriodicalId":371599,"journal":{"name":"2021 11th International Conference on Information Science and Technology (ICIST)","volume":"75 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124667939","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-05-21DOI: 10.1109/ICIST52614.2021.9440633
Jiajun Zhang, Juan Du
Urban tunnels is crucial to the function of modern society. The proper defect diagnosis and maintenance of tunnels are critical to the performance of tunnel infrastructure. Recent years, the data-driven causation analysis method is becoming popular, especially the ontology and rule reasoning method. However most exsisting research creat the ontology and reasoning rules mannully and lack of automatic implementation method. The paper use owlready2 package of python to realize the automatic generation of ontology and the automatic retrieval of ontology rules. Based on the methodology, the paper takes the defect causation analysis as the example, automatically generate the defect causation ontology, and automatically called reasoning rules to analyze the causes of tunnel defects. The proposed methodology provides practical value to defect causation analysis of urban infrastructure.
{"title":"Ontology-based Defect Causation Analysis for Urban Tunnel Maintenance","authors":"Jiajun Zhang, Juan Du","doi":"10.1109/ICIST52614.2021.9440633","DOIUrl":"https://doi.org/10.1109/ICIST52614.2021.9440633","url":null,"abstract":"Urban tunnels is crucial to the function of modern society. The proper defect diagnosis and maintenance of tunnels are critical to the performance of tunnel infrastructure. Recent years, the data-driven causation analysis method is becoming popular, especially the ontology and rule reasoning method. However most exsisting research creat the ontology and reasoning rules mannully and lack of automatic implementation method. The paper use owlready2 package of python to realize the automatic generation of ontology and the automatic retrieval of ontology rules. Based on the methodology, the paper takes the defect causation analysis as the example, automatically generate the defect causation ontology, and automatically called reasoning rules to analyze the causes of tunnel defects. The proposed methodology provides practical value to defect causation analysis of urban infrastructure.","PeriodicalId":371599,"journal":{"name":"2021 11th International Conference on Information Science and Technology (ICIST)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130315379","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-05-21DOI: 10.1109/ICIST52614.2021.9440597
Lu-Ming Wang, Yawen Deng, Fei Xiang, Xiaofeng Gong
In this paper, we propose a complex-valued joint eigenvalue decomposition(C-JEVD) algorithm based on LU de-composition and successive rotations. The proposed algorithm factorizes the matrix of eigenvectors into a lower-triangular matrix and an upper-triangular matrix, and update these two matrices using successive rotations. In each rotation, the elementary rotation matrix contains only one complex-valued parameter, which could be easily obtained via solving a cubic equation. Therefore, the proposed algorithm has low complexity. The proposed algorithm is compared with other C-JEVD methods through simulations.
{"title":"Complex-valued Joint Eigenvalue Decomposition Based on LU Decomposition and Successive Rotations","authors":"Lu-Ming Wang, Yawen Deng, Fei Xiang, Xiaofeng Gong","doi":"10.1109/ICIST52614.2021.9440597","DOIUrl":"https://doi.org/10.1109/ICIST52614.2021.9440597","url":null,"abstract":"In this paper, we propose a complex-valued joint eigenvalue decomposition(C-JEVD) algorithm based on LU de-composition and successive rotations. The proposed algorithm factorizes the matrix of eigenvectors into a lower-triangular matrix and an upper-triangular matrix, and update these two matrices using successive rotations. In each rotation, the elementary rotation matrix contains only one complex-valued parameter, which could be easily obtained via solving a cubic equation. Therefore, the proposed algorithm has low complexity. The proposed algorithm is compared with other C-JEVD methods through simulations.","PeriodicalId":371599,"journal":{"name":"2021 11th International Conference on Information Science and Technology (ICIST)","volume":"12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128097748","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-05-21DOI: 10.1109/ICIST52614.2021.9440642
Linlin Tan, Cheng Xing, Xinzhe Wang, Jianchao Fan
Mangrove is an important wetland ecosystem in coastal areas. It plays an important role in maintaining the coastal ecological environment, and also provides a guarantee for the survival of various organisms. In the past half century, mangrove has been seriously damaged, so it is very important to find an efficient and accurate method to monitor mangrove changes. The remote sensing technology is an important approach to monitor the dynamic changes of mangrove resources and health status. This paper takes the mangrove in Dandou Ocean of Guangxi province as the research area, uses a variety of optical satellite data sources, analyzes the key features of mangrove remote sensing information recognition, and studies the effective methods of mangrove extraction from different data sources. The experimental results show that the accuracy of mangrove extraction is mainly related to the amount of information in the spectrum feature space and the spatial resolution of the data source, and the difficulty of classification is mainly the distinction between terrestrial plants and mangroves. The accuracy of Sentinel-2A satellite using maximum likelihood classification(MLC) and support vector machine classification(SVM) is very close. Landsat8 satellite with medium and low resolution and large number of spectrum feature space and Gaofen-1 satellite with small number of high spatial resolution spectra are more suitable to be extracted by support vector machine classification. The accuracy of landsat8 satellite image extraction by support vector machine classification is the highest, the overall accuracy is 91.42%, and the kappa coefficient is 0.8819.
{"title":"Mangrove Information Extraction Based on Multi-source Remote Sensing Images","authors":"Linlin Tan, Cheng Xing, Xinzhe Wang, Jianchao Fan","doi":"10.1109/ICIST52614.2021.9440642","DOIUrl":"https://doi.org/10.1109/ICIST52614.2021.9440642","url":null,"abstract":"Mangrove is an important wetland ecosystem in coastal areas. It plays an important role in maintaining the coastal ecological environment, and also provides a guarantee for the survival of various organisms. In the past half century, mangrove has been seriously damaged, so it is very important to find an efficient and accurate method to monitor mangrove changes. The remote sensing technology is an important approach to monitor the dynamic changes of mangrove resources and health status. This paper takes the mangrove in Dandou Ocean of Guangxi province as the research area, uses a variety of optical satellite data sources, analyzes the key features of mangrove remote sensing information recognition, and studies the effective methods of mangrove extraction from different data sources. The experimental results show that the accuracy of mangrove extraction is mainly related to the amount of information in the spectrum feature space and the spatial resolution of the data source, and the difficulty of classification is mainly the distinction between terrestrial plants and mangroves. The accuracy of Sentinel-2A satellite using maximum likelihood classification(MLC) and support vector machine classification(SVM) is very close. Landsat8 satellite with medium and low resolution and large number of spectrum feature space and Gaofen-1 satellite with small number of high spatial resolution spectra are more suitable to be extracted by support vector machine classification. The accuracy of landsat8 satellite image extraction by support vector machine classification is the highest, the overall accuracy is 91.42%, and the kappa coefficient is 0.8819.","PeriodicalId":371599,"journal":{"name":"2021 11th International Conference on Information Science and Technology (ICIST)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125745714","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-05-21DOI: 10.1109/icist52614.2021.9440611
Xinjian Ming, Liyuan Qi, Dan Tu, Wei Zhang, Yuming Feng, B. Onasanya
The alternate control systems have been elaborated in detail and have been applied in many areas, such as smart home, smart transportation, etc. However, although alternate control systems with input delays widely exist in real life, not so much attention has been given to them. This paper mainly studies the stability of alternate control systems with input delays. A new mathematical model of the alternate control system with time delay input is proposed. By using a Lyapunov function and linear matrix inequalities, the exponential stability conditions is given. At last, the effectiveness and feasibility of the method are verified through experimental simulations.
{"title":"Alternate control time delay systems with input delays","authors":"Xinjian Ming, Liyuan Qi, Dan Tu, Wei Zhang, Yuming Feng, B. Onasanya","doi":"10.1109/icist52614.2021.9440611","DOIUrl":"https://doi.org/10.1109/icist52614.2021.9440611","url":null,"abstract":"The alternate control systems have been elaborated in detail and have been applied in many areas, such as smart home, smart transportation, etc. However, although alternate control systems with input delays widely exist in real life, not so much attention has been given to them. This paper mainly studies the stability of alternate control systems with input delays. A new mathematical model of the alternate control system with time delay input is proposed. By using a Lyapunov function and linear matrix inequalities, the exponential stability conditions is given. At last, the effectiveness and feasibility of the method are verified through experimental simulations.","PeriodicalId":371599,"journal":{"name":"2021 11th International Conference on Information Science and Technology (ICIST)","volume":"183 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132220506","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-05-21DOI: 10.1109/ICIST52614.2021.9440601
Yaru Zhang, Xijin J. Tang
There are many popular communication tools for news sharing in recent years. However, propagation of fake news becomes a serious issue concerning the public and government due to openness and rapidity of online communication. It is widely concerned how to automatically detect fake news as soon as possible. Nevertheless, most existing methods do not well utilize comments which contain rich semantic information or ignore their effect. Inspired by the revealing role of some comments to the original post, we propose the neural network model which consists of comment-level-attention (CLA) and comment-type-awareness (CTA) for fake news detection. In CLA, we devise the attention mechanism which considers semantic relation between the post and the comments. Based on attention weights we take the weighted sum of different comment representations for the sample as corresponding comment feature, which can capture key comment information. As similar to stance, we assume comments can gather into several different types naturally. Therefore, in CTA, we store comment type representations by the memory matrix which is learned in the training process of sample stream. Comment feature for the sample is aware of the memory matrix, and then corresponding comment type feature is obtained. We concatenate the above two auxiliary features and learned post feature to help detect fake news. Our validation experiments using the Weibo dataset and Pheme dataset demonstrate the effectiveness of the proposed model.
{"title":"CLACTA: Comment-Level-Attention and Comment-Type-Awareness for Fake News Detection","authors":"Yaru Zhang, Xijin J. Tang","doi":"10.1109/ICIST52614.2021.9440601","DOIUrl":"https://doi.org/10.1109/ICIST52614.2021.9440601","url":null,"abstract":"There are many popular communication tools for news sharing in recent years. However, propagation of fake news becomes a serious issue concerning the public and government due to openness and rapidity of online communication. It is widely concerned how to automatically detect fake news as soon as possible. Nevertheless, most existing methods do not well utilize comments which contain rich semantic information or ignore their effect. Inspired by the revealing role of some comments to the original post, we propose the neural network model which consists of comment-level-attention (CLA) and comment-type-awareness (CTA) for fake news detection. In CLA, we devise the attention mechanism which considers semantic relation between the post and the comments. Based on attention weights we take the weighted sum of different comment representations for the sample as corresponding comment feature, which can capture key comment information. As similar to stance, we assume comments can gather into several different types naturally. Therefore, in CTA, we store comment type representations by the memory matrix which is learned in the training process of sample stream. Comment feature for the sample is aware of the memory matrix, and then corresponding comment type feature is obtained. We concatenate the above two auxiliary features and learned post feature to help detect fake news. Our validation experiments using the Weibo dataset and Pheme dataset demonstrate the effectiveness of the proposed model.","PeriodicalId":371599,"journal":{"name":"2021 11th International Conference on Information Science and Technology (ICIST)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134208304","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：