Pub Date : 2021-07-11DOI: 10.1109/FUZZ45933.2021.9494526
Francisco J. Rodríguez-Lozano, D. Guijo-Rubio, Pedro Antonio Gutiérrez, J. M. Soto-Hidalgo, J. C. Gámez-Granados
Classification and regression techniques are two of the main tasks considered by the Machine Learning area. They mainly depend on the target variable to predict. In this context, ordinal classification represents an intermediate task, which is focused on the prediction of nominal variables where the categories follow a specific intrinsic order given by the problem. Nevertheless, the integration of different algorithms able to solve ordinal classification problems is often unavailable in most of existing Machine Learning software, which hinders the use of new approaches. Therefore, this paper focuses on the incorporation of an ordinal classification algorithm (NSLVOrd) in one of the most complete ordinal regression frameworks, “Ordinal Regression and Classification Algorithms framework (ORCA)” by using both fuzzy rules and the JFML library. The use of NSLVOrd in the ORCA tool as well as a case study with a real database are shown where the obtained results are promising.
{"title":"Enhancing the ORCA framework with a new Fuzzy Rule Base System implementation compatible with the JFML library","authors":"Francisco J. Rodríguez-Lozano, D. Guijo-Rubio, Pedro Antonio Gutiérrez, J. M. Soto-Hidalgo, J. C. Gámez-Granados","doi":"10.1109/FUZZ45933.2021.9494526","DOIUrl":"https://doi.org/10.1109/FUZZ45933.2021.9494526","url":null,"abstract":"Classification and regression techniques are two of the main tasks considered by the Machine Learning area. They mainly depend on the target variable to predict. In this context, ordinal classification represents an intermediate task, which is focused on the prediction of nominal variables where the categories follow a specific intrinsic order given by the problem. Nevertheless, the integration of different algorithms able to solve ordinal classification problems is often unavailable in most of existing Machine Learning software, which hinders the use of new approaches. Therefore, this paper focuses on the incorporation of an ordinal classification algorithm (NSLVOrd) in one of the most complete ordinal regression frameworks, “Ordinal Regression and Classification Algorithms framework (ORCA)” by using both fuzzy rules and the JFML library. The use of NSLVOrd in the ORCA tool as well as a case study with a real database are shown where the obtained results are promising.","PeriodicalId":151289,"journal":{"name":"2021 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131249116","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 : 2021-07-11DOI: 10.1109/FUZZ45933.2021.9494570
B. Lipiec, M. Mrugalski, M. Witczak
The paper deals with a problem of a work scheduling of a fleet of cooperating forklifts. Their cooperation means that they can perform a given interchangeability. Unfortunately, it causes an inevitable concurrency issue, which has to be resolved in an optimal way. Since the vehicles are autonomous, there are no human operators whose experience could be a selection criteria in solving the above problem. Thus, the paper proposes a novel health-aware-based cost function which takes into account predictions concerning current operational ability of vehicle batteries. To obtain these predictions a Takagi-Sugeno approach is proposed and validated using Li-Ion battery data set provided by NASA PCoE. Finally, it is incorporated into the health-aware fault tolerant control scheme, which can tolerate inevitable delays present in such a transportation system.
{"title":"Health-aware fault-tolerant control of multiple cooperating autonoumous vehicles","authors":"B. Lipiec, M. Mrugalski, M. Witczak","doi":"10.1109/FUZZ45933.2021.9494570","DOIUrl":"https://doi.org/10.1109/FUZZ45933.2021.9494570","url":null,"abstract":"The paper deals with a problem of a work scheduling of a fleet of cooperating forklifts. Their cooperation means that they can perform a given interchangeability. Unfortunately, it causes an inevitable concurrency issue, which has to be resolved in an optimal way. Since the vehicles are autonomous, there are no human operators whose experience could be a selection criteria in solving the above problem. Thus, the paper proposes a novel health-aware-based cost function which takes into account predictions concerning current operational ability of vehicle batteries. To obtain these predictions a Takagi-Sugeno approach is proposed and validated using Li-Ion battery data set provided by NASA PCoE. Finally, it is incorporated into the health-aware fault tolerant control scheme, which can tolerate inevitable delays present in such a transportation system.","PeriodicalId":151289,"journal":{"name":"2021 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)","volume":"54 2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130905990","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 : 2021-07-11DOI: 10.1109/FUZZ45933.2021.9494414
Piotr Grochowalski, Anna Król, W. Rzasa
The paper presents a modified classification method based on the k-nearest neighbor algorithm. In the modified kNN algorithm some aggregations of fuzzy equivalences are used instead of metrics and the selection of the nearest neighbors is limited by their closeness from a tested object. This procedure is intended to improve suitability of the kNN algorithm, when a significant part of the closest neighbors is not close enough to the tested object. Additionally, some theoretical results concerning fuzzy equivalences and their aggregations are included in the paper.
{"title":"Radius kNN Classifier Using Aggregation of Fuzzy Equivalences","authors":"Piotr Grochowalski, Anna Król, W. Rzasa","doi":"10.1109/FUZZ45933.2021.9494414","DOIUrl":"https://doi.org/10.1109/FUZZ45933.2021.9494414","url":null,"abstract":"The paper presents a modified classification method based on the k-nearest neighbor algorithm. In the modified kNN algorithm some aggregations of fuzzy equivalences are used instead of metrics and the selection of the nearest neighbors is limited by their closeness from a tested object. This procedure is intended to improve suitability of the kNN algorithm, when a significant part of the closest neighbors is not close enough to the tested object. Additionally, some theoretical results concerning fuzzy equivalences and their aggregations are included in the paper.","PeriodicalId":151289,"journal":{"name":"2021 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124443958","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 : 2021-07-11DOI: 10.1109/FUZZ45933.2021.9494484
Ashishsingh Bhatia, H. Hagras
Fuzzy Rule Based Systems (FRBSs) can suffer from incomplete and sparse rule bases as a result of selecting a small number of rules from a large universe of potential rules. This may lead to rational gaps creeping into the input output mapping, where sometimes, strongly correlated inputs displaying a linear relationship with the output do not exhibit the same behaviour during inferencing. This paper proposes a technique for identifying and rectifying such gaps for FRBSs using incomplete rule bases in real-world regression problems.
{"title":"Identifying and Rectifying Rational Gaps in Fuzzy Rule Based Systems for Regression Problems","authors":"Ashishsingh Bhatia, H. Hagras","doi":"10.1109/FUZZ45933.2021.9494484","DOIUrl":"https://doi.org/10.1109/FUZZ45933.2021.9494484","url":null,"abstract":"Fuzzy Rule Based Systems (FRBSs) can suffer from incomplete and sparse rule bases as a result of selecting a small number of rules from a large universe of potential rules. This may lead to rational gaps creeping into the input output mapping, where sometimes, strongly correlated inputs displaying a linear relationship with the output do not exhibit the same behaviour during inferencing. This paper proposes a technique for identifying and rectifying such gaps for FRBSs using incomplete rule bases in real-world regression problems.","PeriodicalId":151289,"journal":{"name":"2021 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114398224","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 : 2021-07-11DOI: 10.1109/FUZZ45933.2021.9494524
Arnab Sircar
This study focused on developing composite indices (CI) to determine the degree to which electric vehicles (EVs) may be adopted by consumers, manufacturers, and investors. These indices may be used as gauges of where resources should be allocated in the EV industry. The first step was to collect opinions from six experts who provided inputs as fuzzy numbers. They provided inputs on twelve different factors which were divided into three categories: Design and Manufacture, Performance and Efficiency, and Sustainability and Environment. The CIs were developed for each category. Using the fuzzy inputs, two different methods of aggregating the opinions were used: the first was the Agreement Matrix method (AM) which focused on the degree of agreement among the experts, and the second one was called the Normalized Defuzzification method (ND) that focused on the weights of various factors as well as a signal-to-noise ratio metric. In order to compare the CIs obtained from these methods, the idea of information loss was used. After performing the calculations, it was observed that the AM method had lower CI information losses for all three categories. A few extensions of this study are provided in the conclusion.
{"title":"Composite Indices for Adoption of Electric Vehicles (EVs)","authors":"Arnab Sircar","doi":"10.1109/FUZZ45933.2021.9494524","DOIUrl":"https://doi.org/10.1109/FUZZ45933.2021.9494524","url":null,"abstract":"This study focused on developing composite indices (CI) to determine the degree to which electric vehicles (EVs) may be adopted by consumers, manufacturers, and investors. These indices may be used as gauges of where resources should be allocated in the EV industry. The first step was to collect opinions from six experts who provided inputs as fuzzy numbers. They provided inputs on twelve different factors which were divided into three categories: Design and Manufacture, Performance and Efficiency, and Sustainability and Environment. The CIs were developed for each category. Using the fuzzy inputs, two different methods of aggregating the opinions were used: the first was the Agreement Matrix method (AM) which focused on the degree of agreement among the experts, and the second one was called the Normalized Defuzzification method (ND) that focused on the weights of various factors as well as a signal-to-noise ratio metric. In order to compare the CIs obtained from these methods, the idea of information loss was used. After performing the calculations, it was observed that the AM method had lower CI information losses for all three categories. A few extensions of this study are provided in the conclusion.","PeriodicalId":151289,"journal":{"name":"2021 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116801075","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 : 2021-07-11DOI: 10.1109/FUZZ45933.2021.9494447
A. Choudhary, Preeti Jha, Aruna Tiwari, Neha Bharill, M. Ratnaparkhe
Learning in non-stationary environments require modern tools and algorithms to quickly adapt to the new pattern because concept drift can change the underlying distribution. So, the existing assumption that the data is independent and identically distributed may be invalid in data stream scenarios. Given the massive volume of high-speed data streams and the concept drift, traditional machine learning algorithms must be self-adapting. One of the difficulties in handling regression tasks is the complexities of equations for the regression models when combined with drift handling techniques. The high dimensional protein data is a major challenge for bioinformatics researchers to analyse the dynamics of the sequences. This paper proposes a Scalable Fuzzy Clustering induced Regression (SFC-R) algorithm to predict the isoelectric point of the plant protein sequences using Apache Spark clusters. The SFC-R algorithm uses the input features extracted from the plant protein sequences and validates performance in terms of mean squared error (MAE) and root-mean-square error (RMSE). Experiments on plant protein datasets are carried out to validate the high accuracy and robustness of our approach.
{"title":"Scalable Fuzzy Clustering-based Regression to Predict the Isoelectric Points of the Plant Protein Sequences using Apache Spark","authors":"A. Choudhary, Preeti Jha, Aruna Tiwari, Neha Bharill, M. Ratnaparkhe","doi":"10.1109/FUZZ45933.2021.9494447","DOIUrl":"https://doi.org/10.1109/FUZZ45933.2021.9494447","url":null,"abstract":"Learning in non-stationary environments require modern tools and algorithms to quickly adapt to the new pattern because concept drift can change the underlying distribution. So, the existing assumption that the data is independent and identically distributed may be invalid in data stream scenarios. Given the massive volume of high-speed data streams and the concept drift, traditional machine learning algorithms must be self-adapting. One of the difficulties in handling regression tasks is the complexities of equations for the regression models when combined with drift handling techniques. The high dimensional protein data is a major challenge for bioinformatics researchers to analyse the dynamics of the sequences. This paper proposes a Scalable Fuzzy Clustering induced Regression (SFC-R) algorithm to predict the isoelectric point of the plant protein sequences using Apache Spark clusters. The SFC-R algorithm uses the input features extracted from the plant protein sequences and validates performance in terms of mean squared error (MAE) and root-mean-square error (RMSE). Experiments on plant protein datasets are carried out to validate the high accuracy and robustness of our approach.","PeriodicalId":151289,"journal":{"name":"2021 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)","volume":"73 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127276135","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 : 2021-07-11DOI: 10.1109/FUZZ45933.2021.9494598
Corrado Mencar, C. Castiello
Fuzzy Rule-Based Systems (FRBSs) are endowed with a knowledge base that can be used to provide model and outcome explanations. Usually, FRBSs are acquired from data by applying some learning methods: it is expected that, when modeling the same phenomenon, the FRBSs resulting from the application of a learning method should provide almost the same explanations. This requires a stability in the description of the knowledge bases that can be evaluated through the proposed measure of Descriptive Stability. The measure has been applied on three methods for generating FRBSs based on three benchmark datasets. The results show that, under same settings, different methods may produce FRBSs with varying stability, which impacts on their ability to provide trustful explanations.
{"title":"Descriptive Stability of Fuzzy Rule-Based Systems","authors":"Corrado Mencar, C. Castiello","doi":"10.1109/FUZZ45933.2021.9494598","DOIUrl":"https://doi.org/10.1109/FUZZ45933.2021.9494598","url":null,"abstract":"Fuzzy Rule-Based Systems (FRBSs) are endowed with a knowledge base that can be used to provide model and outcome explanations. Usually, FRBSs are acquired from data by applying some learning methods: it is expected that, when modeling the same phenomenon, the FRBSs resulting from the application of a learning method should provide almost the same explanations. This requires a stability in the description of the knowledge bases that can be evaluated through the proposed measure of Descriptive Stability. The measure has been applied on three methods for generating FRBSs based on three benchmark datasets. The results show that, under same settings, different methods may produce FRBSs with varying stability, which impacts on their ability to provide trustful explanations.","PeriodicalId":151289,"journal":{"name":"2021 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123329808","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 : 2021-07-11DOI: 10.1109/FUZZ45933.2021.9494434
Hoang Nguyen
Although there are more and more studies on dealing with uncertainty and vagueness of information, there exist still some basic flaws related to distinguishing and comparing them. Most of the existing methods are based on the distance and entropy measures. However, more and more counterintuitive measures have been revealed and published in the literature. In this paper, a novel similarity measure for interval-valued intuitionistic fuzzy sets is proposed based on the generalized score function, which is in turn constructed from the generalized p-norm knowledge measure. The generalized p-norm knowledge measure for interval-valued intuitionistic fuzzy sets incorporates the amount of knowledge and fuzziness of information that provides reasonable measurements regardless of the representation norm. Based on the generalized knowledge measure and score function, the novel similarity measure can incorporate the significance (importance) of information making it more intuitive in comparing them, especially the ill-defined ones with the same amount of approving and disapproving information. The superiority of the proposed methods is shown by comparing with some existing measures in some numerical examples. Furthermore, it is also applied to deal with pattern recognition and medical diagnosis problems, that proves to be more flexible and adequate for dealing with uncertain and vague information.
{"title":"A Novel Similarity Measure Based on Generalized Score Function For Interval-valued Intuitionistic Fuzzy Sets With Applications","authors":"Hoang Nguyen","doi":"10.1109/FUZZ45933.2021.9494434","DOIUrl":"https://doi.org/10.1109/FUZZ45933.2021.9494434","url":null,"abstract":"Although there are more and more studies on dealing with uncertainty and vagueness of information, there exist still some basic flaws related to distinguishing and comparing them. Most of the existing methods are based on the distance and entropy measures. However, more and more counterintuitive measures have been revealed and published in the literature. In this paper, a novel similarity measure for interval-valued intuitionistic fuzzy sets is proposed based on the generalized score function, which is in turn constructed from the generalized p-norm knowledge measure. The generalized p-norm knowledge measure for interval-valued intuitionistic fuzzy sets incorporates the amount of knowledge and fuzziness of information that provides reasonable measurements regardless of the representation norm. Based on the generalized knowledge measure and score function, the novel similarity measure can incorporate the significance (importance) of information making it more intuitive in comparing them, especially the ill-defined ones with the same amount of approving and disapproving information. The superiority of the proposed methods is shown by comparing with some existing measures in some numerical examples. Furthermore, it is also applied to deal with pattern recognition and medical diagnosis problems, that proves to be more flexible and adequate for dealing with uncertain and vague information.","PeriodicalId":151289,"journal":{"name":"2021 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123015518","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 : 2021-07-11DOI: 10.1109/FUZZ45933.2021.9494599
E. Szmidt, J. Kacprzyk, Paweł Bujnowski
We propose here a new proposal for attribute selection in the models expressed by the intuitionistic fuzzy sets. We further develop our previous paper in which the approach was already extended and the first computational tests were performed, i.e., the method was compared with the Principal Component Analysis (PCA). Here we test how the method behaves in comparison with the selection while using the Gain Ratio. We consider classification problems and try to reduce the number of attributes to not obtain substantially worse results.
{"title":"Three term attribute description of Atanassov's Intuitionistic Fuzzy Sets as a basis of attribute selection","authors":"E. Szmidt, J. Kacprzyk, Paweł Bujnowski","doi":"10.1109/FUZZ45933.2021.9494599","DOIUrl":"https://doi.org/10.1109/FUZZ45933.2021.9494599","url":null,"abstract":"We propose here a new proposal for attribute selection in the models expressed by the intuitionistic fuzzy sets. We further develop our previous paper in which the approach was already extended and the first computational tests were performed, i.e., the method was compared with the Principal Component Analysis (PCA). Here we test how the method behaves in comparison with the selection while using the Gain Ratio. We consider classification problems and try to reduce the number of attributes to not obtain substantially worse results.","PeriodicalId":151289,"journal":{"name":"2021 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122245853","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 : 2021-07-11DOI: 10.1109/FUZZ45933.2021.9494581
Ru-xia Liang, Qian Zhang, Jianqiang Wang
Human's group activities have contributed to the development of group recommender systems. The group recommender system can provide personalised services for various online user groups through analysing groups' preferences. However, current group recommendation methods have failed to exploit complex relationships among users, groups and items when extracting groups' preferences. Meanwhile, most previous works are based on crisp techniques, which result in rigid preference profiling. Benefiting from the development of graph attention networks, this paper represents the complex relationships among users, groups and items as various graphs, including user-/group-item graph, user-group graph and user-user graph, and proposes a hierarchical fuzzy graph attention network (HGAT-F) to enhance fuzzy profiling for both groups and items. Experiments results on real world datasets show that HGAT-F has enhanced group recommendation than previous works.
{"title":"Hierarchical Fuzzy Graph Attention Network for Group Recommendation","authors":"Ru-xia Liang, Qian Zhang, Jianqiang Wang","doi":"10.1109/FUZZ45933.2021.9494581","DOIUrl":"https://doi.org/10.1109/FUZZ45933.2021.9494581","url":null,"abstract":"Human's group activities have contributed to the development of group recommender systems. The group recommender system can provide personalised services for various online user groups through analysing groups' preferences. However, current group recommendation methods have failed to exploit complex relationships among users, groups and items when extracting groups' preferences. Meanwhile, most previous works are based on crisp techniques, which result in rigid preference profiling. Benefiting from the development of graph attention networks, this paper represents the complex relationships among users, groups and items as various graphs, including user-/group-item graph, user-group graph and user-user graph, and proposes a hierarchical fuzzy graph attention network (HGAT-F) to enhance fuzzy profiling for both groups and items. Experiments results on real world datasets show that HGAT-F has enhanced group recommendation than previous works.","PeriodicalId":151289,"journal":{"name":"2021 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126044412","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：