Pub Date : 2021-07-11DOI: 10.1109/FUZZ45933.2021.9494400
Wen He, Rosa M. Rodríguez, Bapi Dutta, Luis Martínez
In a group decision making (GDM) problem, the information is fused to obtain a collective result, which helps to choose the best solution/s to the problem. Recently, a new representation model called Extended Comparative Linguistic Expressions with Symbolic Translation (ELICIT), which extends the representation of the comparative linguistic expressions (CLEs) to a continuous domain combining the advantages of the hesitant fuzzy linguistic term sets and 2-tuple linguistic representation model has been proposed to model experts' preferences. Due to the need of fusing experts' preferences in GDM processes, it is convenient to have enough flexible aggregation operators for such processes. However, so far, only two aggregation operators have been introduced to aggregate ELICIT information in GDM problems, the fuzzy arithmetic mean operator and the Bonferroni mean operator. Thus, it seems necessary to define new aggregation operators with different features to model wide range of decision-making scenarios. One widely used operator to aggregate preferences in decision making is the OWA operator. The key issue to apply the OWA operator is the reordering process of the arguments. However, the ELICIT information does not have an inherent order because it is represented by a fuzzy number. Therefore, the aim of this contribution is to define the type-1 ELICIT OWA operator by using crisp and fuzzy weights, particularly interval weights, and define a multi-criteria group decision making model which applies the type-1 ELICIT OWA operator to fuse the information. Additionally, an experimental study is introduced to demonstrate the feasibility of the proposed aggregation operator.
在群体决策(GDM)问题中，信息融合得到一个集体的结果，这有助于选择问题的最佳解决方案。近年来，人们提出了一种新的表征模型——带符号翻译的扩展比较语言表达(Extended Comparative Linguistic Expressions with Symbolic Translation，简称ELICIT)，将比较语言表达(CLEs)的表征扩展到一个连续域，结合犹豫模糊语言术语集和二元组语言表征模型的优点，对专家的偏好进行建模。由于GDM过程需要融合专家的偏好，因此为该过程提供足够灵活的聚合算子是很方便的。然而，到目前为止，在GDM问题中只引入了两种聚合算子来聚合引出信息，即模糊算术均值算子和Bonferroni均值算子。因此，似乎有必要定义具有不同特征的新聚合操作符来模拟广泛的决策场景。在决策过程中，一个广泛用于聚合首选项的操作符是OWA操作符。应用OWA操作符的关键问题是参数的重新排序过程。然而，引出信息没有固有的顺序，因为它是由模糊数表示的。因此，本文的目的是通过使用清晰和模糊的权重，特别是区间权重来定义1型引出OWA算子，并定义一个多准则群体决策模型，该模型应用1型引出OWA算子来融合信息。此外，还介绍了实验研究，以验证所提出的聚合算子的可行性。
{"title":"Exploiting the type-1 OWA operator to fuse the ELICIT information","authors":"Wen He, Rosa M. Rodríguez, Bapi Dutta, Luis Martínez","doi":"10.1109/FUZZ45933.2021.9494400","DOIUrl":"https://doi.org/10.1109/FUZZ45933.2021.9494400","url":null,"abstract":"In a group decision making (GDM) problem, the information is fused to obtain a collective result, which helps to choose the best solution/s to the problem. Recently, a new representation model called Extended Comparative Linguistic Expressions with Symbolic Translation (ELICIT), which extends the representation of the comparative linguistic expressions (CLEs) to a continuous domain combining the advantages of the hesitant fuzzy linguistic term sets and 2-tuple linguistic representation model has been proposed to model experts' preferences. Due to the need of fusing experts' preferences in GDM processes, it is convenient to have enough flexible aggregation operators for such processes. However, so far, only two aggregation operators have been introduced to aggregate ELICIT information in GDM problems, the fuzzy arithmetic mean operator and the Bonferroni mean operator. Thus, it seems necessary to define new aggregation operators with different features to model wide range of decision-making scenarios. One widely used operator to aggregate preferences in decision making is the OWA operator. The key issue to apply the OWA operator is the reordering process of the arguments. However, the ELICIT information does not have an inherent order because it is represented by a fuzzy number. Therefore, the aim of this contribution is to define the type-1 ELICIT OWA operator by using crisp and fuzzy weights, particularly interval weights, and define a multi-criteria group decision making model which applies the type-1 ELICIT OWA operator to fuse the information. Additionally, an experimental study is introduced to demonstrate the feasibility of the proposed aggregation operator.","PeriodicalId":151289,"journal":{"name":"2021 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)","volume":"110 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":"133814847","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/FUZZ45933.2021.9494516
Adrià Torrens Urrutia, M. Dolores Jiménez-López, Antoni Brosa-Rodríguez
One of the currently biggest challenges in NLP is to develop multilingual language technology. Lack of data in low-resources languages poses great difficulty to NLP researchers and limits NLP technology's availability to a small number of resource-rich languages. It has been shown that linguistic typology and the knowledge of language universals can help NLP in the development of multilingual resources. To contribute to this research area, we present a fuzzy approach to language universals. Our proposal combines a constraint-based formalism with fuzzy logic to define a fuzzy-gradient model to characterize linguistic universals. This model will allow us to evaluate linguistic universals and to define a universal grammar. This universal grammar will be integrated into an automatic technique to infer from linguistic data the particular grammar of any understudied natural language.
{"title":"A Fuzzy Approach to Language Universals for NLP","authors":"Adrià Torrens Urrutia, M. Dolores Jiménez-López, Antoni Brosa-Rodríguez","doi":"10.1109/FUZZ45933.2021.9494516","DOIUrl":"https://doi.org/10.1109/FUZZ45933.2021.9494516","url":null,"abstract":"One of the currently biggest challenges in NLP is to develop multilingual language technology. Lack of data in low-resources languages poses great difficulty to NLP researchers and limits NLP technology's availability to a small number of resource-rich languages. It has been shown that linguistic typology and the knowledge of language universals can help NLP in the development of multilingual resources. To contribute to this research area, we present a fuzzy approach to language universals. Our proposal combines a constraint-based formalism with fuzzy logic to define a fuzzy-gradient model to characterize linguistic universals. This model will allow us to evaluate linguistic universals and to define a universal grammar. This universal grammar will be integrated into an automatic technique to infer from linguistic data the particular grammar of any understudied natural language.","PeriodicalId":151289,"journal":{"name":"2021 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)","volume":"16 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":"132634779","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/FUZZ45933.2021.9494500
T. Reddy, Yu-kai Wang, Chin-Teng Lin, Javier Andreu-Perez
Neurons usually converse through electrochemical signals and pooled neuronal firings feasibly be recorded on the scalp through the medium of electroencephalogram (EEG). EEG waveforms are recorded, analysed and categorized across directives concerning a Brain-Computer Interface (BCI). Deteriorated signal to noise ratio and non-stationarities stand as a paramount obstacle in steady decoding of EEG. Appearance of non-stationarities across EEG patterns notably upset the feature waveforms thus worsening the functioning of detection block and as a whole the Brain Computer Interface. Stationary Subspace schemes bring to light subspaces within which data distribution persists stably over time. Current work focuses on the development of a novel spatial transform based feature extraction scheme to address nonstationarity in EEG signals recorded against a drowsiness detection problem (a machine learning regression scenario). The presented approach: F-DIV-IT-JAD-WS derived features distinctly surpassed DivOVR-FuzzyCSP-WS based standard features across RMSE and CC performance criteria pair. We construe that the propounded feature derivation approach based on F-DIV-IT-JAD-WS will usher a significant attention in researchers who are developing algorithms for signal processing, specifically, for BCI regression scenarios.
{"title":"JOINT APPROXIMATE DIAGONALIZATION DIVERGENCE BASED SCHEME FOR EEG DROWSINESS DETECTION BRAIN COMPUTER INTERFACES","authors":"T. Reddy, Yu-kai Wang, Chin-Teng Lin, Javier Andreu-Perez","doi":"10.1109/FUZZ45933.2021.9494500","DOIUrl":"https://doi.org/10.1109/FUZZ45933.2021.9494500","url":null,"abstract":"Neurons usually converse through electrochemical signals and pooled neuronal firings feasibly be recorded on the scalp through the medium of electroencephalogram (EEG). EEG waveforms are recorded, analysed and categorized across directives concerning a Brain-Computer Interface (BCI). Deteriorated signal to noise ratio and non-stationarities stand as a paramount obstacle in steady decoding of EEG. Appearance of non-stationarities across EEG patterns notably upset the feature waveforms thus worsening the functioning of detection block and as a whole the Brain Computer Interface. Stationary Subspace schemes bring to light subspaces within which data distribution persists stably over time. Current work focuses on the development of a novel spatial transform based feature extraction scheme to address nonstationarity in EEG signals recorded against a drowsiness detection problem (a machine learning regression scenario). The presented approach: F-DIV-IT-JAD-WS derived features distinctly surpassed DivOVR-FuzzyCSP-WS based standard features across RMSE and CC performance criteria pair. We construe that the propounded feature derivation approach based on F-DIV-IT-JAD-WS will usher a significant attention in researchers who are developing algorithms for signal processing, specifically, for BCI regression scenarios.","PeriodicalId":151289,"journal":{"name":"2021 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)","volume":"14 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":"122334425","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/FUZZ45933.2021.9494505
S. Kakula, Anthony J. Pinar, T. Havens, Derek T. Anderson
The Choquet integral (ChI) is an aggregation operator defined with respect to a fuzzy measure (FM). The FM encodes the worth of all subsets of the sources of information that are being aggregated. The ChI is capable of representing many aggregation functions and has found its application in a wide range of decision fusion problems. In our prior work, we introduced a data support-based approach for learning the FM for decision fusion problems. This approach applies a quadratic programming (QP)-based method to train the FM. However, since the FM of ChI scales as $2^{N}$, where $N$ is the number of input sources, the space complexity for learning the FM grows exponentially with $N$. This has limited the practical application of ChI-based decision fusion methods to small numbers of dimenstions—$N$ ≲ 6 is practical in most cases. In this work, we propose an iterative gradient descent-based approach to train the FM for ChI with an efficient method for handling the FM constraints. This method processes the training data, one observation at a time, and thereby significantly reduces the space complexity of the training process. We tested our online method on synthetic and real-world data sets, and compared the performance and convergence behaviour with our previously proposed QP-based method (i.e., batch method). On 10 out of 12 data sets, the online learning method has either matched or outperformed the batch method. We also show that we are able to use larger numbers of inputs with the online learning approach, extending the practical application of the ChI.
{"title":"Online Sequential Learning of Fuzzy Measures for Choquet Integral Fusion","authors":"S. Kakula, Anthony J. Pinar, T. Havens, Derek T. Anderson","doi":"10.1109/FUZZ45933.2021.9494505","DOIUrl":"https://doi.org/10.1109/FUZZ45933.2021.9494505","url":null,"abstract":"The Choquet integral (ChI) is an aggregation operator defined with respect to a fuzzy measure (FM). The FM encodes the worth of all subsets of the sources of information that are being aggregated. The ChI is capable of representing many aggregation functions and has found its application in a wide range of decision fusion problems. In our prior work, we introduced a data support-based approach for learning the FM for decision fusion problems. This approach applies a quadratic programming (QP)-based method to train the FM. However, since the FM of ChI scales as $2^{N}$, where $N$ is the number of input sources, the space complexity for learning the FM grows exponentially with $N$. This has limited the practical application of ChI-based decision fusion methods to small numbers of dimenstions—$N$ ≲ 6 is practical in most cases. In this work, we propose an iterative gradient descent-based approach to train the FM for ChI with an efficient method for handling the FM constraints. This method processes the training data, one observation at a time, and thereby significantly reduces the space complexity of the training process. We tested our online method on synthetic and real-world data sets, and compared the performance and convergence behaviour with our previously proposed QP-based method (i.e., batch method). On 10 out of 12 data sets, the online learning method has either matched or outperformed the batch method. We also show that we are able to use larger numbers of inputs with the online learning approach, extending the practical application of the ChI.","PeriodicalId":151289,"journal":{"name":"2021 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)","volume":"41 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":"125364796","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/FUZZ45933.2021.9494571
Carmen Biedma-Rdguez, M. J. Gacto, R. Alcalá, J. Alcalá-Fdez
A large number of systems with a great predictive capacity, such as Deep Learning, are being currently used to solve a wide variety of real problems. However, the models obtained are not easy to understand by scientists, giving rise to the field of eXplainable Artificial Intelligence, which encourage techniques that obtain accurate and understandable models. Fuzzy Association Rules are models that can be understood by themselves, but its interpretability can be improved by representing the same information with fewer and simpler rules. In this work, we propose Meta-Fuzzy Items, which allows to define more generic fuzzy items to represent the same information with fewer rules, and to extend the type of associations that can be represented. Based on this proposal, a new fuzzy data-mining algorithm is presented to extract interesting and interpretable rules from quantitative transactions. The quality of our approach is analyzed using statistical analysis and comparing with a well-known fuzzy data-mining algorithm.
{"title":"Meta-Fuzzy Items for Fuzzy Association Rules","authors":"Carmen Biedma-Rdguez, M. J. Gacto, R. Alcalá, J. Alcalá-Fdez","doi":"10.1109/FUZZ45933.2021.9494571","DOIUrl":"https://doi.org/10.1109/FUZZ45933.2021.9494571","url":null,"abstract":"A large number of systems with a great predictive capacity, such as Deep Learning, are being currently used to solve a wide variety of real problems. However, the models obtained are not easy to understand by scientists, giving rise to the field of eXplainable Artificial Intelligence, which encourage techniques that obtain accurate and understandable models. Fuzzy Association Rules are models that can be understood by themselves, but its interpretability can be improved by representing the same information with fewer and simpler rules. In this work, we propose Meta-Fuzzy Items, which allows to define more generic fuzzy items to represent the same information with fewer rules, and to extend the type of associations that can be represented. Based on this proposal, a new fuzzy data-mining algorithm is presented to extract interesting and interpretable rules from quantitative transactions. The quality of our approach is analyzed using statistical analysis and comparing with a well-known fuzzy data-mining algorithm.","PeriodicalId":151289,"journal":{"name":"2021 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)","volume":"4 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":"121263730","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/FUZZ45933.2021.9494468
Norbert Kukurowski, M. Pazera, M. Witczak
The paper proposes a robust observer-based fault-tolerant tracking control scheme for Takagi-Sugeno fuzzy systems along with its actuator remaining useful life estimation. The difficulty lies in the fact that the system can be occupied by an external disturbances as well as the sensor and actuator faults. A robust stability of the proposed observer and controller is guaranteed by using a quadratic boundedness approach, which uses a simplifying assumption stating that an external disturbances are bounded by an ellipsoid. Subsequently, the actuator remaining useful life scheme for the faulty actuator is developed. Finally, a Takagi-Sugeno fuzzy model of the twin-rotor laboratory system is used to verify the correctness and performance of the proposed strategy.
{"title":"Fault-Tolerant Tracking Control and Remaining Useful Life Estimation for Takagi-Sugeno fuzzy system","authors":"Norbert Kukurowski, M. Pazera, M. Witczak","doi":"10.1109/FUZZ45933.2021.9494468","DOIUrl":"https://doi.org/10.1109/FUZZ45933.2021.9494468","url":null,"abstract":"The paper proposes a robust observer-based fault-tolerant tracking control scheme for Takagi-Sugeno fuzzy systems along with its actuator remaining useful life estimation. The difficulty lies in the fact that the system can be occupied by an external disturbances as well as the sensor and actuator faults. A robust stability of the proposed observer and controller is guaranteed by using a quadratic boundedness approach, which uses a simplifying assumption stating that an external disturbances are bounded by an ellipsoid. Subsequently, the actuator remaining useful life scheme for the faulty actuator is developed. Finally, a Takagi-Sugeno fuzzy model of the twin-rotor laboratory system is used to verify the correctness and performance of the proposed strategy.","PeriodicalId":151289,"journal":{"name":"2021 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)","volume":"75 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":"125448312","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/FUZZ45933.2021.9494413
Fatemeh Rezaee-Ahmadi, H. Rafiei, M. Akbarzadeh-T.
Z-numbers consist of two components, restriction and restriction reliability, to cover both possibilistic and probabilistic uncertainties. So far, the components of Z-numbers are merely determined by expert knowledge and lack automated learning/training. To overcome this limitation, we propose a Z-Adaptive Fuzzy Inference System (ZAFIS) that systematically learns the parameters of Z-numbers from input-output data pairs. We first convert the second component of Z-numbers to a crisp number. We then use this number as a weight for the first fuzzy membership part of Z-numbers. Finally, the resultant membership is placed in a fuzzy inference system, and the parameters of the system are learned based on the input-output data pairs using a gradient descent algorithm. The proposed method is evaluated on several functions (sine, increasing sine, Hermite, Gabor, and a nonlinear function) with/without added noise scenarios. The results show that the ZAFIS is more robust against the noisy inputs and is superior to the Fuzzy Inference Systems (FISs) in terms of MSE.
{"title":"Z-Adaptive Fuzzy Inference Systems","authors":"Fatemeh Rezaee-Ahmadi, H. Rafiei, M. Akbarzadeh-T.","doi":"10.1109/FUZZ45933.2021.9494413","DOIUrl":"https://doi.org/10.1109/FUZZ45933.2021.9494413","url":null,"abstract":"Z-numbers consist of two components, restriction and restriction reliability, to cover both possibilistic and probabilistic uncertainties. So far, the components of Z-numbers are merely determined by expert knowledge and lack automated learning/training. To overcome this limitation, we propose a Z-Adaptive Fuzzy Inference System (ZAFIS) that systematically learns the parameters of Z-numbers from input-output data pairs. We first convert the second component of Z-numbers to a crisp number. We then use this number as a weight for the first fuzzy membership part of Z-numbers. Finally, the resultant membership is placed in a fuzzy inference system, and the parameters of the system are learned based on the input-output data pairs using a gradient descent algorithm. The proposed method is evaluated on several functions (sine, increasing sine, Hermite, Gabor, and a nonlinear function) with/without added noise scenarios. The results show that the ZAFIS is more robust against the noisy inputs and is superior to the Fuzzy Inference Systems (FISs) in terms of MSE.","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":"129336892","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/FUZZ45933.2021.9494582
Adam Kiersztyn, Paweł Karczmarek, Krystyna Kiersztyn, R. Lopucki, S. Grzegórski, W. Pedrycz
With the advent of research into Granular Computing, in particular information granules, the way of thinking about data has changed gradually. Researchers and practitioners do not consider only their specific properties, but also try to look at the data in a more general way, closer to the way people think. This kind of knowledge representation is expressed particularly in approaches based on linguistic modeling or fuzzy techniques such as fuzzy clustering, but also newer approaches related to the explanation of how artificial intelligence works on these data (so-called explainable artificial intelligence). Therefore, especially important from the point of view of the methodology of data research is an attempt to understand their potential as information granules. Such a kind of approach to data presentation and analysis may introduce considerations of a higher, more general level of abstraction, while at the same time reliably describing the network of relationships between the data and the observed information granules. In this study, we tackle this topic with particular emphasis on the problem of choosing a predictive model. In a series of numerical experiments based on both artificially generated data, ecological data on changes in bird arrival dates in the context of climate change, and COVID-19 infections data we demonstrate the effectiveness of the proposed approach built with a novel application of information potential granules.
{"title":"The Concept of Granular Representation of the Information Potential of Variables","authors":"Adam Kiersztyn, Paweł Karczmarek, Krystyna Kiersztyn, R. Lopucki, S. Grzegórski, W. Pedrycz","doi":"10.1109/FUZZ45933.2021.9494582","DOIUrl":"https://doi.org/10.1109/FUZZ45933.2021.9494582","url":null,"abstract":"With the advent of research into Granular Computing, in particular information granules, the way of thinking about data has changed gradually. Researchers and practitioners do not consider only their specific properties, but also try to look at the data in a more general way, closer to the way people think. This kind of knowledge representation is expressed particularly in approaches based on linguistic modeling or fuzzy techniques such as fuzzy clustering, but also newer approaches related to the explanation of how artificial intelligence works on these data (so-called explainable artificial intelligence). Therefore, especially important from the point of view of the methodology of data research is an attempt to understand their potential as information granules. Such a kind of approach to data presentation and analysis may introduce considerations of a higher, more general level of abstraction, while at the same time reliably describing the network of relationships between the data and the observed information granules. In this study, we tackle this topic with particular emphasis on the problem of choosing a predictive model. In a series of numerical experiments based on both artificially generated data, ecological data on changes in bird arrival dates in the context of climate change, and COVID-19 infections data we demonstrate the effectiveness of the proposed approach built with a novel application of information potential granules.","PeriodicalId":151289,"journal":{"name":"2021 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)","volume":"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":"128129823","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/FUZZ45933.2021.9494487
E. Rak, A. Szczur
Currently, we observe an enormous growth in the frequency of using the Internet, which is also causing an increase in attacks on computer nets. These phenomena significantly raise the importance of the use of Intrusion Detection Systems (IDS). Classification systems are an essential part of a cyber-attack detection task by classifying the attacks based on certain criteria. The purpose of this research is to assess the relative performance of five extensions of well-known classification methods using the distributivity law. The results of this investigation can help in the design of classification systems that use several classification methods, namely k-Nearest Neighbor, Naive Bayes, Support Vector Machine, Random Forests, and Multilayer Perceptron Network can be employed to increase the accuracy of the classification. This method requires the use of some adequate aggregation operators (e.g. average functions and triangular norms/conorms) for which the distributivity law occurs. The work contains principally the results of experiments carried out on the KDD'Cup 99 dataset using WEKA (Waikato Environment for Knowledge Analysis) tool.
目前，我们观察到使用互联网的频率有了巨大的增长，这也导致了对计算机网络的攻击增加。这些现象显著地提高了使用入侵检测系统(IDS)的重要性。分类系统是网络攻击检测任务的重要组成部分，它根据一定的标准对攻击进行分类。本研究的目的是评估使用分配律的五种知名分类方法的扩展的相对性能。本研究的结果可以帮助分类系统的设计，这些分类系统可以使用k-最近邻、朴素贝叶斯、支持向量机、随机森林和多层感知器网络等几种分类方法来提高分类的准确性。这种方法需要使用一些适当的聚合算子(例如，平均函数和三角规范/规范)，其中分布律出现。这项工作主要包含使用WEKA (Waikato Environment for Knowledge Analysis)工具在KDD'Cup 99数据集上进行的实验结果。
{"title":"Comparative assessment of aggregated classification algorithms with the use to mining a cyber-attack dataset","authors":"E. Rak, A. Szczur","doi":"10.1109/FUZZ45933.2021.9494487","DOIUrl":"https://doi.org/10.1109/FUZZ45933.2021.9494487","url":null,"abstract":"Currently, we observe an enormous growth in the frequency of using the Internet, which is also causing an increase in attacks on computer nets. These phenomena significantly raise the importance of the use of Intrusion Detection Systems (IDS). Classification systems are an essential part of a cyber-attack detection task by classifying the attacks based on certain criteria. The purpose of this research is to assess the relative performance of five extensions of well-known classification methods using the distributivity law. The results of this investigation can help in the design of classification systems that use several classification methods, namely k-Nearest Neighbor, Naive Bayes, Support Vector Machine, Random Forests, and Multilayer Perceptron Network can be employed to increase the accuracy of the classification. This method requires the use of some adequate aggregation operators (e.g. average functions and triangular norms/conorms) for which the distributivity law occurs. The work contains principally the results of experiments carried out on the KDD'Cup 99 dataset using WEKA (Waikato Environment for Knowledge Analysis) tool.","PeriodicalId":151289,"journal":{"name":"2021 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)","volume":"31 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":"124594346","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/FUZZ45933.2021.9494553
Bradley Schneider, Tanvi Banerjee
In this work, we describe a system for classifying activities in first-person video using a fuzzy inference system. Our fuzzy inference system is built on top of traditional object-and motion-based video features and provides a description of activities in terms of multiple fuzzy output variables. We demonstrate the application of the fuzzy system on a well known dataset of unscripted first person videos to classify actions into four categories. Comparing the results to other supervised learning techniques and the state-of-the-art, we find that our fuzzy system outperforms alternatives. Further, the fuzzy outputs have the potential to be much more descriptive than conventional classifiers due to their ability to handle uncertainty and produce explainable results.
{"title":"Bridging the Gap between Atomic and Complex Activities in First Person Video","authors":"Bradley Schneider, Tanvi Banerjee","doi":"10.1109/FUZZ45933.2021.9494553","DOIUrl":"https://doi.org/10.1109/FUZZ45933.2021.9494553","url":null,"abstract":"In this work, we describe a system for classifying activities in first-person video using a fuzzy inference system. Our fuzzy inference system is built on top of traditional object-and motion-based video features and provides a description of activities in terms of multiple fuzzy output variables. We demonstrate the application of the fuzzy system on a well known dataset of unscripted first person videos to classify actions into four categories. Comparing the results to other supervised learning techniques and the state-of-the-art, we find that our fuzzy system outperforms alternatives. Further, the fuzzy outputs have the potential to be much more descriptive than conventional classifiers due to their ability to handle uncertainty and produce explainable results.","PeriodicalId":151289,"journal":{"name":"2021 IEEE International Conference on Fuzzy Systems (FUZZ-IEEE)","volume":"33 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":"126331000","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：