Pub Date : 2021-04-01DOI: 10.2478/jaiscr-2022-0010
Csaba Brunner, Andrea Ko, Szabina Fodor
Abstract Security threats, among other intrusions affecting the availability, confidentiality and integrity of IT resources and services, are spreading fast and can cause serious harm to organizations. Intrusion detection has a key role in capturing intrusions. In particular, the application of machine learning methods in this area can enrich the intrusion detection efficiency. Various methods, such as pattern recognition from event logs, can be applied in intrusion detection. The main goal of our research is to present a possible intrusion detection approach using recent machine learning techniques. In this paper, we suggest and evaluate the usage of stacked ensembles consisting of neural network (SNN) and autoen-coder (AE) models augmented with a tree-structured Parzen estimator hyperparameter optimization approach for intrusion detection. The main contribution of our work is the application of advanced hyperparameter optimization and stacked ensembles together. We conducted several experiments to check the effectiveness of our approach. We used the NSL-KDD dataset, a common benchmark dataset in intrusion detection, to train our models. The comparative results demonstrate that our proposed models can compete with and, in some cases, outperform existing models.
{"title":"An Autoencoder-Enhanced Stacking Neural Network Model for Increasing the Performance of Intrusion Detection","authors":"Csaba Brunner, Andrea Ko, Szabina Fodor","doi":"10.2478/jaiscr-2022-0010","DOIUrl":"https://doi.org/10.2478/jaiscr-2022-0010","url":null,"abstract":"Abstract Security threats, among other intrusions affecting the availability, confidentiality and integrity of IT resources and services, are spreading fast and can cause serious harm to organizations. Intrusion detection has a key role in capturing intrusions. In particular, the application of machine learning methods in this area can enrich the intrusion detection efficiency. Various methods, such as pattern recognition from event logs, can be applied in intrusion detection. The main goal of our research is to present a possible intrusion detection approach using recent machine learning techniques. In this paper, we suggest and evaluate the usage of stacked ensembles consisting of neural network (SNN) and autoen-coder (AE) models augmented with a tree-structured Parzen estimator hyperparameter optimization approach for intrusion detection. The main contribution of our work is the application of advanced hyperparameter optimization and stacked ensembles together. We conducted several experiments to check the effectiveness of our approach. We used the NSL-KDD dataset, a common benchmark dataset in intrusion detection, to train our models. The comparative results demonstrate that our proposed models can compete with and, in some cases, outperform existing models.","PeriodicalId":48494,"journal":{"name":"Journal of Artificial Intelligence and Soft Computing Research","volume":"12 1","pages":"149 - 163"},"PeriodicalIF":2.8,"publicationDate":"2021-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"46009423","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-01-29DOI: 10.2478/jaiscr-2021-0008
Nassima Bougueroua, S. Mazouzi, Mohamed Belaoued, N. Seddari, A. Derhab, A. Bouras
Abstract Multi-Agent Systems (MAS) have been widely used in many areas like modeling and simulation of complex phenomena, and distributed problem solving. Likewise, MAS have been used in cyber-security, to build more efficient Intrusion Detection Systems (IDS), namely Collaborative Intrusion Detection Systems (CIDS). This work presents a taxonomy for classifying the methods used to design intrusion detection systems, and how such methods were used alongside with MAS in order to build IDS that are deployed in distributed environments, resulting in the emergence of CIDS. The proposed taxonomy, consists of three parts: 1) general architecture of CIDS, 2) the used agent technology, and 3) decision techniques, in which used technologies are presented. The proposed taxonomy reviews and classifies the most relevant works in this topic and highlights open research issues in view of recent and emerging threats. Thus, this work provides a good insight regarding past, current, and future solutions for CIDS, and helps both researchers and professionals design more effective solutions.
{"title":"A Survey on Multi-Agent Based Collaborative Intrusion Detection Systems","authors":"Nassima Bougueroua, S. Mazouzi, Mohamed Belaoued, N. Seddari, A. Derhab, A. Bouras","doi":"10.2478/jaiscr-2021-0008","DOIUrl":"https://doi.org/10.2478/jaiscr-2021-0008","url":null,"abstract":"Abstract Multi-Agent Systems (MAS) have been widely used in many areas like modeling and simulation of complex phenomena, and distributed problem solving. Likewise, MAS have been used in cyber-security, to build more efficient Intrusion Detection Systems (IDS), namely Collaborative Intrusion Detection Systems (CIDS). This work presents a taxonomy for classifying the methods used to design intrusion detection systems, and how such methods were used alongside with MAS in order to build IDS that are deployed in distributed environments, resulting in the emergence of CIDS. The proposed taxonomy, consists of three parts: 1) general architecture of CIDS, 2) the used agent technology, and 3) decision techniques, in which used technologies are presented. The proposed taxonomy reviews and classifies the most relevant works in this topic and highlights open research issues in view of recent and emerging threats. Thus, this work provides a good insight regarding past, current, and future solutions for CIDS, and helps both researchers and professionals design more effective solutions.","PeriodicalId":48494,"journal":{"name":"Journal of Artificial Intelligence and Soft Computing Research","volume":"11 1","pages":"111 - 142"},"PeriodicalIF":2.8,"publicationDate":"2021-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"43194730","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-01-29DOI: 10.2478/jaiscr-2021-0006
A. Niewiadomski, Marcin Kacprowicz
Abstract The article presents our research on applications of fuzzy logic to reduce air pollution by DeNOx filters. The research aim is to manage data on Selective Catalytic Reduction (SCR) process responsible for reducing the emission of nitrogen oxide (NO) and nitrogen dioxide (NO2). Dedicated traditional Fuzzy Logic Systems (FLS) and Type-2 Fuzzy Logic Systems (T2FLS) are proposed with the use of new methods for learning fuzzy rules and with new types of fuzzy implications (the so-called ”engineering implications”). The obtained results are consistent with the results provided by experts. The main advantage of this paper is that type-2 fuzzy logic systems with ”engineering implications” and new methods of learning fuzzy rules give results closer to expert expectations than those based on traditional fuzzy logic systems. According to the literature review, no T2FLS were applied to manage DeNOx filter prior to the research presented here.
{"title":"Type-2 Fuzzy Logic Systems in Applications: Managing Data in Selective Catalytic Reduction for Air Pollution Prevention","authors":"A. Niewiadomski, Marcin Kacprowicz","doi":"10.2478/jaiscr-2021-0006","DOIUrl":"https://doi.org/10.2478/jaiscr-2021-0006","url":null,"abstract":"Abstract The article presents our research on applications of fuzzy logic to reduce air pollution by DeNOx filters. The research aim is to manage data on Selective Catalytic Reduction (SCR) process responsible for reducing the emission of nitrogen oxide (NO) and nitrogen dioxide (NO2). Dedicated traditional Fuzzy Logic Systems (FLS) and Type-2 Fuzzy Logic Systems (T2FLS) are proposed with the use of new methods for learning fuzzy rules and with new types of fuzzy implications (the so-called ”engineering implications”). The obtained results are consistent with the results provided by experts. The main advantage of this paper is that type-2 fuzzy logic systems with ”engineering implications” and new methods of learning fuzzy rules give results closer to expert expectations than those based on traditional fuzzy logic systems. According to the literature review, no T2FLS were applied to manage DeNOx filter prior to the research presented here.","PeriodicalId":48494,"journal":{"name":"Journal of Artificial Intelligence and Soft Computing Research","volume":"11 1","pages":"85 - 97"},"PeriodicalIF":2.8,"publicationDate":"2021-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"42686584","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-01-29DOI: 10.2478/jaiscr-2021-0007
M. Kopczynski, T. Grzes
Abstract This paper presents FPGA and softcore CPU based solution for large datasets parallel core calculation using rough set methods. Architectures shown in this paper have been tested on two real datasets running presented solutions inside FPGA unit. Tested datasets had 1 000 to 10 000 000 objects. The same operations were performed in software implementation. Obtained results show the big acceleration in computation time using hardware supporting core generation in comparison to pure software implementation.
{"title":"Hardware Rough Set Processor Parallel Architecture in FPGA for Finding Core in Big Datasets","authors":"M. Kopczynski, T. Grzes","doi":"10.2478/jaiscr-2021-0007","DOIUrl":"https://doi.org/10.2478/jaiscr-2021-0007","url":null,"abstract":"Abstract This paper presents FPGA and softcore CPU based solution for large datasets parallel core calculation using rough set methods. Architectures shown in this paper have been tested on two real datasets running presented solutions inside FPGA unit. Tested datasets had 1 000 to 10 000 000 objects. The same operations were performed in software implementation. Obtained results show the big acceleration in computation time using hardware supporting core generation in comparison to pure software implementation.","PeriodicalId":48494,"journal":{"name":"Journal of Artificial Intelligence and Soft Computing Research","volume":"11 1","pages":"99 - 110"},"PeriodicalIF":2.8,"publicationDate":"2021-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"45023347","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-01-29DOI: 10.2478/jaiscr-2021-0010
Ludmila Dymova, Krzysztof Kaczmarek, Pavel V. Sevastjanov, L. Sulkowski, K. Przybyszewski
Abstract A generalization of technique for establishing order preference by similarity to the ideal solution (TOPSIS) in the intuitionistic fuzzy setting based on the redefinition of intuitionistic fuzzy sets theory (A IFS) in the framework of Dempster-Shafer theory (DST) of evidence is proposed. The use of DST mathematical tools makes it possible to avoid a set of limitations and drawbacks revealed recently in the conventional Atanassov’s operational laws defined on intuitionistic fuzzy values, which may produce unacceptable results in the solution of multiple criteria decision-making problems. This boosts considerably the quality of aggregating operators used in the intuitionistic fuzzy TOPSIS method. It is pointed out that the conventional TOPSIS method may be naturally treated as a weighted sum of some modified local criteria. Because this aggregating approach does not always reflects well intentions of decision makers, two additional aggregating methods that cannot be defined in the framework of conventional A IFS based on local criteria weights being intuitionistic fuzzy values, are introduced. Having in mind that different aggregating methods generally produce different alternative rankings to obtain the compromise ranking, the method for aggregating of aggregation modes has been applied. Some examples are used to illustrate the validity and features of the proposed approach.
{"title":"An Approach to Generalization of the Intuitionistic Fuzzy Topsis Method in the Framework of Evidence Theory","authors":"Ludmila Dymova, Krzysztof Kaczmarek, Pavel V. Sevastjanov, L. Sulkowski, K. Przybyszewski","doi":"10.2478/jaiscr-2021-0010","DOIUrl":"https://doi.org/10.2478/jaiscr-2021-0010","url":null,"abstract":"Abstract A generalization of technique for establishing order preference by similarity to the ideal solution (TOPSIS) in the intuitionistic fuzzy setting based on the redefinition of intuitionistic fuzzy sets theory (A IFS) in the framework of Dempster-Shafer theory (DST) of evidence is proposed. The use of DST mathematical tools makes it possible to avoid a set of limitations and drawbacks revealed recently in the conventional Atanassov’s operational laws defined on intuitionistic fuzzy values, which may produce unacceptable results in the solution of multiple criteria decision-making problems. This boosts considerably the quality of aggregating operators used in the intuitionistic fuzzy TOPSIS method. It is pointed out that the conventional TOPSIS method may be naturally treated as a weighted sum of some modified local criteria. Because this aggregating approach does not always reflects well intentions of decision makers, two additional aggregating methods that cannot be defined in the framework of conventional A IFS based on local criteria weights being intuitionistic fuzzy values, are introduced. Having in mind that different aggregating methods generally produce different alternative rankings to obtain the compromise ranking, the method for aggregating of aggregation modes has been applied. Some examples are used to illustrate the validity and features of the proposed approach.","PeriodicalId":48494,"journal":{"name":"Journal of Artificial Intelligence and Soft Computing Research","volume":"11 1","pages":"157 - 175"},"PeriodicalIF":2.8,"publicationDate":"2021-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"47401026","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-01-29DOI: 10.2478/jaiscr-2021-0009
Tacjana Niksa-Rynkiewicz, Natalia Szewczuk-Krypa, A. Witkowska, K. Cpałka, Marcin Zalasiński, A. Cader
Abstract Artificial Intelligence algorithms are being increasingly used in industrial applications. Their important function is to support operation of diagnostic systems. This paper presents a new approach to the monitoring of a regenerative heat exchanger in a steam power plant, which is based on a specific use of the Recurrent Neural Network (RNN). The proposed approach was tested using real data. This approach can be easily adapted to similar monitoring applications of other industrial dynamic objects.
{"title":"Monitoring Regenerative Heat Exchanger in Steam Power Plant by Making Use of the Recurrent Neural Network","authors":"Tacjana Niksa-Rynkiewicz, Natalia Szewczuk-Krypa, A. Witkowska, K. Cpałka, Marcin Zalasiński, A. Cader","doi":"10.2478/jaiscr-2021-0009","DOIUrl":"https://doi.org/10.2478/jaiscr-2021-0009","url":null,"abstract":"Abstract Artificial Intelligence algorithms are being increasingly used in industrial applications. Their important function is to support operation of diagnostic systems. This paper presents a new approach to the monitoring of a regenerative heat exchanger in a steam power plant, which is based on a specific use of the Recurrent Neural Network (RNN). The proposed approach was tested using real data. This approach can be easily adapted to similar monitoring applications of other industrial dynamic objects.","PeriodicalId":48494,"journal":{"name":"Journal of Artificial Intelligence and Soft Computing Research","volume":"11 1","pages":"143 - 155"},"PeriodicalIF":2.8,"publicationDate":"2021-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44952092","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-01-01DOI: 10.1007/978-3-030-87897-9
{"title":"Artificial Intelligence and Soft Computing: 20th International Conference, ICAISC 2021, Virtual Event, June 21–23, 2021, Proceedings, Part II","authors":"","doi":"10.1007/978-3-030-87897-9","DOIUrl":"https://doi.org/10.1007/978-3-030-87897-9","url":null,"abstract":"","PeriodicalId":48494,"journal":{"name":"Journal of Artificial Intelligence and Soft Computing Research","volume":"66 1","pages":""},"PeriodicalIF":2.8,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81837046","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2021-01-01DOI: 10.1007/978-3-030-87986-0
{"title":"Artificial Intelligence and Soft Computing: 20th International Conference, ICAISC 2021, Virtual Event, June 21–23, 2021, Proceedings, Part I","authors":"","doi":"10.1007/978-3-030-87986-0","DOIUrl":"https://doi.org/10.1007/978-3-030-87986-0","url":null,"abstract":"","PeriodicalId":48494,"journal":{"name":"Journal of Artificial Intelligence and Soft Computing Research","volume":"31 1","pages":""},"PeriodicalIF":2.8,"publicationDate":"2021-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78783332","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-12-03DOI: 10.2478/jaiscr-2021-0002
F. Alsaadi, Syed Ahtsham ul Haq Bokhary, Aqsa Shah, Usman Ali, Jinde Cao, M. Alassafi, M. U. Rehman, J. Rahman
Abstract The main purpose of a topological index is to encode a chemical structure by a number. A topological index is a graph invariant, which decribes the topology of the graph and remains constant under a graph automorphism. Topological indices play a wide role in the study of QSAR (quantitative structure-activity relationship) and QSPR (quantitative structure-property relationship). Topological indices are implemented to judge the bioactivity of chemical compounds. In this article, we compute the ABC (atom-bond connectivity); ABC4 (fourth version of ABC), GA (geometric arithmetic) and GA5 (fifth version of GA) indices of some networks sheet. These networks include: octonano window sheet; equilateral triangular tetra sheet; rectangular sheet; and rectangular tetra sheet networks.
{"title":"On Knowledge Discovery and Representations of Molecular Structures Using Topological Indices","authors":"F. Alsaadi, Syed Ahtsham ul Haq Bokhary, Aqsa Shah, Usman Ali, Jinde Cao, M. Alassafi, M. U. Rehman, J. Rahman","doi":"10.2478/jaiscr-2021-0002","DOIUrl":"https://doi.org/10.2478/jaiscr-2021-0002","url":null,"abstract":"Abstract The main purpose of a topological index is to encode a chemical structure by a number. A topological index is a graph invariant, which decribes the topology of the graph and remains constant under a graph automorphism. Topological indices play a wide role in the study of QSAR (quantitative structure-activity relationship) and QSPR (quantitative structure-property relationship). Topological indices are implemented to judge the bioactivity of chemical compounds. In this article, we compute the ABC (atom-bond connectivity); ABC4 (fourth version of ABC), GA (geometric arithmetic) and GA5 (fifth version of GA) indices of some networks sheet. These networks include: octonano window sheet; equilateral triangular tetra sheet; rectangular sheet; and rectangular tetra sheet networks.","PeriodicalId":48494,"journal":{"name":"Journal of Artificial Intelligence and Soft Computing Research","volume":"11 1","pages":"21 - 32"},"PeriodicalIF":2.8,"publicationDate":"2020-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"44401120","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2020-12-03DOI: 10.2478/jaiscr-2021-0005
M. Pawlak, G. Panesar, M. Korytkowski
Abstract In this paper we propose a novel method for invariant image reconstruction with the properly selected degree of symmetry. We make use of Zernike radial moments to represent an image due to their invariance properties to isometry transformations and the ability to uniquely represent the salient features of the image. The regularized ridge regression estimation strategy under symmetry constraints for estimating Zernike moments is proposed. This extended regularization problem allows us to enforces the bilateral symmetry in the reconstructed object. This is achieved by the proper choice of two regularization parameters controlling the level of reconstruction accuracy and the acceptable degree of symmetry. As a byproduct of our studies we propose an algorithm for estimating an angle of the symmetry axis which in turn is used to determine the possible asymmetry present in the image. The proposed image recovery under the symmetry constraints model is tested in a number of experiments involving image reconstruction and symmetry estimation.
{"title":"A Novel Method for Invariant Image Reconstruction","authors":"M. Pawlak, G. Panesar, M. Korytkowski","doi":"10.2478/jaiscr-2021-0005","DOIUrl":"https://doi.org/10.2478/jaiscr-2021-0005","url":null,"abstract":"Abstract In this paper we propose a novel method for invariant image reconstruction with the properly selected degree of symmetry. We make use of Zernike radial moments to represent an image due to their invariance properties to isometry transformations and the ability to uniquely represent the salient features of the image. The regularized ridge regression estimation strategy under symmetry constraints for estimating Zernike moments is proposed. This extended regularization problem allows us to enforces the bilateral symmetry in the reconstructed object. This is achieved by the proper choice of two regularization parameters controlling the level of reconstruction accuracy and the acceptable degree of symmetry. As a byproduct of our studies we propose an algorithm for estimating an angle of the symmetry axis which in turn is used to determine the possible asymmetry present in the image. The proposed image recovery under the symmetry constraints model is tested in a number of experiments involving image reconstruction and symmetry estimation.","PeriodicalId":48494,"journal":{"name":"Journal of Artificial Intelligence and Soft Computing Research","volume":"11 1","pages":"69 - 80"},"PeriodicalIF":2.8,"publicationDate":"2020-12-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"41926081","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"计算机科学","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：