Pub Date : 2023-12-01DOI: 10.2478/jaiscr-2024-0002
Luping Wang, Hui Wei
Abstract Scene understanding is a core problem for field robots. However, many unsolved problems, like understanding bending paths, severely hinder the implementation due to varying illumination, irregular features and unstructured boundaries in field environments. Traditional three-dimensional(3D) environmental perception from 3D point clouds or fused sensors are costly and account poorly for field unstructured semantic information. In this paper, we propose a new methodology to understand field bending paths and build their 3D reconstruction from a monocular camera without prior training. Bending angle projections are assigned to clusters. Through compositions of their sub-clusters, bending surfaces are estimated by geometric inferences. Bending path scenes are approximated bending structures in the 3D reconstruction. Understanding sloping gradient is helpful for a navigating mobile robot to automatically adjust their speed. Based on geometric constraints from a monocular camera, the approach requires no prior training, and is robust to varying color and illumination. The percentage of incorrectly classified pixels were compared to the ground truth. Experimental results demonstrated that the method can successfully understand bending path scenes, meeting the requirements of robot navigation in an unstructured environment.
{"title":"Bending Path Understanding Based on Angle Projections in Field Environments","authors":"Luping Wang, Hui Wei","doi":"10.2478/jaiscr-2024-0002","DOIUrl":"https://doi.org/10.2478/jaiscr-2024-0002","url":null,"abstract":"Abstract Scene understanding is a core problem for field robots. However, many unsolved problems, like understanding bending paths, severely hinder the implementation due to varying illumination, irregular features and unstructured boundaries in field environments. Traditional three-dimensional(3D) environmental perception from 3D point clouds or fused sensors are costly and account poorly for field unstructured semantic information. In this paper, we propose a new methodology to understand field bending paths and build their 3D reconstruction from a monocular camera without prior training. Bending angle projections are assigned to clusters. Through compositions of their sub-clusters, bending surfaces are estimated by geometric inferences. Bending path scenes are approximated bending structures in the 3D reconstruction. Understanding sloping gradient is helpful for a navigating mobile robot to automatically adjust their speed. Based on geometric constraints from a monocular camera, the approach requires no prior training, and is robust to varying color and illumination. The percentage of incorrectly classified pixels were compared to the ground truth. Experimental results demonstrated that the method can successfully understand bending path scenes, meeting the requirements of robot navigation in an unstructured environment.","PeriodicalId":48494,"journal":{"name":"Journal of Artificial Intelligence and Soft Computing Research","volume":"3 1","pages":"25 - 43"},"PeriodicalIF":2.8,"publicationDate":"2023-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139188080","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 : 2023-12-01DOI: 10.2478/jaiscr-2024-0001
Lukasz Smietanka, Tomasz Maka
Abstract The paper describes the relations of speech signal representation in the layers of the convolutional neural network. Using activation maps determined by the Grad-CAM algorithm, energy distribution in the time–frequency space and their relationship with prosodic properties of the considered emotional utterances have been analysed. After preliminary experiments with the expressive speech classification task, we have selected the CQT-96 time–frequency representation. Also, we have used a custom CNN architecture with three convolutional layers in the main experimental phase of the study. Based on the performed analysis, we show the relationship between activation levels and changes in the voiced parts of the fundamental frequency trajectories. As a result, the relationships between the individual activation maps, energy distribution, and fundamental frequency trajectories for six emotional states were described. The results show that the convolutional neural network in the learning process uses similar fragments from time–frequency representation, which are also related to the prosodic properties of emotional speech utterances. We also analysed the relations of the obtained activation maps with time-domain envelopes. It allowed observing the importance of the speech signals energy in classifying individual emotional states. Finally, we compared the energy distribution of the CQT representation in relation to the regions’ energy overlapping with masks of individual emotional states. In the result, we obtained information on the variability of energy distributions in the selected signal representation speech for particular emotions.
{"title":"Interpreting Convolutional Layers in DNN Model Based on Time–Frequency Representation of Emotional Speech","authors":"Lukasz Smietanka, Tomasz Maka","doi":"10.2478/jaiscr-2024-0001","DOIUrl":"https://doi.org/10.2478/jaiscr-2024-0001","url":null,"abstract":"Abstract The paper describes the relations of speech signal representation in the layers of the convolutional neural network. Using activation maps determined by the Grad-CAM algorithm, energy distribution in the time–frequency space and their relationship with prosodic properties of the considered emotional utterances have been analysed. After preliminary experiments with the expressive speech classification task, we have selected the CQT-96 time–frequency representation. Also, we have used a custom CNN architecture with three convolutional layers in the main experimental phase of the study. Based on the performed analysis, we show the relationship between activation levels and changes in the voiced parts of the fundamental frequency trajectories. As a result, the relationships between the individual activation maps, energy distribution, and fundamental frequency trajectories for six emotional states were described. The results show that the convolutional neural network in the learning process uses similar fragments from time–frequency representation, which are also related to the prosodic properties of emotional speech utterances. We also analysed the relations of the obtained activation maps with time-domain envelopes. It allowed observing the importance of the speech signals energy in classifying individual emotional states. Finally, we compared the energy distribution of the CQT representation in relation to the regions’ energy overlapping with masks of individual emotional states. In the result, we obtained information on the variability of energy distributions in the selected signal representation speech for particular emotions.","PeriodicalId":48494,"journal":{"name":"Journal of Artificial Intelligence and Soft Computing Research","volume":"9 6","pages":"5 - 23"},"PeriodicalIF":2.8,"publicationDate":"2023-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139189498","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}
Abstract Atrial fibrillation is a common cardiac arrhythmia, and its incidence increases with age. Currently, numerous deep learning methods have been proposed for AF detection. However, these methods either have complex structures or poor robustness. Given the evidence from recent studies, it is not surprising to observe the limitations in the learning performance of these approaches. This can be attributed to their strictly homogenous conguration, which solely relies on the linear neuron model. The limitations mentioned above have been addressed by operational neural networks (ONNs). These networks employ a heterogeneous network configuration, incorporating neurons equipped with diverse nonlinear operators. Therefore, in this study, to enhance the detection performance while maintaining computational efficiency, a novel model named multi-scale Self-ONNs (MSSelf-ONNs) was proposed to identify AF. The proposed model possesses a significant advantage and superiority over conventional ONNs due to their self-organization capability. Unlike conventional ONNs, MSSelf -ONNs eliminate the need for prior operator search within the operator set library to find the optimal set of operators. This unique characteristic sets MSSelf -ONNs apart and enhances their overall performance. To validate and evaluate the system, we have implemented the experiments on the well-known MIT-BIH atrial fibrillation database. The proposed model yields total accuracies and kappa coefficients of 98% and 0.95, respectively. The experiment results demonstrate that the proposed model outperform the state-of-the-art deep CNN in terms of both performance and computational complexity.
{"title":"Self-Organized Operational Neural Networks for The Detection of Atrial Fibrillation","authors":"Junming Zhang, Hao Dong, Jinfeng Gao, Ruxian Yao, Gangqiang Li, Haitao Wu","doi":"10.2478/jaiscr-2024-0004","DOIUrl":"https://doi.org/10.2478/jaiscr-2024-0004","url":null,"abstract":"Abstract Atrial fibrillation is a common cardiac arrhythmia, and its incidence increases with age. Currently, numerous deep learning methods have been proposed for AF detection. However, these methods either have complex structures or poor robustness. Given the evidence from recent studies, it is not surprising to observe the limitations in the learning performance of these approaches. This can be attributed to their strictly homogenous conguration, which solely relies on the linear neuron model. The limitations mentioned above have been addressed by operational neural networks (ONNs). These networks employ a heterogeneous network configuration, incorporating neurons equipped with diverse nonlinear operators. Therefore, in this study, to enhance the detection performance while maintaining computational efficiency, a novel model named multi-scale Self-ONNs (MSSelf-ONNs) was proposed to identify AF. The proposed model possesses a significant advantage and superiority over conventional ONNs due to their self-organization capability. Unlike conventional ONNs, MSSelf -ONNs eliminate the need for prior operator search within the operator set library to find the optimal set of operators. This unique characteristic sets MSSelf -ONNs apart and enhances their overall performance. To validate and evaluate the system, we have implemented the experiments on the well-known MIT-BIH atrial fibrillation database. The proposed model yields total accuracies and kappa coefficients of 98% and 0.95, respectively. The experiment results demonstrate that the proposed model outperform the state-of-the-art deep CNN in terms of both performance and computational complexity.","PeriodicalId":48494,"journal":{"name":"Journal of Artificial Intelligence and Soft Computing Research","volume":"19 5","pages":"63 - 75"},"PeriodicalIF":2.8,"publicationDate":"2023-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139189340","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 : 2023-12-01DOI: 10.2478/jaiscr-2024-0003
Maciej Aleksandrowicz, Joanna Jaworek-Korjakowska
Abstract In this work, a study focusing on proposing generalization metrics for Deep Reinforcement Learning (DRL) algorithms was performed. The experiments were conducted in DeepMind Control (DMC) benchmark suite with parameterized environments. The performance of three DRL algorithms in selected ten tasks from the DMC suite has been analysed with existing generalization gap formalism and the proposed ratio and decibel metrics. The results were presented with the proposed methods: average transfer metric and plot for environment normal distribution. These efforts allowed to highlight major changes in the model’s performance and add more insights about making decisions regarding models’ requirements.
{"title":"Metrics for Assessing Generalization of Deep Reinforcement Learning in Parameterized Environments","authors":"Maciej Aleksandrowicz, Joanna Jaworek-Korjakowska","doi":"10.2478/jaiscr-2024-0003","DOIUrl":"https://doi.org/10.2478/jaiscr-2024-0003","url":null,"abstract":"Abstract In this work, a study focusing on proposing generalization metrics for Deep Reinforcement Learning (DRL) algorithms was performed. The experiments were conducted in DeepMind Control (DMC) benchmark suite with parameterized environments. The performance of three DRL algorithms in selected ten tasks from the DMC suite has been analysed with existing generalization gap formalism and the proposed ratio and decibel metrics. The results were presented with the proposed methods: average transfer metric and plot for environment normal distribution. These efforts allowed to highlight major changes in the model’s performance and add more insights about making decisions regarding models’ requirements.","PeriodicalId":48494,"journal":{"name":"Journal of Artificial Intelligence and Soft Computing Research","volume":"76 ","pages":"45 - 61"},"PeriodicalIF":2.8,"publicationDate":"2023-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139195661","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 : 2023-12-01DOI: 10.2478/jaiscr-2024-0005
Hui Liu, Chunjie Wang, Xin Jiang, M. Khishe
Abstract Accurate and efficient COVID-19 diagnosis is crucial in clinical settings. However, the limited availability of labeled data poses a challenge for traditional machine learning algorithms. To address this issue, we propose Turning Point (TP), a few-shot learning (FSL) approach that leverages high-level turning point mappings to build sophisticated representations across previously labeled data. Unlike existing FSL models, TP learns using quasi-configured topological spaces and efficiently combines the outputs of diverse TP learners. We evaluated TPFSL using three COVID-19 datasets and compared it with seven different benchmarks. Results show that TPFSL outperformed the top-performing benchmark models in both one-shot and five-shot tasks, with an average improvement of 4.50% and 4.43%, respectively. Additionally, TPFSL significantly outperformed the ProtoNet benchmark by 12.966% and 11.033% in one-shot and five-shot classification problems across all datasets. Ablation experiments were also conducted to analyze the impact of variables such as TP density, network topology, distance measure, and TP placement. Overall, TPFSL has the potential to improve the accuracy and speed of diagnoses for COVID-19 in clinical settings and can be a valuable tool for medical professionals.
{"title":"A Few-Shot Learning Approach for Covid-19 Diagnosis Using Quasi-Configured Topological Spaces","authors":"Hui Liu, Chunjie Wang, Xin Jiang, M. Khishe","doi":"10.2478/jaiscr-2024-0005","DOIUrl":"https://doi.org/10.2478/jaiscr-2024-0005","url":null,"abstract":"Abstract Accurate and efficient COVID-19 diagnosis is crucial in clinical settings. However, the limited availability of labeled data poses a challenge for traditional machine learning algorithms. To address this issue, we propose Turning Point (TP), a few-shot learning (FSL) approach that leverages high-level turning point mappings to build sophisticated representations across previously labeled data. Unlike existing FSL models, TP learns using quasi-configured topological spaces and efficiently combines the outputs of diverse TP learners. We evaluated TPFSL using three COVID-19 datasets and compared it with seven different benchmarks. Results show that TPFSL outperformed the top-performing benchmark models in both one-shot and five-shot tasks, with an average improvement of 4.50% and 4.43%, respectively. Additionally, TPFSL significantly outperformed the ProtoNet benchmark by 12.966% and 11.033% in one-shot and five-shot classification problems across all datasets. Ablation experiments were also conducted to analyze the impact of variables such as TP density, network topology, distance measure, and TP placement. Overall, TPFSL has the potential to improve the accuracy and speed of diagnoses for COVID-19 in clinical settings and can be a valuable tool for medical professionals.","PeriodicalId":48494,"journal":{"name":"Journal of Artificial Intelligence and Soft Computing Research","volume":"19 5-6","pages":"77 - 95"},"PeriodicalIF":2.8,"publicationDate":"2023-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139195203","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}
The Internet of Senses (IoS) is an emerging field that aims to enhance human-machine interaction by enabling individuals to experience the digital world with their senses. This article, which explores a highly novel research topic, is at the forefront of Ericsson engineers' investigations, providing pioneering insights into the subject matter.IoS employs technologies such as virtual and augmented reality, haptic feedback, and olfactory and gustatory systems to provide multi-sensory experiences. This article provides an overview of the latest trends and innovations in IoS, highlighting its potential for human well-being and progress as well as the challenges that need to be addressed to ensure its safe and ethical implementation. The article also emphasizes the role of 6G in enabling IoS and the potential benefits of incorporating the chemical senses into digital technology. Overall, the IoS has the potential to revolutionize human-machine interaction and create immersive digital experiences.
{"title":"Internet of Senses - Potential Applications and Implications","authors":"Kaan CÖMERT, Mustafa AKKAŞ","doi":"10.55195/jscai.1316512","DOIUrl":"https://doi.org/10.55195/jscai.1316512","url":null,"abstract":"The Internet of Senses (IoS) is an emerging field that aims to enhance human-machine interaction by enabling individuals to experience the digital world with their senses. This article, which explores a highly novel research topic, is at the forefront of Ericsson engineers' investigations, providing pioneering insights into the subject matter.IoS employs technologies such as virtual and augmented reality, haptic feedback, and olfactory and gustatory systems to provide multi-sensory experiences. This article provides an overview of the latest trends and innovations in IoS, highlighting its potential for human well-being and progress as well as the challenges that need to be addressed to ensure its safe and ethical implementation. The article also emphasizes the role of 6G in enabling IoS and the potential benefits of incorporating the chemical senses into digital technology. Overall, the IoS has the potential to revolutionize human-machine interaction and create immersive digital experiences.","PeriodicalId":48494,"journal":{"name":"Journal of Artificial Intelligence and Soft Computing Research","volume":"86 4","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135774092","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}
Two major earthquakes in Kahramanmaraş on February 6, 2023, 9 hours apart, affected many countries, especially Turkey and Syria. It caused the death and injury of thousands of people. Earthquake survivors shared their help on social media after the earthquake. While people under the rubble shared some posts, some were for living materials. There were also posts unrelated to the earthquake. It is essential to analyze social media shares to plan the process management effectively, save time, and reach the victims as soon as possible. For this reason, about 500 tweets about the 2023 Turkey-Syria earthquake were analyzed in this study. The tweets were classified according to their content as user tweets under debris and user tweets requesting life material. Popular machine learning methods such as DT, kNN, LR, MNB, RF, SVM, and XGBoost were compared in detail. Experimental results showed that RF has over 99% classification accuracy.
{"title":"Machine Learning Based a Comparative Analysis for Detecting Tweets of Earthquake Victims Asking for Help in The 2023 Turkey-Syria Earthquake","authors":"Anıl UTKU, Ümit CAN","doi":"10.55195/jscai.1365639","DOIUrl":"https://doi.org/10.55195/jscai.1365639","url":null,"abstract":"Two major earthquakes in Kahramanmaraş on February 6, 2023, 9 hours apart, affected many countries, especially Turkey and Syria. It caused the death and injury of thousands of people. Earthquake survivors shared their help on social media after the earthquake. While people under the rubble shared some posts, some were for living materials. There were also posts unrelated to the earthquake. It is essential to analyze social media shares to plan the process management effectively, save time, and reach the victims as soon as possible. For this reason, about 500 tweets about the 2023 Turkey-Syria earthquake were analyzed in this study. The tweets were classified according to their content as user tweets under debris and user tweets requesting life material. Popular machine learning methods such as DT, kNN, LR, MNB, RF, SVM, and XGBoost were compared in detail. Experimental results showed that RF has over 99% classification accuracy.","PeriodicalId":48494,"journal":{"name":"Journal of Artificial Intelligence and Soft Computing Research","volume":"14 2","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-11-04","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135774240","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 : 2023-10-01DOI: 10.2478/jaiscr-2023-0018
Ivan Laktionov, Grygorii Diachenko, Danuta Rutkowska, Marek Kisiel-Dorohinicki
Abstract The proliferation of computer-oriented and information digitalisation technologies has become a hallmark across various sectors in today’s rapidly evolving environment. Among these, agriculture emerges as a pivotal sector in need of seamless incorporation of high-performance information technologies to address the pressing needs of national economies worldwide. The aim of the present article is to substantiate scientific and applied approaches to improving the efficiency of computer-oriented agrotechnical monitoring systems by developing an intelligent software component for predicting the probability of occurrence of corn diseases during the full cycle of its cultivation. The object of research is non-stationary processes of intelligent transformation and predictive analytics of soil and climatic data, which are factors of the occurrence and development of diseases in corn. The subject of the research is methods and explainable AI models of intelligent predictive analysis of measurement data on the soil and climatic condition of agricultural enterprises specialised in growing corn. The main scientific and practical effect of the research results is the development of IoT technologies for agrotechnical monitoring through the development of a computer-oriented model based on the ANFIS technique and the synthesis of structural and algorithmic provision for identifying and predicting the probability of occurrence of corn diseases during the full cycle of its cultivation.
{"title":"An Explainable AI Approach to Agrotechnical Monitoring and Crop Diseases Prediction in Dnipro Region of Ukraine","authors":"Ivan Laktionov, Grygorii Diachenko, Danuta Rutkowska, Marek Kisiel-Dorohinicki","doi":"10.2478/jaiscr-2023-0018","DOIUrl":"https://doi.org/10.2478/jaiscr-2023-0018","url":null,"abstract":"Abstract The proliferation of computer-oriented and information digitalisation technologies has become a hallmark across various sectors in today’s rapidly evolving environment. Among these, agriculture emerges as a pivotal sector in need of seamless incorporation of high-performance information technologies to address the pressing needs of national economies worldwide. The aim of the present article is to substantiate scientific and applied approaches to improving the efficiency of computer-oriented agrotechnical monitoring systems by developing an intelligent software component for predicting the probability of occurrence of corn diseases during the full cycle of its cultivation. The object of research is non-stationary processes of intelligent transformation and predictive analytics of soil and climatic data, which are factors of the occurrence and development of diseases in corn. The subject of the research is methods and explainable AI models of intelligent predictive analysis of measurement data on the soil and climatic condition of agricultural enterprises specialised in growing corn. The main scientific and practical effect of the research results is the development of IoT technologies for agrotechnical monitoring through the development of a computer-oriented model based on the ANFIS technique and the synthesis of structural and algorithmic provision for identifying and predicting the probability of occurrence of corn diseases during the full cycle of its cultivation.","PeriodicalId":48494,"journal":{"name":"Journal of Artificial Intelligence and Soft Computing Research","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136153698","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 : 2023-10-01DOI: 10.2478/jaiscr-2023-0017
Meng Huang, Tao Li, Beibei Li, Nian Zhang, Hanyuan Huang
Abstract Integrating industrial cyber-physical systems (ICPSs) with modern information technologies (5G, artificial intelligence, and big data analytics) has led to the development of industrial intelligence. Still, it has increased the vulnerability of such systems regarding cybersecurity. Traditional network intrusion detection methods for ICPSs are limited in identifying minority attack categories and suffer from high time complexity. To address these issues, this paper proposes a network intrusion detection scheme, which includes an information-theoretic hybrid feature selection method to reduce data dimensionality and the ALLKNN-LightGBM intrusion detection framework. Experimental results on three industrial datasets demonstrate that the proposed method outperforms four mainstream machine learning methods and other advanced intrusion detection techniques regarding accuracy, F-score, and run time complexity.
{"title":"Fast Attack Detection Method for Imbalanced Data in Industrial Cyber-Physical Systems","authors":"Meng Huang, Tao Li, Beibei Li, Nian Zhang, Hanyuan Huang","doi":"10.2478/jaiscr-2023-0017","DOIUrl":"https://doi.org/10.2478/jaiscr-2023-0017","url":null,"abstract":"Abstract Integrating industrial cyber-physical systems (ICPSs) with modern information technologies (5G, artificial intelligence, and big data analytics) has led to the development of industrial intelligence. Still, it has increased the vulnerability of such systems regarding cybersecurity. Traditional network intrusion detection methods for ICPSs are limited in identifying minority attack categories and suffer from high time complexity. To address these issues, this paper proposes a network intrusion detection scheme, which includes an information-theoretic hybrid feature selection method to reduce data dimensionality and the ALLKNN-LightGBM intrusion detection framework. Experimental results on three industrial datasets demonstrate that the proposed method outperforms four mainstream machine learning methods and other advanced intrusion detection techniques regarding accuracy, F-score, and run time complexity.","PeriodicalId":48494,"journal":{"name":"Journal of Artificial Intelligence and Soft Computing Research","volume":"3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136153718","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 : 2023-10-01DOI: 10.2478/jaiscr-2023-0016
Youn Kyu Lee, Seong Hee Park, Min Young Lim, Soo-Hyun Lee, Jongwook Jeong
Abstract With the widespread of systems incorporating multiple deep learning models, ensuring interoperability between target models has become essential. However, due to the unreliable performance of existing model conversion solutions, it is still challenging to ensure interoperability between the models developed on different deep learning frameworks. In this paper, we propose a systematic method for verifying interoperability between pre- and post-conversion deep learning models based on the validation and verification approach. Our proposed method ensures interoperability by conducting a series of systematic verifications from multiple perspectives. The case study confirmed that our method successfully discovered the interoperability issues that have been reported in deep learning model conversions.
{"title":"Towards Ensuring Software Interoperability Between Deep Learning Frameworks","authors":"Youn Kyu Lee, Seong Hee Park, Min Young Lim, Soo-Hyun Lee, Jongwook Jeong","doi":"10.2478/jaiscr-2023-0016","DOIUrl":"https://doi.org/10.2478/jaiscr-2023-0016","url":null,"abstract":"Abstract With the widespread of systems incorporating multiple deep learning models, ensuring interoperability between target models has become essential. However, due to the unreliable performance of existing model conversion solutions, it is still challenging to ensure interoperability between the models developed on different deep learning frameworks. In this paper, we propose a systematic method for verifying interoperability between pre- and post-conversion deep learning models based on the validation and verification approach. Our proposed method ensures interoperability by conducting a series of systematic verifications from multiple perspectives. The case study confirmed that our method successfully discovered the interoperability issues that have been reported in deep learning model conversions.","PeriodicalId":48494,"journal":{"name":"Journal of Artificial Intelligence and Soft Computing Research","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136153078","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：