Francesco Di Rienzo, Alessandro Madonna, Nicola Carbonaro, Alessandro Tognetti, Antonio Virdis, Carlo Vallati
Indoor short-range localization is crucial in many Industry 4.0 applications. Production monitoring for assembly lines, for instance, requires fine-grained positioning for parts or goods in order to keep track of the production process and the stations traversed by each product. Due to the unavailability of the Global Positioning System (GPS) for indoor positioning, a different approach is required. In this paper, we propose a specific design for short-range indoor positioning based on the analysis of the Received Signal Strength Indicator (RSSI) of Bluetooth beacons. To this aim, different machine learning techniques are considered and assessed: regressors, Convolution Neural Network (CNN) and Recurrent Neural Network (RNN). A realistic testbed is created to collect data for the training of the models and to assess the performance of each technique. Our analysis highlights the best models and the most convenient and suitable configuration for indoor localization. Finally, the localization accuracy is calculated in the considered use case, i.e., production monitoring. Our results show that the best performance is obtained using the K-Nearest Neighbors technique, which results in a good performance for general localization and in a high level of accuracy, 99%, for industrial production monitoring.
室内短距离定位在许多工业4.0应用中至关重要。例如，装配线的生产监控需要对零件或货物进行精细定位，以便跟踪生产过程和每个产品经过的工位。由于全球定位系统(GPS)无法用于室内定位，因此需要采用不同的方法。本文在分析蓝牙信标接收信号强度指标(Received Signal Strength Indicator, RSSI)的基础上，提出了一种针对室内短距离定位的具体设计方案。为此，考虑和评估了不同的机器学习技术:回归量、卷积神经网络(CNN)和循环神经网络(RNN)。创建了一个真实的测试平台来收集模型训练的数据，并评估每种技术的性能。我们的分析强调了室内定位的最佳模型和最方便、最合适的配置。最后，在考虑的用例(即生产监控)中计算定位精度。我们的研究结果表明，使用k近邻技术获得了最佳性能，这使得一般定位具有良好的性能，并且在工业生产监控中具有高达99%的高精度。
{"title":"Short-Range Localization via Bluetooth Using Machine Learning Techniques for Industrial Production Monitoring","authors":"Francesco Di Rienzo, Alessandro Madonna, Nicola Carbonaro, Alessandro Tognetti, Antonio Virdis, Carlo Vallati","doi":"10.3390/jsan12050075","DOIUrl":"https://doi.org/10.3390/jsan12050075","url":null,"abstract":"Indoor short-range localization is crucial in many Industry 4.0 applications. Production monitoring for assembly lines, for instance, requires fine-grained positioning for parts or goods in order to keep track of the production process and the stations traversed by each product. Due to the unavailability of the Global Positioning System (GPS) for indoor positioning, a different approach is required. In this paper, we propose a specific design for short-range indoor positioning based on the analysis of the Received Signal Strength Indicator (RSSI) of Bluetooth beacons. To this aim, different machine learning techniques are considered and assessed: regressors, Convolution Neural Network (CNN) and Recurrent Neural Network (RNN). A realistic testbed is created to collect data for the training of the models and to assess the performance of each technique. Our analysis highlights the best models and the most convenient and suitable configuration for indoor localization. Finally, the localization accuracy is calculated in the considered use case, i.e., production monitoring. Our results show that the best performance is obtained using the K-Nearest Neighbors technique, which results in a good performance for general localization and in a high level of accuracy, 99%, for industrial production monitoring.","PeriodicalId":37584,"journal":{"name":"Journal of Sensor and Actuator Networks","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136184704","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}
Walaa M. Elsayed, Engy El-Shafeiy, Mohamed Elhoseny, Mohammed K. Hassan
To avoid overloading a network, it is critical to continuously monitor the natural environment and disseminate data streams in synchronization. Based on self-maintaining technology, this study presents a technique called self-configuration management (SCM). The purpose is to ensure consistency in the performance, functionality, and physical attributes of a wireless sensor network (WSN) over its lifetime. During device communication, the SCM approach delivers an operational software package for the radio board of system problematic nodes. We offered two techniques to help cluster heads manage autonomous configuration. First, we created a separate capability to determine which defective devices require the operating system (OS) replica. The software package was then delivered from the head node to the network’s malfunctioning device via communication roles. Second, we built an autonomous capability to automatically install software packages and arrange the time. The simulations revealed that the suggested technique was quick in transfers and used less energy. It also provided better coverage of system fault peaks than competitors. We used the proposed SCM approach to distribute homogenous sensor networks, and it increased system fault tolerance to 93.2%.
{"title":"Self-Configuration Management towards Fix-Distributed Byzantine Sensors for Clustering Schemes in Wireless Sensor Networks","authors":"Walaa M. Elsayed, Engy El-Shafeiy, Mohamed Elhoseny, Mohammed K. Hassan","doi":"10.3390/jsan12050074","DOIUrl":"https://doi.org/10.3390/jsan12050074","url":null,"abstract":"To avoid overloading a network, it is critical to continuously monitor the natural environment and disseminate data streams in synchronization. Based on self-maintaining technology, this study presents a technique called self-configuration management (SCM). The purpose is to ensure consistency in the performance, functionality, and physical attributes of a wireless sensor network (WSN) over its lifetime. During device communication, the SCM approach delivers an operational software package for the radio board of system problematic nodes. We offered two techniques to help cluster heads manage autonomous configuration. First, we created a separate capability to determine which defective devices require the operating system (OS) replica. The software package was then delivered from the head node to the network’s malfunctioning device via communication roles. Second, we built an autonomous capability to automatically install software packages and arrange the time. The simulations revealed that the suggested technique was quick in transfers and used less energy. It also provided better coverage of system fault peaks than competitors. We used the proposed SCM approach to distribute homogenous sensor networks, and it increased system fault tolerance to 93.2%.","PeriodicalId":37584,"journal":{"name":"Journal of Sensor and Actuator Networks","volume":"55 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135918537","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}
Ahmad Al-Daraiseh, Yousef Sanjalawe, Salam Al-E’mari, Salam Fraihat, Mohammad Bany Taha, Muhammed Al-Muhammed
In recent years, there has been an increasing interest in employing chaotic-based random number generators for cryptographic purposes. However, many of these generators produce sequences that lack the necessary strength for cryptographic systems, such as Tent-Map. However, these generators still suffer from common issues when generating random numbers, including issues related to speed, randomness, lack of statistical properties, and lack of uniformity. Therefore, this paper introduces an efficient pseudo-random number generator, called State-Based Tent-Map (SBTM), based on a modified Tent-Map, which addresses this and other limitations by providing highly robust sequences suitable for cryptographic applications. The proposed generator is specifically designed to generate sequences with exceptional statistical properties and a high degree of security. It utilizes a modified 1D chaotic Tent-Map with enhanced attributes to produce the chaotic sequences. Rigorous randomness testing using the Dieharder test suite confirmed the promising results of the generated keystream bits. The comprehensive evaluation demonstrated that approximately 97.4% of the tests passed successfully, providing further evidence of the SBTM’s capability to produce sequences with sufficient randomness and statistical properties.
{"title":"Cryptographic Grade Chaotic Random Number Generator Based on Tent-Map","authors":"Ahmad Al-Daraiseh, Yousef Sanjalawe, Salam Al-E’mari, Salam Fraihat, Mohammad Bany Taha, Muhammed Al-Muhammed","doi":"10.3390/jsan12050073","DOIUrl":"https://doi.org/10.3390/jsan12050073","url":null,"abstract":"In recent years, there has been an increasing interest in employing chaotic-based random number generators for cryptographic purposes. However, many of these generators produce sequences that lack the necessary strength for cryptographic systems, such as Tent-Map. However, these generators still suffer from common issues when generating random numbers, including issues related to speed, randomness, lack of statistical properties, and lack of uniformity. Therefore, this paper introduces an efficient pseudo-random number generator, called State-Based Tent-Map (SBTM), based on a modified Tent-Map, which addresses this and other limitations by providing highly robust sequences suitable for cryptographic applications. The proposed generator is specifically designed to generate sequences with exceptional statistical properties and a high degree of security. It utilizes a modified 1D chaotic Tent-Map with enhanced attributes to produce the chaotic sequences. Rigorous randomness testing using the Dieharder test suite confirmed the promising results of the generated keystream bits. The comprehensive evaluation demonstrated that approximately 97.4% of the tests passed successfully, providing further evidence of the SBTM’s capability to produce sequences with sufficient randomness and statistical properties.","PeriodicalId":37584,"journal":{"name":"Journal of Sensor and Actuator Networks","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136295273","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}
The application of wireless sensor networks (WSNs) in smart agriculture requires accurate path loss prediction to determine the coverage area and system capacity. However, fast fading from environment changes, such as leaf movement, unsymmetrical tree structures and near-ground effects, makes the path loss prediction inaccurate. Artificial intelligence (AI) technologies can be used to facilitate this task for training the real environments. In this study, we performed path loss measurements in a Ruby mango plantation at a frequency of 433 MHz. Then, an adaptive neuro-fuzzy inference system (ANFIS) was applied to path loss prediction. The ANFIS required two inputs for the path loss prediction: the distance and antenna height corresponding to the tree level (i.e., trunk and bottom, middle, and top canopies). We evaluated the performance of the ANFIS by comparing it with empirical path loss models widely used in the literature. The ANFIS demonstrated a superior prediction accuracy with high sensitivity compared to the empirical models, although the performance was affected by the tree level.
{"title":"Applying an Adaptive Neuro-Fuzzy Inference System to Path Loss Prediction in a Ruby Mango Plantation","authors":"Supachai Phaiboon, Pisit Phokharatkul","doi":"10.3390/jsan12050071","DOIUrl":"https://doi.org/10.3390/jsan12050071","url":null,"abstract":"The application of wireless sensor networks (WSNs) in smart agriculture requires accurate path loss prediction to determine the coverage area and system capacity. However, fast fading from environment changes, such as leaf movement, unsymmetrical tree structures and near-ground effects, makes the path loss prediction inaccurate. Artificial intelligence (AI) technologies can be used to facilitate this task for training the real environments. In this study, we performed path loss measurements in a Ruby mango plantation at a frequency of 433 MHz. Then, an adaptive neuro-fuzzy inference system (ANFIS) was applied to path loss prediction. The ANFIS required two inputs for the path loss prediction: the distance and antenna height corresponding to the tree level (i.e., trunk and bottom, middle, and top canopies). We evaluated the performance of the ANFIS by comparing it with empirical path loss models widely used in the literature. The ANFIS demonstrated a superior prediction accuracy with high sensitivity compared to the empirical models, although the performance was affected by the tree level.","PeriodicalId":37584,"journal":{"name":"Journal of Sensor and Actuator Networks","volume":"68 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135300760","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}
The majority of the Earth’s surface is covered by water, with oceans holding approximately 97% of this water and serving as the lifeblood of our planet. These oceans are essential for various purposes, including transportation, sustenance, and communication. However, establishing effective communication networks between the numerous sub-islands present in many parts of the world poses significant challenges. Underwater optical wireless communication, or UWOC, can indeed be an excellent solution to provide seamless connectivity underwater. UWOC holds immense significance due to its ability to transmit data at high rates, low latency, and enhanced security. In this work, we propose polarization division multiplexing-based UWOC system under the impact of salinity with an on–off keying (OOK) modulation format. The proposed system aims to establish high-speed network connectivity between underwater divers/submarines in oceans at different salinity levels. The numerical simulation results demonstrate the effectiveness of our proposed system with a 2 Gbps data rate up to 10.5 m range in freshwater and up to 1.8 m in oceanic waters with salinity up to 35 ppt. Successful transmission of high-speed data is reported in underwater optical wireless communication, especially where salinity impact is higher.
{"title":"A Salinity-Impact Analysis of Polarization Division Multiplexing-Based Underwater Optical Wireless Communication System with High-Speed Data Transmission","authors":"Sushank Chaudhary, Abhishek Sharma, Sunita Khichar, Shashi Shah, Rizwan Ullah, Amir Parnianifard, Lunchakorn Wuttisittikulkij","doi":"10.3390/jsan12050072","DOIUrl":"https://doi.org/10.3390/jsan12050072","url":null,"abstract":"The majority of the Earth’s surface is covered by water, with oceans holding approximately 97% of this water and serving as the lifeblood of our planet. These oceans are essential for various purposes, including transportation, sustenance, and communication. However, establishing effective communication networks between the numerous sub-islands present in many parts of the world poses significant challenges. Underwater optical wireless communication, or UWOC, can indeed be an excellent solution to provide seamless connectivity underwater. UWOC holds immense significance due to its ability to transmit data at high rates, low latency, and enhanced security. In this work, we propose polarization division multiplexing-based UWOC system under the impact of salinity with an on–off keying (OOK) modulation format. The proposed system aims to establish high-speed network connectivity between underwater divers/submarines in oceans at different salinity levels. The numerical simulation results demonstrate the effectiveness of our proposed system with a 2 Gbps data rate up to 10.5 m range in freshwater and up to 1.8 m in oceanic waters with salinity up to 35 ppt. Successful transmission of high-speed data is reported in underwater optical wireless communication, especially where salinity impact is higher.","PeriodicalId":37584,"journal":{"name":"Journal of Sensor and Actuator Networks","volume":"68 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-10-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135300581","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}
Human activity recognition has been widely used to monitor users during physical activities. By embedding a pre-trained model into wearable devices with an inertial measurement unit, it is possible to identify the activity being executed, count steps and activity duration time, and even predict when the user should hydrate himself. Despite these interesting applications, these approaches are limited by a set of pre-trained activities, making them unable to learn new human activities. In this paper, we introduce a novel approach for generating runtime models to give the users feedback that helps them to correctly perform repetitive physical activities. To perform a distributed analysis, the methodology focuses on applying the proposed method to each specific body segment. The method adopts the Restricted Boltzmann Machine to learn the patterns of repetitive physical activities and, at the same time, provides suggestions for adjustments if the repetition is not consistent with the model. The learning and the suggestions are both based on inertial measurement data mainly considering movement acceleration and amplitude. The results show that by applying the model’s suggestions to the evaluation data, the adjusted output was up to 3.68x more similar to the expected movement than the original data.
{"title":"An Online Method for Supporting and Monitoring Repetitive Physical Activities Based on Restricted Boltzmann Machines","authors":"Marcio Alencar, Raimundo Barreto, Eduardo Souto, Horacio Oliveira","doi":"10.3390/jsan12050070","DOIUrl":"https://doi.org/10.3390/jsan12050070","url":null,"abstract":"Human activity recognition has been widely used to monitor users during physical activities. By embedding a pre-trained model into wearable devices with an inertial measurement unit, it is possible to identify the activity being executed, count steps and activity duration time, and even predict when the user should hydrate himself. Despite these interesting applications, these approaches are limited by a set of pre-trained activities, making them unable to learn new human activities. In this paper, we introduce a novel approach for generating runtime models to give the users feedback that helps them to correctly perform repetitive physical activities. To perform a distributed analysis, the methodology focuses on applying the proposed method to each specific body segment. The method adopts the Restricted Boltzmann Machine to learn the patterns of repetitive physical activities and, at the same time, provides suggestions for adjustments if the repetition is not consistent with the model. The learning and the suggestions are both based on inertial measurement data mainly considering movement acceleration and amplitude. The results show that by applying the model’s suggestions to the evaluation data, the adjusted output was up to 3.68x more similar to the expected movement than the original data.","PeriodicalId":37584,"journal":{"name":"Journal of Sensor and Actuator Networks","volume":"89 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136094261","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}
This article is aimed at designing an inventive compact-size quad-port antenna that can be operated within terahertz (THz) frequency spectra for a 6G high-speed wireless communication link. The single-element antenna comprises a lotus-petal-like radiating patch and a defected ground structure (DGS) on a 20 × 20 × 2 µm3 polyamide substrate and is designed to operate within the 8.96–13.5 THz frequency range. The THz antenna is deployed for a two-port MIMO configuration having a size of 46 × 20 × 2 µm3 with interelement separation of less than a quarter-wavelength of 0.18λ (λ at 9 THz). The two-port configuration operates in the 9–13.25 THz frequency range, with better than −25 dB isolation. Further, the two-port THz antenna is mirrored vertically with a separation of 0.5λ to form the four-port MIMO configuration. The proposed four-port THz antenna has dimensions of 46 × 46 × 2 µm3 and operates in the frequency range of 9–13 THz. Isolation improvement better than −25 dB is realized by incorporating parasitic elements onto the ground plane. Performance analysis of the proposed antenna in terms of MIMO diversity parameters, viz., envelope correlation coefficient (ECC) < 0.05, diversity gain (DG) ≈ 10, mean effective gain (MEG) < −3 dB, total active reflection coefficient (TARC) < −10 dB, channel capacity loss (CCL) < 0.3 bps/Hz, and multiplexing efficiency (ME) < 0 dB, is performed to justify the appropriateness of the proposed antenna for MIMO applications. The antenna has virtuous radiation properties with good gain, which is crucial for any wireless communication system, especially for the THz communication network.
{"title":"A Quad-Port Nature-Inspired Lotus-Shaped Wideband Terahertz Antenna for Wireless Applications","authors":"Jeenal Raghunathan, Praveen Kumar, Tanweer Ali, Pradeep Kumar, Parveez Shariff Bhadrvathi Ghouse, Sameena Pathan","doi":"10.3390/jsan12050069","DOIUrl":"https://doi.org/10.3390/jsan12050069","url":null,"abstract":"This article is aimed at designing an inventive compact-size quad-port antenna that can be operated within terahertz (THz) frequency spectra for a 6G high-speed wireless communication link. The single-element antenna comprises a lotus-petal-like radiating patch and a defected ground structure (DGS) on a 20 × 20 × 2 µm3 polyamide substrate and is designed to operate within the 8.96–13.5 THz frequency range. The THz antenna is deployed for a two-port MIMO configuration having a size of 46 × 20 × 2 µm3 with interelement separation of less than a quarter-wavelength of 0.18λ (λ at 9 THz). The two-port configuration operates in the 9–13.25 THz frequency range, with better than −25 dB isolation. Further, the two-port THz antenna is mirrored vertically with a separation of 0.5λ to form the four-port MIMO configuration. The proposed four-port THz antenna has dimensions of 46 × 46 × 2 µm3 and operates in the frequency range of 9–13 THz. Isolation improvement better than −25 dB is realized by incorporating parasitic elements onto the ground plane. Performance analysis of the proposed antenna in terms of MIMO diversity parameters, viz., envelope correlation coefficient (ECC) < 0.05, diversity gain (DG) ≈ 10, mean effective gain (MEG) < −3 dB, total active reflection coefficient (TARC) < −10 dB, channel capacity loss (CCL) < 0.3 bps/Hz, and multiplexing efficiency (ME) < 0 dB, is performed to justify the appropriateness of the proposed antenna for MIMO applications. The antenna has virtuous radiation properties with good gain, which is crucial for any wireless communication system, especially for the THz communication network.","PeriodicalId":37584,"journal":{"name":"Journal of Sensor and Actuator Networks","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136129702","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}
Matthieu Mouyart, Guilherme Medeiros Machado, Jae-Yun Jun
Intrusion detection systems can defectively perform when they are adjusted with datasets that are unbalanced in terms of attack data and non-attack data. Most datasets contain more non-attack data than attack data, and this circumstance can introduce biases in intrusion detection systems, making them vulnerable to cyberattacks. As an approach to remedy this issue, we considered the Conditional Tabular Generative Adversarial Network (CTGAN), with its hyperparameters optimized using the tree-structured Parzen estimator (TPE), to balance an insider threat tabular dataset called the CMU-CERT, which is formed by discrete-value and continuous-value columns. We showed through this method that the mean absolute errors between the probability mass functions (PMFs) of the actual data and the PMFs of the data generated using the CTGAN can be relatively small. Then, from the optimized CTGAN, we generated synthetic insider threat data and combined them with the actual ones to balance the original dataset. We used the resulting dataset for an intrusion detection system implemented with the Adversarial Environment Reinforcement Learning (AE-RL) algorithm in a multi-agent framework formed by an attacker and a defender. We showed that the performance of detecting intrusions using the framework of the CTGAN and the AE-RL is significantly improved with respect to the case where the dataset is not balanced, giving an F1-score of 0.7617.
{"title":"A Multi-Agent Intrusion Detection System Optimized by a Deep Reinforcement Learning Approach with a Dataset Enlarged Using a Generative Model to Reduce the Bias Effect","authors":"Matthieu Mouyart, Guilherme Medeiros Machado, Jae-Yun Jun","doi":"10.3390/jsan12050068","DOIUrl":"https://doi.org/10.3390/jsan12050068","url":null,"abstract":"Intrusion detection systems can defectively perform when they are adjusted with datasets that are unbalanced in terms of attack data and non-attack data. Most datasets contain more non-attack data than attack data, and this circumstance can introduce biases in intrusion detection systems, making them vulnerable to cyberattacks. As an approach to remedy this issue, we considered the Conditional Tabular Generative Adversarial Network (CTGAN), with its hyperparameters optimized using the tree-structured Parzen estimator (TPE), to balance an insider threat tabular dataset called the CMU-CERT, which is formed by discrete-value and continuous-value columns. We showed through this method that the mean absolute errors between the probability mass functions (PMFs) of the actual data and the PMFs of the data generated using the CTGAN can be relatively small. Then, from the optimized CTGAN, we generated synthetic insider threat data and combined them with the actual ones to balance the original dataset. We used the resulting dataset for an intrusion detection system implemented with the Adversarial Environment Reinforcement Learning (AE-RL) algorithm in a multi-agent framework formed by an attacker and a defender. We showed that the performance of detecting intrusions using the framework of the CTGAN and the AE-RL is significantly improved with respect to the case where the dataset is not balanced, giving an F1-score of 0.7617.","PeriodicalId":37584,"journal":{"name":"Journal of Sensor and Actuator Networks","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135202441","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}
The frequency of cyber-attacks on the Internet of Things (IoT) networks has significantly increased in recent years. Anomaly-based network intrusion detection systems (NIDSs) offer an additional layer of network protection by detecting and reporting the infamous zero-day attacks. However, the efficiency of real-time detection systems relies on several factors, including the number of features utilized to make a prediction. Thus, minimizing them is crucial as it implies faster prediction and lower storage space. This paper utilizes recursive feature elimination with cross-validation using a decision tree model as an estimator (DT-RFECV) to select an optimal subset of 15 of UNSW-NB15’s 42 features and evaluates them using several ML classifiers, including tree-based ones, such as random forest. The proposed NIDS exhibits an accurate prediction model for network flow with a binary classification accuracy of 95.30% compared to 95.56% when using the entire feature set. The reported scores are comparable to those attained by the state-of-the-art systems despite decreasing the number of utilized features by about 65%.
{"title":"Recursive Feature Elimination with Cross-Validation with Decision Tree: Feature Selection Method for Machine Learning-Based Intrusion Detection Systems","authors":"Mohammed Awad, Salam Fraihat","doi":"10.3390/jsan12050067","DOIUrl":"https://doi.org/10.3390/jsan12050067","url":null,"abstract":"The frequency of cyber-attacks on the Internet of Things (IoT) networks has significantly increased in recent years. Anomaly-based network intrusion detection systems (NIDSs) offer an additional layer of network protection by detecting and reporting the infamous zero-day attacks. However, the efficiency of real-time detection systems relies on several factors, including the number of features utilized to make a prediction. Thus, minimizing them is crucial as it implies faster prediction and lower storage space. This paper utilizes recursive feature elimination with cross-validation using a decision tree model as an estimator (DT-RFECV) to select an optimal subset of 15 of UNSW-NB15’s 42 features and evaluates them using several ML classifiers, including tree-based ones, such as random forest. The proposed NIDS exhibits an accurate prediction model for network flow with a binary classification accuracy of 95.30% compared to 95.56% when using the entire feature set. The reported scores are comparable to those attained by the state-of-the-art systems despite decreasing the number of utilized features by about 65%.","PeriodicalId":37584,"journal":{"name":"Journal of Sensor and Actuator Networks","volume":"15 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135109997","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}
The integration of communication channels with the feedback loop in a networked control system (NCS) is attractive for many applications. A major challenge in the NCS is to reduce transmissions over the network between the sensors, the controller, and the actuators to avoid network congestion. An efficient approach to achieving this goal is the event-triggered implementation where the control actions are only updated when necessary from stability/performance perspectives. In particular, periodic event-triggered control (PETC) has garnered recent attention because of its practical implementation advantages. This paper focuses on the design of stabilizing PETC for linear time-invariant systems. It is assumed that the plant state is partially known; the feedback signal is sent to the controller at discrete-time instants via a digital channel; and an event-triggered controller is synthesized, solely based on the available plant measurement. The constructed event-triggering law is novel and only verified at periodic time instants; it is more adapted to practical implementations. The proposed approach ensures a global asymptotic stability property for the closed-loop system under mild conditions. The overall model is developed as a hybrid dynamical system to truly describe the mixed continuous-time and discrete-time dynamics. The stability is studied using appropriate Lyapunov functions. The efficiency of the technique is illustrated in the dynamic model of the tunnel diode system.
{"title":"Output-Based Dynamic Periodic Event-Triggered Control with Application to the Tunnel Diode System","authors":"Mahmoud Abdelrahim, Dhafer Almakhles","doi":"10.3390/jsan12050066","DOIUrl":"https://doi.org/10.3390/jsan12050066","url":null,"abstract":"The integration of communication channels with the feedback loop in a networked control system (NCS) is attractive for many applications. A major challenge in the NCS is to reduce transmissions over the network between the sensors, the controller, and the actuators to avoid network congestion. An efficient approach to achieving this goal is the event-triggered implementation where the control actions are only updated when necessary from stability/performance perspectives. In particular, periodic event-triggered control (PETC) has garnered recent attention because of its practical implementation advantages. This paper focuses on the design of stabilizing PETC for linear time-invariant systems. It is assumed that the plant state is partially known; the feedback signal is sent to the controller at discrete-time instants via a digital channel; and an event-triggered controller is synthesized, solely based on the available plant measurement. The constructed event-triggering law is novel and only verified at periodic time instants; it is more adapted to practical implementations. The proposed approach ensures a global asymptotic stability property for the closed-loop system under mild conditions. The overall model is developed as a hybrid dynamical system to truly describe the mixed continuous-time and discrete-time dynamics. The stability is studied using appropriate Lyapunov functions. The efficiency of the technique is illustrated in the dynamic model of the tunnel diode system.","PeriodicalId":37584,"journal":{"name":"Journal of Sensor and Actuator Networks","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2023-09-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134914136","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：