Anonymous networks, which aim primarily to protect user identities, have gained prominence as tools for enhancing network security and anonymity. Nonetheless, these networks have become a platform for adversarial affairs and sources of suspicious attack traffic. To defend against unpredictable adversaries on the Internet, detecting anonymous network traffic has emerged as a necessity. Many supervised approaches to identify anonymous traffic have harnessed machine learning strategies. However, many require access to engineered datasets and complex architectures to extract the desired information. Due to the resistance of anonymous network traffic to traffic analysis and the scarcity of publicly available datasets, those approaches may need to improve their training efficiency and achieve a higher performance when it comes to anonymous traffic detection. This study utilizes feature engineering techniques to extract pattern information and rank the feature importance of the static traces of anonymous traffic. To leverage these pattern attributes effectively, we developed a reinforcement learning framework that encompasses four key components: states, actions, rewards, and state transitions. A lightweight system is devised to classify anonymous and non-anonymous network traffic. Subsequently, two fine-tuned thresholds are proposed to substitute the traditional labels in a binary classification system. The system will identify anonymous network traffic without reliance on labeled data. The experimental results underscore that the system can identify anonymous traffic with an accuracy rate exceeding 80% (when based on pattern information).
{"title":"Anonymous Traffic Detection Based on Feature Engineering and Reinforcement Learning","authors":"Dazhou Liu, Younghee Park","doi":"10.3390/s24072295","DOIUrl":"https://doi.org/10.3390/s24072295","url":null,"abstract":"Anonymous networks, which aim primarily to protect user identities, have gained prominence as tools for enhancing network security and anonymity. Nonetheless, these networks have become a platform for adversarial affairs and sources of suspicious attack traffic. To defend against unpredictable adversaries on the Internet, detecting anonymous network traffic has emerged as a necessity. Many supervised approaches to identify anonymous traffic have harnessed machine learning strategies. However, many require access to engineered datasets and complex architectures to extract the desired information. Due to the resistance of anonymous network traffic to traffic analysis and the scarcity of publicly available datasets, those approaches may need to improve their training efficiency and achieve a higher performance when it comes to anonymous traffic detection. This study utilizes feature engineering techniques to extract pattern information and rank the feature importance of the static traces of anonymous traffic. To leverage these pattern attributes effectively, we developed a reinforcement learning framework that encompasses four key components: states, actions, rewards, and state transitions. A lightweight system is devised to classify anonymous and non-anonymous network traffic. Subsequently, two fine-tuned thresholds are proposed to substitute the traditional labels in a binary classification system. The system will identify anonymous network traffic without reliance on labeled data. The experimental results underscore that the system can identify anonymous traffic with an accuracy rate exceeding 80% (when based on pattern information).","PeriodicalId":221960,"journal":{"name":"Sensors (Basel, Switzerland)","volume":"124 ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140766584","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}
Alessandro Cabras, P. Ortu, T. Pisanu, Paolo Maxia, Roberto Caocci
In a cooling system for radio astronomy receivers, maintaining cold heads and compressors is essential for consistent performance. This project focuses on monitoring the power currents of the cold head’s motor to address potential mechanical deterioration, which could jeopardize the overall functionality of the system. Using Hall effect sensors, a microcontroller-based electronic board, and artificial intelligence, the system detects and predicts anomalies. The model operates using an unsupervised approach based on incremental clustering. Since potential fault scenarios can be multiple and often challenging to simulate or identify during training, the system is initially trained using known operational categories. Over time, the system adapts and evolves by incorporating new data, which can be assigned to existing categories or, in the case of new anomalies, form new categories. This incremental approach enables the system to enhance its performance over the years, adapting to new anomaly scenarios and ensuring precise and reliable monitoring of the cold head’s health.
{"title":"Incremental Clustering for Predictive Maintenance in Cryogenics for Radio Astronomy","authors":"Alessandro Cabras, P. Ortu, T. Pisanu, Paolo Maxia, Roberto Caocci","doi":"10.3390/s24072278","DOIUrl":"https://doi.org/10.3390/s24072278","url":null,"abstract":"In a cooling system for radio astronomy receivers, maintaining cold heads and compressors is essential for consistent performance. This project focuses on monitoring the power currents of the cold head’s motor to address potential mechanical deterioration, which could jeopardize the overall functionality of the system. Using Hall effect sensors, a microcontroller-based electronic board, and artificial intelligence, the system detects and predicts anomalies. The model operates using an unsupervised approach based on incremental clustering. Since potential fault scenarios can be multiple and often challenging to simulate or identify during training, the system is initially trained using known operational categories. Over time, the system adapts and evolves by incorporating new data, which can be assigned to existing categories or, in the case of new anomalies, form new categories. This incremental approach enables the system to enhance its performance over the years, adapting to new anomaly scenarios and ensuring precise and reliable monitoring of the cold head’s health.","PeriodicalId":221960,"journal":{"name":"Sensors (Basel, Switzerland)","volume":"59 2","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140764896","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}
An efficient path integral (PI) model for the accurate analysis of curved dielectric structures on coarse grids via the two-dimensional nonstandard finite-difference time-domain (NS-FDTD) technique is introduced in this paper. In contrast to previous PI implementations of the perfectly electric conductor case, which accommodates orthogonal cells in the vicinity of curved surfaces, the novel PI model employs the occupation ratio of dielectrics in the necessary cells, providing thus a straightforward and instructive means to treat an assortment of practical applications. For its verification, the reflection from a flat plate and the scattering from a cylinder using the PI model are investigated. Results indicate that the featured methodology can enable the reliable and precise modeling of arbitrarily shaped dielectrics in the NS-FDTD algorithm on coarse grids.
本文介绍了一种高效的路径积分（PI）模型，用于通过二维非标准有限差分时域（NS-FDTD）技术精确分析粗网格上的弯曲介电结构。与以往完全电导体情况下的 PI 实现（在弯曲表面附近采用正交单元）不同，新的 PI 模型采用了必要单元中介质的占位比，从而为处理各种实际应用提供了直接而有指导意义的方法。为了验证该模型，我们使用 PI 模型研究了平板的反射和圆柱体的散射。结果表明，在粗网格上的 NS-FDTD 算法中，该特色方法可以对任意形状的电介质进行可靠而精确的建模。
{"title":"Accurate Nonstandard Path Integral Models for Arbitrary Dielectric Boundaries in 2-D NS-FDTD Domains","authors":"T. Ohtani, Y. Kanai, N. Kantartzis","doi":"10.3390/s24072373","DOIUrl":"https://doi.org/10.3390/s24072373","url":null,"abstract":"An efficient path integral (PI) model for the accurate analysis of curved dielectric structures on coarse grids via the two-dimensional nonstandard finite-difference time-domain (NS-FDTD) technique is introduced in this paper. In contrast to previous PI implementations of the perfectly electric conductor case, which accommodates orthogonal cells in the vicinity of curved surfaces, the novel PI model employs the occupation ratio of dielectrics in the necessary cells, providing thus a straightforward and instructive means to treat an assortment of practical applications. For its verification, the reflection from a flat plate and the scattering from a cylinder using the PI model are investigated. Results indicate that the featured methodology can enable the reliable and precise modeling of arbitrarily shaped dielectrics in the NS-FDTD algorithm on coarse grids.","PeriodicalId":221960,"journal":{"name":"Sensors (Basel, Switzerland)","volume":"824 ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140776926","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}
Amirhossein Moshrefi, H. H. Tawfik, M. Elsayed, F. Nabki
Ultrasonic diagnostics is the earliest way to predict industrial faults. Usually, a contact microphone is employed for detection, but the recording will be contaminated with noise. In this paper, a dataset that contains 10 main faults of pipelines and motors is analyzed from which 30 different features in the time and frequency domains are extracted. Afterward, for dimensionality reduction, principal component analysis (PCA), linear discriminant analysis (LDA), and t-distributed stochastic neighbor embedding (t-SNE) are performed. In the subsequent phase, recursive feature elimination (RFE) is employed as a strategic method to analyze and select the most relevant features for the classifiers. Next, predictive models consisting of k-Nearest Neighbor (KNN), Logistic Regression (LR), Decision Tree (DT), Gaussian Naive Bayes (GNB), and Support Vector Machine (SVM) are employed. Then, in order to solve the classification problem, a stacking classifier based on a meta-classifier which combines multiple classification models is introduced. Furthermore, the k-fold cross-validation technique is employed to assess the effectiveness of the model in handling new data for the evaluation of experimental results in ultrasonic fault detection. With the proposed method, the accuracy is around 5% higher over five cross folds with the least amount of variation. The timing evaluation of the meta model on the 64 MHz Cortex M4 microcontroller unit (MCU) revealed an execution time of 11 ms, indicating it could be a promising solution for real-time monitoring.
超声波诊断是预测工业故障的最早方法。通常使用接触式麦克风进行检测，但记录会受到噪声的污染。本文分析了包含管道和电机 10 种主要故障的数据集，从中提取了 30 种不同的时域和频域特征。之后，为了降低维度，进行了主成分分析（PCA）、线性判别分析（LDA）和 t 分布随机邻域嵌入（t-SNE）。在随后的阶段，采用递归特征消除法（RFE）作为一种策略方法，为分类器分析和选择最相关的特征。接下来，预测模型包括 k-Nearest Neighbor (KNN)、Logistic Regression (LR)、Decision Tree (DT)、Gaussian Naive Bayes (GNB) 和 Support Vector Machine (SVM)。然后，为了解决分类问题，引入了基于元分类器的堆叠分类器，该分类器结合了多个分类模型。此外，在超声波故障检测的实验结果评估中，采用了 k 折交叉验证技术来评估模型处理新数据的有效性。采用所提出的方法，在五次交叉验证中，准确率提高了约 5%，且变化量最小。在 64 MHz Cortex M4 微控制器单元（MCU）上对元模型进行的时序评估显示，执行时间为 11 毫秒，这表明它是一种很有前途的实时监测解决方案。
{"title":"Industrial Fault Detection Employing Meta Ensemble Model Based on Contact Sensor Ultrasonic Signal","authors":"Amirhossein Moshrefi, H. H. Tawfik, M. Elsayed, F. Nabki","doi":"10.3390/s24072297","DOIUrl":"https://doi.org/10.3390/s24072297","url":null,"abstract":"Ultrasonic diagnostics is the earliest way to predict industrial faults. Usually, a contact microphone is employed for detection, but the recording will be contaminated with noise. In this paper, a dataset that contains 10 main faults of pipelines and motors is analyzed from which 30 different features in the time and frequency domains are extracted. Afterward, for dimensionality reduction, principal component analysis (PCA), linear discriminant analysis (LDA), and t-distributed stochastic neighbor embedding (t-SNE) are performed. In the subsequent phase, recursive feature elimination (RFE) is employed as a strategic method to analyze and select the most relevant features for the classifiers. Next, predictive models consisting of k-Nearest Neighbor (KNN), Logistic Regression (LR), Decision Tree (DT), Gaussian Naive Bayes (GNB), and Support Vector Machine (SVM) are employed. Then, in order to solve the classification problem, a stacking classifier based on a meta-classifier which combines multiple classification models is introduced. Furthermore, the k-fold cross-validation technique is employed to assess the effectiveness of the model in handling new data for the evaluation of experimental results in ultrasonic fault detection. With the proposed method, the accuracy is around 5% higher over five cross folds with the least amount of variation. The timing evaluation of the meta model on the 64 MHz Cortex M4 microcontroller unit (MCU) revealed an execution time of 11 ms, indicating it could be a promising solution for real-time monitoring.","PeriodicalId":221960,"journal":{"name":"Sensors (Basel, Switzerland)","volume":"84 ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140783177","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}
Marta Freitas, Francisco Pinho, Liliana Pinho, Sandra Silva, Vânia Figueira, J. Vilas-Boas, Augusta Silva
Non-linear and dynamic systems analysis of human movement has recently become increasingly widespread with the intention of better reflecting how complexity affects the adaptability of motor systems, especially after a stroke. The main objective of this scoping review was to summarize the non-linear measures used in the analysis of kinetic, kinematic, and EMG data of human movement after stroke. PRISMA-ScR guidelines were followed, establishing the eligibility criteria, the population, the concept, and the contextual framework. The examined studies were published between 1 January 2013 and 12 April 2023, in English or Portuguese, and were indexed in the databases selected for this research: PubMed®, Web of Science®, Institute of Electrical and Electronics Engineers®, Science Direct® and Google Scholar®. In total, 14 of the 763 articles met the inclusion criteria. The non-linear measures identified included entropy (n = 11), fractal analysis (n = 1), the short-term local divergence exponent (n = 1), the maximum Floquet multiplier (n = 1), and the Lyapunov exponent (n = 1). These studies focused on different motor tasks: reaching to grasp (n = 2), reaching to point (n = 1), arm tracking (n = 2), elbow flexion (n = 5), elbow extension (n = 1), wrist and finger extension upward (lifting) (n = 1), knee extension (n = 1), and walking (n = 4). When studying the complexity of human movement in chronic post-stroke adults, entropy measures, particularly sample entropy, were preferred. Kinematic assessment was mainly performed using motion capture systems, with a focus on joint angles of the upper limbs.
{"title":"Biomechanical Assessment Methods Used in Chronic Stroke: A Scoping Review of Non-Linear Approaches","authors":"Marta Freitas, Francisco Pinho, Liliana Pinho, Sandra Silva, Vânia Figueira, J. Vilas-Boas, Augusta Silva","doi":"10.3390/s24072338","DOIUrl":"https://doi.org/10.3390/s24072338","url":null,"abstract":"Non-linear and dynamic systems analysis of human movement has recently become increasingly widespread with the intention of better reflecting how complexity affects the adaptability of motor systems, especially after a stroke. The main objective of this scoping review was to summarize the non-linear measures used in the analysis of kinetic, kinematic, and EMG data of human movement after stroke. PRISMA-ScR guidelines were followed, establishing the eligibility criteria, the population, the concept, and the contextual framework. The examined studies were published between 1 January 2013 and 12 April 2023, in English or Portuguese, and were indexed in the databases selected for this research: PubMed®, Web of Science®, Institute of Electrical and Electronics Engineers®, Science Direct® and Google Scholar®. In total, 14 of the 763 articles met the inclusion criteria. The non-linear measures identified included entropy (n = 11), fractal analysis (n = 1), the short-term local divergence exponent (n = 1), the maximum Floquet multiplier (n = 1), and the Lyapunov exponent (n = 1). These studies focused on different motor tasks: reaching to grasp (n = 2), reaching to point (n = 1), arm tracking (n = 2), elbow flexion (n = 5), elbow extension (n = 1), wrist and finger extension upward (lifting) (n = 1), knee extension (n = 1), and walking (n = 4). When studying the complexity of human movement in chronic post-stroke adults, entropy measures, particularly sample entropy, were preferred. Kinematic assessment was mainly performed using motion capture systems, with a focus on joint angles of the upper limbs.","PeriodicalId":221960,"journal":{"name":"Sensors (Basel, Switzerland)","volume":"271 ","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140793559","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}
T. Venckunas, Andrius Satas, M. Brazaitis, N. Eimantas, S. Sipaviciene, S. Kamandulis
Near-infrared spectroscopy (NIRS) during repeated limb occlusions is a noninvasive tool for assessing muscle oxidative capacity. However, the method’s reliability and validity remain under investigation. This study aimed to determine the reliability of the NIRS-derived mitochondrial power of the musculus vastus lateralis and its correlation with whole-body (cycling) aerobic power (V˙O2 peak). Eleven healthy active men (28 ± 10 y) twice (2 days apart) underwent repeated arterial occlusions to induce changes in muscle oxygen delivery after 15 s of electrical muscle stimulation. The muscle oxygen consumption (mV˙O2) recovery time and rate (k) constants were calculated from the NIRS O2Hb signal. We assessed the reliability (coefficient of variation and intraclass coefficient of correlation [ICC]) and equivalency (t-test) between visits. The results showed high reproducibility for the mV˙O2 recovery time constant (ICC = 0.859) and moderate reproducibility for the k value (ICC = 0.674), with no significant differences between visits (p > 0.05). NIRS-derived k did not correlate with the V˙O2 peak relative to body mass (r = 0.441, p = 0.17) or the absolute V˙O2 peak (r = 0.366, p = 0.26). In conclusion, NIRS provides a reproducible estimate of muscle mitochondrial power, which, however, was not correlated with whole-body aerobic capacity in the current study, suggesting that even if somewhat overlapping, not the same set of factors underpin these distinct indices of aerobic capacity at the different (peripheral and whole-body systemic) levels.
{"title":"Near-InfraRed Spectroscopy Provides a Reproducible Estimate of Muscle Aerobic Capacity, but Not Whole-Body Aerobic Power","authors":"T. Venckunas, Andrius Satas, M. Brazaitis, N. Eimantas, S. Sipaviciene, S. Kamandulis","doi":"10.3390/s24072277","DOIUrl":"https://doi.org/10.3390/s24072277","url":null,"abstract":"Near-infrared spectroscopy (NIRS) during repeated limb occlusions is a noninvasive tool for assessing muscle oxidative capacity. However, the method’s reliability and validity remain under investigation. This study aimed to determine the reliability of the NIRS-derived mitochondrial power of the musculus vastus lateralis and its correlation with whole-body (cycling) aerobic power (V˙O2 peak). Eleven healthy active men (28 ± 10 y) twice (2 days apart) underwent repeated arterial occlusions to induce changes in muscle oxygen delivery after 15 s of electrical muscle stimulation. The muscle oxygen consumption (mV˙O2) recovery time and rate (k) constants were calculated from the NIRS O2Hb signal. We assessed the reliability (coefficient of variation and intraclass coefficient of correlation [ICC]) and equivalency (t-test) between visits. The results showed high reproducibility for the mV˙O2 recovery time constant (ICC = 0.859) and moderate reproducibility for the k value (ICC = 0.674), with no significant differences between visits (p > 0.05). NIRS-derived k did not correlate with the V˙O2 peak relative to body mass (r = 0.441, p = 0.17) or the absolute V˙O2 peak (r = 0.366, p = 0.26). In conclusion, NIRS provides a reproducible estimate of muscle mitochondrial power, which, however, was not correlated with whole-body aerobic capacity in the current study, suggesting that even if somewhat overlapping, not the same set of factors underpin these distinct indices of aerobic capacity at the different (peripheral and whole-body systemic) levels.","PeriodicalId":221960,"journal":{"name":"Sensors (Basel, Switzerland)","volume":"62 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140757282","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}
Under a foggy environment, the air contains a large number of suspended particles, which lead to the loss of image information and decline of contrast collected by the vision system. This makes subsequent processing and analysis difficult. At the same time, the current stage of the defogging system has problems such as high hardware cost and poor real-time processing. In this article, an image defogging system is designed based on the ZYNQ platform. First of all, on the basis of the traditional dark-channel defogging algorithm, an algorithm for segmenting the sky is proposed, and in this way, the image distortion caused by the sky region is avoided, and the atmospheric light value and transmittance are estimated more accurately. Then color balancing is performed after image defogging to improve the quality of the final output image. The parallel computing advantage and logic resources of the PL (Programmable Logic) part (FPGA) of ZYNQ are fully utilized through instruction constraints and logic optimization. Finally, the visible light detector is used as the input to build a real-time video processing experiment platform. The experimental results show that the system has a good defogging effect and meet the real-time requirements.
{"title":"ZYNQ-Based Visible Light Defogging System Design Realization","authors":"Bohan Liu, Qihai Wei, Kun Ding","doi":"10.3390/s24072276","DOIUrl":"https://doi.org/10.3390/s24072276","url":null,"abstract":"Under a foggy environment, the air contains a large number of suspended particles, which lead to the loss of image information and decline of contrast collected by the vision system. This makes subsequent processing and analysis difficult. At the same time, the current stage of the defogging system has problems such as high hardware cost and poor real-time processing. In this article, an image defogging system is designed based on the ZYNQ platform. First of all, on the basis of the traditional dark-channel defogging algorithm, an algorithm for segmenting the sky is proposed, and in this way, the image distortion caused by the sky region is avoided, and the atmospheric light value and transmittance are estimated more accurately. Then color balancing is performed after image defogging to improve the quality of the final output image. The parallel computing advantage and logic resources of the PL (Programmable Logic) part (FPGA) of ZYNQ are fully utilized through instruction constraints and logic optimization. Finally, the visible light detector is used as the input to build a real-time video processing experiment platform. The experimental results show that the system has a good defogging effect and meet the real-time requirements.","PeriodicalId":221960,"journal":{"name":"Sensors (Basel, Switzerland)","volume":"257 1","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140776645","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}
Eldor B. Ibragimov, Yongsoo Kim, Jung Hee Lee, Junsang Cho, Jong-Jae Lee
The degradation of road pavements due to environmental factors is a pressing issue in infrastructure maintenance, necessitating precise identification of pavement distresses. The pavement condition index (PCI) serves as a critical metric for evaluating pavement conditions, essential for effective budget allocation and performance tracking. Traditional manual PCI assessment methods are limited by labor intensity, subjectivity, and susceptibility to human error. Addressing these challenges, this paper presents a novel, end-to-end automated method for PCI calculation, integrating deep learning and image processing technologies. The first stage employs a deep learning algorithm for accurate detection of pavement cracks, followed by the application of a segmentation-based skeleton algorithm in image processing to estimate crack width precisely. This integrated approach enhances the assessment process, providing a more comprehensive evaluation of pavement integrity. The validation results demonstrate a 95% accuracy in crack detection and 90% accuracy in crack width estimation. Leveraging these results, the automated PCI rating is achieved, aligned with standards, showcasing significant improvements in the efficiency and reliability of PCI evaluations. This method offers advancements in pavement maintenance strategies and potential applications in broader road infrastructure management.
{"title":"Automated Pavement Condition Index Assessment with Deep Learning and Image Analysis: An End-to-End Approach","authors":"Eldor B. Ibragimov, Yongsoo Kim, Jung Hee Lee, Junsang Cho, Jong-Jae Lee","doi":"10.3390/s24072333","DOIUrl":"https://doi.org/10.3390/s24072333","url":null,"abstract":"The degradation of road pavements due to environmental factors is a pressing issue in infrastructure maintenance, necessitating precise identification of pavement distresses. The pavement condition index (PCI) serves as a critical metric for evaluating pavement conditions, essential for effective budget allocation and performance tracking. Traditional manual PCI assessment methods are limited by labor intensity, subjectivity, and susceptibility to human error. Addressing these challenges, this paper presents a novel, end-to-end automated method for PCI calculation, integrating deep learning and image processing technologies. The first stage employs a deep learning algorithm for accurate detection of pavement cracks, followed by the application of a segmentation-based skeleton algorithm in image processing to estimate crack width precisely. This integrated approach enhances the assessment process, providing a more comprehensive evaluation of pavement integrity. The validation results demonstrate a 95% accuracy in crack detection and 90% accuracy in crack width estimation. Leveraging these results, the automated PCI rating is achieved, aligned with standards, showcasing significant improvements in the efficiency and reliability of PCI evaluations. This method offers advancements in pavement maintenance strategies and potential applications in broader road infrastructure management.","PeriodicalId":221960,"journal":{"name":"Sensors (Basel, Switzerland)","volume":"398 3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140778624","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}
Milad Behnamfar, Alexander Stevenson, Mohd Tariq, Arif Sarwat
Dynamic wireless charging (DWC) has emerged as a viable approach to mitigate range anxiety by ensuring continuous and uninterrupted charging for electric vehicles in motion. DWC systems rely on the length of the transmitter, which can be categorized into long-track transmitters and segmented coil arrays. The segmented coil array, favored for its heightened efficiency and reduced electromagnetic interference, stands out as the preferred option. However, in such DWC systems, the need arises to detect the vehicle’s position, specifically to activate the transmitter coils aligned with the receiver pad and de-energize uncoupled transmitter coils. This paper introduces various machine learning algorithms for precise vehicle position determination, accommodating diverse ground clearances of electric vehicles and various speeds. Through testing eight different machine learning algorithms and comparing the results, the random forest algorithm emerged as superior, displaying the lowest error in predicting the actual position.
{"title":"Vehicle Position Detection Based on Machine Learning Algorithms in Dynamic Wireless Charging","authors":"Milad Behnamfar, Alexander Stevenson, Mohd Tariq, Arif Sarwat","doi":"10.3390/s24072346","DOIUrl":"https://doi.org/10.3390/s24072346","url":null,"abstract":"Dynamic wireless charging (DWC) has emerged as a viable approach to mitigate range anxiety by ensuring continuous and uninterrupted charging for electric vehicles in motion. DWC systems rely on the length of the transmitter, which can be categorized into long-track transmitters and segmented coil arrays. The segmented coil array, favored for its heightened efficiency and reduced electromagnetic interference, stands out as the preferred option. However, in such DWC systems, the need arises to detect the vehicle’s position, specifically to activate the transmitter coils aligned with the receiver pad and de-energize uncoupled transmitter coils. This paper introduces various machine learning algorithms for precise vehicle position determination, accommodating diverse ground clearances of electric vehicles and various speeds. Through testing eight different machine learning algorithms and comparing the results, the random forest algorithm emerged as superior, displaying the lowest error in predicting the actual position.","PeriodicalId":221960,"journal":{"name":"Sensors (Basel, Switzerland)","volume":"42 14","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140797397","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}
Jiasheng Pan, Songyi Zhong, Tao Yue, Yankun Yin, Yanhao Tang
Fusing multiple sensor perceptions, specifically LiDAR and camera, is a prevalent method for target recognition in autonomous driving systems. Traditional object detection algorithms are limited by the sparse nature of LiDAR point clouds, resulting in poor fusion performance, especially for detecting small and distant targets. In this paper, a multi-task parallel neural network based on the Transformer is constructed to simultaneously perform depth completion and object detection. The loss functions are redesigned to reduce environmental noise in depth completion, and a new fusion module is designed to enhance the network’s perception of the foreground and background. The network leverages the correlation between RGB pixels for depth completion, completing the LiDAR point cloud and addressing the mismatch between sparse LiDAR features and dense pixel features. Subsequently, we extract depth map features and effectively fuse them with RGB features, fully utilizing the depth feature differences between foreground and background to enhance object detection performance, especially for challenging targets. Compared to the baseline network, improvements of 4.78%, 8.93%, and 15.54% are achieved in the difficult indicators for cars, pedestrians, and cyclists, respectively. Experimental results also demonstrate that the network achieves a speed of 38 fps, validating the efficiency and feasibility of the proposed method.
{"title":"Multi-Task Foreground-Aware Network with Depth Completion for Enhanced RGB-D Fusion Object Detection Based on Transformer","authors":"Jiasheng Pan, Songyi Zhong, Tao Yue, Yankun Yin, Yanhao Tang","doi":"10.3390/s24072374","DOIUrl":"https://doi.org/10.3390/s24072374","url":null,"abstract":"Fusing multiple sensor perceptions, specifically LiDAR and camera, is a prevalent method for target recognition in autonomous driving systems. Traditional object detection algorithms are limited by the sparse nature of LiDAR point clouds, resulting in poor fusion performance, especially for detecting small and distant targets. In this paper, a multi-task parallel neural network based on the Transformer is constructed to simultaneously perform depth completion and object detection. The loss functions are redesigned to reduce environmental noise in depth completion, and a new fusion module is designed to enhance the network’s perception of the foreground and background. The network leverages the correlation between RGB pixels for depth completion, completing the LiDAR point cloud and addressing the mismatch between sparse LiDAR features and dense pixel features. Subsequently, we extract depth map features and effectively fuse them with RGB features, fully utilizing the depth feature differences between foreground and background to enhance object detection performance, especially for challenging targets. Compared to the baseline network, improvements of 4.78%, 8.93%, and 15.54% are achieved in the difficult indicators for cars, pedestrians, and cyclists, respectively. Experimental results also demonstrate that the network achieves a speed of 38 fps, validating the efficiency and feasibility of the proposed method.","PeriodicalId":221960,"journal":{"name":"Sensors (Basel, Switzerland)","volume":"389 3","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140778760","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：