Location via proxy:   [ UP ]  
[Report a bug]   [Manage cookies]                
 
 
Sign in to use this feature.

Years

Between: -

Subjects

remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline

Journals

remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline

Article Types

Countries / Regions

remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline
remove_circle_outline

Search Results (3,879)

Search Parameters:
Keywords = anomalies detection

Order results
Result details
Results per page
Select all
Export citation of selected articles as:
14 pages, 3571 KiB  
Article
Application of the Buccal Micronucleus Cytome Assay for Genotoxicity Detection in Dogs
by Bruna Filipa Tavares da Costa, Alexandra Teixeira, Joana C. Prata and Daniel Pérez-Mongiovi
Animals 2025, 15(3), 382; https://doi.org/10.3390/ani15030382 (registering DOI) - 28 Jan 2025
Abstract
In Europe, there is a growing concern for animal welfare, encompassing both their rights and health. Consequently, identifying biomarkers that predict serious pathological conditions has become crucial in veterinary medicine. The Buccal Micronucleus Cytome (BMCyt) assay is a minimally invasive method that uses [...] Read more.
In Europe, there is a growing concern for animal welfare, encompassing both their rights and health. Consequently, identifying biomarkers that predict serious pathological conditions has become crucial in veterinary medicine. The Buccal Micronucleus Cytome (BMCyt) assay is a minimally invasive method that uses biomarkers to evaluate DNA damage and chromosomal instability, using exfoliated buccal cells. A rising frequency of anomalies, such as micronuclei formation, strongly indicates an elevated risk of cancer, neurodegenerative diseases, or accelerated aging, potentially originating from exposure to genotoxins and cytotoxins. This method has been validated in humans, but very little research has been conducted on animals. This work aims to provide a detailed description of an optimized method for collecting buccal exfoliated cells in dogs and to characterize a biomarker related to genomic damage using optical and fluorescent microscopy. Samples from dogs in breeding kennels, including pregnant animals, were tested for chromosomal instability. By following procedures similar to those used in humans, we were able to detect and count major nuclear abnormalities. The percentage of micronuclei was higher compared to other studies. Technical aspects, such as avoiding artifacts and ensuring prior training of the operator, must be taken into account. This work validated the BMCyt method for collecting and processing samples in dogs, potentially enhancing the understanding of micronuclei as biomarkers for pre-pathological states in canines. Full article
(This article belongs to the Section Veterinary Clinical Studies)
Show Figures

Figure 1

11 pages, 220 KiB  
Article
Exonic and Intronic WNT10A Variants Isolated from Korean Children with Non-Syndromic Tooth Agenesis
by Yeonjin Ju, Joo Yeon Lee, Woochang Hwang, Jonghyun Shin, Hyung-Sik Kim, Junho K. Hur and Eungyung Lee
Diagnostics 2025, 15(3), 310; https://doi.org/10.3390/diagnostics15030310 - 28 Jan 2025
Abstract
Background/Objectives: Tooth agenesis (TA) is a developmental anomaly prevalent in humans. It is particularly significant in children and adolescents because it is related to esthetic, physiological, and functional problems, including malocclusion, periodontal damage, and insufficient alveolar growth. WNT10A mutations have been identified [...] Read more.
Background/Objectives: Tooth agenesis (TA) is a developmental anomaly prevalent in humans. It is particularly significant in children and adolescents because it is related to esthetic, physiological, and functional problems, including malocclusion, periodontal damage, and insufficient alveolar growth. WNT10A mutations have been identified as the main genetic alterations associated with tooth agenesis. Most previous studies have investigated WNT10A mutations in patients with tooth agenesis using single nucleotide polymorphism (SNP) arrays or exome sequencing. In this study, we conducted a comprehensive profiling of mutations within the exons and introns of WNT10A in Korean patients with non-syndromic tooth agenesis. Methods: Saliva samples were collected from Korean children and adolescents with non-syndromic tooth agenesis. Tagmentation-based sequencing was conducted to acquire mutation information for all exonic and intronic bases of the WNT10A gene. Results: Mutations were detected exclusively in the patient samples: 629C>G and 1100C>T in exon 1, 1977T>C in intron 1, 10256C>T and 10382G>A in exon 3, and 15953G>A in intron 4. Additional mutations were also observed at high ratios in the patient samples. Conclusions: The mutations identified in this study differ from previous findings. These results may provide useful information for understanding the pathogenicity of WNT10A mutations in Korean patients with tooth agenesis and support future diagnostic and therapeutic approaches. Full article
(This article belongs to the Special Issue Insights into Pediatric Genetics)
59 pages, 3383 KiB  
Article
Enhanced Hybrid Deep Learning Models-Based Anomaly Detection Method for Two-Stage Binary and Multi-Class Classification of Attacks in Intrusion Detection Systems
by Hesham Kamal and Maggie Mashaly
Algorithms 2025, 18(2), 69; https://doi.org/10.3390/a18020069 - 28 Jan 2025
Abstract
As security threats become more complex, the need for effective intrusion detection systems (IDSs) has grown. Traditional machine learning methods are limited by the need for extensive feature engineering and data preprocessing. To overcome this, we propose two enhanced hybrid deep learning models, [...] Read more.
As security threats become more complex, the need for effective intrusion detection systems (IDSs) has grown. Traditional machine learning methods are limited by the need for extensive feature engineering and data preprocessing. To overcome this, we propose two enhanced hybrid deep learning models, an autoencoder–convolutional neural network (Autoencoder–CNN) and a transformer–deep neural network (Transformer–DNN). The Autoencoder reshapes network traffic data, addressing class imbalance, and the CNN performs precise classification. The transformer component extracts contextual features, which the DNN uses for accurate classification. Our approach utilizes an enhanced hybrid adaptive synthetic sampling–synthetic minority oversampling technique (ADASYN-SMOTE) for binary classification and enhanced SMOTE for multi-class classification, along with edited nearest neighbors (ENN) for further class imbalance handling. The models were designed to minimize false positives and negatives, improve real-time detection, and identify zero-day attacks. Evaluations based on the CICIDS2017 dataset showed 99.90% accuracy for Autoencoder–CNN and 99.92% for Transformer–DNN in binary classification, and 99.95% and 99.96% in multi-class classification, respectively. On the NF-BoT-IoT-v2 dataset, the Autoencoder–CNN achieved 99.98% in binary classification and 97.95% in multi-class classification, while the Transformer–DNN reached 99.98% and 97.90%, respectively. These results demonstrate the superior performance of the proposed models compared with traditional methods for handling diverse network attacks. Full article
(This article belongs to the Section Algorithms for Multidisciplinary Applications)
Show Figures

Figure 1

39 pages, 25363 KiB  
Article
An Agglomerative Clustering Combined with an Unsupervised Feature Selection Approach for Structural Health Monitoring
by Tales Boratto, Heder Soares Bernardino, Alex Borges Vieira, Tiago Silveira Gontijo, Matteo Bodini, Dmitriy A. Martyushev, Camila Martins Saporetti, Alexandre Cury, Flávio Barbosa and Leonardo Goliatt
Infrastructures 2025, 10(2), 32; https://doi.org/10.3390/infrastructures10020032 - 28 Jan 2025
Viewed by 11
Abstract
Structural health monitoring (SHM) is critical for ensuring the safety and longevity of structures, yet existing methodologies often face challenges such as high data dimensionality, lack of interpretability, and reliance on extensive label datasets. Current research in SHM has primarily focused on supervised [...] Read more.
Structural health monitoring (SHM) is critical for ensuring the safety and longevity of structures, yet existing methodologies often face challenges such as high data dimensionality, lack of interpretability, and reliance on extensive label datasets. Current research in SHM has primarily focused on supervised approaches, which require significant manual effort for data labeling and are less adaptable to new environments. Additionally, the large volume of data generated from dynamic structural monitoring campaigns often includes irrelevant or redundant features, further complicating the analysis and reducing computational efficiency. This study addresses these issues by introducing an unsupervised learning approach for SHM, employing an agglomerative clustering model alongside an unsupervised feature selection technique utilizing box-plot statistics. The proposed method is assessed through raw acceleration signals obtained from four dynamic structural monitoring campaigns, including 44 features with temporal, statistical, and spectral information. In addition, these features are also evaluated in terms of their relevance, and the most important ones are selected for a new execution of the computational procedure. The proposed feature selection not only reduces data dimensionality but also enhances model interpretability, improving the clustering performance in terms of homogeneity, completeness, V-measure, and adjusted Rand score. The results obtained for the four analyzed cases provide clear insights into the patterns of behavior and structural anomalies. Full article
21 pages, 28526 KiB  
Article
Vibration-Based Anomaly Detection for Induction Motors Using Machine Learning
by Ihsan Ullah, Nabeel Khan, Sufyan Ali Memon, Wan-Gu Kim, Jawad Saleem and Sajjad Manzoor
Sensors 2025, 25(3), 773; https://doi.org/10.3390/s25030773 - 27 Jan 2025
Viewed by 218
Abstract
Predictive maintenance of induction motors continues to be a significant challenge in ensuring industrial reliability and minimizing downtime. In this study, machine learning techniques are utilized to enhance fault diagnosis through the use of the Machinery Fault Database (MAFAULDA). A detailed extraction of [...] Read more.
Predictive maintenance of induction motors continues to be a significant challenge in ensuring industrial reliability and minimizing downtime. In this study, machine learning techniques are utilized to enhance fault diagnosis through the use of the Machinery Fault Database (MAFAULDA). A detailed extraction of statistical features was performed on multivariate time-series data to capture essential patterns that could indicate potential faults. Three machine learning algorithms—deep neural networks (DNNs), support vector machines (SVMs), and K-nearest neighbors (KNNs)—were applied to the dataset. Optimization strategies were carefully implemented along with oversampling techniques to improve model performance and handle imbalanced data. The results achieved through these models are highly promising. The SVM model demonstrated an accuracy of 95.4%, while KNN achieved an accuracy of 92.8%. Notably, the combination of deep neural networks with fast Fourier transform (FFT)-based autocorrelation features produced the highest performance, reaching an impressive accuracy of 99.7%. These results provide a novel approach to machine learning techniques in enhancing operational health and predictive maintenance of induction motor systems. Full article
(This article belongs to the Special Issue Fault Diagnosis and Vibration Signal Processing in Rotor Systems)
17 pages, 3899 KiB  
Article
Evaluating Pipeline Inspection Technologies for Enhanced Corrosion Detection in Mining Water Transport Systems
by Víctor Tuninetti, Matías Huentemilla, Álvaro Gómez, Angelo Oñate, Brahim Menacer, Sunny Narayan and Cristóbal Montalba
Appl. Sci. 2025, 15(3), 1316; https://doi.org/10.3390/app15031316 - 27 Jan 2025
Viewed by 293
Abstract
Water transport pipelines in the mining industry face significant corrosion challenges due to extreme environmental conditions, such as arid climates, temperature fluctuations, and abrasive soils. This study evaluates the effectiveness of three advanced inspection technologies—Guided Wave Ultrasonic Testing (GWUT), Metal Magnetic Memory (MMM), [...] Read more.
Water transport pipelines in the mining industry face significant corrosion challenges due to extreme environmental conditions, such as arid climates, temperature fluctuations, and abrasive soils. This study evaluates the effectiveness of three advanced inspection technologies—Guided Wave Ultrasonic Testing (GWUT), Metal Magnetic Memory (MMM), and In-Line Inspection (ILI)—in maintaining pipeline integrity under such conditions. A structured methodology combining diagnostic assessment, technology research, and comparative evaluation was applied, using key performance indicators like detection capability, operational impact, and feasibility. The results show that GWUT effectively identifies surface anomalies and wall thinning over long pipeline sections but faces depth and diameter limitations. MMM excels at detecting early-stage stress and corrosion in inaccessible locations, benefiting from minimal preparation and strong market availability. ILI provides comprehensive internal and external assessments but requires piggable pipelines and operational adjustments, limiting its use in certain systems. A case study of critical aqueducts of mining site water supply illustrates real-world technology selection challenges. The findings underscore the importance of an integrated inspection approach, leveraging the complementary strengths of these technologies to ensure reliable pipeline integrity management. Future research should focus on quantitative performance metrics and cost-effectiveness analyses to optimize inspection strategies for mining infrastructure. Full article
Show Figures

Figure 1

18 pages, 1123 KiB  
Article
Intelligent Upgrading of the Localized GNSS Monitoring System: Profound Integration of Blockchain and AI
by Tianzeng Lu, Yanan Sun, Qinglin Zhu, Xiaolin Zhou, Qiaoyang Li and Jianan Liu
Electronics 2025, 14(3), 490; https://doi.org/10.3390/electronics14030490 - 25 Jan 2025
Viewed by 332
Abstract
With the extensive application of the Global Navigation Satellite System (GNSS), the intelligent upgrading of the GNSS monitoring system is of particular significance. Traditional GNSS monitoring systems typically rely on a centralized architecture, which possesses certain drawbacks when it comes to data tampering, [...] Read more.
With the extensive application of the Global Navigation Satellite System (GNSS), the intelligent upgrading of the GNSS monitoring system is of particular significance. Traditional GNSS monitoring systems typically rely on a centralized architecture, which possesses certain drawbacks when it comes to data tampering, fault tolerance, and data sharing. This paper presents an intelligently upgraded localized GNSS monitoring system that integrates blockchain and artificial intelligence (AI) technology to achieve the deep integration of security, transparency, and intelligent processing of monitoring data. Firstly, this paper employs blockchain technology to guarantee the integrity and tamper-resistance of GNSS monitoring data and utilizes a distributed ledger structure to realize the decentralization of data storage and transmission, thereby enhancing the anti-attack capability and reliability of the system. Secondly, the LSTM model is utilized to analyze and predict the vast amount of monitoring data in real-time, enabling the intelligent detection of GNSS signal anomalies and deviations and providing real-time early warnings to optimize the monitoring effect. Based on this architecture, we also combine the trained model with smart contracts to realize real-time monitoring and early warnings of GNSS satellites. By integrating the security guarantee of blockchain and the intelligent analysis ability of AI, the localized GNSS monitoring system can offer more efficient and accurate data monitoring and management services. In the study, we constructed a prototype system and tested it in both simulated and real environments. The results indicate that the system can effectively identify and respond to GNSS signal anomalies, and enhance the monitoring accuracy and response speed. Additionally, the application of blockchain enhances the immutability and traceability of data, providing a solid foundation for the long-term storage and auditing of GNSS data. The introduction of AI algorithms, especially the application of the Long Short-Term Memory (LSTM) network in anomaly detection, has significantly enhanced the system’s ability to recognize complex patterns. Full article
(This article belongs to the Special Issue AI in Blockchain Assisted Cyber-Physical Systems)
Show Figures

Figure 1

21 pages, 1936 KiB  
Article
Leveraging Quantum Machine Learning to Address Class Imbalance: A Novel Approach for Enhanced Predictive Accuracy
by Seongjun Kwon, Jihye Huh, Sang Ji Kwon, Sang-ho Choi and Ohbyung Kwon
Symmetry 2025, 17(2), 186; https://doi.org/10.3390/sym17020186 - 25 Jan 2025
Viewed by 271
Abstract
The class imbalance problem presents a critical challenge in real-world applications, particularly in high-stakes domains such as healthcare, finance, disaster management, and fault diagnosis, where accurate anomaly detection is paramount. Class imbalance often disrupts the inherent symmetry of data distributions, resulting in suboptimal [...] Read more.
The class imbalance problem presents a critical challenge in real-world applications, particularly in high-stakes domains such as healthcare, finance, disaster management, and fault diagnosis, where accurate anomaly detection is paramount. Class imbalance often disrupts the inherent symmetry of data distributions, resulting in suboptimal performance of traditional machine learning models. Conventional approaches such as undersampling and oversampling are commonly employed to address this issue; however, these methods can introduce additional asymmetries, including information loss and overfitting, which ultimately compromise model efficacy. This study introduces an innovative approach leveraging quantum machine learning (QML), specifically the Variational Quantum Classifier (VQC), to restore and capitalize on the symmetrical properties of data distributions without relying on resampling techniques. By employing quantum circuits optimized to mitigate the asymmetries inherent in imbalanced datasets, the proposed method demonstrates consistently superior performance across diverse datasets, with notable improvements in Recall for minority classes. These findings underscore the potential of quantum machine learning as a robust alternative to classical methods, offering a symmetry-aware solution to class imbalance and advancing QML-driven technologies in fields where equitable representation and symmetry are of critical importance. Full article
(This article belongs to the Section Computer)
24 pages, 5044 KiB  
Article
Autonomous Quality Control of High Spatiotemporal Resolution Automatic Weather Station Precipitation Data
by Hongxiang Ouyang, Zhengkun Qin, Xingsheng Xu, Yuan Xu, Jiang Huangfu, Xiaomin Li, Jiahui Hu, Zixuan Zhan and Junjie Yu
Remote Sens. 2025, 17(3), 404; https://doi.org/10.3390/rs17030404 - 24 Jan 2025
Viewed by 261
Abstract
How to prevent the influence of precipitation’s localized and sudden characteristics is the most formidable challenge in the quality control (QC) of precipitation observations. However, with sufficiently high spatiotemporal resolution in observational data, nuanced information can aid us in accurately distinguishing between intense, [...] Read more.
How to prevent the influence of precipitation’s localized and sudden characteristics is the most formidable challenge in the quality control (QC) of precipitation observations. However, with sufficiently high spatiotemporal resolution in observational data, nuanced information can aid us in accurately distinguishing between intense, localized precipitation events, and anomalies in precipitation data. China has deployed over 70,000 automatic weather stations (AWSs) that provide high spatiotemporal resolution surface meteorological observations. This study developed a new method for performing QC of precipitation data based on the high spatiotemporal resolution characteristics of observations from surface AWSs in China. The proposed QC algorithm uses the cumulative average method to standardize the probability distribution characteristics of precipitation data and further uses the empirical orthogonal function (EOF) decomposition method to effectively identify the small-scale spatial structure of precipitation data. Leveraging the spatial correlation characteristics of precipitation, partitioned EOF detection with a 0.5° spatial coverage effectively minimizes the influence of local precipitation on quality control. Analysis of precipitation probability distribution reveals that reconstruction based on the first three EOF modes can accurately capture the organized structural features of precipitation within the detection area. Thereby, based on the randomness characteristics of the residuals, when the residual of a certain observation is greater than 2.5 times the standard deviation calculated from all residuals in the region, it can be determined that the data are erroneous. Although the quality control is primarily aimed at accumulated precipitation, the randomness of erroneous data indicates that 84 continuous instances of error data in accumulated precipitation can effectively trace back to erroneous hourly precipitation observations. This ultimately enables the QC of hourly precipitation data from surface AWSs. Analysis of the QC of precipitation data from 2530 AWSs in Jiangxi Province (China) revealed that the new method can effectively identify incorrect precipitation data under the conditions of extreme weather and complex terrain, with an average rejection rate of about 5%. The EOF-based QC method can accurately detect strong precipitation events resulting from small-scale weather disturbances, thereby preventing local heavy rainfall from being incorrectly classified as erroneous data. Comparison with the quality control results in the Tianqing System, an operational QC system of the China Meteorological Administration, revealed that the proposed method has advantages in handling extreme and scattered outliers, and that the precipitation observation data, following quality control procedures, exhibits enhanced similarity with the CMAPS merged precipitation data. The novel quality control approach not only elevates the average spatial correlation coefficient between the two datasets by 0.01 but also diminishes the root mean square error by 1 mm. Full article
21 pages, 1003 KiB  
Article
Neural Network Based Power Meter Wiring Fault Recognition of Smart Grids Under Abnormal Reactive Power Compensation Scenarios
by Huizhe Zheng, Zhongshuo Lin, Huan Lin, Chaokai Huang, Xiaoqi Huang, Suna Ji and Xiaoshun Zhang
Energies 2025, 18(3), 545; https://doi.org/10.3390/en18030545 - 24 Jan 2025
Viewed by 287
Abstract
This paper explores the challenges of detecting wiring anomalies in three-phase, four-wire energy metering devices, especially when large amounts of reactive power compensation are involved. Traditional methods, such as the hexagon phasor diagram technique, perform well under standard loads, but struggle to adapt [...] Read more.
This paper explores the challenges of detecting wiring anomalies in three-phase, four-wire energy metering devices, especially when large amounts of reactive power compensation are involved. Traditional methods, such as the hexagon phasor diagram technique, perform well under standard loads, but struggle to adapt to new situations, such as over- or under-compensation. To overcome these limitations, this paper proposes a hybrid approach that combines mechanism-based knowledge with data-driven technologies, including backpropagation neural networks (BPNNs). This method improves the accuracy and efficiency of anomaly detection and can better adapt to a dynamic power environment. The result is improved universality of anomaly detection, which helps to achieve safer, more accurate, and more efficient smart grid operation in complex situations. Full article
22 pages, 3342 KiB  
Article
Detection of Pipe Ruptures in Shipboard Firefighting Systems Using Machine Learning and Deep Learning Techniques
by Sara Ferreno-Gonzalez, Vicente Diaz-Casas, Marcos Miguez-Gonzalez and Carlos G. San-Gabino
Appl. Sci. 2025, 15(3), 1181; https://doi.org/10.3390/app15031181 - 24 Jan 2025
Viewed by 263
Abstract
In this paper, the application of machine learning and deep learning algorithms for fault and failure detection in maritime systems is examined, specifically focusing on the detection of pipe ruptures in a ship’s saltwater firefighting (FiFi) system using pressure sensor data. Neural network [...] Read more.
In this paper, the application of machine learning and deep learning algorithms for fault and failure detection in maritime systems is examined, specifically focusing on the detection of pipe ruptures in a ship’s saltwater firefighting (FiFi) system using pressure sensor data. Neural network models were developed to distinguish between normal operational states and anomalies, as well as to accurately locate pipe faults within the ship. Data were collected using real-world tests with FiFi system sensors, capturing both normal operations and simulated pipe ruptures, and were meticulously labeled to facilitate neural network training. Two neural network models were introduced: one for classifying system states (normal or anomalous) based on time-series pressure data, and another for identifying the location of anomalies related to pipe ruptures. Experimental results demonstrated the efficacy of these models in detecting and localizing pipe faults, with performance evaluated using mean squared error (MSE) across different network configurations. The successful implementation of these machine learning and deep learning algorithms highlights their potential for enhancing maritime safety and operational efficiency. Full article
(This article belongs to the Special Issue The Internet of Things (IoT) and Its Application in Monitoring)
Show Figures

Figure 1

18 pages, 1716 KiB  
Article
Investigating the Potential of Latent Space for the Classification of Paint Defects
by Doaa Almhaithawi, Alessandro Bellini, Georgios C. Chasparis and Tania Cerquitelli
J. Imaging 2025, 11(2), 33; https://doi.org/10.3390/jimaging11020033 - 24 Jan 2025
Viewed by 356
Abstract
Defect detection methods have greatly assisted human operators in various fields, from textiles to surfaces and mechanical components, by facilitating decision-making processes and reducing visual fatigue. This area of research is widely recognized as a cross-industry concern, particularly in the manufacturing sector. Nevertheless, [...] Read more.
Defect detection methods have greatly assisted human operators in various fields, from textiles to surfaces and mechanical components, by facilitating decision-making processes and reducing visual fatigue. This area of research is widely recognized as a cross-industry concern, particularly in the manufacturing sector. Nevertheless, each specific application brings unique challenges that require tailored solutions. This paper presents a novel framework for leveraging latent space representations in defect detection tasks, focusing on improving explainability while maintaining accuracy. This work delves into how latent spaces can be utilized by integrating unsupervised and supervised analyses. We propose a hybrid methodology that not only identifies known defects but also provides a mechanism for detecting anomalies and dynamically adapting to new defect types. This dual approach supports human operators, reducing manual workload and enhancing interpretability. Full article
(This article belongs to the Section AI in Imaging)
Show Figures

Figure 1

17 pages, 20460 KiB  
Article
Integration of Arc and Microstructural Analysis for Anomaly Detection in Walls Manufactured by GMA-Based WAAM
by Lucas J. E. B. Santos, Joyce I. V. Souto, Igo J. S. Azevedo, Walman B. Castro, Jefferson S. Lima, João M. P. Q. Delgado, Renato A. C. Santana, Ricardo S. Gomez, André L. D. Bezerra and Antonio G. B. Lima
Metals 2025, 15(2), 110; https://doi.org/10.3390/met15020110 - 24 Jan 2025
Viewed by 310
Abstract
Wire Arc Additive Manufacturing (WAAM) is a process for fabricating metal parts known for its high productivity and material flexibility. However, defects such as overheating, residual stresses, distortions, porosity, and a non-homogeneous microstructure limit its commercial applications. Therefore, the present study aims to [...] Read more.
Wire Arc Additive Manufacturing (WAAM) is a process for fabricating metal parts known for its high productivity and material flexibility. However, defects such as overheating, residual stresses, distortions, porosity, and a non-homogeneous microstructure limit its commercial applications. Therefore, the present study aims to analyze the correlation between electrical sensing anomalies in the Gas Metal Arc (GMA) during WAAM and the occurrence of microscopic defects caused by external contamination. To achieve this, experiments were conducted to fabricate walls using WAAM with controlled contaminant introduction. Simultaneously, electrical arc data, specifically voltage and current, were segmented and acquired during the wall deposition process. Metallographic analysis confirmed the presence of microscopic defects or changes in the solidification patterns in regions with contaminant inclusion, distinguishing them from other areas of the analyzed samples. Similarly, the contaminations were proven to cause anomalies in attributes associated with the electrical arc. Therefore, this approach confirms the criticality of electrical arc monitoring in WAAM, as it demonstrates that anomalies in the electrical arc could lead to microstructural consequences. Full article
Show Figures

Figure 1

24 pages, 534 KiB  
Article
Anomaly Detection in High-Dimensional Time Series Data with Scaled Bregman Divergence
by Yunge Wang, Lingling Zhang, Tong Si, Graham Bishop and Haijun Gong
Algorithms 2025, 18(2), 62; https://doi.org/10.3390/a18020062 - 24 Jan 2025
Viewed by 317
Abstract
The purpose of anomaly detection is to identify special data points or patterns that significantly deviate from the expected or typical behavior of the majority of the data, and it has a wide range of applications across various domains. Most existing statistical and [...] Read more.
The purpose of anomaly detection is to identify special data points or patterns that significantly deviate from the expected or typical behavior of the majority of the data, and it has a wide range of applications across various domains. Most existing statistical and machine learning-based anomaly detection algorithms face challenges when applied to high-dimensional data. For instance, the unconstrained least-squares importance fitting (uLSIF) method, a state-of-the-art anomaly detection approach, encounters the unboundedness problem under certain conditions. In this study, we propose a scaled Bregman divergence-based anomaly detection algorithm using both least absolute deviation and least-squares loss for parameter learning. This new algorithm effectively addresses the unboundedness problem, making it particularly suitable for high-dimensional data. The proposed technique was evaluated on both synthetic and real-world high-dimensional time series datasets, demonstrating its effectiveness in detecting anomalies. Its performance was also compared to other density ratio estimation-based anomaly detection methods. Full article
(This article belongs to the Special Issue Machine Learning Models and Algorithms for Image Processing)
Show Figures

Figure 1

29 pages, 1721 KiB  
Review
Cybersecurity of Automotive Wired Networking Systems: Evolution, Challenges, and Countermeasures
by Nicasio Canino, Pierpaolo Dini, Stefano Mazzetti, Daniele Rossi, Sergio Saponara and Ettore Soldaini
Electronics 2025, 14(3), 471; https://doi.org/10.3390/electronics14030471 - 24 Jan 2025
Viewed by 462
Abstract
The evolution of Electrical and Electronic (E/E) architectures in the automotive industry has been a significant factor in the transformation of vehicles from traditional mechanical systems to sophisticated, software-defined machines. With increasing vehicle connectivity and the growing threats from cyberattacks that could compromise [...] Read more.
The evolution of Electrical and Electronic (E/E) architectures in the automotive industry has been a significant factor in the transformation of vehicles from traditional mechanical systems to sophisticated, software-defined machines. With increasing vehicle connectivity and the growing threats from cyberattacks that could compromise safety and violate user privacy, the incorporation of cybersecurity into the automotive development process is becoming imperative. As vehicles evolve into sophisticated interconnected systems, understanding their vulnerabilities becomes essential to improve cybersecurity. This paper also discusses the role of evolving standards and regulations, such as ISO 26262 and ISO/SAE 21434, in ensuring both the safety and cybersecurity of modern vehicles. This paper offers a comprehensive review of the current challenges in automotive cybersecurity, with a focus on the vulnerabilities of the Controller Area Network (CAN) protocol. Additionally, we explore state-of-the-art countermeasures, focusing on Intrusion Detection Systems (IDSs), which are increasingly leveraging artificial intelligence and machine learning techniques to detect anomalies and prevent attacks in real time. Through an analysis of publicly available CAN datasets, we evaluate the effectiveness of IDS frameworks in mitigating these threats. Full article
(This article belongs to the Special Issue Machine Learning and Cybersecurity—Trends and Future Challenges)
Show Figures

Graphical abstract

Back to TopTop