Search

Sea surface target detection is a key stage in a typical target detection system and directly influences the performance of the whole system. As an effective discriminator, the one-class support vector machine (OCSVM) has been widely used in target detection. In OCSCM, training samples are first mapped to the hypersphere in the kernel space with the Gaussian kernel function, and then, a linear classification hyperplane is constructed in each cluster to separate target samples from other classes of samples. However, when the distribution of the original data is complex, the transformed data in the kernel space may be nonlinearly separable. In this situation, OCSVM cannot classify the data correctly, because only a linear hyperplane is constructed in the kernel space. To solve this problem, a novel one-class classification algorithm, referred to as ensemble one-class support vector machine (En-OCSVM), is proposed in this paper. En-OCSVM is a hybrid model based on k -means clustering and OCSVM. In En-OCSVM, training samples are clustered in the kernel space with the k -means clustering algorithm, while a linear decision hyperplane is constructed in each cluster. With the combination of multiple linear classification hyperplanes, a complex nonlinear classification boundary can be achieved in the kernel space. Moreover, the joint optimization of the k -means clustering model and OCSVM model is realized in the proposed method, which ensures the linear separability of each cluster. The experimental results based on the synthetic dataset, benchmark datasets, IPIX datasets, and SAR real data demonstrate the better performance of our method over other related methods. [ABSTRACT FROM AUTHOR]

Multiple variable splitting is a general technique for decomposing problems by using copies of variables and additional linking constraints that equate their values. The resulting large optimization problem can be solved with a specialized interior-point method that exploits the problem structure and computes the Newton direction with a combination of direct and iterative solvers (i.e. Cholesky factorizations and preconditioned conjugate gradients for linear systems related to, respectively, subproblems and new linking constraints). The present work applies this method to solving real-world binary classification and novelty (or outlier) detection problems by means of, respectively, two-class and one-class linear support vector machines (SVMs). Unlike previous interior-point approaches for SVMs, which were practical only with low-dimensional points, the new proposal can also deal with high-dimensional data. The new method is compared with state-of-the-art solvers for SVMs that are based on either interior-point algorithms (such as SVM-OOPS) or specific algorithms developed by the machine learning community (such as LIBSVM and LIBLINEAR). The computational results show that, for two-class SVMs, the new proposal is competitive not only against previous interior-point methods—and much more efficient than they are with high-dimensional data—but also against LIBSVM, whereas LIBLINEAR generally outperformed the proposal. For one-class SVMs, the new method consistently outperformed all other approaches, in terms of either solution time or solution quality. [ABSTRACT FROM AUTHOR]

A new solution to the problem of offline signature verification is presented. Digital images of signatures are processed and converted into a binary representation of a certain size. Then their contours are traced, and from them, two original features are calculated for describing the local structural features of the signature in the form of vectors of normalized frequency distributions of local binary pattern codes and values of local curvature of the signature contours. A new feature space is formed in which the pattern describes the proximity of pairs of signatures, and its coordinates are the rank correlation coefficients between the feature vectors of these signatures. In real practice, the expert has M (from 5 to 15) genuine signatures of a person; there are no forged signatures at all. On these M available genuine signatures of a single person, we train a one-class support vector machine model and obtain a single-writer-dependent classifier. A verifiable signature is considered forged if the classifier model considers it to be an outlier. The accuracy of our approach in verifying the genuineness of all 2640 signatures from the CEDAR database was 99.77%. All forged signatures in this database were correctly recognized. [ABSTRACT FROM AUTHOR]

This study presents a comprehensive evaluation of five prominent unsupervised machine learning anomaly detection algorithms: One-Class Support Vector Machine (One-Class SVM), One-Class SVM with Stochastic Gradient Descent (SGD), Isolation Forest (iForest), Local Outlier Factor (LOF), and Robust Covariance (Elliptic Envelope). Through systematic analysis on a synthetically simulated dataset, the study assessed each algorithm’s predictive performance using accuracy, precision, recall, and F1 score specifically for outlier detection. The evaluation reveals that One-Class SVM, Isolation Forest, and Robust Covariance are more effective in identifying outliers in the synthetic simulated dataset, with Isolation Forest slightly outperforming the other algorithms in terms of balancing precision and recall. One-Class SVM with SGD shows promise in precision but needs adjustment to improve recall. Local Outlier Factor may require parameter tuning or may not be as suitable for this particular dataset’s characteristics. The findings reveal significant variations in performance, highlighting the strengths and limitations of each method in identifying anomalies. This research contributes to the field of machine learning by demonstrating that the selection of an anomaly detection algorithm should be a considered decision, taking into account the specific characteristics of the data and the operational context of its application. Future work should explore parameter optimization, the impact of dataset characteristics on model performance, and the application of these models to real-world datasets to validate their efficacy in practical anomaly detection scenarios.

The conventional way of respiratory coronavirus disease 2019 (COVID-19) diagnosis is reverse transcription polymerase chain reaction (RT-PCR), which is less sensitive during early stages; especially if the patient is asymptomatic, which may further cause more severe pneumonia. In this context, several deep learning models have been proposed to identify pulmonary infections using publicly available chest X-ray (CXR) image datasets for early diagnosis, better treatment and quick cure. In these datasets, the presence of less number of COVID-19 positive samples compared to other classes (normal, pneumonia and Tuberculosis) raises the challenge for unbiased learning of deep learning models. This learning problem can be considered as one-class classification problem where the target class samples are present and other classes are absent or ill-defined. All deep learning models opted class balancing techniques to solve this issue; which however should be avoided in any medical diagnosis process. Moreover, the deep learning models are also data hungry and need massive computation resources. Therefore, for quicker diagnosis, this research proposes a novel pinball loss function based one-class support vector machine (PB-OCSVM), that can work in presence of limited COVID-19 positive CXR samples (target class or class-of-interest (CoI) samples) with objectives to maximize the learning efficiency and to minimize the false predictions. The performance of the proposed model is compared with conventional OCSVM and recent deep learning models, and the experimental results prove that the proposed model outperformed state-of-the-art methods. To validate the robustness of the proposed model, experiments are also performed with noisy CXR images and UCI benchmark datasets. [ABSTRACT FROM AUTHOR]

Copyright of Journal of National University of Defense Technology / Guofang Keji Daxue Xuebao is the property of NUDT Press and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The goal of change point detection (CPD) is to identify abrupt changes in the statistics of signals or time series that reflect transitions in the underlying system's properties or states. While many statistical and learning-based approaches have been proposed to address this task, most state-of-the-art methods still treat this problem in an unsupervised setting. As a result, there is often a large gap between the algorithm-detected results and the expected outcomes of the user. To bridge this gap, we propose an active-learning strategy for the CPD problem that combines with the one-class support vector machine (OCSVM) model, resulting in an interactive CPD algorithm that improves itself by querying the end-user. This approach enables us to focus on detecting the desired change points and ignore false-positives or irrelevant change points. We demonstrate that the interactive OCSVM model can be combined with various unsupervised CPD models to function in a semi-supervised setting, resulting in improved detection accuracy. Our experimental results on various simulated and real-life datasets demonstrate a significant improvement in detection performance on both single- and multi-channel time series, even with a limited number of queries. [ABSTRACT FROM AUTHOR]

Anomaly in geoacoustic emission is an important earthquake precursor. Current geoacoustic anomaly detection methods are limited by their low signal-to-noise ratio, low intensity, sample imbalance, and low accuracy. Therefore, this paper proposes a clone selection algorithm optimized one-class support vector machine method (CSA-OCSVM) for geoacoustic anomaly detection. First, the interquartile range (IQR), cubic spline interpolation, and time window are designed to amplify the geoacoustic signal intensity and energy change rules to reduce the interference of geoacoustic signal noise and intensity. Secondly, to address the imbalance of positive and negative samples in geoacoustic anomaly detection, a one-class support vector machine is introduced for anomaly detection. Meanwhile, in view of the optimization capabilities of the clone selection algorithm, it is adopted to optimize the hyperparameters of OCSVM to improve its detection accuracy. Finally, the proposed model is applied to geoacoustic data anomaly detection in nine different datasets, which are derived from our self-developed acoustic electromagnetic to AI (AETA) system, to verify its effectiveness. By designing comparative experiments with IQR, genetic algorithm OCSVM (GA-OCSVM), particle swarm optimization OCSVM (PSO-OCSVM), and evaluating the performance of the true positive rate (TPR) and false positive rate (FPR), the experimental results depict that the proposed model is superior to the existing state-of-the-art geoacoustic anomaly detection approaches. [ABSTRACT FROM AUTHOR]

This study evaluates the potential for mineral prospectivity mapping (MPM) within the Kerkesha area, southwestern Eritrea, using remote sensing and geochemical data analysis. The Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER) remote sensing data were used for mapping zones of hydrothermal alteration, while assessment of geologic structures was based on automated extraction of lineaments from a digital elevation model (DEM). Integration of these alteration and structural datasets with surface geochemical data was carried out to identify pathfinder elements associated with Au–Cu–Zn mineralization as well as to evaluate and delineate anomalous regions in this relatively underexplored region of the Arabia Nubia Shield (ANS). Specifically, the modeling approach for the extraction and interpretation of mineralization-related spectral footprints was the selective principal component analysis (SPCA), and the lineament features extracted from DEM derivatives were integrated with the soil geochemical data and modeled by principal component analysis (PCA). The results revealed a NE–SW trend of lineaments, delineated zones of hydrothermal alteration indicating the presence of multi-deposit type mineralization, and identified pathfinder elements. In addition, Au–Cu–Zn anomalous zones were extracted by one-class support vector machine (OCSVM) and the performance of such classification was validated by the area under the curve (AUC) and the Youden index computed from receiver operating characteristic (ROC) curves and the Kruskal–Wallis test. The results showed significance in differences between the anomalous and non-anomalous zones and existence of a relationship between known mineral deposits and predicted anomalies. The proposed MPM shows promising results for robust automated delineation and understanding of mineralization processes. [ABSTRACT FROM AUTHOR]

Sea surface target detection is a key stage in a typical target detection system and directly influences the performance of the whole system. As an effective discriminator, the one-class support vector machine (OCSVM) has been widely used in target detection. In OCSCM, training samples are first mapped to the hypersphere in the kernel space with the Gaussian kernel function, and then, a linear classification hyperplane is constructed in each cluster to separate target samples from other classes of samples. However, when the distribution of the original data is complex, the transformed data in the kernel space may be nonlinearly separable. In this situation, OCSVM cannot classify the data correctly, because only a linear hyperplane is constructed in the kernel space. To solve this problem, a novel one-class classification algorithm, referred to as ensemble one-class support vector machine (En-OCSVM), is proposed in this paper. En-OCSVM is a hybrid model based on k-means clustering and OCSVM. In En-OCSVM, training samples are clustered in the kernel space with the k-means clustering algorithm, while a linear decision hyperplane is constructed in each cluster. With the combination of multiple linear classification hyperplanes, a complex nonlinear classification boundary can be achieved in the kernel space. Moreover, the joint optimization of the k-means clustering model and OCSVM model is realized in the proposed method, which ensures the linear separability of each cluster. The experimental results based on the synthetic dataset, benchmark datasets, IPIX datasets, and SAR real data demonstrate the better performance of our method over other related methods.

This study investigates the impact of assimilating Aircraft Meteorological Data Relay (AMDAR) observations on the prediction of two typhoons, Nesat and Haitang (2017), using the Gridpoint Statistical Interpolation (GSI) assimilation system and the Weather Research and Forecasting (WRF) model. Two quality control (QC) methods, Minimum Covariance Determinant (MCD) and one-class Support Vector Machine (OCSVM), were employed to perform QC on the AMDAR observations before data assimilation. The QC results indicated that both methods significantly reduced kurtosis, skewness, and discrepancies between the AMDAR data and the reanalysis data. The data distribution after applying the MCD-QC method exhibited a closer resemblance to a Gaussian distribution. Four numerical experiments were conducted to assess the impact of different AMDAR data qualities on typhoon forecasting, including a control experiment without data assimilation (EXP-CNTL), assimilating all AMDAR observations (EXP-RAW), assimilating observations after applying MCD-QC (EXP-MCD), and assimilating observations after applying OCSVM-QC (EXP-SVM). The results demonstrated that using AMDAR data in assimilation improved the track and intensity prediction of the typhoons. Furthermore, utilizing QC before assimilation enhanced the performance of track forecasting prediction, with EXP-MCD showing the best performance. As for intensity prediction, the three assimilation experiments exhibited varying strengths and weaknesses at different times, with EXP-MCD showing smaller intensity forecast errors on average. [ABSTRACT FROM AUTHOR]

The existing one-class support vector machine algorithms are based on the idea of "minimum margin". They consider only the noise close to the space origin and are sensitive to noise. The purpose of this paper is to improve the anti-noise ability of the one-class support vector machine through the idea of "optimal margin distribution", which considers both of the noise close to the space origin and that far from the space origin. This paper proposes a novel One-Class Optimal Margin Distribution Machine (OCODM) method. This method maximizes the margin and minimizes the margin variance to optimize the margin distribution. The experimental results have shown that compared to the existing one-class support vector machine algorithms, this method has better robustness. The conclusion is that this method is a supplement of the existing one-class support vector machine algorithms and can enhance the anti-noise ability of existing methods. [ABSTRACT FROM AUTHOR]

With the rapid development of the Internet,the security of network equipment has received extensive attention.Aiming at the problems of that the existing network equipment anomaly detection technology is destructive and difficult to detect,the paper uses the packets delay spent by the network equipment to transmit and process data packets as the detection basis,and proposes an anomaly detection scheme based on delay characteristics.The proposed scheme adopts side channel analysis,and it does not need to upgrade the equipment's software or hardware.It has the characteristics of non-intrusive and easy to implement.Firstly,the method uses the high-precision timing technology time stamp machine to collect the time delay information,and uses the genetic algorithm to extract the peak position feature of the delay distribution.Secondly,to solve the problem of the imbalance of data set,the method uses one-class support vector machine algorithm to construct anomaly detection algorithm.Finally,the validity of the method is verified by building an experimental platform,and the experimental results are evaluated.Experimental results show that the proposed method is feasible and effective.

The signature is a behavioral-based human characteristics that is extensively used as legal evidence of identification on bank checks, credit cards, and wills. Developing a good offline signature verification (OSV) system is essential to avoid fraud. Due to the plurality of signature styles and sample contexts, feature extraction (FE) is challenging for OSV systems. Current signature verification methods present promising results in distinguishing between genuine and forged signatures, but they are far from satisfactory. Regarding feature selection (FS), stable and appropriate features substantially impact signature verification. The issue with current approaches is that they apply combination features without addressing correlation and discriminant. A genetic algorithm (GA) is popularly deployed as a method for optimization to identify the best features. Regrettably, GA has drawbacks when the search dimension is expanded, such as a lack of comprehensive exploitation, difficulties in achieving good convergence, and therefore increased computation. This study addresses the aforementioned challenges by introducing multifeature fusion and discriminant FS using a novel quantum inspired GA (QIGA). QIGAs are constructed using quantum computing concepts such as qubits (Q-bits) and superposition of states. QIGA is able to express a linear superposition of solutions with the objective of increasing gene diversity by utilizing the qubit as a representation. Quantum rotation computing (QRC) enhances population diversity and tackles computing complexity and early convergence issues in GA. The superposition concept in QRC utilizes both mutation (divergence) and crossover (convergence) procedures to expand diversity and improve population selection. QIGA performs better in a parallel structure because of its quick convergence and robust global search capabilities. This implies that QIGA embodies features of both exploration and exploitation. The studied approach is applied to three different databases of signatures: SID-Arabic handwritten signatures, CEDAR, and UTSIG. Consequently, the proposed OSV based on the QIGA improved equal error rate (EER) between 10% and 20% over the GA without influencing computation complexity.

Copyright of Journal of Nanchang University (Engineering & Technology) is the property of Nanchang University and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Network Intrusion Detection Systems(NIDSs) are crucial for resisting cyber threats. However, NIDSs equipped with supervised learning models do not generalize well to unknown attacks because the training samples for previously unseen new intrusions are usually not available in advance. Thus, a new framework based on a Hierarchical Attention-based Triplet network with Unsupervised Domain Adaptation(HAT-UDA) is proposed for this purpose. Concretely, a joint loss is introduced to force HAT-UDA to learn compact and discriminative embeddings for benign network traffic while being far from the representations of known attacks. Then, a One-class Support Vector Machine(OCSVM) model is trained on top of the benign embeddings for the unknown attack detection task. Furthermore, we propose an unsupervised domain adaptation module in an adversarial manner to reduce the false positives of HAT-UDA when applied to new network scenarios. HAT-UDA provides a novel approach for building a robust NIDS from benign traffic and available (known) attacks. This is particularly meaningful since collecting samples for benign traffic and known attacks is much easier than obtaining instances for unseen new attacks. Extensive experiments show that HAT-UDA outperforms other state-of-the-art methods and significantly improves the detection rate of unknown attacks. [ABSTRACT FROM AUTHOR]

Modern production lines for molded plastic parts often have automated inspection systems to detect defective parts reliably and efficiently. However, these conventional inspection systems have low flexibility and versatility, leading to difficulties when dealing with complicated requests such as when small quantities of many different parts are manufactured on the same production line. The proposed system can be implemented quickly using low-cost off-the-shelf components and does not require accurate alignment of production parts, reducing the need for manual inspections and increasing work efficiency when handling complex workloads. The inspection algorithm combines higher-order local auto correlation (HLAC) features with one-class support vector machine (one-class SVM) and principal component analysis (PCA) to extract, transform, and classify the differential feature vector between conforming and nonconforming plastic parts. To verify its validity and effectiveness, we compared defect detection accuracy and speed between the developed inspection system and manual inspection experimentally. Extremely high accuracy (Recall = 0.93, Specificity = 1.00) and speed (10 inspections in 30[sec]) was obtained with 7 types (1 conforming type, 6 nonconforming types) of sample parts (30 samples each). We demonstrated a 400 % increase in speed can be gained relative to manual inspection.

Recently, signature verification systems have been widely adopted for verifying individuals based on their handwritten signatures, especially in forensic and commercial transactions. Generally, feature extraction and classification tremendously impact the accuracy of system authentication. Feature extraction is challenging for signature verification systems due to the diverse forms of signatures and sample circumstances. Current signature verification techniques demonstrate promising results in identifying genuine and forged signatures. However, the overall performance of skilled forgery detection remains rigid to deliver high contentment. Furthermore, most of the current signature verification techniques demand a large number of learning samples to increase verification accuracy. This is the primary disadvantage of using deep learning, as the figure of signature samples is mainly restricted to the functional application of the signature verification system. In addition, the system inputs are scanned signatures that comprise noisy pixels, a complicated background, blurriness, and contrast decay. The main challenge has been attaining a balance between noise and data loss, since some essential information is lost during preprocessing, probably influencing the subsequent stages of the system. This paper tackles the aforementioned issues by presenting four main steps: preprocessing, multifeature fusion, discriminant feature selection using a genetic algorithm based on one class support vector machine (OCSVM-GA), and a one-class learning strategy to address imbalanced signature data in the practical application of a signature verification system. The suggested method employs three databases of signatures: SID-Arabic handwritten signatures, CEDAR, and UTSIG. Experimental results depict that the proposed approach outperforms current systems in terms of false acceptance rate (FAR), false rejection rate (FRR), and equal error rate (EER). [ABSTRACT FROM AUTHOR]

The signature is a behavioral-based human characteristics that is extensively used as legal evidence of identification on bank checks, credit cards, and wills. Developing a good offline signature verification (OSV) system is essential to avoid fraud. Due to the plurality of signature styles and sample contexts, feature extraction (FE) is challenging for OSV systems. Current signature verification methods present promising results in distinguishing between genuine and forged signatures, but they are far from satisfactory. Regarding feature selection (FS), stable and appropriate features substantially impact signature verification. The issue with current approaches is that they apply combination features without addressing correlation and discriminant. A genetic algorithm (GA) is popularly deployed as a method for optimization to identify the best features. Regrettably, GA has drawbacks when the search dimension is expanded, such as a lack of comprehensive exploitation, difficulties in achieving good convergence, and therefore increased computation. This study addresses the aforementioned challenges by introducing multifeature fusion and discriminant FS using a novel quantum inspired GA (QIGA). QIGAs are constructed using quantum computing concepts such as qubits (Q-bits) and superposition of states. QIGA is able to express a linear superposition of solutions with the objective of increasing gene diversity by utilizing the qubit as a representation. Quantum rotation computing (QRC) enhances population diversity and tackles computing complexity and early convergence issues in GA. The superposition concept in QRC utilizes both mutation (divergence) and crossover (convergence) procedures to expand diversity and improve population selection. QIGA performs better in a parallel structure because of its quick convergence and robust global search capabilities. This implies that QIGA embodies features of both exploration and exploitation. The studied approach is applied to three different databases of signatures: SID-Arabic handwritten signatures, CEDAR, and UTSIG. Consequently, the proposed OSV based on the QIGA improved equal error rate (EER) between 10% and 20% over the GA without influencing computation complexity. [ABSTRACT FROM AUTHOR]

Intrusion detection systems (IDSs) play a significant role in the field of network security, dealing with the ever-increasing number of network threats. Machine learning-based IDSs have attracted a lot of interest owing to their powerful data-driven learning capabilities. However, it is challenging to train the supervised learning algorithms when there are no attack data at hand. Semi-supervised anomaly detection algorithms, which train the model with only normal data, are more suitable. In this study, we propose a novel semi-supervised anomaly detection-based IDS that leverages the capabilities of representation learning and two anomaly detectors. In detail, the autoencoder (AE) is applied to extract representative features of normal data in the first step, and then two semi-supervised detectors, the one-class support vector machine (OCSVM) and Gaussian mixture model (GMM), are trained on the derived features. The two detectors collaborate to detect anomalous samples. The OCSVM predicts the abnormal samples initially, and after that, the GMM is applied to recheck the misclassified samples further. The experiments demonstrate that the AE improves the detection rate, and two detectors are more promising than a single one. [ABSTRACT FROM AUTHOR]

The environmental regulations on vessels being strengthened by the International Maritime Organization has led to a steady growth in the eco-friendly ship market. Related research is being actively conducted, including many studies on the maintenance and predictive maintenance of propulsion systems (including electric motors and rotating bodies) in electric propulsion vessels. The present study intends to enhance the artificial intelligence (AI)-based failure-diagnosis rate for electric propulsion vessel propulsion systems. To verify the proposed AI-based failure diagnosis algorithm for electric motors, this study utilized the vibration data of mechanical equipment (electric motors) in an urban railway station. Securing and preprocessing high-quality data is crucial for improving the failure-diagnosis rate, in addition to the performance of the diagnostic algorithm. However, the conventional wavelet transform method, which is generally used for machine signal processing, has a disadvantage of data losswhen the data distribution is abnormal or skewed. This study, to overcome this shortcoming, proposes an AI-based denoising auto encoder (DAE) method that can remove noise while maintaining data characteristics for signal processing of mechanical equipment. This study preprocessed vibration data by using the DAE method, and extracted significant features from the data through the feature extraction method. The extracted features were utilized to train the one-class support vector machinemodel and to allow the model to diagnose the failure. Finally, the F-1 score was calculated by using the failure diagnosis results, and the most meaningful feature extraction method was determined for the vibration data. In addition, this study compared and evaluated the preprocessing performance based on the DAE and the wavelet transform methods. [ABSTRACT FROM AUTHOR]

The network system has become an indispensable component of modern infrastructure. DDoS attacks and their variants remain a potential and persistent cybersecurity threat. DDoS attacks block services to legitimate users by incorporating large amounts of malicious traffic in a short period or depleting system resources through methods specific to each client, causing the victim to lose reputation, finances, and potential customers. With the advancement and maturation of artificial intelligence technology, machine learning and deep learning are widely used to detect DDoS attacks with significant success. However, traditional supervised machine learning must depend on the categorized training sets, so the recognition rate plummets when the model encounters patterns outside the dataset. In addition, DDoS attack techniques continue to evolve, rendering training based on conventional data models unable to meet contemporary requirements. Since closed-set classifiers have excellent performance in cybersecurity and are quite mature, this study will investigate the identification of open-set recognition issues where the attack pattern does not accommodate the distribution learned by the model. This research proposes a framework that uses reconstruction error and distributes hidden layer characteristics to detect unknown DDoS attacks. This study will employ deep hierarchical reconstruction nets (DHRNet) architecture and reimplement it with a 1D integrated neural network employing loss function combined with spatial location constraint prototype loss (SLCPL) as a solution for open-set risks. At the output, a one-class SVM (one-class support vector machine) based on a random gradient descent approximation is used to recognize the unknown patterns in the subsequent stage. The model achieves an impressive detection rate of more than 99% in testing. Furthermore, the incremental learning module utilizing unknown traffic labeled by telecom technicians during tracking has enhanced the model's performance by 99.8% against unknown threats based on the CICIDS2017 Friday open dataset. [ABSTRACT FROM AUTHOR]

Hyperspectral anomaly detection is a popular research direction for hyperspectral images; however, it is problematic because it separates the background and anomaly without prior target information. Currently, deep neural networks are used as an extractor to mine intrinsic features in hyperspectral images, which can be fed into separate anomaly detection methods to improve their performances. However, this hybrid approach is suboptimal because the subsequent detector is unable to drive the data representation in hidden layers, which makes it a challenge to maximize the capabilities of deep neural networks when extracting the underlying features customized for anomaly detection. To address this issue, a novel unsupervised, self-attention-based, one-class neural network (SAOCNN) is proposed in this paper. SAOCNN consists of two components: a novel feature extraction network and a one-class SVM (OC-SVM) anomaly detection method, which are interconnected and jointly trained by the OC-SVM-like loss function. The adoption of co-training updates the feature extraction network together with the anomaly detector, thus improving the whole network's detection performance. Considering that the prominent feature of an anomaly lies in its difference from the background, we designed a deep neural extraction network to learn more comprehensive hyperspectral image features, including spectral, global correlation, and local spatial features. To accomplish this goal, we adopted an adversarial autoencoder to produce the residual image with highlighted anomaly targets and a suppressed background, which is input into an improved non-local module to adaptively select the useful global information in the whole deep feature space. In addition, we incorporated a two-layer convolutional network to obtain local features. SAOCNN maps the original hyperspectral data to a learned feature space with better anomaly separation from the background, making it possible for the hyperplane to separate them. Our experiments on six public hyperspectral datasets demonstrate the state-of-the-art performance and superiority of our proposed SAOCNN when extracting deep potential features, which are more conducive to anomaly detection. [ABSTRACT FROM AUTHOR]

This study investigates the impact of assimilating Aircraft Meteorological Data Relay (AMDAR) observations on the prediction of two typhoons, Nesat and Haitang (2017), using the Gridpoint Statistical Interpolation (GSI) assimilation system and the Weather Research and Forecasting (WRF) model. Two quality control (QC) methods, Minimum Covariance Determinant (MCD) and one-class Support Vector Machine (OCSVM), were employed to perform QC on the AMDAR observations before data assimilation. The QC results indicated that both methods significantly reduced kurtosis, skewness, and discrepancies between the AMDAR data and the reanalysis data. The data distribution after applying the MCD-QC method exhibited a closer resemblance to a Gaussian distribution. Four numerical experiments were conducted to assess the impact of different AMDAR data qualities on typhoon forecasting, including a control experiment without data assimilation (EXP-CNTL), assimilating all AMDAR observations (EXP-RAW), assimilating observations after applying MCD-QC (EXP-MCD), and assimilating observations after applying OCSVM-QC (EXP-SVM). The results demonstrated that using AMDAR data in assimilation improved the track and intensity prediction of the typhoons. Furthermore, utilizing QC before assimilation enhanced the performance of track forecasting prediction, with EXP-MCD showing the best performance. As for intensity prediction, the three assimilation experiments exhibited varying strengths and weaknesses at different times, with EXP-MCD showing smaller intensity forecast errors on average.

In our previous studies, we proposed crossing‐gate rod breakage detection methods based on machine learning techniques for the telemeter system installed by the Shikoku Railway Company (JR Shikoku) on railway lines in the Shikoku area to collect real‐time equipment data. However, these methods involve batch processing of many training data over several days, making them unsuitable for real‐time detection because of the long computation time. Therefore, this study improves these methods by performing sequential processing for real‐time detection for installation in the railway field. A one‐class support vector machine‐based detection method was applied to sequential processing to perform detection at each sampling period every few seconds. The proposed method is evaluated and its effectiveness is demonstrated in two representative cases of crossing‐gate rod breakage. © 2023 Institute of Electrical Engineer of Japan and Wiley Periodicals LLC. [ABSTRACT FROM AUTHOR]

Copyright of Journal of China University of Petroleum is the property of China University of Petroleum and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The cyber-security of the power grid is of extreme significance due to growing dependency on modern technologies. Several recent real-world incidents reveal the risk associated with false data injection attacks. Besides corrupting the sensor’s data, intruders can also target real-time dispatch signals (DS) sent to generation systems over an unsecured network to launch financially motivated attacks. To conduct the attacks, we construct a novel self-adaptive undetectable attack model, termed Imposter Attacks (IA). The devised IA adjusts its intensity based on system conditions allowing energy providers to unethically raise profit without impacting the grid stability. It is shown that by adopting IA, the infected DS remains undetectable by traditional detectors. Unlike existing attack models, the IA tend to hide the corrupted quantity among the normal system data making them extremely difficult to identify. The feasibility of the IA is studied on the Automatic Generation Control system of the IEEE-39 bus system. [ABSTRACT FROM AUTHOR]

To integrate the evidential signatures into a mineral prospective map, it is necessary to model the observed data of metallogenic predictors with complex relationships. In this paper, a methodology was developed for gold prospectivity modeling by combining Laplacian eigenmaps (LEMS) and the least angle regression (LARS). LEMS were used to transform metallogenic predictors into Laplacian spectra to enhance the data classification ability, and the Laplacian spectra were used in LARS for gold prospectivity modeling. The Jinchanggouliang area, an important gold metallogenic district in China, was taken as the study area. Based on the geological and geochemical survey data of the study area, the LARS model, the combination of LEMS and LARS (LEMS–LARS) model, the logistic regression (LGR) model and the one-class support vector machine (OCSVM) model were each established for gold prospectivity modeling in the study area. The performances of these four models were measured using different performance evaluation methods. The receiver operating characteristic (ROC) analysis reveals that the LEMS–LARS model, the LGR model and the OCSVM model yield comparable performances and were superior to the LARS model, for gold prospectivity modeling in the study area. The prediction–area (P–A) plots of the four models show that the LEMS–LARS model, the LGR model and the OCSVM model each predicted about 20% of the study area as gold prospective areas, which contain about 80% of the known gold deposit locations. However, the performance of the LARS model was difficult to evaluate by the P-A plot because its prediction curve overlaps with its area curve, forming a straight-line segment, in the P-A plot. The gold prospective areas delineated optimally separately by the LEMS–LARS model, the LGR model and the OCSVM model are associated spatially with areas having favorable metallogenic conditions. The case study illustrates that the LEMS–LARS model can be used as a data-driven mineral prospectivity method, and its performance, in gold prospectivity modeling in the study area, is comparable to that of the LGR method and OCSVM method. [ABSTRACT FROM AUTHOR]

In one-class classification (OCC) tasks, only the target class (class-of-interest (CoI)) samples are well defined during training, whereas the other class samples are totally absent. In OCC algorithms, the high dimensional data adds computational overhead apart from its intrinsic property of curse of dimensionality. For target class learning, conventional dimensionality reduction (DR) techniques are not suitable due to negligence of the unique statistical properties of CoI samples. In this context, the present research proposes a novel target class guided DR technique to extract the eigen knowledge grid that contains the most promising eigenvectors of variance-covariance matrix of CoI samples. In this process the lower and higher eigenvalued eigenvectors are rejected via statistical analysis because the high variance may split the target class itself, whereas the lower variance do not contribute significant information. Furthermore, the identified eigen knowledge grid is utilized to transform high dimensional samples to the lower dimensional eigen subspace. The proposed approach is named as learning target class eigen subspace (LTS-ES) that ensures strong separation of the target class from other classes. To show the effectiveness of transformed lower dimensional eigen subspace, oneclass support vector machine (OCSVM) has been experimented on wide variety of benchmark datasets in presence of: original feature space, transformed features obtained via eigenvectors of approximately 80%-90% cumulative variance, transformed features obtained via knowledge grid and transformed features obtained via eigenvectors of approximately 50% cumulative variance. Finally, a new performance measure parameter called stability factor is introduced to validate the robustness of the proposed approach. [ABSTRACT FROM AUTHOR]

To reduce the levelized cost of wind energy, through the reduction in operation and maintenance costs, it is imperative that the wind turbine downtime is reduced through maintenance strategies based on condition monitoring. The standard approach toward this challenge is based on vibration monitoring, which requires the installation of specific tailored sensors that incur associated added costs. On the other hand, the life expectancy of wind parks built during the 1990s wind power boom is dwindling, and data-driven maintenance strategies issued from already accessible supervisory control and data acquisition (SCADA) data is an auspicious competitive solution because no additional sensors are required. Note that it is a major issue to provide fault diagnosis approaches built only on SCADA data, as these data were not established with the objective of being used for condition monitoring but rather for control capacities. The present study posits an early fault diagnosis strategy based exclusively on SCADA data and supports it with results on a real wind park with 18 wind turbines. The contributed methodology is an anomaly detection model based on a one-class support vector machine classifier; that is, it is a semi-supervised approach that trains a decision function that categorizes fresh data as similar or dissimilar to the training set. Therefore, only healthy (normal operation) data is required to train the model, which greatly expands the possibility of employing this methodology (because there is no need for faulty data from the past, and only normal operation SCADA data is needed). The results obtained from the real wind park show that this is a promising strategy. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Chongqing University of Posts & Telecommunications (Natural Science Edition) is the property of Chongqing University of Posts & Telecommunications and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Online clustering of multivariate streaming data has attracted considerable interest in recent years due to the abundance of data sources. Numerous studies in this field have been performed, but they usually suffer from the practical problems associated with discovering arbitrary‐shaped clusters, specifying major parameters in advance, and detecting aberrant observations. Addressing these issues is important for online‐clustering tasks, where data arrive in continuous streams and group behaviors change simultaneously. In this paper, we propose a kernel‐based online dependence clustering, namely, KODC, that not only estimates the cluster membership using one‐class support vector machines (OC‐SVMs), but also detects outliers distant from the identified clusters by aggregating OC‐SVM decisions in a realtime basis. At the base level, we use a new measure of connective dependence that forms the graph connected via modified Markovian transitions to enable large‐scale clustering. The proposed framework introduces the coherence threshold to extract data points, which can represent a cluster to which they belong, thus controlling the computational complexity without degrading the clustering performance. To track the pattern evolution over time, KODC also updates the classifier configuration maximizing the total group connective dependence. We evaluate this framework on both several synthetic and real‐world data sets involving multivariate streaming data, and compare it experimentally with other popular online‐clustering methods in terms of four evaluation metrics. The results show that our framework effectively identifies the clusters and outliers, especially in various shaped data subject to change over time, without requiring any prior knowledge of the data. [ABSTRACT FROM AUTHOR]

Data-driven models are becoming increasingly popular in engineering, on their own or in combination with mechanistic models. Commonly, the trained models are subsequently used in model-based optimization of design and/or operation of processes. Thus, it is critical to ensure that data-driven models are not evaluated outside their validity domain during process optimization. We propose a method to learn this validity domain and encode it as constraints in process optimization. We first perform a topological data analysis using persistent homology identifying potential holes or separated clusters in the training data. In case clusters or holes are identified, we train a one-class classifier, i.e., a one-class support vector machine, on the training data domain and encode it as constraints in the subsequent process optimization. Otherwise, we construct the convex hull of the data and encode it as constraints. We finally perform deterministic global process optimization with the data-driven models subject to their respective validity constraints. To ensure computational tractability, we develop a reduced-space formulation for trained one-class support vector machines and show that our formulation outperforms common full-space formulations by a factor of over 3000, making it a viable tool for engineering applications. The method is ready-to-use and available open-source as part of our MeLOn toolbox (https://git.rwth-aachen.de/avt.svt/public/MeLOn). [ABSTRACT FROM AUTHOR]