Anomaly Classification Research Articles

Anomaly Detection Method for Industrial Control System Operation Data Based on Time-Frequency Fusion Feature Attention Encoding.

Anomaly detection in industrial control system (ICS) data is one of the key technologies for ensuring the security monitoring of ICSs. ICS data are characterized as complex, multi-dimensional, and long-sequence time-series data that embody ICS business logic. Due to its complex and varying periodic characteristics, as well as the presence of long-distance and misaligned temporal associations among features, current anomaly detection methods in ICS are insufficient for feature extraction. This paper proposes an anomaly detection method named TFANet, based on time-frequency fusion feature attention encoding. Considering that periodic variations are more concentrated in the frequency domain, this method first transforms the time-domain data into the frequency domain, obtaining both amplitude and phase data. Then, these data, together with the original time-series data, are used to extract features from two perspectives: long-term temporal changes and long-distance associations. Finally, the six features learned from both the time and frequency domains are fused, and the feature weights are calculated using an attention mechanism to complete the anomaly classification. In multi-classification tasks on three ICS datasets, the proposed method outperforms three popular time-series models-iTransformer, Crossformer, and TimesNet-across five metrics: accuracy, precision, recall, F1 score, and AUC-ROC, with average improvements of approximately 19%, 37%, 31%, 35%, and 22%, respectively.

Anomaly Detection in Sound Activity with Generative Adversarial Network Models

In state-of-art anomaly detection research, prevailing methodologies predominantly employ Generative Adversarial Networks and Autoencoders for image-based applications. Despite the efficacy demonstrated in the visual domain, there remains a notable dearth of studies showcasing the application of these architectures in anomaly detection within the sound domain. This paper introduces tailored adaptations of cutting-edge architectures for anomaly detection in audio and conducts a comprehensive comparative analysis to substantiate the viability of this novel approach. The evaluation is performed on the DCASE 2020 dataset, encompassing over 180 hours of industrial machinery sound recordings. Our results indicate superior anomaly classification, with an average Area Under the Curve (AUC) of 88.16% and partial AUC of 78.05%, surpassing the performance of established baselines. This study not only extends the applicability of advanced architectures to the audio domain but also establishes their effectiveness in the challenging context of industrial sound anomaly detection.

DB-MAGS: Multi-Anomaly Data Generation System for Transactional Databases

Existing database performance anomaly datasets have the problems of comprehensiveness in anomaly types, coarse-grained root causes, and unrealistic simulation for reproducing concurrent anomalies. To address these issues, we propose a data generation system tailored for Multi-Anomaly Reproduction in Databases (DB-MAGS). DB-MAGS guarantees unified, authentic, and comprehensive data generation, while also providing fine-grained root causes. In the case of only a single anomaly occurred in the database, we categorize the factors affecting database performance anomalies, select five major categories of anomalies, and further subdivide each category into eighteen minor categories. This finer granularity of anomaly classification facilitates more specific and targeted anomaly remediation. For multiple anomalies simultaneously occurred in a database system, we categorize the relationships between anomalies into causal and concurrent, and enumerate different combinations of multiple anomalies, making the simulation of multiple anomaly scenarios more comprehensive and enhancing the diversity of generated data.

Detecting faults in the cooling systems by monitoring temperature and energy

The cooling systems contribute to 40% of overall building energy consumption. Out of which, 40% is wasted because of faulty parts that cause anomalies in the cooling systems. We propose a three-stage, non-invasive part-level anomaly detection technique to identify anomalies in both cooling systems, a ducted-centralized and a ductless-split. We use COTS sensors to monitor temperature and energy without invading the cooling system. After identifying the anomalies, we find the cause of the anomaly. Based on the anomaly, the solution recommends a fix. If there is a technical fault, our proposed technique informs the technician regarding the faulty part, reducing the cost and time needed to repair it. In the first stage, we propose a domain-inspired time-series statistical technique to identify anomalies in cooling systems. We observe an AUC-ROC score of more than 0.93 in simulation and experimentation. In the second stage, we propose using a rule-based technique to identify the cause of the anomaly. We classify causes of anomalies into three classes. We observe an AUC-ROC score of 1. Based on the anomaly classification, we identify the faulty part of the cooling system in the third stage. We use the Nearest-Neighbour Density-Based Spatial Clustering of Applications with Noise (NN-DBSCAN) algorithm with transfer learning capabilities to train the model only once, where it learns the domain knowledge using the simulated data. The trained model is used in different environmental scenarios with both types of cooling systems. The proposed algorithm shows an accuracy score of 0.82 in simulation deployment and 0.88 in experimentation. In the simulation we used both ducted-centralized and ductless-split cooling systems and in the experimentation we evaluated the solution with ductless-split cooling systems. The overall accuracy of the three-stage technique is 0.82 and 0.86 in simulation and experimentation, respectively. We observe energy savings of up to 68% in simulation and 42% during experimentation, with a reduction of ten days in the cooling system’s downtime and up to 75% in repair cost.

On Evaluating Black-Box Explainable AI Methods for Enhancing Anomaly Detection in Autonomous Driving Systems.

The recent advancements in autonomous driving come with the associated cybersecurity issue of compromising networks of autonomous vehicles (AVs), motivating the use of AI models for detecting anomalies on these networks. In this context, the usage of explainable AI (XAI) for explaining the behavior of these anomaly detection AI models is crucial. This work introduces a comprehensive framework to assess black-box XAI techniques for anomaly detection within AVs, facilitating the examination of both global and local XAI methods to elucidate the decisions made by XAI techniques that explain the behavior of AI models classifying anomalous AV behavior. By considering six evaluation metrics (descriptive accuracy, sparsity, stability, efficiency, robustness, and completeness), the framework evaluates two well-known black-box XAI techniques, SHAP and LIME, involving applying XAI techniques to identify primary features crucial for anomaly classification, followed by extensive experiments assessing SHAP and LIME across the six metrics using two prevalent autonomous driving datasets, VeReMi and Sensor. This study advances the deployment of black-box XAI methods for real-world anomaly detection in autonomous driving systems, contributing valuable insights into the strengths and limitations of current black-box XAI methods within this critical domain.

Machine-Learning and Physics-Based Tool for Anomaly Identification in Propulsion Systems

Launch anomalies occur frequently during the early phase of a program, with many of the anomalies attributed to propulsion systems. Approaches for identifying and mitigating potential propulsion failures can aid development programs and accelerate the resolution of root cause investigations. In reusable systems, anomaly detection methods can be employed to detect latent system health issues that could become problematic as the system ages. Modern launch support relies on human judgement for redline limit generation and visual family data comparison for many operational aspects, which makes it challenging to identify failure modes and to diagnose an anomaly. Additionally, family data comparison is unavailable for the first few launches of a new vehicle. Automated tools to quickly identify system failures of new and reusable systems can bridge these gaps. Physics-based modeling and machine learning (PBMML) offers methods that can improve the reliability of new or reusable launch vehicles by identifying propulsion anomalies or issues before they jeopardize future space missions. PBMML can then be used to inform corrective actions. This paper describes an anomaly data generation module which automates the process of simulating anomalous scenarios in launch vehicle and fluid networks, while a long-term short-term memory network is used to provide real-time anomaly classification on a simplified stage test case.

MedicalCLIP: Anomaly-Detection Domain Generalization with Asymmetric Constraints.

Medical data have unique specificity and professionalism, requiring substantial domain expertise for their annotation. Precise data annotation is essential for anomaly-detection tasks, making the training process complex. Domain generalization (DG) is an important approach to enhancing medical image anomaly detection (AD). This paper introduces a novel multimodal anomaly-detection framework called MedicalCLIP. MedicalCLIP utilizes multimodal data in anomaly-detection tasks and establishes irregular constraints within modalities for images and text. The key to MedicalCLIP lies in learning intramodal detailed representations, which are combined with text semantic-guided cross-modal contrastive learning, allowing the model to focus on semantic information while capturing more detailed information, thus achieving more fine-grained anomaly detection. MedicalCLIP relies on GPT prompts to generate text, reducing the demand for professional descriptions of medical data. Text construction for medical data helps to improve the generalization ability of multimodal models for anomaly-detection tasks. Additionally, during the text-image contrast-enhancement process, the model's ability to select and extract information from image data is improved. Through hierarchical contrastive loss, fine-grained representations are achieved in the image-representation process. MedicalCLIP has been validated on various medical datasets, showing commendable domain generalization performance in medical-data anomaly detection. Improvements were observed in both anomaly classification and segmentation metrics. In the anomaly classification (AC) task involving brain data, the method demonstrated a 2.81 enhancement in performance over the best existing approach.

Anomaly classification based on self-supervised learning and its application

BackgroundAnomaly classification remains a challenging task in computer vision applications across diverse practical fields such as industrial detection and security check. The purpose of this study is to develop a new anomaly classification method based on self-supervised learning (Self-ACM), which is expected to enhance anomaly classification accuracy significantly. MethodsThe feature maps of images were abstracted using VGG16 model pre-trained on ImageNet, which were then fed into the innovative model to capture the normality distribution within the dataset domain. Then, a self-supervised adversarial anomaly classification learning framework was proposed to facilitate the acquisition of a higher-level semantic representations for improved anomaly detection. Thirdly, we collected and constructed a novel terahertz (THZ) dataset, which serves as a pioneering resource for benchmarking anomaly classification tasks in the field. ResultsThrough a series of rigorous experiments, our findings unequivocally demonstrate the following key insights: Firstly, harnessing feature maps as input data yielded a significant enhancement in anomaly detection performance, underscoring the effectiveness of this approach. Secondly, the integration of self-supervision enriched the dataset with invaluable information, empowering both the discriminator and generator to acquire superior feature representations. The culmination of these advancements is our novel method achieving unparalleled state-of-the-art performance across multiple benchmark datasets. This breakthrough underscores the transformative impact of our approach on anomaly detection methodologies, solidifying its position as a pioneering solution in the field. ConclusionThe Self-ACM strategy not only advances anomaly detection methodologies but also offers a remarkable contribution to dataset creation, setting a new standard for anomaly classification research.

MCAD: Multi-classification anomaly detection with relational knowledge distillation

With the wide application of deep learning in anomaly detection (AD), industrial vision AD has achieved remarkable success. However, current AD usually focuses on anomaly localization and rarely investigates anomaly classification. Furthermore, anomaly classification is currently requested for quality management and anomaly reason analysis. Therefore, it is essential to classify anomalies while improving the accuracy of AD. This paper designs a novel multi-classification AD (MCAD) framework to achieve high-accuracy AD with an anomaly classification function. In detail, the proposal model based on relational knowledge distillation consists of two components. The first one employs a teacher–student AD model, utilizing a relational knowledge distillation approach to transfer the interrelationships of images. The teacher–student critical layer feature activation values are used in the knowledge transfer process to achieve anomaly detection. The second component realizes anomaly multi-classification using the lightweight convolutional neural network. Our proposal has achieved 98.95, 96.04, and 92.94% AUROC AD results on MNIST, FashionMNIST, and CIFAR10 datasets. Meanwhile, we earn 97.58 and 98.10% AUROC for AD and localization in the MVTecAD dataset. The average classification accuracy of anomaly classification has reached 76.37% in fifteen categories of the MVTec-AD dataset. In particular, the classification accuracy of the leather category has gained 95.24%. The results on the MVTec-AD dataset show that MCAD achieves excellent detection, localization, and classification results.

AIS-based kinematic anomaly classification for maritime surveillance

Anomaly detection is crucial for maritime surveillance and law enforcement. Early identification of abnormal behavior ensures maritime order and fosters a safer environment for maritime traffic. However, anomaly identification and classification methods often suffer from vagueness because of the complexity of anomalies, limiting their effectiveness. We propose a systematic and data-driven framework for kinematic anomaly classification and detection. Through extensive inspection and experiments, a comprehensive characterization of diverse anomalies is provided to classify vessel kinematic anomalies into three categories, including Speed and Course Anomaly (SCA), Turning Anomaly (TA) and Loitering Anomaly (LA), along with detection methods that are tailored to each anomaly type to facilitate the production of high-quality anomaly labels. Subsequently, supervised training is exploited for anomaly classification. The effectiveness of the proposed method is validated using the open Automatic Identification System (AIS) dataset provided by the Danish Maritime Authority (DMA). With proper feature design, the proposed method can achieve a classification accuracy of approximately 99% using simple neural networks.

Multi-Source Data Aggregation and Real-Time Anomaly Classification and Localization in Power Distribution Systems

Multi-Source Data Aggregation and Real-Time Anomaly Classification and Localization in Power Distribution Systems

Performance Analysis of Various Image Feature Extractor Filters for Pothole Anomaly Classification

Performance Analysis of Various Image Feature Extractor Filters for Pothole Anomaly Classification

OTSUCNV: an adaptive segmentation and OTSU-based anomaly classification method for CNV detection using NGS data

Copy-number variations (CNVs), which refer to deletions and duplications of chromosomal segments, represent a significant source of variation among individuals, contributing to human evolution and being implicated in various diseases ranging from mental illness and developmental disorders to cancer. Despite the development of several methods for detecting copy number variations based on next-generation sequencing (NGS) data, achieving robust detection performance for CNVs with arbitrary coverage and amplitude remains challenging due to the inherent complexity of sequencing samples. In this paper, we propose an alternative method called OTSUCNV for CNV detection on whole genome sequencing (WGS) data. This method utilizes a newly designed adaptive sequence segmentation algorithm and an OTSU-based CNV prediction algorithm, which does not rely on any distribution assumptions or involve complex outlier factor calculations. As a result, the effective detection of CNVs is achieved with lower computational complexity. The experimental results indicate that the proposed method demonstrates outstanding performance, and hence it may be used as an effective tool for CNV detection.

Improving Anomaly Classification using Combined Data Transformation and Machine Learning Methods

Improving Anomaly Classification using Combined Data Transformation and Machine Learning Methods

A Framework for Anomaly Classification and Segmentation in Remanufacturing using Autoencoders and Simulated Data

In remanufacturing, reusable end-of-life products must be separated from those for which remanufacturing is not economical. In this process, the focus is initially on the detection and evaluation of surface defects of the used product. Due to the use phase of the product, these show a great variety with strongly differing degrees of severity. Deep-learning-based autoencoders offer the advantage of defect-independent detection of anomalies by detecting deviations from a defect-free product condition. In the present work, anomaly detection based on synthetically generated image data is investigated. In addition, a framework for classification and segmentation is developed and presented. The results show that the approach presented in the paper is effective in detecting anomalies with potential for improvement through adjustments such as perceptual loss or image processing methods. However, challenges remain in accurately detecting anomalies in the presence of missing parts, large anomalies, and image data with high variance.

Automated Anomaly Detection and Multi-label Anomaly Classification in Crowd Scenes based on Optimal Thresholding and Deep Learning Strategy

Automated Anomaly Detection and Multi-label Anomaly Classification in Crowd Scenes based on Optimal Thresholding and Deep Learning Strategy

Automated anomaly detection and multi-label anomaly classification in crowd scenes based on optimal thresholding and deep learning strategy

Automated anomaly detection and multi-label anomaly classification in crowd scenes based on optimal thresholding and deep learning strategy

Dynamic Threshold Fine-Tuning in Anomaly Severity Classification for Enhanced Solar Power Optimization

This study explores an innovative approach to anomaly severity classification within the realm of solar power optimization. Leveraging established machine learning algorithms—including Isolation Forest (IF), Local Outlier Factor (LOF), and Principal Component Analysis (PCA)—we introduce a novel framework marked by dynamic threshold fine-tuning. This adaptive paradigm aims to refine the accuracy of anomaly classification under varying environmental conditions, addressing factors such as dust storms and equipment irregularities. The research builds upon datasets derived from Errachidia, Morocco. Results underscore the effectiveness of dynamically adjusting severity thresholds in optimizing anomaly classification and subsequently improving the overall efficiency of solar power generation. The study not only reaffirms the robustness of the initial framework but also emphasizes the practical significance of fine-tuning anomaly severity classification for real-world applications in solar energy management. By providing a more nuanced perspective on anomaly detection, this research advances our understanding of the intricate precision required for optimal solar power generation efficiency. The findings contribute valuable insights into the broader field of machine learning applications in renewable energy, offering a pathway for the refinement of existing frameworks for enhanced sustainability and operational effectiveness.

P2 random walk: self-supervised anomaly detection with pixel-point random walk

In the domain of intelligent manufacturing, automatic anomaly detection plays a pivotal role and holds great significance for improving production efficiency and product quality. However, the scarcity and uncertainty of anomalous data pose significant challenges in this field. Data augmentation methods, such as Cutout, which are widely adopted in existing methodologies, tend to generate patterned data, leading to biased data and compromised detection performance. To deal with this issue, we propose an approach termed self-supervised anomaly detection with pixel-point random walk (P2 Random Walk), which combines data augmentation and Siamese neural networks. We develop a pixel-level data augmentation technique to enhance the randomness of generated data and establish a two-stage anomaly classification framework. The effectiveness of the P2 Random Walk method has been demonstrated on the MVTec dataset, achieving an AUROC of 96.2% and 96.3% for classification and segmentation, respectively, by using only data augmentation-based techniques. Specifically, our method outperforms other state-of-the-art methods in several categories, improving the AUROC for classification and segmentation by 0.5% and 0.3%, respectively, which demonstrates the high performance and strong academic value of our method in anomaly detection tasks.

Management of congenital urogenital and perineal vascular malformations: correlation of clinical findings with diagnostic imaging for treatment decision.

Analysis of clinical and diagnostic findings in rare urogenital and perineal vascular malformations only occurring in 2-3 % of vascular anomalies with regard to clinical symptoms and treatment decisions. All 25 out of 537 patients presenting with congenital urogenital and perineal vascular malformations at our institution from 2014 to 2021 were included. Vascular anomaly classification, anatomical location, clinical symptoms at presentation, diagnostic imaging, and pain intensity were retrospectively assessed from the patient record and therapy management was evaluated. In total, 25 patients (10 females (40 %), 15 males (60 %)), aged 6 to 77 years were included. Diagnoses were: 10 (40 %) venous malformations (VMs), 5 (20 %) lymphatic malformations (LMs) and 10 (40 %) arteriovenous malformations (AVMs). Malformation manifestations were: 12 (32 %) lesser pelvis, 12 (32 %) external genitalia, and 13 (34 %) perineal/gluteal region. One AVM was located in the kidney. The leading clinical symptom was pain. The mean intensity was 6.0/10 for LM, 5.7/10 for VM, and 4.5/10 for AVM. Further major symptoms included physical impairment, local swelling, and skin discoloration. Bleeding complications or sexual dysfunction were rare findings. Patients with VM reported significantly more symptoms than patients with AVM (p = 0.0129). In 13 patients (52 %) minimally invasive therapy was indicated: 10 (77 %) sclerotherapies and 3 (23 %) transcatheter embolization procedures. Complete symptomatic remission was achieved in 9 (69 %) patients, partial response in 3 (23 %) patients, and 1 patient showed no clinical response to therapy. Follow-up appointments without the need for immediate minimally invasive therapy were significantly more common in patients with AVMs than in patients with VMs (p = 0.0198). To create a higher awareness of congenital urogenital and perineal vascular malformations. Awareness of this rare condition avoids misdiagnosis. Therapy decisions should be symptom-oriented. Emergency intervention is rarely required, even in fast-flow vascular malformations. · Venous malformations cause more symptoms with higher pain intensity than arteriovenous malformations.. · Diagnosis and adequate treatment can be hampered by a lack of awareness of the clinical presentation.. · Bleeding complications are rare, even in high-flow vascular malformations.. · Pain and physical impairment are the most commonly observed symptoms in these patients..