RESUMEN

Intrusion detection systems have proliferated with varying capabilities for data generation and learning towards detecting abnormal behavior. The goal of green intrusion detection systems is to design intrusion detection systems for energy efficiency, taking into account the resource constraints of embedded devices and analyzing energy-performance-security trade-offs. Towards this goal, we provide a comprehensive survey of existing green intrusion detection systems and analyze their effectiveness in terms of performance, overhead, and energy consumption for a wide variety of low-power embedded systems such as the Internet of Things (IoT) and cyber physical systems. Finally, we provide future directions that can be leveraged by existing systems towards building a secure and greener environment.

RESUMEN

Anomaly detection has gained significant attention with the advancements in deep neural networks. Effective training requires both normal and anomalous data, but this often leads to a class imbalance, as anomalous data is scarce. Traditional augmentation methods struggle to maintain the correlation between anomalous patterns and their surroundings. To address this, we propose an adjacent augmentation technique that generates synthetic anomaly images, preserving object shapes while distorting contours to enhance correlation. Experimental results show that adjacent augmentation captures high-quality anomaly features, achieving superior AU-ROC and AU-PR scores compared to existing methods. Additionally, our technique produces synthetic normal images, aiding in learning detailed normal data features and reducing sensitivity to minor variations. Our framework considers all training images within a batch as positive pairs, pairing them with synthetic normal images as positive pairs and with synthetic anomaly images as negative pairs. This compensates for the lack of anomalous features and effectively distinguishes between normal and anomalous features, mitigating class imbalance. Using the ResNet50 network, our model achieved perfect AU-ROC and AU-PR scores of 100% in the bottle category of the MVTec-AD dataset. We are also investigating the relationship between anomalous pattern size and detection performance.

RESUMEN

Detection of abnormal situations in mobile systems not only provides predictions about risky situations but also has the potential to increase energy efficiency. In this study, two real-world drives of a battery electric vehicle and unsupervised hybrid anomaly detection approaches were developed. The anomaly detection performances of hybrid models created with the combination of Long Short-Term Memory (LSTM)-Autoencoder, the Local Outlier Factor (LOF), and the Mahalanobis distance were evaluated with the silhouette score, Davies-Bouldin index, and Calinski-Harabasz index, and the potential energy recovery rates were also determined. Two driving datasets were evaluated in terms of chaotic aspects using the Lyapunov exponent, Kolmogorov-Sinai entropy, and fractal dimension metrics. The developed hybrid models are superior to the sub-methods in anomaly detection. Hybrid Model-2 had 2.92% more successful results in anomaly detection compared to Hybrid Model-1. In terms of potential energy saving, Hybrid Model-1 provided 31.26% superiority, while Hybrid Model-2 provided 31.48%. It was also observed that there is a close relationship between anomaly and chaoticity. In the literature where cyber security and visual sources dominate in anomaly detection, a strategy was developed that provides energy efficiency-based anomaly detection and chaotic analysis from data obtained without additional sensor data.

RESUMEN

In the traditional method for hyperspectral anomaly detection, spectral feature mapping is used to map hyperspectral data to a high-level feature space to make features more easily distinguishable between different features. However, the uncertainty in the mapping direction makes the mapped features ineffective in distinguishing anomalous targets from the background. To address this problem, a hyperspectral anomaly detection algorithm based on the spectral similarity variability feature (SSVF) is proposed. First, the high-dimensional similar neighborhoods are fused into similar features using AE networks, and then the SSVF are obtained using residual autoencoder. Finally, the final detection of SSVF was obtained using Reed and Xiaoli (RX) detectors. Compared with other comparison algorithms with the highest accuracy, the overall detection accuracy (AUCODP) of the SSVFRX algorithm is increased by 0.2106. The experimental results show that SSVF has great advantages in both highlighting anomalous targets and improving separability between different ground objects.

RESUMEN

The problem of Power Quality analysis is becoming crucial to ensuring the proper functioning of complex systems and big plants. In this regard, it is essential to rapidly detect anomalies in voltage and current signals to ensure a prompt response and maximize the system's availability with the minimum maintenance cost. In this paper, anomaly detection algorithms based on machine learning, such as One Class Support Vector Machine (OCSVM), Isolation Forest (IF), and Angle-Based Outlier Detection (ABOD), are used as a first tool for rapid and effective clustering of the measured voltage and current signals directly on-line on the sensing unit. If the proposed anomaly detection algorithm detects an anomaly, further investigations using suitable classification algorithms are required. The main advantage of the proposed solution is the ability to rapidly and efficiently detect different types of anomalies with low computational complexity, allowing the implementation of the algorithm directly on the sensor node used for signal acquisition. A suitable experimental platform has been established to evaluate the advantages of the proposed method. All the different models were tested using a consistent set of hyperparameters and an output dataset generated from the principal component analysis technique. The best results achieved included models reaching 100% recall and a 92% F1 score.

RESUMEN

The detection of anomalies in dam deformation is paramount for evaluating structural integrity and facilitating early warnings, representing a critical aspect of dam health monitoring (DHM). Conventional data-driven methods for dam anomaly detection depend extensively on historical data; however, obtaining annotated data is both expensive and labor-intensive. Consequently, methodologies that leverage unlabeled or semi-labeled data are increasingly gaining popularity. This paper introduces a spatiotemporal contrastive learning pretraining (STCLP) strategy designed to extract discriminative features from unlabeled datasets of dam deformation. STCLP innovatively combines spatial contrastive learning based on temporal contrastive learning to capture representations embodying both spatial and temporal characteristics. Building upon this, a novel anomaly detection method for dam deformation utilizing STCLP is proposed. This method transfers pretrained parameters to targeted downstream classification tasks and leverages prior knowledge for enhanced fine-tuning. For validation, an arch dam serves as the case study. The results reveal that the proposed method demonstrates excellent performance, surpassing other benchmark models.

RESUMEN

Advanced metering infrastructures (AMIs) aim to enhance the efficiency, reliability, and stability of electrical systems while offering advanced functionality. However, an AMI collects copious volumes of data and information, making the entire system sensitive and vulnerable to malicious attacks that may cause substantial damage, such as a deficit in national security, a disturbance of public order, or significant economic harm. As a result, it is critical to guarantee a steady and dependable supply of information and electricity. Furthermore, storing massive quantities of data in one central entity leads to compromised data privacy. As such, it is imperative to engineer decentralized, federated learning (FL) solutions. In this context, the performance of participating clients has a significant impact on global performance. Moreover, FL models have the potential for a Single Point of Failure (SPoF). These limitations contribute to system failure and performance degradation. This work aims to develop a performance-based hierarchical federated learning (HFL) anomaly detection system for an AMI through (1) developing a deep learning model that detects attacks against this critical infrastructure; (2) developing a novel aggregation strategy, FedAvg-P, to enhance global performance; and (3) proposing a peer-to-peer architecture guarding against a SPoF. The proposed system was employed in experiments on the CIC-IDS2017 dataset. The experimental results demonstrate that the proposed system can be used to develop a reliable anomaly detection system for AMI networks.

RESUMEN

Diffusion probabilistic models (DPMs) have exhibited significant effectiveness in computer vision tasks, particularly in image generation. However, their notable performance heavily relies on labelled datasets, which limits their application in medical images due to the associated high-cost annotations. Current DPM-related methods for lesion detection in medical imaging, which can be categorized into two distinct approaches, primarily rely on image-level annotations. The first approach, based on anomaly detection, involves learning reference healthy brain representations and identifying anomalies based on the difference in inference results. In contrast, the second approach, resembling a segmentation task, employs only the original brain multi-modalities as prior information for generating pixel-level annotations. In this paper, our proposed model - discrepancy distribution medical diffusion (DDMD) - for lesion detection in brain MRI introduces a novel framework by incorporating distinctive discrepancy features, deviating from the conventional direct reliance on image-level annotations or the original brain modalities. In our method, the inconsistency in image-level annotations is translated into distribution discrepancies among heterogeneous samples while preserving information within homogeneous samples. This property retains pixel-wise uncertainty and facilitates an implicit ensemble of segmentation, ultimately enhancing the overall detection performance. Thorough experiments conducted on the BRATS2020 benchmark dataset containing multimodal MRI scans for brain tumour detection demonstrate the great performance of our approach in comparison to state-of-the-art methods.

Asunto(s)

RESUMEN

Automated defect detection in electroluminescence (EL) images of photovoltaic (PV) modules on production lines remains a significant challenge, crucial for replacing labor-intensive and costly manual inspections and enhancing production capacity. This paper presents a novel PV defect detection algorithm that leverages the YOLO architecture, integrating an attention mechanism and the Transformer module. We introduce a polarized self-attention mechanism in the feature extraction stage, enabling separate extraction of spatial and semantic features of PV modules, combined with the original input features, to enhance the network's feature representation capabilities. Subsequently, we integrate the proposed CNN Combined Transformer (CCT) module into the model. The CCT module employs the transformer to extract contextual semantic information more effectively, improving detection accuracy. The experimental results demonstrate that the proposed method achieves a 77.9% mAP50 on the PVEL-AD dataset while preserving real-time detection capabilities. This method enhances the mAP50 by 17.2% compared to the baseline, and the mAP50:95 metric exhibits an 8.4% increase over the baseline.

RESUMEN

Understanding the relationship between tongue motion patterns during speech and their resulting speech acoustic outcomes-i.e., articulatory-acoustic relation-is of great importance in assessing speech quality and developing innovative treatment and rehabilitative strategies. This is especially important when evaluating and detecting abnormal articulatory features in patients with speech-related disorders. In this work, we aim to develop a framework for detecting speech motion anomalies in conjunction with their corresponding speech acoustics. This is achieved through the use of a deep cross-modal translator trained on data from healthy individuals only, which bridges the gap between 4D motion fields obtained from tagged MRI and 2D spectrograms derived from speech acoustic data. The trained translator is used as an anomaly detector, by measuring the spectrogram reconstruction quality on healthy individuals or patients. In particular, the cross-modal translator is likely to yield limited generalization capabilities on patient data, which includes unseen out-of-distribution patterns and demonstrates subpar performance, when compared with healthy individuals. A one-class SVM is then used to distinguish the spectrograms of healthy individuals from those of patients. To validate our framework, we collected a total of 39 paired tagged MRI and speech waveforms, consisting of data from 36 healthy individuals and 3 tongue cancer patients. We used both 3D convolutional and transformer-based deep translation models, training them on the healthy training set and then applying them to both the healthy and patient testing sets. Our framework demonstrates a capability to detect abnormal patient data, thereby illustrating its potential in enhancing the understanding of the articulatory-acoustic relation for both healthy individuals and patients.

RESUMEN

Most existing log-driven anomaly detection methods assume that logs are static and unchanged, which is often impractical. To address this, we propose a log anomaly detection model called DualAttlog. This model includes word-level and sequence-level semantic encoding modules, as well as a context-aware dual attention module. Specifically, The word-level semantic encoding module utilizes a self-matching attention mechanism to explore the interactive properties between words in log sequences. By performing word embedding and semantic encoding, it captures the associations and evolution processes between words, extracting local-level semantic information. while The sequence-level semantic encoding module encoding the entire log sequence using a pre-trained model. This extracts global semantic information, capturing overall patterns and trends in the logs. The context-aware dual attention module integrates these two levels of encoding, utilizing contextual information to reduce redundancy and enhance detection accuracy. Experimental results show that the DualAttlog model achieves an F1-Score of over 95% on 7 public datasets. Impressively, it achieves an F1-Score of 82.35% on the Real-Industrial W dataset and 83.54% on the Real-Industrial Q dataset. It outperforms existing baseline techniques on 9 datasets, demonstrating its significant advantages.

RESUMEN

Effectively identifying deviations in real-world medical time-series data is a critical endeavor, essential for early surveillance of disease outbreaks. This paper demonstrates the integration of time-series anomaly detection techniques to develop surveillance systems for disease outbreaks. Utilizing data from Sweden's telephone counseling service (1177), we first illustrate the trends in physical and mental symptoms recorded as contact reasons, offering valuable insights for outbreak detection. Subsequently, an advanced anomaly detection technique is applied incrementally to these time-series symptoms as univariate and multivariate approaches to assess the effectiveness of a machine learning-based method on early detection of the COVID-19 outbreak.

Asunto(s)

RESUMEN

Maintaining consistent and accurate temperature is critical for the safe and effective storage of vaccines. Traditional monitoring methods often lack real-time capabilities and may not be sensitive enough to detect subtle anomalies. This paper presents a novel deep learning-based system for real-time temperature fault detection in refrigeration systems used for vaccine storage. Our system utilizes a semi-supervised Convolutional Autoencoder (CAE) model deployed on a resource-constrained ESP32 microcontroller. The CAE is trained on real-world temperature sensor data to capture temporal patterns and reconstruct normal temperature profiles. Deviations from the reconstructed profiles are flagged as potential anomalies, enabling real-time fault detection. Evaluation using real-time data demonstrates an impressive 92% accuracy in identifying temperature faults. The system's low energy consumption (0.05 watts) and memory usage (1.2 MB) make it suitable for deployment in resource-constrained environments. This work paves the way for improved monitoring and fault detection in refrigeration systems, ultimately contributing to the reliable storage of life-saving vaccines.

RESUMEN

Software systems log massive amounts of data, recording important runtime information. Such logs are used, for example, for log-based anomaly detection, which aims to automatically detect abnormal behaviors of the system under analysis by processing the information recorded in its logs. Many log-based anomaly detection techniques based on deep learning models include a pre-processing step called log parsing. However, understanding the impact of log parsing on the accuracy of anomaly detection techniques has received surprisingly little attention so far. Investigating what are the key properties log parsing techniques should ideally have to help anomaly detection is therefore warranted. In this paper, we report on a comprehensive empirical study on the impact of log parsing on anomaly detection accuracy, using 13 log parsing techniques, seven anomly detection techniques (five based on deep learning and two based on traditional machine learning) on three publicly available log datasets. Our empirical results show that, despite what is widely assumed, there is no strong correlation between log parsing accuracy and anomaly detection accuracy, regardless of the metric used for measuring log parsing accuracy. Moreover, we experimentally confirm existing theoretical results showing that it is a property that we refer to as distinguishability in log parsing results-as opposed to their accuracy-that plays an essential role in achieving accurate anomaly detection.

RESUMEN

Wireless sensor networks (WSNs) are essential for a wide range of applications, including environmental monitoring and smart city developments, thanks to their ability to collect and transmit diverse physical and environmental data. The nature of WSNs, coupled with the variability and noise sensitivity of cost-effective sensors, presents significant challenges in achieving accurate data analysis and anomaly detection. To address these issues, this paper presents a new framework, called Online Adaptive Kalman Filtering (OAKF), specifically designed for real-time anomaly detection within WSNs. This framework stands out by dynamically adjusting the filtering parameters and anomaly detection threshold in response to live data, ensuring accurate and reliable anomaly identification amidst sensor noise and environmental changes. By highlighting computational efficiency and scalability, the OAKF framework is optimized for use in resource-constrained sensor nodes. Validation on different WSN dataset sizes confirmed its effectiveness, showing 95.4% accuracy in reducing false positives and negatives as well as achieving a processing time of 0.008 s per sample.

RESUMEN

Support vector data description (SVDD) is widely regarded as an effective technique for addressing anomaly detection problems. However, its performance can significantly deteriorate when the training data are affected by outliers or mislabeled observations. This study introduces a universal truncated loss function framework into the SVDD model to enhance its robustness and employs the fast alternating direction method of multipliers (ADMM) algorithm to solve various truncated loss functions. Moreover, the convergence of the fast ADMM algorithm is analyzed theoretically. Within this framework, we developed the truncated generalized ramp, truncated binary cross entropy, and truncated linear exponential loss functions for SVDD. We conducted extensive experiments on synthetic and real-world datasets to validate the effectiveness of these three SVDD models in handling data with different noise levels, demonstrating their superior robustness and generalization capabilities compared to other SVDD models.

RESUMEN

Anomaly detection systems based on artificial intelligence (AI) have demonstrated high performance and efficiency in a wide range of applications such as power plants and smart factories. However, due to the inherent reliance of AI systems on the quality of training data, they still demonstrate poor performance in certain environments. Especially in hazardous facilities with constrained data collection, deploying these systems remains a challenge. In this paper, we propose Generative Anomaly Detection using Prototypical Networks (GAD-PN) designed to detect anomalies using only a limited number of normal samples. GAD-PN is a structure that integrates CycleGAN with Prototypical Networks (PNs), learning from metadata similar to the target environment. This approach enables the collection of data that are difficult to gather in real-world environments by using simulation or demonstration models, thus providing opportunities to learn a variety of environmental parameters under ideal and normal conditions. During the inference phase, PNs can classify normal and leak samples using only a small number of normal data from the target environment by prototypes that represent normal and abnormal features. We also complement the challenge of collecting anomaly data by generating anomaly data from normal data using CycleGAN trained on anomaly features. It can also be adapted to various environments that have similar anomalous scenarios, regardless of differences in environmental parameters. To validate the proposed structure, data were collected specifically targeting pipe leakage scenarios, which are significant problems in environments such as power plants. In addition, acoustic ultrasound signals were collected from the pipe nozzles in three different environments. As a result, the proposed model achieved a leak detection accuracy of over 90% in all environments, even with only a small number of normal data. This performance shows an average improvement of approximately 30% compared with traditional unsupervised learning models trained with a limited dataset.

RESUMEN

The imperative to preserve environmental resources has transcended traditional conservation efforts, becoming a crucial element for sustaining life. Our deep interconnectedness with the natural environment, which directly impacts our well-being, emphasizes this urgency. Contaminants such as leachate from landfills are increasingly threatening groundwater, a vital resource that provides drinking water for nearly half of the global population. This critical environmental threat requires advanced detection and monitoring solutions to effectively safeguard our groundwater resources. To address this pressing need, we introduce the Multifaceted Anomaly Detection Framework (MADF), which integrates Electrical Resistivity Tomography (ERT) with advanced machine learning models-Isolation Forest (IF), One-Class Support Vector Machines (OC-SVM), and Local Outlier Factor (LOF). MADF processes and analyzes ERT data, employing these hybrid machine learning models to identify and quantify anomaly signals accurately via the majority vote strategy. Applied to the Chaling landfill site in Zhuzhou, China, MADF demonstrated significant improvements in detection capability. The framework enhanced the precision of anomaly detection, evidenced by higher Youden Index values (≈ 6.216%), with a 30% increase in sensitivity and a 25% reduction in false positives compared to traditional ERT inversion methods. Indeed, these enhancements are crucial for effective environmental monitoring, where the cost of missing a leak could be catastrophic, and for reducing unnecessary interventions that can be resource-intensive. These results underscore MADF's potential as a robust tool for proactive environmental management, offering a scalable and adaptable solution for comprehensive landfill monitoring and pollution prevention across varied environmental settings.

Asunto(s)

RESUMEN

Identifying anomalies in multi-dimensional sequential data is crucial for ensuring optimal performance across various domains and in large-scale systems. Traditional contrastive methods utilize feature similarity between different features extracted from multidimensional raw inputs as an indicator of anomaly severity. However, the complex objective functions and meticulously designed modules of these methods often lead to efficiency issues and a lack of interpretability. Our study introduces a structural framework called SimDetector, which is a Local-Global Multi-Scale Similarity Contrast network. Specifically, the restructured and enhanced GRU module extracts more generalized local features, including long-term cyclical trends. The multi-scale sparse attention module efficiently extracts multi-scale global features with pattern information. Additionally, we modified the KL divergence to suit the characteristics of time series anomaly detection, proposing a symmetric absolute KL divergence that focuses more on overall distribution differences. The proposed method achieves results that surpass or approach the State-of-the-Art (SOTA) on multiple real-world datasets and synthetic datasets, while also significantly reducing Multiply-Accumulate Operations (MACs) and memory usage.

RESUMEN

Classification systems based on machine learning (ML) models, critical in predictive maintenance and fault diagnosis, are subject to an error rate that can pose significant risks, such as unnecessary downtime due to false alarms. Propagating the uncertainty of input data through the model can define confidence bands to determine whether an input is classifiable, preferring to indicate a result of unclassifiability rather than misclassification. This study presents an electrical fault diagnosis system on asynchronous motors using an artificial neural network (ANN) model trained with vibration measurements. It is shown how vibration analysis can be effectively employed to detect and locate motor malfunctions, helping reduce downtime, improve process control and lower maintenance costs. In addition, measurement uncertainty information is introduced to increase the reliability of the diagnosis system, ensuring more accurate and preventive decisions.