Fully learnable deep wavelet transform for unsupervised monitoring of high-frequency time series.

High-frequency (HF) signals are ubiquitous in the industrial world and are of great use for monitoring of industrial assets. Most deep-learning tools are designed for inputs of fixed and/or very limited size and many successful applications of deep learning to the industrial context use as inputs extracted features, which are a manually and often arduously obtained compact representation of the original signal. In this paper, we propose a fully unsupervised deep-learning framework that is able to extract a meaningful and sparse representation of raw HF signals. We embed in our architecture important properties of the fast discrete wavelet transform (FDWT) such as 1) the cascade algorithm; 2) the conjugate quadrature filter property that links together the wavelet, the scaling, and transposed filter functions; and 3) the coefficient denoising. Using deep learning, we make this architecture fully learnable: Both the wavelet bases and the wavelet coefficient denoising become learnable. To achieve this objective, we propose an activation function that performs a learnable hard thresholding of the wavelet coefficients. With our framework, the denoising FDWT becomes a fully learnable unsupervised tool that does not require any type of pre- or postprocessing or any prior knowledge on wavelet transform. We demonstrate the benefits of embedding all these properties on three machine-learning tasks performed on open-source sound datasets. We perform an ablation study of the impact of each property on the performance of the architecture, achieve results well above baseline, and outperform other state-of-the-art methods.

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.

AI-Enhanced Detection of Clinically Relevant Structural and Functional Anomalies in MRI: Traversing the Landscape of Conventional to Explainable Approaches.

Anomaly detection in medical imaging, particularly within the realm of magnetic resonance imaging (MRI), stands as a vital area of research with far-reaching implications across various medical fields. This review meticulously examines the integration of artificial intelligence (AI) in anomaly detection for MR images, spotlighting its transformative impact on medical diagnostics. We delve into the forefront of AI applications in MRI, exploring advanced machine learning (ML) and deep learning (DL) methodologies that are pivotal in enhancing the precision of diagnostic processes. The review provides a detailed analysis of preprocessing, feature extraction, classification, and segmentation techniques, alongside a comprehensive evaluation of commonly used metrics. Further, this paper explores the latest developments in ensemble methods and explainable AI, offering insights into future directions and potential breakthroughs. This review synthesizes current insights, offering a valuable guide for researchers, clinicians, and medical imaging experts. It highlights AI's crucial role in improving the precision and speed of detecting key structural and functional irregularities in MRI. Our exploration of innovative techniques and trends furthers MRI technology development, aiming to refine diagnostics, tailor treatments, and elevate patient care outcomes. LEVEL OF EVIDENCE: 5 TECHNICAL EFFICACY: Stage 1.

Early warning systems for malaria outbreaks in Thailand: an anomaly detection approach.

BACKGROUND: Malaria continues to pose a significant health threat. Rapid identification of malaria infections and the deployment of active surveillance tools are crucial for achieving malaria elimination in regions where malaria is endemic, such as certain areas of Thailand. In this study, an anomaly detection system is introduced as an early warning mechanism for potential malaria outbreaks in countries like Thailand. METHODS: Unsupervised clustering-based, and time series-based anomaly detection algorithms are developed and compared to identify abnormal malaria activity in Thailand. Additionally, a user interface tailored for anomaly detection is designed, enabling the Thai malaria surveillance team to utilize these algorithms and visualize regions exhibiting unusual malaria patterns. RESULTS: Nine distinct anomaly detection algorithms we developed. Their efficacy in pinpointing verified outbreaks was assessed using malaria case data from Thailand spanning 2012 to 2022. The historical average threshold-based anomaly detection method triggered three times fewer alerts, while correctly identifying the same number of verified outbreaks when compared to the current method used in Thailand. A limitation of this analysis is the small number of verified outbreaks; further consultation with the Division of Vector Borne Disease could help identify more verified outbreaks. The developed dashboard, designed specifically for anomaly detection, allows disease surveillance professionals to easily identify and visualize unusual malaria activity at a provincial level across Thailand. CONCLUSION: An enhanced early warning system is proposed to bolster malaria elimination efforts for countries with a similar malaria profile to Thailand. The developed anomaly detection algorithms, after thorough comparison, have been optimized for integration with the current malaria surveillance infrastructure. An anomaly detection dashboard for Thailand is built and supports early detection of abnormal malaria activity. In summary, the proposed early warning system enhances the identification process for provinces at risk of outbreaks and offers easy integration with Thailand's established malaria surveillance framework.

Multivariate anomaly detection models enhance identification of errors in routine clinical chemistry testing.

OBJECTIVES: Conventional autoverification rules evaluate analytes independently, potentially missing unusual patterns of results indicative of errors such as serum contamination by collection tube additives. This study assessed whether multivariate anomaly detection algorithms could enhance the detection of such errors. METHODS: Multivariate Gaussian, k-nearest neighbours (KNN) distance, and one-class support vector machine (SVM) anomaly detection models, along with conventional limit checks, were developed using a training dataset of 127,451 electrolyte, urea, and creatinine (EUC) results, with a 5 % flagging rate targeted for all approaches. The models were compared with limit checks for their ability to detect atypical EUC results from samples spiked with additives from collection tubes: EDTA, fluoride, sodium citrate, or acid citrate dextrose (n=200 per contaminant). The study additionally assessed the ability of the models to identify 127,449 single-analyte errors, a potential weakness of multivariate models. RESULTS: The KNN distance and SVM models outperformed limit checks for detecting all contaminants (p-values <0.05). The multivariate Gaussian model did not surpass limit checks for detecting EDTA contamination but was superior for detecting the other additives. All models surpassed limit checks for identifying single-analyte errors, with the KNN distance model demonstrating the highest overall sensitivity. CONCLUSIONS: Multivariate anomaly detection models, particularly the KNN distance model, were superior to the conventional approach for detecting serum contamination and single-analyte errors. Developing multivariate approaches to autoverification is warranted to optimise error detection and improve patient safety.

Enhanced patient-based real-time quality control using the graph-based anomaly detection.

OBJECTIVES: Patient-based real-time quality control (PBRTQC) is an alternative tool for laboratories that has gained increasing attention. Despite the progress made by using various algorithms, the problems of data volume imbalance between in-control and out-of-control results, as well as the issue of variation remain challenges. We propose a novel integrated framework using anomaly detection and graph neural network, combining clinical variables and statistical algorithms, to improve the error detection performance of patient-based quality control. METHODS: The testing results of three representative analytes (sodium, potassium, and calcium) and eight independent variables of patients (test date, time, gender, age, department, patient type, and reference interval limits) were collected. Graph-based anomaly detection network was modeled and used to generate control limits. Proportional and random errors were simulated for performance evaluation. Five mainstream PBRTQC statistical algorithms were chosen for comparison. RESULTS: The framework of a patient-based graph anomaly detection network for real-time quality control (PGADQC) was established and proven feasible for error detection. Compared with classic PBRTQC, the PGADQC showed a more balanced performance for both positive and negative biases. For different analytes, the average number of patient samples until error detection (ANPed) of PGADQC decreased variably, and reductions could reach up to approximately 95 % at a small bias of 0.02 taking calcium as an example. CONCLUSIONS: The PGADQC is an effective framework for patient-based quality control, integrating statistical and artificial intelligence algorithms. It improves error detection in a data-driven fashion and provides a new approach for PBRTQC from the data science perspective.

An automatic analysis and quality assurance method for lymphocyte subset identification.

OBJECTIVES: Lymphocyte subsets are the predictors of disease diagnosis, treatment, and prognosis. Determination of lymphocyte subsets is usually carried out by flow cytometry. Despite recent advances in flow cytometry analysis, most flow cytometry data can be challenging with manual gating, which is labor-intensive, time-consuming, and error-prone. This study aimed to develop an automated method to identify lymphocyte subsets. METHODS: We propose a knowledge-driven combined with data-driven method which can gate automatically to achieve subset identification. To improve accuracy and stability, we have implemented a Loop Adjustment Gating to optimize the gating result of the lymphocyte population. Furthermore, we have incorporated an anomaly detection mechanism to issue warnings for samples that might not have been successfully analyzed, ensuring the quality of the results. RESULTS: The evaluation showed a 99.2 % correlation between our method results and manual analysis with a dataset of 2,000 individual cases from lymphocyte subset assays. Our proposed method attained 97.7 % accuracy for all cases and 100 % for the high-confidence cases. With our automated method, 99.1 % of manual labor can be saved when reviewing only the low-confidence cases, while the average turnaround time required is only 29 s, reducing by 83.7 %. CONCLUSIONS: Our proposed method can achieve high accuracy in flow cytometry data from lymphocyte subset assays. Additionally, it can save manual labor and reduce the turnaround time, making it have the potential for application in the laboratory.

Convolutional autoencoder based on latent subspace projection for anomaly detection.

Image anomaly detection (AD) is widely researched on many occasions in computer vision tasks. High-dimensional data, such as image data, with noise and complex background is still challenging to detect anomalies under the situation that imbalanced or incomplete data are available. Some deep learning methods can be trained in an unsupervised way and map the original input into low-dimensional manifolds to predict larger differences in anomalies according to normal ones by dimension reduction. However, training a single low-dimension latent space is limited to present the low-dimensional features due to the fact that the noise and irreverent features are mapped into this space, resulting in that the manifolds are not discriminative for detecting anomalies. To address this problem, a new autoencoder framework is proposed in this study with two trainable mutually orthogonal complementary subspaces in the latent space, by latent subspace projection (LSP) mechanism, which is named as LSP-CAE. Specifically, latent subspace projection is used to train the latent image subspace (LIS) and the latent kernel subspace (LKS) in the latent space of the autoencoder-like model respectively, which can enhance learning power of different features from the input instance. The features of normal data are projected into the latent image subspace, while the latent kernel subspace is trained to extract the irrelevant information according to normal features by end-to-end training. To verify the generality and effectiveness of the proposed method, we replace the convolutional network with the fully-connected network contucted in the real-world medical datasets. The anomaly score based on projection norms in two subspace is used to evaluate the anomalies in the testing. Consequently, our proposed method can achieve the best performance according to four public datasets in comparison of the state-of-the-art methods.

EHR-BERT: A BERT-based model for effective anomaly detection in electronic health records.

OBJECTIVE: Physicians and clinicians rely on data contained in electronic health records (EHRs), as recorded by health information technology (HIT), to make informed decisions about their patients. The reliability of HIT systems in this regard is critical to patient safety. Consequently, better tools are needed to monitor the performance of HIT systems for potential hazards that could compromise the collected EHRs, which in turn could affect patient safety. In this paper, we propose a new framework for detecting anomalies in EHRs using sequence of clinical events. This new framework, EHR-Bidirectional Encoder Representations from Transformers (BERT), is motivated by the gaps in the existing deep-learning related methods, including high false negatives, sub-optimal accuracy, higher computational cost, and the risk of information loss. EHR-BERT is an innovative framework rooted in the BERT architecture, meticulously tailored to navigate the hurdles in the contemporary BERT method; thus, enhancing anomaly detection in EHRs for healthcare applications. METHODS: The EHR-BERT framework was designed using the Sequential Masked Token Prediction (SMTP) method. This approach treats EHRs as natural language sentences and iteratively masks input tokens during both training and prediction stages. This method facilitates the learning of EHR sequence patterns in both directions for each event and identifies anomalies based on deviations from the normal execution models trained on EHR sequences. RESULTS: Extensive experiments on large EHR datasets across various medical domains demonstrate that EHR-BERT markedly improves upon existing models. It significantly reduces the number of false positives and enhances the detection rate, thus bolstering the reliability of anomaly detection in electronic health records. This improvement is attributed to the model's ability to minimize information loss and maximize data utilization effectively. CONCLUSION: EHR-BERT showcases immense potential in decreasing medical errors related to anomalous clinical events, positioning itself as an indispensable asset for enhancing patient safety and the overall standard of healthcare services. The framework effectively overcomes the drawbacks of earlier models, making it a promising solution for healthcare professionals to ensure the reliability and quality of health data.

Machine learning and user interface for cyber risk management of water infrastructure.

With the continuous modernization of water plants, the risk of cyberattacks on them potentially endangers public health and the economic efficiency of water treatment and distribution. This article signifies the importance of developing improved techniques to support cyber risk management for critical water infrastructure, given an evolving threat environment. In particular, we propose a method that uniquely combines machine learning, the theory of belief functions, operational performance metrics, and dynamic visualization to provide the required granularity for attack inference, localization, and impact estimation. We illustrate how the focus on visual domain-aware anomaly exploration leads to performance improvement, more precise anomaly localization, and effective risk prioritization. Proposed elements of the method can be used independently, supporting the exploration of various anomaly detection methods. It thus can facilitate the effective management of operational risk by providing rich context information and bridging the interpretation gap.

Intelligent systems for sitting posture monitoring and anomaly detection: an overview.

The number of people who need to use wheelchair for proper mobility is increasing. The integration of technology into these devices enables the simultaneous and objective assessment of posture, while also facilitating the concurrent monitoring of the functional status of wheelchair users. In this way, both the health personnel and the user can be provided with relevant information for the recovery process. This information can be used to carry out an early adaptation of the rehabilitation of patients, thus allowing to prevent further musculoskeletal problems, as well as risk situations such as ulcers or falls. Thus, a higher quality of life is promoted in affected individuals. As a result, this paper presents an orderly and organized analysis of the existing postural diagnosis systems for detecting sitting anomalies in the literature. This analysis can be divided into two parts that compose such postural diagnosis: on the one hand, the monitoring devices necessary for the collection of postural data and, on the other hand, the techniques used for anomaly detection. These anomaly detection techniques will be explained under two different approaches: the traditional generalized approach followed to date by most works, where anomalies are treated as incorrect postures, and a new individualized approach treating anomalies as changes with respect to the normal sitting pattern. In this way, the advantages, limitations and opportunities of the different techniques are analyzed. The main contribution of this overview paper is to synthesize and organize information, identify trends, and provide a comprehensive understanding of sitting posture diagnosis systems, offering researchers an accessible resource for navigating the current state of knowledge of this particular field.

Artificial Intelligence-Based Anomaly Detection Technology over Encrypted Traffic: A Systematic Literature Review.

As cyber-attacks increase in unencrypted communication environments such as the traditional Internet, protected communication channels based on cryptographic protocols, such as transport layer security (TLS), have been introduced to the Internet. Accordingly, attackers have been carrying out cyber-attacks by hiding themselves in protected communication channels. However, the nature of channels protected by cryptographic protocols makes it difficult to distinguish between normal and malicious network traffic behaviors. This means that traditional anomaly detection models with features from packets extracted a deep packet inspection (DPI) have been neutralized. Recently, studies on anomaly detection using artificial intelligence (AI) and statistical characteristics of traffic have been proposed as an alternative. In this review, we provide a systematic review for AI-based anomaly detection techniques over encrypted traffic. We set several research questions on the review topic and collected research according to eligibility criteria. Through the screening process and quality assessment, 30 research articles were selected with high suitability to be included in the review from the collected literature. We reviewed the selected research in terms of dataset, feature extraction, feature selection, preprocessing, anomaly detection algorithm, and performance indicators. As a result of the literature review, it was confirmed that various techniques used for AI-based anomaly detection over encrypted traffic were used. Some techniques are similar to those used for AI-based anomaly detection over unencrypted traffic, but some technologies are different from those used for unencrypted traffic.

Scalable Learning Framework for Detecting New Types of Twitter Spam with Misuse and Anomaly Detection.

The growing popularity of social media has engendered the social problem of spam proliferation through this medium. New spam types that evade existing spam detection systems are being developed continually, necessitating corresponding countermeasures. This study proposes an anomaly detection-based framework to detect new Twitter spam, which works by modeling the characteristics of non-spam tweets and using anomaly detection to classify tweets deviating from this model as anomalies. However, because modeling varied non-spam tweets is challenging, the technique's spam detection and false positive (FP) rates are low and high, respectively. To overcome this shortcoming, anomaly detection is performed on known spam tweets pre-detected using a trained decision tree while modeling normal tweets. A one-class support vector machine and an autoencoder with high detection rates are used for anomaly detection. The proposed framework exhibits superior detection rates for unknown spam compared to conventional techniques, while maintaining equivalent or improved detection and FP rates for known spam. Furthermore, the framework can be adapted to changes in spam conditions by adjusting the costs of detection errors.

An Unsupervised Method for Industrial Image Anomaly Detection with Vision Transformer-Based Autoencoder.

Existing industrial image anomaly detection techniques predominantly utilize codecs based on convolutional neural networks (CNNs). However, traditional convolutional autoencoders are limited to local features, struggling to assimilate global feature information. CNNs' generalizability enables the reconstruction of certain anomalous regions. This is particularly evident when normal and abnormal regions, despite having similar pixel values, contain different semantic information, leading to ineffective anomaly detection. Furthermore, collecting abnormal image samples during actual industrial production poses challenges, often resulting in data imbalance. To mitigate these issues, this study proposes an unsupervised anomaly detection model employing the Vision Transformer (ViT) architecture, incorporating a Transformer structure to understand the global context between image blocks, thereby extracting a superior representation of feature information. It integrates a memory module to catalog normal sample features, both to counteract anomaly reconstruction issues and bolster feature representation, and additionally introduces a coordinate attention (CA) mechanism to intensify focus on image features at both spatial and channel dimensions, minimizing feature information loss and thereby enabling more precise anomaly identification and localization. Experiments conducted on two public datasets, MVTec AD and BeanTech AD, substantiate the method's effectiveness, demonstrating an approximate 20% improvement in average AUROC% at the image level over traditional convolutional encoders.

Anomaly Detection in Railway Sensor Data Environments: State-of-the-Art Methods and Empirical Performance Evaluation.

To date, significant progress has been made in the field of railway anomaly detection using technologies such as real-time data analytics, the Internet of Things, and machine learning. As technology continues to evolve, the ability to detect and respond to anomalies in railway systems is once again in the spotlight. However, railway anomaly detection faces challenges related to the vast infrastructure, dynamic conditions, aging infrastructure, and adverse environmental conditions on the one hand, and the scale, complexity, and critical safety implications of railway systems on the other. Our study is underpinned by the three objectives. Specifically, we aim to identify time series anomaly detection methods applied to railway sensor device data, recognize the advantages and disadvantages of these methods, and evaluate their effectiveness. To address the research objectives, the first part of the study involved a systematic literature review and a series of controlled experiments. In the case of the former, we adopted well-established guidelines to structure and visualize the review. In the second part, we investigated the effectiveness of selected machine learning methods. To evaluate the predictive performance of each method, a five-fold cross-validation approach was applied to ensure the highest accuracy and generality. Based on the calculated accuracy, the results show that the top three methods are CatBoost (96%), Random Forest (91%), and XGBoost (90%), whereas the lowest accuracy is observed for One-Class Support Vector Machines (48%), Local Outlier Factor (53%), and Isolation Forest (55%). As the industry moves toward a zero-defect paradigm on a global scale, ongoing research efforts are focused on improving existing methods and developing new ones that contribute to the safety and quality of rail transportation. In this sense, there are at least four avenues for future research worth considering: testing richer data sets, hyperparameter optimization, and implementing other methods not included in the current study.

Determinants of Maximum Magnetic Anomaly Detection Distance.

The maximum detection distance is usually the primary concern of magnetic anomaly detection (MAD). Intuition tells us that larger object size, stronger magnetization and finer measurement resolution guarantee a further detectable distance. However, the quantitative relationship between detection distance and the above determinants is seldom studied. In this work, unmanned aerial vehicle-based MAD field experiments are conducted on cargo vessels and NdFeB magnets as typical magnetic objects to give a set of visualized magnetic field flux density images. Isometric finite element models are established, calibrated and analyzed according to the experiment configuration. A maximum detectable distance map as a function of target size and measurement resolution is then obtained from parametric sweeping on an experimentally calibrated finite element analysis model. We find that the logarithm of detectable distance is positively proportional to the logarithm of object size while negatively proportional to the logarithm of resolution, within the ranges of 1 m~500 m and 1 pT~1 µT, respectively. A three-parameter empirical formula (namely distance-size-resolution logarithmic relationship) is firstly developed to determine the most economic sensor configuration for a given detection task, to estimate the maximum detection distance for a given magnetic sensor and object, or to evaluate minimum detectable object size at a given magnetic anomaly detection scenario.

Towards Reliability in Smart Water Sensing Technology: Evaluating Classical Machine Learning Models for Outlier Detection.

In recent years, smart water sensing technology has played a crucial role in water management, addressing the pressing need for efficient monitoring and control of water resources analysis. The challenge in smart water sensing technology resides in ensuring the reliability and accuracy of the data collected by sensors. Outliers are a well-known problem in smart sensing as they can negatively affect the viability of useful analysis and make it difficult to evaluate pertinent data. In this study, we evaluate the performance of four sensors: electrical conductivity (EC), dissolved oxygen (DO), temperature (Temp), and pH. We implement four classical machine learning models: support vector machine (SVM), artifical neural network (ANN), decision tree (DT), and isolated forest (iForest)-based outlier detection as a pre-processing step before visualizing the data. The dataset was collected by a real-time smart water sensing monitoring system installed in Brussels' lakes, rivers, and ponds. The obtained results clearly show that the SVM outperforms the other models, showing 98.38% F1-score rates for pH, 96.98% F1-score rates for temp, 97.88% F1-score rates for DO, and 98.11% F1-score rates for EC. Furthermore, ANN also achieves a significant results, establishing it as a viable alternative.

Malware Detection for Internet of Things Using One-Class Classification.

The increasing usage of interconnected devices within the Internet of Things (IoT) and Industrial IoT (IIoT) has significantly enhanced efficiency and utility in both personal and industrial settings but also heightened cybersecurity vulnerabilities, particularly through IoT malware. This paper explores the use of one-class classification, a method of unsupervised learning, which is especially suitable for unlabeled data, dynamic environments, and malware detection, which is a form of anomaly detection. We introduce the TF-IDF method for transforming nominal features into numerical formats that avoid information loss and manage dimensionality effectively, which is crucial for enhancing pattern recognition when combined with n-grams. Furthermore, we compare the performance of multi-class vs. one-class classification models, including Isolation Forest and deep autoencoder, that are trained with both benign and malicious NetFlow samples vs. trained exclusively on benign NetFlow samples. We achieve 100% recall with precision rates above 80% and 90% across various test datasets using one-class classification. These models show the adaptability of unsupervised learning, especially one-class classification, to the evolving malware threats in the IoT domain, offering insights into enhancing IoT security frameworks and suggesting directions for future research in this critical area.

Development and Integration of a Digital Twin Model for a Real Hydroelectric Power Plant.

In this study, a digital twin model of a hydroelectric power plant has been created. Models of the entire power plant have been created and malfunction situations of a sensor located after the inlet valve of the plant have been analyzed using a programmable logic controller (PLC). As a feature of the digital twin (DT), the error prediction and prevention function has been studied specifically for the pressure sensor. The accuracy and reliability of the data obtained from the sensor are compared with the data obtained from the DT model. The comparison results are evaluated and erroneous data are identified. In this way, it is determined whether the malfunction occurring in the system is a real malfunction or a malfunction caused by measurement or connection errors. In the case of sensor failure or measurement-related malfunction, this situation is determined through the digital twin-based control mechanism. In the case of actual failure, the system is stopped, but in the case of measurement or connection errors, since the data are calculated by the DT model, the value in the specified region is known and thus there is no need to stop the system. This prevents production loss in the hydroelectric power plant by ensuring the continuity of the system in case of errors.

Leak Event Diagnosis for Power Plants: Generative Anomaly Detection Using Prototypical Networks.

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.