scholarly journals Anomaly Detection in Predictive Maintenance: A New Evaluation Framework for Temporal Unsupervised Anomaly Detection Algorithms

2021 ◽  
Author(s):  
Jacinto Carrasco ◽  
Irina Markova ◽  
David Lopez ◽  
Ignacio Aguilera-Martos ◽  
Diego Garcia-Gil ◽  
...  
Keyword(s):  
Anomaly Detection ◽  
Evaluation Framework ◽  
Predictive Maintenance ◽  
Detection Algorithms ◽  
Unsupervised Anomaly Detection

scholarly journals Unsupervised Anomaly Detection with Distillated Teacher-Student Network Ensemble

Entropy ◽  
2021 ◽  
Vol 23 (2) ◽  
pp. 201
Author(s):  
Qinfeng Xiao ◽  
Jing Wang ◽  
Youfang Lin ◽  
Wenbo Gongsa ◽  
Ganghui Hu ◽  
...  
Keyword(s):  
Anomaly Detection ◽  
Multivariate Data ◽  
Failure Detection ◽  
Superior Performance ◽  
Detection Algorithms ◽  
Teacher Student ◽  
Model Complex ◽  
Unsupervised Anomaly Detection ◽  
Real World Datasets ◽  
Complex Features

We address the problem of unsupervised anomaly detection for multivariate data. Traditional machine learning based anomaly detection algorithms rely on specific assumptions of normal patterns and fail to model complex feature interactions and relations. Recently, existing deep learning based methods are promising for extracting representations from complex features. These methods train an auxiliary task, e.g., reconstruction and prediction, on normal samples. They further assume that anomalies fail to perform well on the auxiliary task since they are never trained during the model optimization. However, the assumption does not always hold in practice. Deep models may also perform the auxiliary task well on anomalous samples, leading to the failure detection of anomalies. To effectively detect anomalies for multivariate data, this paper introduces a teacher-student distillation based framework Distillated Teacher-Student Network Ensemble (DTSNE). The paradigm of the teacher-student distillation is able to deal with high-dimensional complex features. In addition, an ensemble of student networks provides a better capability to avoid generalizing the auxiliary task performance on anomalous samples. To validate the effectiveness of our model, we conduct extensive experiments on real-world datasets. Experimental results show superior performance of DTSNE over competing methods. Analysis and discussion towards the behavior of our model are also provided in the experiment section.

scholarly journals Add-On Anomaly Threshold Technique for Improving Unsupervised Intrusion Detection on SCADA Data

Electronics ◽  
2020 ◽  
Vol 9 (6) ◽  
pp. 1017 ◽  
Author(s):  
Abdulmohsen Almalawi ◽  
Adil Fahad ◽  
Zahir Tari ◽  
Asif Irshad Khan ◽  
Nouf Alzahrani ◽  
...  
Keyword(s):  
Anomaly Detection ◽  
Supervisory Control ◽  
State Of The Art ◽  
Current Approach ◽  
Industrial Processes ◽  
Parameter Choice ◽  
Detection Algorithms ◽  
Detection Approach ◽  
Unsupervised Anomaly Detection ◽  
Threshold Technique

Supervisory control and data acquisition (SCADA) systems monitor and supervise our daily infrastructure systems and industrial processes. Hence, the security of the information systems of critical infrastructures cannot be overstated. The effectiveness of unsupervised anomaly detection approaches is sensitive to parameter choices, especially when the boundaries between normal and abnormal behaviours are not clearly distinguishable. Therefore, the current approach in detecting anomaly for SCADA is based on the assumptions by which anomalies are defined; these assumptions are controlled by a parameter choice. This paper proposes an add-on anomaly threshold technique to identify the observations whose anomaly scores are extreme and significantly deviate from others, and then such observations are assumed to be ”abnormal”. The observations whose anomaly scores are significantly distant from ”abnormal” ones will be assumed as ”normal”. Then, the ensemble-based supervised learning is proposed to find a global and efficient anomaly threshold using the information of both ”normal”/”abnormal” behaviours. The proposed technique can be used for any unsupervised anomaly detection approach to mitigate the sensitivity of such parameters and improve the performance of the SCADA unsupervised anomaly detection approaches. Experimental results confirm that the proposed technique achieved a significant improvement compared to the state-of-the-art of two unsupervised anomaly detection algorithms.

scholarly journals Evaluation of Unsupervised Anomaly Detection Methods in Sentiment Mining

2019 ◽  
Vol 8 (9) ◽  
pp. 1080-1085
Keyword(s):  
Anomaly Detection ◽  
Computation Time ◽  
Vital Role ◽  
Detection Methods ◽  
Research Focus ◽  
Comparative Performance ◽  
Detection Techniques ◽  
Detection Algorithms ◽  
Sentiment Mining ◽  
Unsupervised Anomaly Detection

Anomaly detection has vital role in data preprocessing and also in the mining of outstanding points for marketing, network sensors, fraud detection, intrusion detection, stock market analysis. Recent studies have been found to concentrate more on outlier detection for real time datasets. Anomaly detection study is at present focuses on the expansion of innovative machine learning methods and on enhancing the computation time. Sentiment mining is the process to discover how people feel about a particular topic. Though many anomaly detection techniques have been proposed, it is also notable that the research focus lacks a comparative performance evaluation in sentiment mining datasets. In this study, three popular unsupervised anomaly detection algorithms such as density based, statistical based and cluster based anomaly detection methods are evaluated on movie review sentiment mining dataset. This paper will set a base for anomaly detection methods in sentiment mining research. The results show that density based (LOF) anomaly detection method suits best for the movie review sentiment dataset.

An Ensemble Approach for Detecting Anomalous User Behaviors

2018 ◽  
Vol 28 (11n12) ◽  
pp. 1637-1656
Author(s):  
Xiangyu Xi ◽  
Tong Zhang ◽  
Wei Ye ◽  
Zhao Wen ◽  
Shikun Zhang ◽  
...  
Keyword(s):  
Anomaly Detection ◽  
User Behavior ◽  
Behavior Patterns ◽  
Training Set ◽  
Sensitive Data ◽  
False Negatives ◽  
Detection Algorithms ◽  
User Behaviors ◽  
Unsupervised Anomaly Detection ◽  
Isolation Forest

An intruder of a company’s network may use stolen login credentials to silently collect sensitive data. Such malicious user behavior is difficult to detect as long as it does not trigger access violation or data leak alert. In this paper, we propose to use an ensemble of three unsupervised anomaly detection algorithms, namely OCSVM, RNN and Isolation Forest, to detect abnormal user behavior patterns. Besides, an User Behavior Analytics (UBA) Platform is proposed to collect logs, extract features and conduct experiments. The experiment results indicate that our algorithm outperforms each individual algorithm with recall of 96.55% and precision of 91.24% on average, while both OCSVM and RNN suffer from anomalies in the training set, and [Formula: see text] produces more false positives and false negatives in prediction.

scholarly journals Relevance of Drift Components and Unit-to-Unit Variability in the Predictive Maintenance of Low-Cost Electrochemical Sensor Systems in Air Quality Monitoring

Sensors ◽  
2021 ◽  
Vol 21 (9) ◽  
pp. 3298
Author(s):  
Georgi Tancev
Keyword(s):  
Air Quality ◽  
Anomaly Detection ◽  
Low Cost ◽  
Predictive Maintenance ◽  
Quality Monitoring ◽  
Calibration Data ◽  
Sensor Systems ◽  
Air Quality Monitoring ◽  
Measurement Results ◽  
Unsupervised Anomaly Detection

As key components of low-cost sensor systems in air quality monitoring, electrochemical gas sensors have recently received a lot of interest but suffer from unit-to-unit variability and different drift components such as aging and concept drift, depending on the calibration approach. Magnitudes of drift can vary across sensors of the same type, and uniform recalibration intervals might lead to insufficient performance for some sensors. This publication evaluates the opportunity to perform predictive maintenance solely by the use of calibration data, thereby detecting the optimal moment for recalibration and improving recalibration intervals and measurement results. Specifically, the idea is to define confidence regions around the calibration data and to monitor the relative position of incoming sensor signals during operation. The emphasis lies on four algorithms from unsupervised anomaly detection—namely, robust covariance, local outlier factor, one-class support vector machine, and isolation forest. Moreover, the behavior of unit-to-unit variability and various drift components on the performance of the algorithms is discussed by analyzing published field experiments and by performing Monte Carlo simulations based on sensing and aging models. Although unsupervised anomaly detection on calibration data can disclose the reliability of measurement results, simulation results suggest that this does not translate to every sensor system due to unfavorable arrangements of baseline drifts paired with sensitivity drift.

scholarly journals A Novel Active Anomaly Discovery Method and its Applications in Additive Manufacturing

2021 ◽  
Author(s):  
Bo Shen ◽  
Zhenyu Kong
Keyword(s):  
Additive Manufacturing ◽  
Anomaly Detection ◽  
State Of The Art ◽  
Detection Algorithm ◽  
The State ◽  
Detection Accuracy ◽  
Detection Algorithms ◽  
Detection Analysis ◽  
Unsupervised Anomaly Detection ◽  
Discovery Method

Anomaly detection aims to identify the true anomalies from a given set of data instances. Unsupervised anomaly detection algorithms are applied to an unlabeled dataset by producing a ranked list based on anomaly scores. Unfortunately, due to the inherent limitations, many of the top-ranked instances by unsupervised algorithms are not anomalies or not interesting from an application perspective, which leads to high false-positive rates. Active anomaly discovery (AAD) is proposed to overcome this deficiency, which sequentially selects instances to get the labeling information and incorporate it into the anomaly detection algorithm to improve the detection accuracy iteratively. However, labeling is often costly. Therefore, the way to balance detection accuracy and labeling cost is essential. Along this line, this paper proposes a novel AAD method to achieve the goal. Our approach is based on the state-of-the-art unsupervised anomaly detection algorithm, namely, Isolation Forest, to extract features. Thereafter, the sparsity of the extracted features is utilized to improve its anomaly detection performance. To enforce the sparsity of the features and subsequent improvement of the detection analysis, a new algorithm based on online gradient descent, namely, Sparse Approximated Linear Anomaly Discovery (SALAD), is proposed with its theoretical Regret analysis. Extensive experiments on both open-source and additive manufacturing datasets demonstrate that the proposed algorithm significantly outperforms the state-of-the-art algorithms for anomaly detection.

scholarly journals A Novel Active Anomaly Discovery Method and its Applications in Additive Manufacturing

2021 ◽  
Author(s):  
Bo Shen ◽  
Zhenyu Kong
Keyword(s):  
Additive Manufacturing ◽  
Anomaly Detection ◽  
State Of The Art ◽  
Detection Algorithm ◽  
The State ◽  
Detection Accuracy ◽  
Detection Algorithms ◽  
Detection Analysis ◽  
Unsupervised Anomaly Detection ◽  
Discovery Method

Anomaly detection aims to identify the true anomalies from a given set of data instances. Unsupervised anomaly detection algorithms are applied to an unlabeled dataset by producing a ranked list based on anomaly scores. Unfortunately, due to the inherent limitations, many of the top-ranked instances by unsupervised algorithms are not anomalies or not interesting from an application perspective, which leads to high false-positive rates. Active anomaly discovery (AAD) is proposed to overcome this deficiency, which sequentially selects instances to get the labeling information and incorporate it into the anomaly detection algorithm to improve the detection accuracy iteratively. However, labeling is often costly. Therefore, the way to balance detection accuracy and labeling cost is essential. Along this line, this paper proposes a novel AAD method to achieve the goal. Our approach is based on the state-of-the-art unsupervised anomaly detection algorithm, namely, Isolation Forest, to extract features. Thereafter, the sparsity of the extracted features is utilized to improve its anomaly detection performance. To enforce the sparsity of the features and subsequent improvement of the detection analysis, a new algorithm based on online gradient descent, namely, Sparse Approximated Linear Anomaly Discovery (SALAD), is proposed with its theoretical Regret analysis. Extensive experiments on both open-source and additive manufacturing datasets demonstrate that the proposed algorithm significantly outperforms the state-of-the-art algorithms for anomaly detection.

scholarly journals Detection of Insulin Pump Malfunctioning to Improve Safety in Artificial Pancreas Using Unsupervised Algorithms

2019 ◽  
Vol 13 (6) ◽  
pp. 1065-1076 ◽  
Author(s):  
Lorenzo Meneghetti ◽  
Gian Antonio Susto ◽  
Simone Del Favero
Keyword(s):  
Anomaly Detection ◽  
New Technologies ◽  
Insulin Pump ◽  
Artificial Pancreas ◽  
False Positives ◽  
New Paradigm ◽  
Detection Algorithms ◽  
Unsupervised Anomaly Detection ◽  
Unsupervised Algorithms ◽  
Optimal Feature

Background: Recent development of automated closed-loop (CL) insulin delivery systems, the so-called artificial pancreas (AP), improved the quality of type 1 diabetes (T1D) therapy. As new technologies emerge, patients put increasing trust in their therapeutic devices; therefore, it becomes increasingly important to detect malfunctioning affecting such devices. In this work, we explore a new paradigm to detect insulin pump faults (IPFs) that use unsupervised anomaly detection. Methods: We generated CL data corrupted with IPFs using the latest version of the T1D Padova/UVA simulator. From the data, we extracted several features capable to describe the patient dynamics and making more apparent suspicious data portions. Then, a feature selection is performed to determine the optimal feature set. Finally, the performance of several popular unsupervised anomaly detection algorithms is analyzed and compared on the identified optimal feature set. Results: Using the identified optimal configuration, the best performance is obtained by the Histogram-Based Outlier Score (HBOS) algorithm, which detected 87% of the IPF with only 0.08 false positives per day on average. Isolation forest is the best algorithm that offers more conservative performances, detection of 85% of the faults but only 0.06 false positives per day on average. Conclusion: Unsupervised anomaly detection algorithms can be used effectively to detect IPFs and improve the safety of the AP. Future studies will be dedicated to test the presented method inside dedicated clinical trials.

Sign in / Sign up

Export Citation Format

Share Document