• Journal of Intelligence and Information Systems
• /
• v.29 no.3
• /
• pp.229-247
• /
• 2023

With the increasing emphasis on anomaly detection across various fields, diverse anomaly detection algorithms have been developed for various data types and anomaly patterns. However, the performance of anomaly detection algorithms is generally evaluated on publicly available datasets, and the specific performance of each algorithm on anomalies of particular types remains unexplored. Consequently, selecting an appropriate anomaly detection algorithm for specific analytical contexts poses challenges. Therefore, in this paper, we aim to investigate the types of anomalies and various attributes of data. Subsequently, we intend to propose approaches that can assist in the selection of appropriate anomaly detection algorithms based on this understanding. Specifically, this study compares the performance of anomaly detection algorithms for four types of anomalies: local, global, contextual, and clustered anomalies. Through further analysis, the impact of label availability, data quantity, and dimensionality on algorithm performance is examined. Experimental results demonstrate that the most effective algorithm varies depending on the type of anomaly, and certain algorithms exhibit stable performance even in the absence of anomaly-specific information. Furthermore, in some types of anomalies, the performance of unsupervised anomaly detection algorithms was observed to be lower than that of supervised and semi-supervised learning algorithms. Lastly, we found that the performance of most algorithms is more strongly influenced by the type of anomalies when the data quantity is relatively scarce or abundant. Additionally, in cases of higher dimensionality, it was noted that excellent performance was exhibited in detecting local and global anomalies, while lower performance was observed for clustered anomaly types.

• Journal of Korean Society for Quality Management
• /
• v.50 no.3
• /
• pp.459-471
• /
• 2022

Purpose: The purpose of this study was to increase prediction accuracy for an anomaly interval identified using an artificial intelligence-based time series anomaly detection technique by establishing a pre-processing process. Methods: Significant variables were extracted by applying feature selection techniques, and anomalies were derived using the TadGAN time series anomaly detection algorithm. After applying machine learning and deep learning methodologies using normal section data (excluding anomaly sections), the explanatory power of the anomaly sections was demonstrated through performance comparison. Results: The results of the machine learning methodology, the performance was the best when SHAP and TadGAN were applied, and the results in the deep learning, the performance was excellent when Chi-square Test and TadGAN were applied. Comparing each performance with the papers applied with a Conventional methodology using the same data, it can be seen that the performance of the MLR was significantly improved to 15%, Random Forest to 24%, XGBoost to 30%, Lasso Regression to 73%, LSTM to 17% and GRU to 19%. Conclusion: Based on the proposed process, when detecting unsupervised learning anomalies of data that are not actually labeled in various fields such as cyber security, financial sector, behavior pattern field, SNS. It is expected to prove the accuracy and explanation of the anomaly detection section and improve the performance of the model.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.10a
• /
• pp.19-21
• /
• 2022

Anomaly detection using self-supervised learning typically generates synthetic data to learn to classify normal and abnormal, and uses real abnormal data as test data to measure anomaly detection performance. In a study using this method to generate synthetic data similar to normal data, anomaly detection was carried out by generating synthetic data by cutting and pasting a specific patch from the original image. In this way, the degree of similarity to normal data depends on the number and size of patches, which affects anomaly detection performance. In this paper, synthetic data were generated by varying patch sizes and numbers, and then similarity and analysis with normal data were conducted using a pre-trained model, and anomaly detection performance was measured by learning the model.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.10 no.8
• /
• pp.3865-3883
• /
• 2016

Infrastructure as a Service (IaaS) encapsulates computer hardware into a large amount of virtual and manageable instances mainly in the form of virtual machine (VM), and provides rental service for users. Currently, VM anomaly incidents occasionally occur, which leads to performance issues and even downtime. This paper aims at detecting anomalous VMs based on performance metrics data of VMs. Due to the dynamic nature and increasing scale of IaaS, detecting anomalous VMs from voluminous correlated and non-Gaussian monitored performance data is a challenging task. This paper designs an anomaly detection framework to solve this challenge. First, it collects 53 performance metrics to reflect the running state of each VM. The collected performance metrics are testified not to follow the Gaussian distribution. Then, it employs independent components analysis (ICA) instead of principal component analysis (PCA) to extract independent components from collected non-Gaussian performance metric data. For anomaly detection, it employs multi-class Bayesian classification to determine the current state of each VM. To evaluate the performance of the designed detection framework, four types of anomalies are separately or jointly injected into randomly selected VMs in a campus-wide testbed. The experimental results show that ICA-based detection mechanism outperforms PCA-based and LDA-based detection mechanisms in terms of sensitivity and specificity.

• Journal of Institute of Control, Robotics and Systems
• /
• v.18 no.11
• /
• pp.997-1004
• /
• 2012

In enterprise software projects, performance issues have become more critical during recent decades. While developing software products, many performance tests are executed in the earlier development phase against the newly added code pieces to detect possible performance regressions. In our previous research, we introduced the framework to enable automated performance anomaly detection and reduce the analysis overhead for identifying the root causes, and showed Statistical Process Control (SPC) can be successfully applied to anomaly detection. In this paper, we explain the special performance trend in which the existing anomaly detection system can hardly detect the noticeable performance change especially when a performance regression is introduced and recovered again a while later. Within the fixed number of sampling period, the fluctuation gets aggravated and the lower and upper control limit get relaxed so that sometimes the existing system hardly detect the noticeable performance change. To resolve the issue, we apply dynamically tuned sampling window size based on the performance trend, and Fuzzy theory to find an appropriate size of the moving window.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.15 no.1
• /
• pp.69-75
• /
• 2022

Due to the increase in the demand for anomaly detection according to the ageing of power generation facilities, the need for developing an anomaly detection method that can provide high-reliability turbine blade anomaly detection performance has been continuously raised. Additionally, the false detection results caused by a human error accelerates the increase of the need. In this paper, we propose an anomaly detection technique for turbine blades in power plants using deep neural networks. Experimental results prove that the proposed technique achieves stable anomaly detection performance while minimizing human factor intervention.

• ETRI Journal
• /
• v.41 no.5
• /
• pp.684-695
• /
• 2019

In a cloud environment, performance degradation, or even downtime, of virtual machines (VMs) usually appears gradually along with anomalous states of VMs. To better characterize the state of a VM, all possible performance metrics are collected. For such high-dimensional datasets, this article proposes a feature extraction algorithm based on unsupervised fuzzy linear discriminant analysis with kernel (UFKLDA). By introducing the kernel method, UFKLDA can not only effectively deal with non-Gaussian datasets but also implement nonlinear feature extraction. Two sets of experiments were undertaken. In discriminability experiments, this article introduces quantitative criteria to measure discriminability among all classes of samples. The results show that UFKLDA improves discriminability compared with other popular feature extraction algorithms. In detection accuracy experiments, this article computes accuracy measures of an anomaly detection algorithm (i.e., C-SVM) on the original performance metrics and extracted features. The results show that anomaly detection with features extracted by UFKLDA improves the accuracy of detection in terms of sensitivity and specificity.

• Smart Structures and Systems
• /
• v.30 no.6
• /
• pp.613-626
• /
• 2022

Guaranteeing the quality and integrity of structural health monitoring (SHM) data is very important for an effective assessment of structural condition. However, sensory system may malfunction due to sensor fault or harsh operational environment, resulting in multiple types of data anomaly existing in the measured data. Efficiently and automatically identifying anomalies from the vast amounts of measured data is significant for assessing the structural conditions and early warning for structural failure in SHM. The major challenges of current automated data anomaly detection methods are the imbalance of dataset categories. In terms of the feature of actual anomalous data, this paper proposes a data anomaly detection method based on data-level and deep learning technique for SHM of civil engineering structures. The proposed method consists of a data balancing phase to prepare a comprehensive training dataset based on data-level technique, and an anomaly detection phase based on a sophisticatedly designed network. The advanced densely connected convolutional network (DenseNet) and Transformer encoder are embedded in the specific network to facilitate extraction of both detail and global features of response data, and to establish the mapping between the highest level of abstractive features and data anomaly class. Numerical studies on a steel frame model are conducted to evaluate the performance and noise immunity of using the proposed network for data anomaly detection. The applicability of the proposed method for data anomaly classification is validated with the measured data of a practical supertall structure. The proposed method presents a remarkable performance on data anomaly detection, which reaches a 95.7% overall accuracy with practical engineering structural monitoring data, which demonstrates the effectiveness of data balancing and the robust classification capability of the proposed network.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.8
• /
• pp.2787-2800
• /
• 2022

The aging society increases emergency situations of the elderly living alone and a variety of social crimes. In order to prevent them, techniques to detect emergency situations through voice are actively researched. This study proposes CutPaste-based anomaly detection model using multi-scale feature extraction in time series streaming data. In the proposed method, an audio file is converted into a spectrogram. In this way, it is possible to use an algorithm for image data, such as CNN. After that, mutli-scale feature extraction is applied. Three images drawn from Adaptive Pooling layer that has different-sized kernels are merged. In consideration of various types of anomaly, including point anomaly, contextual anomaly, and collective anomaly, the limitations of a conventional anomaly model are improved. Finally, CutPaste-based anomaly detection is conducted. Since the model is trained through self-supervised learning, it is possible to detect a diversity of emergency situations as anomaly without labeling. Therefore, the proposed model overcomes the limitations of a conventional model that classifies only labelled emergency situations. Also, the proposed model is evaluated to have better performance than a conventional anomaly detection model.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.32 no.4
• /
• pp.691-708
• /
• 2022

As the technology of machine learning and deep learning became common, it began to be applied to research on anomaly(abnormal) detection of industrial control systems. In Korea, the HAI dataset was developed and published to activate artificial intelligence research for abnormal detection of industrial control systems, and an AI contest for detecting industrial control system security threats is being conducted. Most of the anomaly detection studies have been to create a learning model with improved performance through the ensemble model method, which is applied either by modifying the existing deep learning algorithm or by applying it together with other algorithms. In this study, a study was conducted to improve the performance of anomaly detection with a post-processing method that detects abnormal data and corrects the labeling results, rather than the learning algorithm and data pre-processing process. Results It was confirmed that the results were improved by about 10% or more compared to the anomaly detection performance of the existing model.