• Journal of Computing Science and Engineering
• /
• 제7권4호
• /
• pp.272-284
• /
• 2013

In this paper, we propose a new framework for anomaly detection in medical wireless sensor networks, which are used for remote monitoring of patient vital signs. The proposed framework performs sequential data analysis on a mini gateway used as a base station to detect abnormal changes and to cope with unreliable measurements in collected data without prior knowledge of anomalous events or normal data patterns. The proposed approach is based on the Mahalanobis distance for spatial analysis, and a kernel density estimator for the identification of abnormal temporal patterns. Our main objective is to distinguish between faulty measurements and clinical emergencies in order to reduce false alarms triggered by faulty measurements or ill-behaved sensors. Our experimental results on both real and synthetic medical datasets show that the proposed approach can achieve good detection accuracy with a low false alarm rate (less than 5.5%).

• 한국항공운항학회지
• /
• 제16권2호
• /
• pp.12-20
• /
• 2008

Japanese MSAS (Multi-functional Satellite Augmentation System) satellites have been transmitting GPS satellite orbit and ionosphere correction information since 2005. MSAS coverage includes Far East Asia, and it can improve the accuracy and integrity of GPS position solutions in Korea. This research analyzed the ionosphere correction information from the MSAS ionosphere correction data. The ionosphere delay data observed by a dual frequency receiver is compared with the MSAS ionosphere correction data. The variation of MSAS GIVE values are analyzed in connection with the equatorial anomaly and ionosphere scintillation.

• Journal of Electrical Engineering and Technology
• /
• 제9권4호
• /
• pp.1171-1181
• /
• 2014

Different power quality (PQ) disturbance sources can have major impacts on the power supply grid. This study proposes, for the first time, an early warning approach to identifying PQ problems and providing early warning prompts based on the monitored data of PQ disturbance sources. To establish a steady-state power quality early warning index system, the characteristics of PQ disturbance sources are analyzed and summed up. The higher order statistics anomaly detection (HOSAD) algorithm, based on skewness and kurtosis, and hierarchical power quality early warning flow, were then used to mine limit-exceeding and abnormal data and analyze their severity. Cases studies show that the proposed approach is effective and feasible, and that it is possible to provide timely power quality early warnings for limit-exceeding and abnormal data.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2021년도 추계학술대회
• /
• pp.85-88
• /
• 2021

제조 설비에서 짧은 주기로 수집된 제조 데이터는 시간 간격이 일정하지 않은 불규칙 샘플링 시계열이고 값이 불안정하여 큰 분산을 가지는 경우가 많다. 본 논문에서는 단순이동평균법을 이용하여 불규칙 시계열의 시간 간격을 일정하게 보정함과 동시에 값의 분산을 줄이는 보정 기법을 제안하고, 제안된 보정 기법이 생산 설비의 이상탐지의 성능 향상에 효과가 있음을 확인하였다.

• ETRI Journal
• /
• 제41권5호
• /
• pp.608-618
• /
• 2019

We propose a general framework for keyed learning, where a secret key is used as an additional input of an adversarial learning system. We also define models and formal challenges for an adversary who knows the learning algorithm and its input data but has no access to the key value. This adversarial learning framework is subsequently applied to a more specific context of anomaly detection, where the secret key finds additional practical uses and guides the entire learning and alarm-generating procedure.

• Smart Structures and Systems
• /
• 제29권1호
• /
• pp.53-62
• /
• 2022

The deployment of advanced structural health monitoring (SHM) systems in large-scale civil structures collects large amounts of data. Note that these data may contain multiple types of anomalies (e.g., missing, minor, outlier, etc.) caused by harsh environment, sensor faults, transfer omission and other factors. These anomalies seriously affect the evaluation of structural performance. Therefore, the effective analysis and mining of SHM data is an extremely important task. Inspired by the deep learning paradigm, this study develops a novel generative adversarial network (GAN) and convolutional neural network (CNN)-based data anomaly detection approach for SHM. The framework of the proposed approach includes three modules : (a) A three-channel input is established based on fast Fourier transform (FFT) and Gramian angular field (GAF) method; (b) A GANomaly is introduced and trained to extract features from normal samples alone for class-imbalanced problems; (c) Based on the output of GANomaly, a CNN is employed to distinguish the types of anomalies. In addition, a dataset-oriented method (i.e., multistage sampling) is adopted to obtain the optimal sampling ratios between all different samples. The proposed approach is tested with acceleration data from an SHM system of a long-span bridge. The results show that the proposed approach has a higher accuracy in detecting the multi-pattern anomalies of SHM data.

• 한국컴퓨터정보학회논문지
• /
• 제28권2호
• /
• pp.9-17
• /
• 2023

본 논문에서는 베어링의 결함 진단을 위한 단일 클래스 분류의 진동 이상 탐지 시스템을 제안한다. 베어링 고장으로 인해 발생하는 경제적 및 시간적 손실을 줄이기 위해 정확한 결함 진단시스템은 필수적이며 문제 해결을 위해 딥러닝 기반의 결함 진단 시스템들이 널리 연구되고 있다. 그러나 딥러닝 학습을 위한 실제 데이터 채집 환경에서 비정상 데이터 확보에 어려움이 있으며 이는 데이터 편향을 초래한다. 이에 정상 데이터만 활용하는 단일 클래스 분류 방법을 활용한다. 일반적인 방법으로는 AutoEncoder를 통한 압축과 복원 과정을 학습하여 진동 데이터의 특성을 추출한다. 추출된 특성으로 단일 클래스 분류기를 학습하여 이상 탐지를 실시한다. 하지만 이와 같은 방법은 진동 데이터의 주파수 특성을 고려하지 않아서 진동 데이터의 특성을 효율적 추출할 수 없다. 이러한 문제를 해결하기 위해 진동 데이터의 주파수 특성을 고려한 AutoEncoder 모델을 제안한다. 분류 성능은 accuracy 0.910, precision 1.0, recall 0.820, f1-score 0.901이 나왔다. 주파수 특성을 고려한 네트워크 설계로 기존 방법들보다 우수한 성능을 확인하였다.

• Smart Structures and Systems
• /
• 제29권1호
• /
• pp.117-127
• /
• 2022

Data anomalies seriously threaten the reliability of the bridge structural health monitoring system and may trigger system misjudgment. To overcome the above problem, an efficient and accurate data anomaly detection method is desiderated. Traditional anomaly detection methods extract various abnormal features as the key indicators to identify data anomalies. Then set thresholds artificially for various features to identify specific anomalies, which is the artificial experience method. However, limited by the poor generalization ability among sensors, this method often leads to high labor costs. Another approach to anomaly detection is a data-driven approach based on machine learning methods. Among these, the bidirectional long-short memory neural network (BiLSTM), as an effective classification method, excels at finding complex relationships in multivariate time series data. However, training unprocessed original signals often leads to low computation efficiency and poor convergence, for lacking appropriate feature selection. Therefore, this article combines the advantages of the two methods by proposing a deep learning method with manual experience statistical features fed into it. Experimental comparative studies illustrate that the BiLSTM model with appropriate feature input has an accuracy rate of over 87-94%. Meanwhile, this paper provides basic principles of data cleaning and discusses the typical features of various anomalies. Furthermore, the optimization strategies of the feature space selection based on artificial experience are also highlighted.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권6호
• /
• pp.1516-1529
• /
• 2023

In this paper, a motor gearbox fault-detection system based on a hierarchical flow-based model is proposed. The proposed system is used for the anomaly detection of a motion sound-based actuator module. The proposed flow-based model, which is a generative model, learns by directly modeling a data distribution function. As the objective function is the maximum likelihood value of the input data, the training is stable and simple to use for anomaly detection. The operation sound of a car's side-view mirror motor is converted into a Mel-spectrogram image, consisting of a folding signal and an unfolding signal, and used as training data in this experiment. The proposed system is composed of an encoder and a decoder. The data extracted from the layer of the pretrained feature extractor are used as the decoder input data in the encoder. This information is used in the decoder by performing an interlayer cross-scale convolution operation. The experimental results indicate that the context information of various dimensions extracted from the interlayer hierarchical data improves the defect detection accuracy. This paper is notable because it uses acoustic data and a normalizing flow model to detect outliers based on the features of experimental data.

• 한국인터넷방송통신학회논문지
• /
• 제24권1호
• /
• pp.55-58
• /
• 2024

본 논문은 빅데이터 기반 미세먼지 이상 탐지 머신러닝 시스템 설계 및 구현을 제안한다. 제안하는 시스템은 빅데이터로 구성된 미세먼지 및 기상 정보를 통해 미세먼지 대기환경지수를 분류하는 시스템이다. 이 시스템은 머신러닝 기반의 대기환경지수 분류 카테고리별 이상치에 따른 이상치 탐지 알고리즘 설계를 통해 미세먼지를 분류한다. 카메라에서 수집된 영상의 심도 데이터는 미세먼지 농도에 따른 영상을 수집한 후 미세먼지 가시마스크를 생성합니다. 그리고 모노 심도 추정 알고리즘을 통한 학습 기반 핑거프린팅 기법으로 모노스코프 카메라에서 수집된 미세먼지의 가시거리를 추론하여 미세먼지 농도를 도출합니다. 본 방법의 실험 및 분석을 위해 미세먼지 농도 데이터와 지역별, 시간별 CCTV 영상 데이터를 매칭하여 학습 데이터를 생성한 후 모델을 생성하여 실제 환경에서 테스트한다.