• Proceedings of the Korean Institute of Navigation and Port Research Conference
• /
• 2022.11a
• /
• pp.289-290
• /
• 2022

본 연구에서는 선박의 중요부품인 메인엔진에서 수집되는 센서 데이터를 사용하여 선박 메인엔진의 이상치를 탐지하는 시스템을 소개한다. 본 시스템의 특장점은 이상치 탐지 뿐만 아니라, 이상치의 센서별 기여도를 정량화 함으로써, 이상치 발생을 유형화 하고 추가적인 분석을 가능하게 해준다. 또한 웹 인터페이스 형태의 편리한 UI를 개발하여 사용자들이 보다 편리하게 이상치

• The Korean Journal of Applied Statistics
• /
• v.34 no.3
• /
• pp.507-521
• /
• 2021

Detecting outliers among high-dimensional data encounters a challenging problem of screening the variables since relevant information is often contained in only a few of the variables. Otherwise, when a number of irrelevant variables are included in the data, the distances between all observations tend to become similar which leads to making the degree of outlierness of all observations alike. The subspace outlier detection method overcomes the problem by measuring the degree of outlierness of the observation based on the relevant subsets of the entire variables. In this paper, we survey recent subspace outlier detection techniques, classifying them into three major types according to the subspace selection method. And we summarize the techniques of each type based on how to select the relevant subspaces and how to measure the degree of outlierness. In addition, we introduce some computing tools for implementing the subspace outlier detection techniques and present results from the simulation study and real data analysis.

• Proceedings of the Korean Information Science Society Conference
• /
• 2010.06c
• /
• pp.452-457
• /
• 2010

고차원 공간에서 효과적인 이상치 탐지 방법으로 제안되었던 각도 기반 이상치 탐지(Angle Based Outlier Detection)는 객체와 객체를 비교하는 척도로 각도 개념을 사용하여 고차원 공간에서도 일반적인 거리기반 이상치 측정 방법보다 좋은 이상치 탐지 성능을 가진다. 그러나 어떤 이상치가 다른 이상치에 의해 둘러싸인 경우 정상객체와 구분하기 어렵다는 문제가 있다. 이 논문에서는 기존의 이상치 탐지 방법을 개선한 방법을 제안하고 실험을 통하여 기존의 방법과 제안한 새로운 방법을 비교하여 향상된 성능을 입증한다.

• Smart Media Journal
• /
• v.13 no.4
• /
• pp.48-56
• /
• 2024

In the livestock industry, detecting environmental outliers and predicting data are crucial tasks. Outliers in livestock environment data, typically gathered through time-series methods, can signal rapid changes in the environment and potential unexpected epidemics. Prompt detection and response to these outliers are essential to minimize stress in livestock and reduce economic losses for farmers by early detection of epidemic conditions. This study employs two methods to experiment and compare performances in setting thresholds that define outliers in livestock environment data outlier detection. The first method is an outlier detection using Mean Squared Error (MSE), and the second is an outlier detection using a Dynamic Threshold, which analyzes variability against the average value of previous data to identify outliers. The MSE-based method demonstrated a 94.98% accuracy rate, while the Dynamic Threshold method, which uses standard deviation, showed superior performance with 99.66% accuracy.

• 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.

• The Korean Journal of Applied Statistics
• /
• v.29 no.4
• /
• pp.699-706
• /
• 2016

Outlier detection methods without performing a test often do not succeed in detecting multiple outliers because they are structurally vulnerable to a masking effect or a swamping effect. This paper considers testing procedures supplemented to a clustering-based method of identifying the group with a minority of the observations as outliers. One of general steps is performing a variety of t-test on individual outlier-candidates. This paper proposes a sequential procedure for searching for outliers by changing cutoff values on a cluster tree and performing a test on a set of outlier-candidates. The proposed method is illustrated and compared to existing methods by an example and Monte Carlo studies.

• The Korean Journal of Applied Statistics
• /
• v.23 no.1
• /
• pp.41-47
• /
• 2010

In this paper, we show the performance evaluation of outlier detection methods based on the GARCH model. We first introduce GARCH model and the methods of outlier detection in the GARCH model. The results of small simulation and the real KOSPI data show the out-performance of the outlier detection method over the traditional method in the GARCH model.

• Proceedings of the Korean Statistical Society Conference
• /
• 2003.10a
• /
• pp.281-283
• /
• 2003

시계열 모형을 따르는 자료의 예측(Forecasting)이나 공정조정(Process Adjustment)의 경우, 자료의 마지막 부분에 발생한 이상치(Outlier)에 의해 크게 영향 받을 수 있다. 그러나 지금까지 제안된 이상치 탐지 방법은 주로 자료의 중간 부분에 발생한 이상치를 검출하는데 효율적이라고 알려져 왔다. 본 연구에서는 자료의 마지막 부분에 발생한 이상치에 대한 기존 탐지 방법의 검출력을 모의 실험을 통해 분석하였다 또한, 이를 개선할 수 있는 방안을 제시하고, 모의 실험을 통해 기존의 검출력과 비교하였다.

• The Korean Journal of Applied Statistics
• /
• v.26 no.4
• /
• pp.687-696
• /
• 2013

The detection and the examination of outliers are important parts of data analysis because some outliers in the data may have a detrimental effect on statistical analysis. Outlier detection methods have been discussed by many authors. In this article, we propose to apply Hadi and Simonoff's (1993) method to penalized spline a regression model to detect multiple outliers. Simulated data sets and real data sets are used to illustrate and compare the proposed procedure to a penalized spline regression and a robust penalized spline regression.

• KIPS Transactions on Software and Data Engineering
• /
• v.7 no.11
• /
• pp.435-442
• /
• 2018

Outlier detection means to detect data samples that deviate significantly from the distribution of normal data. Most outlier detection methods calculate an outlier score that indicates the extent to which a data sample is out of normal state and determine it to be an outlier when its outlier score is above a given threshold. However, since the range of an outlier score is different for each data and the outliers exist at a smaller ratio than the normal data, it is very difficult to determine the threshold value for an outlier score. Further, in an actual situation, it is not easy to acquire data including a sufficient amount of outliers available for learning. In this paper, we propose a clustering-based outlier detection method by constructing a model representing a normal data region using only normal data and performing binary classification of outliers and normal data for new data samples. Then, by dividing the given normal data into chunks, and constructing a clustering model for each chunk, we expand it to the ensemble method combining the decision by the models and apply it to the streaming data with dynamic changes. Experimental results using real data and artificial data show high performance of the proposed method.