• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제8권2호
• /
• pp.664-677
• /
• 2014

Wind energy has proven its viability by the emergence of countless wind turbines around the world which greatly contribute to the increased electrical generating capacity of wind farm operators. These infrastructures are usually deployed in not easily accessible areas; therefore, maintenance routines should be based on a well-guided decision so as to minimize cost. To aid operators prior to the maintenance process, a condition monitoring system should be able to accurately reflect the actual state of the wind turbine and its major components in order to execute specific preventive measures using as little resources as possible. In this paper, we propose a fault detection approach which combines cluster analysis and frequent pattern mining to accurately reflect the deteriorating condition of a wind turbine and to indicate the components that need attention. Using SCADA data, we extracted operational status patterns and developed a rule repository for monitoring wind turbine systems. Results show that the proposed scheme is able to detect the deteriorating condition of a wind turbine as well as to explicitly identify faulty components.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2005년도 Proceedings of ISRS 2005
• /
• pp.713-716
• /
• 2005

In this paper, in order to identify and recognize attack patterns, we propose a Bayesian classification using frequent patterns. In theory, Bayesian classifiers guarantee the minimum error rate compared to all other classifiers. However, in practice this is not always the case owing to inaccuracies in the unrealistic assumption{ class conditional independence) made for its use. Our method addresses the problem of attribute dependence by discovering frequent patterns. It generates frequent patterns using an efficient FP-growth approach. Since the volume of patterns produced can be large, we propose a pruning technique for selection only interesting patterns. Also, this method estimates the probability of a new case using different product approximations, where each product approximation assumes different independence of the attributes. Our experiments show that the proposed classifier achieves higher accuracy and is more efficient than other classifiers.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제9권1호
• /
• pp.169-189
• /
• 2015

Detection of anomalous events from video streams is a challenging problem in many video surveillance applications. One such application that has received significant attention from the computer vision community is traffic video surveillance. In this paper, a Lossy Count based Sequential Temporal Pattern mining approach (LC-STP) is proposed for detecting spatio-temporal abnormal events (such as a traffic violation at junction) from sequences of video streams. The proposed approach relies mainly on spatial abstractions of each object, mining frequent temporal patterns in a sequence of video frames to form a regular temporal pattern. In order to detect each object in every frame, the input video is first pre-processed by applying Gaussian Mixture Models. After the detection of foreground objects, the tracking is carried out using block motion estimation by the three-step search method. The primitive events of the object are represented by assigning spatial and temporal symbols corresponding to their location and time information. These primitive events are analyzed to form a temporal pattern in a sequence of video frames, representing temporal relation between various object's primitive events. This is repeated for each window of sequences, and the support for temporal sequence is obtained based on LC-STP to discover regular patterns of normal events. Events deviating from these patterns are identified as anomalies. Unlike the traditional frequent item set mining methods, the proposed method generates maximal frequent patterns without candidate generation. Furthermore, experimental results show that the proposed method performs well and can detect video anomalies in real traffic video data.

• 대한기계학회논문집A
• /
• 제27권4호
• /
• pp.537-543
• /
• 2003

Transient vibration generated by developing localized fault in gear can be used as indicators in gear fault detection. This vibration signal suffers from the background noise such as gear meshing frequency and its harmonics and broadband noise. Thus in order to extract the information about the only gear fault from the raw vibration signal measured on the gearbox this signal is processed to reduce the background noise with many kinds of signal-processing tools. However, these signal-processing tools are often very complex and time waste. Thus. in this paper. we propose a novel approach detecting the damage of gearbox and analyzing its pattern using the raw vibration signal. In order to do this, the residual signal. which consists of the sideband components of the gear meshing frequent) and its harmonics frequencies, is extracted from the raw signal by the power spectral density (PSD) to obtain the information about the fault and is used as the input data of the artificial neural network (ANN) for analysis of the pattern of gear fault. This novel approach has been very successfully applied to the damage analysis of a laboratory gearbox.

• 한국콘텐츠학회논문지
• /
• 제18권2호
• /
• pp.147-157
• /
• 2018

최근 네트워크 기술 발전과 함께 IoT 및 소셜 네트워크 서비스의 활성화로 인해 많은 그래프 스트림 데이터가 생성되고 있다. 이와 같은 그래프 스트림에서 객체들 사이의 관계가 동적으로 변화함에 따라 그래프의 변화를 탐지하거나 분석하기 위한 연구들이 진행되고 있다. 본 논문에서는 그래프 스트림에서 이전 슬라이딩 윈도우에서 검출한 빈발 패턴에 대한 정보를 이용해 빈발 패턴을 점진적으로 검출하는 기법을 제안한다. 제안하는 기법은 이전 슬라이딩 윈도우에서 검출된 패턴이 앞으로 몇 슬라이딩 윈도우동안 빈발할지 또는 빈발하지 않을지를 계산하여 빈발 패턴 관리 테이블에 저장한다. 그리고 이 값을 통해 다음 슬라이딩 윈도우에서는 필요한 계산만 수행함으로써 전체 연산량을 감소시킨다. 또한 패턴 간에 간선을 통해 연결되어있는 것만 하나의 패턴으로 인식함으로써 더 유의미한 패턴만을 검출한다. 본 논문에서는 제안하는 기법의 우수함을 보이기 위해 여러 성능 평가를 진행하였다. 그래프 데이터의 크기가 커지고 슬라이딩 윈도우의 크기가 커질수록 중복되는 데이터가 증가되기 때문에 기존 기법보다 빠른 처리 속도를 나타낸다.

• 인터넷정보학회논문지
• /
• 제10권2호
• /
• pp.1-13
• /
• 2009

침입탐지란 컴퓨터와 네트워크 자원에 대한 유해한 침입 행동을 식별하고 대응하는 과정이다. 최근 인터넷의 급속한 발달과 함께 침입의 유형들이 복잡해지고 새로운 침입유형의 발생빈도가 높아져 이에 대한 빠르고 정확한 대응이 필요하다. 따라서 이 논문에서는 침입탐지 시스템의 이러한 문제점을 해결하기 위한 한 방안으로 지능적이고 자동화된 탐지를 지원하기 위한 경보데이터 순차 패턴 마이닝 기법을 제안한다. 제안된 순차 패턴 마이닝 기법은 기존의 마이닝 기법 중 prefixSpan 알고리즘을 경보데이터의 특성에 맞게 확장 설계하였다. 이 확장 설계된 순차패턴 마이너는 보안정책 실행시스템의 경보데이터 분석기의 일부분으로 구성된다. 구현된 순차패턴 마이너는 탐사된 패턴 내에서 적용 가능한 침입패턴들을 찾아내어 효율적으로 침입을 탐지하여 보안정책 실행 시스템에서 이를 기반으로 새로운 보안규칙을 생성하고 침입에 대응할 수 있다. 제안된 경보데이터 순차 패턴 마이너를 이용하여 침입의 시퀀스의 행동을 예측하거나 기술하는 규칙들을 생성하므로 침입을 효율적으로 예측하고 대응할 수 있다.

• 국제학술발표논문집
• /
• The 9th International Conference on Construction Engineering and Project Management
• /
• pp.11-17
• /
• 2022

Design-bid-build (DBB) is the most common project delivery method among highway projects. State Highway Agencies (SHAs) usually apply a low-bid approach to select contractors for their DBB projects. In this approach, the Federal Highway Agency suggests SHAs heighten contractors' competition to lower bid prices. However, these attempts may become ineffective due to collusive bidding arrangements among certain contractors. One common strategy is the rotation of winning bidders of a group of contractors who bid on many of the same projects. These arrangements may also be specific to a particular region or vary in time. Despite the practices' adverse effects on bidding outcomes, an effective model to detect red-flag bidding patterns is lacking. This study fills the gap by proposing a novel framework that utilizes pattern mining techniques and statistical tests for unusual pattern detection. A case study with historical data from an SHA is conducted to illustrate the proposed framework.

• 대한의생명과학회지
• /
• 제14권2호
• /
• pp.115-118
• /
• 2008

Salmonella typhi is frequent causes of foodborne illness and its detection is important for monitoring disease progression. In this study, by using general PCR and novel LAMP (Loop Mediated Isothermal Amplification) assay, we evaluated the usefulness of LAMP assay for detection of Salmonella typhi. In this LAMP assay, forward inner primer (FIP) and back inner primer (BIP) was specially designed for recognizing target invA gene. Target DNA was amplified and visualized as ladder-like pattern of bands on agarose gel within 60 min under isothermal conditions at $65^{\circ}C$. When the sensitivity and reproducibility of LAMP were compared to general PCR, there was no difference of reproducibility but sensitivity of LAMP assay was more efficient than PCR (the detection limit of LAMP assay was 30 fg, while the PCR assay was 3 pg). These results indicate that the LAMP assay is a potential and valuable means for detection of Salmonella typhi, especially for its rapidity, simplicity and low cost.

• International Journal of Computer Science & Network Security
• /
• 제21권9호
• /
• pp.31-40
• /
• 2021

The increasing number of credit card fraud cases has become a considerable problem since the past decades. This phenomenon is due to the expansion of new technologies, including the increased popularity and volume of online banking transactions and e-commerce. In order to address the problem of credit card fraud detection, a rule-based approach has been widely utilized to detect and guard against fraudulent activities. However, it requires huge computational power and high complexity in defining and building the rule base for pattern matching, in order to precisely identifying the fraud patterns. In addition, it does not come with intelligence and ability in predicting or analysing transaction data in looking for new fraud patterns and strategies. As such, Data Mining and Machine Learning algorithms are proposed to overcome the shortcomings in this paper. The aim of this paper is to highlight the important techniques and methodologies that are employed in fraud detection, while at the same time focusing on the existing literature. Methods such as Artificial Neural Networks (ANNs), Support Vector Machines (SVMs), naïve Bayesian, k-Nearest Neighbour (k-NN), Decision Tree and Frequent Pattern Mining algorithms are reviewed and evaluated for their performance in detecting fraudulent transaction.

• Journal of Information Processing Systems
• /
• 제17권4호
• /
• pp.675-689
• /
• 2021

Nowadays, cloud computing is being adopted for more organizations. However, since cloud computing has a virtualized, volatile, scalable and multi-tenancy distributed nature, it is challenging task to perform attack detection in the cloud following conventional processes. This work proposes a solution which aims to collect web server logs by using Flume and filter them through Spark Streaming in order to only consider suspicious data or data related to denial-of-service attacks and reduce the data that will be stored in Hadoop Distributed File System for posterior analysis with the frequent pattern (FP)-Growth algorithm. With the proposed system, we can address some of the difficulties in security for cloud environment, facilitating the data collection, reducing detection time and consequently enabling an almost real-time attack detection.