지원사업
학술연구/단체지원/교육 등 연구자 활동을 지속하도록 DBpia가 지원하고 있어요.
커뮤니티
연구자들이 자신의 연구와 전문성을 널리 알리고, 새로운 협력의 기회를 만들 수 있는 네트워킹 공간이에요.
논문 기본 정보
- 자료유형
- 학술저널
- 저자정보
- 발행연도
- 2018.3
- 수록면
- 20 - 32 (13page)
- DOI
- 10.33162/JAR.2018.03.18.1.20
이용수
초록· 키워드
오류제보하기
Purpose: The purpose of this study is to set up an anomaly detection criteria for sensor data coming from a motorcycle.
Methods: Five sensor values for accelerator pedal, engine rpm, transmission rpm, gear and speed are obtained every 0.02 second from a motorcycle. Exploratory data analysis is used to find any pattern in the data. Traditional process control methods such as X control chart and time series models are fitted to find any anomaly behavior in the data. Finally unsupervised learning algorithm such as k-means clustering is used to find any anomaly spot in the sensor data.
Results: According to exploratory data analysis, the distribution of accelerator pedal sensor values is very much skewed to the left. The motorcycle seemed to have been driven in a city at speed less than 45 kilometers per hour. Traditional process control charts such as X control chart fail due to severe autocorrelation in each sensor data. However, ARIMA model found three abnormal points where they are beyond 2 sigma limits in the control chart. We applied a copula based Markov chain to perform statistical process control for correlated observations. Copula based Markov model found anomaly behavior in the similar places as ARIMA model. In an unsupervised learning algorithm, large sensor values get subdivided into two, three, and four disjoint regions. So extreme sensor values are the ones that need to be tracked down for any sign of anomaly behavior in the sensor values.
Conclusion: Exploratory data analysis is useful to find any pattern in the sensor data. Process control chart using ARIMA and Joe’s copula based Markov model also give warnings near similar places in the data. Unsupervised learning algorithm shows us that the extreme sensor values are the ones that need to be tracked down for any sign of anomaly behavior.
Methods: Five sensor values for accelerator pedal, engine rpm, transmission rpm, gear and speed are obtained every 0.02 second from a motorcycle. Exploratory data analysis is used to find any pattern in the data. Traditional process control methods such as X control chart and time series models are fitted to find any anomaly behavior in the data. Finally unsupervised learning algorithm such as k-means clustering is used to find any anomaly spot in the sensor data.
Results: According to exploratory data analysis, the distribution of accelerator pedal sensor values is very much skewed to the left. The motorcycle seemed to have been driven in a city at speed less than 45 kilometers per hour. Traditional process control charts such as X control chart fail due to severe autocorrelation in each sensor data. However, ARIMA model found three abnormal points where they are beyond 2 sigma limits in the control chart. We applied a copula based Markov chain to perform statistical process control for correlated observations. Copula based Markov model found anomaly behavior in the similar places as ARIMA model. In an unsupervised learning algorithm, large sensor values get subdivided into two, three, and four disjoint regions. So extreme sensor values are the ones that need to be tracked down for any sign of anomaly behavior in the sensor values.
Conclusion: Exploratory data analysis is useful to find any pattern in the sensor data. Process control chart using ARIMA and Joe’s copula based Markov model also give warnings near similar places in the data. Unsupervised learning algorithm shows us that the extreme sensor values are the ones that need to be tracked down for any sign of anomaly behavior.
목차
1. Introduction
2. Exploratory Data Analysis
3. Control Charts
4. Unsupervised Learning
5. Conclusion and Comments
References
참고문헌 (37)
참고문헌 신청
Akyildiz, I. F. / 2002 / Wireless sensor networks: A survey / Computer Networks 38:393~422
Amitai, A. / 2016 / Change and anomaly detection framework for Internet of Things data streams
Anderson, T. W. / 2011 / The statistical analysis of time series, Vol. 19 / John Wiley & Sons
Anscombe, F. J. / 1960 / Rejection of outliers / Technometrics 2(2):123~146
Arampatzis, T. / 2005 / A survey of applications of wireless sensors and wireless sensor networks / Proceedings of the 2005 IEEE international symposium on intelligent control and 13th Mediterranean conference on control and automation :719~724
Amitai, A. / 2016 / Change and anomaly detection framework for Internet of Things data streams
Anderson, T. W. / 2011 / The statistical analysis of time series, Vol. 19 / John Wiley & Sons
Anscombe, F. J. / 1960 / Rejection of outliers / Technometrics 2(2):123~146
Arampatzis, T. / 2005 / A survey of applications of wireless sensors and wireless sensor networks / Proceedings of the 2005 IEEE international symposium on intelligent control and 13th Mediterranean conference on control and automation :719~724
함께 읽어보면 좋을 논문
논문 유사도에 따라 DBpia 가 추천하는 논문입니다. 함께 보면 좋을 연관 논문을 확인해보세요!
-
무선 센서 네트워크의 다종 센서에 대한 에너지 효율적인 클러스터링 기법
멀티미디어학회논문지
2016 .03
-
상태천이모델 기반의 센서 노드 설계
멀티미디어학회논문지
2017 .08
-
Sensor 기반 제조설비 데이터수집 유형과 활용에 대한 연구
한국정밀공학회 학술발표대회 논문집
2016 .05
-
재실 감지 센서를 이용한 다용도 스마트 센서 개발
한국생산제조학회지
2015 .02
-
Monitoring Process Variability Using Double Moving Average Control Chart
Industrial Engineering & Management Systems
2019 .06
-
LSTM 기반의 이상데이터가 포함된 센서 신호 예측 및 성능평가
제어로봇시스템학회 논문지
2023 .12
-
언택트 스토어 차량 구동시스템에 대한 통합 고장진단/대응 알고리즘
한국자동차공학회 추계학술대회 및 전시회
2022 .11
-
Anomaly Detection System for Semiconductor Deposition Process using Transformer
제어로봇시스템학회 국제학술대회 논문집
2024 .10
-
Implementation of an Integrated Pressure-sensor System Adapted to the Optimum Sensitivity
JOURNAL OF SEMICONDUCTOR TECHNOLOGY AND SCIENCE
2017 .04
-
Deep Unsupervised Anomaly Detection Methods for Multi-Channel Signal Data: A Comparative Study
대한산업공학회 추계학술대회 논문집
2018 .11
-
가상센서 기반의 문제해결형 인공지능 접근 방법을 통해 설비 이상 인지 기술 개발
대한전자공학회 학술대회
2024 .11
-
로버스트 추정에 근거한 수정된 x-s 관리도의 설계
산업경영시스템학회지
2015 .01
-
위치모수를 이용한 로버스트 CV 관리도의 설계
산업경영시스템학회지
2016 .01
-
실시간 수돗물 통합관제를 위한 이상탐지 시스템
한국지능정보시스템학회 학술대회논문집
2021 .12
-
건물에너지시스템 센서 네트워크에서의 백업 가상센서 성능 향상을 위한 시계열 데이터 다운스케일링 방법
설비공학논문집
2022 .03
-
Structural health monitoring data anomaly detection by transformer enhanced densely connected neural networks
Smart Structures and Systems, An International Journal
2022 .12
-
주변 센서 정보를 이용한 자동차 엔진 이상 탐지
한국소음진동공학회논문집
2022 .10
-
4차산업 혁명에 적용되는 센서 기술 동향
멀티미디어학회논문지
2023 .02
-
Investigation of an integrated sensor to determine junction temperature of SiC MOSFETs during power cycling tests
ICPE(ISPE)논문집
2019 .05
-
Suggestion for deep learning approach to solve the interference effect of ammonium ion on potassium ion-selective electrode
한국표면공학회지
2022 .06
이 논문의 저자 정보
이 논문과 함께 이용한 논문
빅데이터 기반의 IoT 이상 장애 탐지 시스템 설계
나성일
,
김형중
디지털콘텐츠학회논문지
2018
.02
LSTM-based Anomaly Detection on Big Data for Smart Factory Monitoring
Van Quan Nguyen
,
Linh Van Ma
,
Jinsul Kim
디지털콘텐츠학회논문지
2018
.04
GANs을 이용한 보안 로그 데이터의 이상탐지
이상진
,
김기천
한국통신학회 학술대회논문집
2018
.01
자연어 처리 기법을 이용한 무선 네트워크 이상 감지 시스템
한명승
,
유인태
한국정보과학회 학술발표논문집
2017
.12
연료전지 고분자 전해질 분리막의 나노구조화 효과 연구
고준혁
,
박상진
,
문명운
대한기계학회 춘추학술대회
2022
.06
최근 본 자료
댓글(0)
0