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
- 2019.6
- 수록면
- 167 - 178 (12page)
- DOI
- 10.33162/JAR.2019.06.19.2.167
이용수
이 논문의 연구 히스토리 (2)
- 이 논문의 후속연구가 궁금하신가요?
- 연관 학술논문 또는 학술발표를 통해 보다 발전된 연구결과를 확인하실 수 있습니다.
- 이 논문의 연구 히스토리 확인하기
초록· 키워드
오류제보하기
Purpose: This paper presents the clustering results of time series multiple sensor data using deep neural networks based unsupervised learning algorithm without target variables.
Methods: Time series data collected from multiple sensors were clustered using two clustering algorithms based on deep learning: Deep Embedding Clustering (DEC) and Jointly Deep Embedding Clustering (JDEC). DEC and JDEC are designed based on the autoencoder and the convolutional neural network, which are representative neural network structures. They allow highdimensional data to be represented by low-dimensional data and clustered based on their corresponding low-dimensional values.
Results: Two data sets, real time series data collected from manufacturing processes and simulated data, were used in the experiments. The simulated data’s performance was evaluated for accuracy, while the clustering performance of the real data was visually evaluated by mapping data and their clusters into a two-dimensional space. The experimental results show that the proposed methods were more accurate than K-means clustering.
Conclusion: Real time series data collected from manufacturing processes and simulated data were analyzed and meaningful clustering results were obtained. The proposed methods enabled the unsupervised learning of time series multiple sensor data without target variables by a deep neural network and showed good clustering performance.
Methods: Time series data collected from multiple sensors were clustered using two clustering algorithms based on deep learning: Deep Embedding Clustering (DEC) and Jointly Deep Embedding Clustering (JDEC). DEC and JDEC are designed based on the autoencoder and the convolutional neural network, which are representative neural network structures. They allow highdimensional data to be represented by low-dimensional data and clustered based on their corresponding low-dimensional values.
Results: Two data sets, real time series data collected from manufacturing processes and simulated data, were used in the experiments. The simulated data’s performance was evaluated for accuracy, while the clustering performance of the real data was visually evaluated by mapping data and their clusters into a two-dimensional space. The experimental results show that the proposed methods were more accurate than K-means clustering.
Conclusion: Real time series data collected from manufacturing processes and simulated data were analyzed and meaningful clustering results were obtained. The proposed methods enabled the unsupervised learning of time series multiple sensor data without target variables by a deep neural network and showed good clustering performance.
목차
1. 서론
2. 딥러닝 기반 시계열 군집화 알고리즘
3. 딥러닝 기반 시계열 군집화 알고리즘 성능평가
4. 실험결과
5. 결론 및 향후 연구과제
References
참고문헌 (15)
참고문헌 신청
Krizhevsky, A. / 2009 / Learning multiple layers of features from tiny images
Bengio, Y. / 2013 / Representation learning: A review and new perspectives / IEEE Transactions On Pattern Analysis And Machine Intelligence 35(8):1798~1828
Ding, C. / 2004 / K-Means clustering via principal component analysis / Proceedings of the 21st International Conference on Machine Learning (ICML)
Dizaji, K. G. / 2017 / Deep clustering via joint convolutional autoencoder embedding and relative entropy minimization / Proceedings of 2017 IEEE International Conference on Computer Vision (ICCV) :5747~5756
Aljalbout, E. / 2018 / Clustering with deep learning:taxonomy and new methods
Bengio, Y. / 2013 / Representation learning: A review and new perspectives / IEEE Transactions On Pattern Analysis And Machine Intelligence 35(8):1798~1828
Ding, C. / 2004 / K-Means clustering via principal component analysis / Proceedings of the 21st International Conference on Machine Learning (ICML)
Dizaji, K. G. / 2017 / Deep clustering via joint convolutional autoencoder embedding and relative entropy minimization / Proceedings of 2017 IEEE International Conference on Computer Vision (ICCV) :5747~5756
Aljalbout, E. / 2018 / Clustering with deep learning:taxonomy and new methods
함께 읽어보면 좋을 논문
논문 유사도에 따라 DBpia 가 추천하는 논문입니다. 함께 보면 좋을 연관 논문을 확인해보세요!
-
합성곱 오토인코더 기반의 응집형 계층적 군집 분석
멀티미디어학회논문지
2020 .01
-
다차원 데이터에 대한 심층 군집 네트워크의 성능향상 방법
멀티미디어학회논문지
2018 .08
-
이상치를 고려한 딥러닝 기반 웨이퍼 맵 결함 패턴 클러스터링
신뢰성응용연구
2022 .12
-
Deep Clustering Method for PD Data Based on Time Series Representation Learning Model
한국정보과학회 학술발표논문집
2024 .06
-
Synthesis of clustering algorithms based on selection of centroids
제어로봇시스템학회 국제학술대회 논문집
2018 .10
-
상황인식 기반 클러스터링의 비지도 학습
한국정보통신학회 종합학술대회 논문집
2020 .07
-
클러스터링 기법을 이용한 수용가별 전력 데이터 패턴 분석
KEPCO Journal on electric power and energy
2016 .01
-
비지도학습 데이터의 정확성 측정을 위한 클러스터별 분류 평가 예측 모델에 대한 연구
멀티미디어학회논문지
2018 .07
-
Automatic Determination of the Number of Clusters for Semi-Supervised Relational Fuzzy Clustering
INTERNATIONAL JOURNAL of FUZZY LOGIC and INTELLIGENT SYSTEMS
2020 .06
-
The Effect of Bias in Data Set for Conceptual Clustering Algorithms
International journal of advanced smart convergence
2019 .01
-
Performance evaluation of principal component analysis for clustering problems
Journal of Advanced Marine Engineering and Technology (JAMET)
2016 .10
-
Experiment Results of Data-Driven Contact Clustering
대한기계학회 춘추학술대회
2019 .05
-
Spectral clustering based on the local similarity measure of shared neighbors
[ETRI] ETRI Journal
2022 .10
-
Fine-Grained Mobile Application Clustering Model Using Retrofitted Document Embedding
[ETRI] ETRI Journal
2017 .08
-
상황인식 기반 클러스터링의 적응적 자율 학습 분할 알고리즘
한국정보통신학회 종합학술대회 논문집
2022 .10
-
상황인식 기반 클러스터링의 적응적 자율 학습 분할 알고리즘
한국정보통신학회 종합학술대회 논문집
2022 .05
-
딥 임베딩을 이용한 파형 군집화
한국가스학회 학술대회논문집
2019 .10
-
A deep clustering approach on the stock market for compact and similar size cluster
대한산업공학회 추계학술대회 논문집
2020 .11
-
신경망 및 클러스터링을 기반으로 콘크리트 구조물의 균열 분류 및 분석
제어로봇시스템학회 국내학술대회 논문집
2024 .07
이 논문의 저자 정보
이 논문과 함께 이용한 논문
GPGPU를 사용한 효율적인 공간 데이터 클러스터링 기법
오병우
한국정보기술학회논문지
2019
.04
Twitter Hashtags Clustering with Word Embedding
Tien Anh Nguyen
,
Hyung-Jeong Yang
한국콘텐츠학회 종합학술대회 논문집
2019
.05
다중 관점으로 본 뉴스기사의 군집화
김재훈
,
최우용
,
박세영
한국정보과학회 학술발표논문집
2018
.06
Women’s Right to Breastfeed in the Workplace : Legal Lacunae in Malaysia
Kamal Halili Hassan
,
No
,
suhaida Che Musa
Asian Women
2014
.06
공간 클러스터링을 활용한 초고속인터넷 해지율 예측 정확도 향상 방안에 대한 연구
박장혁
,
박상언
,
김우주
Korea Business Review
2019
.08
최근 본 자료
댓글(0)
0
UCI(KEPA) : I410-ECN-0101-2019-323-000903281