Feature Construction Using Persistence Landscapes for Clustering Noisy IoT Time Series
With the advancement of IoT technologies, there is a large amount of data available from wireless sensor networks (WSN), particularly for studying climate change. Clustering long and noisy time series has become an important research area for analyzing this data. This paper proposes a feature-based...
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-05-01
|
| Series: | Future Internet |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1999-5903/15/6/195 |
| _version_ | 1827737274582827008 |
|---|---|
| author | Renjie Chen Nalini Ravishanker |
| author_facet | Renjie Chen Nalini Ravishanker |
| author_sort | Renjie Chen |
| collection | DOAJ |
| description | With the advancement of IoT technologies, there is a large amount of data available from wireless sensor networks (WSN), particularly for studying climate change. Clustering long and noisy time series has become an important research area for analyzing this data. This paper proposes a feature-based clustering approach using topological data analysis, which is a set of methods for finding topological structure in data. Persistence diagrams and landscapes are popular topological summaries that can be used to cluster time series. This paper presents a framework for selecting an optimal number of persistence landscapes, and using them as features in an unsupervised learning algorithm. This approach reduces computational cost while maintaining accuracy. The clustering approach was demonstrated to be accurate on simulated data, based on only four, three, and three features, respectively, selected in Scenarios 1–3. On real data, consisting of multiple long temperature streams from various US locations, our optimal feature selection method achieved approximately a 13 times speed-up in computing. |
| first_indexed | 2024-03-11T02:26:21Z |
| format | Article |
| id | doaj.art-5f24da4c4a7d44b4be92d21e6cd6996f |
| institution | Directory Open Access Journal |
| issn | 1999-5903 |
| language | English |
| last_indexed | 2024-03-11T02:26:21Z |
| publishDate | 2023-05-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Future Internet |
| spelling | doaj.art-5f24da4c4a7d44b4be92d21e6cd6996f2023-11-18T10:30:15ZengMDPI AGFuture Internet1999-59032023-05-0115619510.3390/fi15060195Feature Construction Using Persistence Landscapes for Clustering Noisy IoT Time SeriesRenjie Chen0Nalini Ravishanker1Department of Statistics, University of Connecticut, Storrs, CT 06269, USADepartment of Statistics, University of Connecticut, Storrs, CT 06269, USAWith the advancement of IoT technologies, there is a large amount of data available from wireless sensor networks (WSN), particularly for studying climate change. Clustering long and noisy time series has become an important research area for analyzing this data. This paper proposes a feature-based clustering approach using topological data analysis, which is a set of methods for finding topological structure in data. Persistence diagrams and landscapes are popular topological summaries that can be used to cluster time series. This paper presents a framework for selecting an optimal number of persistence landscapes, and using them as features in an unsupervised learning algorithm. This approach reduces computational cost while maintaining accuracy. The clustering approach was demonstrated to be accurate on simulated data, based on only four, three, and three features, respectively, selected in Scenarios 1–3. On real data, consisting of multiple long temperature streams from various US locations, our optimal feature selection method achieved approximately a 13 times speed-up in computing.https://www.mdpi.com/1999-5903/15/6/195elbow methodfeature constructionIoT time seriespersistence landscapetopological data analysisunsupervised learning |
| spellingShingle | Renjie Chen Nalini Ravishanker Feature Construction Using Persistence Landscapes for Clustering Noisy IoT Time Series Future Internet elbow method feature construction IoT time series persistence landscape topological data analysis unsupervised learning |
| title | Feature Construction Using Persistence Landscapes for Clustering Noisy IoT Time Series |
| title_full | Feature Construction Using Persistence Landscapes for Clustering Noisy IoT Time Series |
| title_fullStr | Feature Construction Using Persistence Landscapes for Clustering Noisy IoT Time Series |
| title_full_unstemmed | Feature Construction Using Persistence Landscapes for Clustering Noisy IoT Time Series |
| title_short | Feature Construction Using Persistence Landscapes for Clustering Noisy IoT Time Series |
| title_sort | feature construction using persistence landscapes for clustering noisy iot time series |
| topic | elbow method feature construction IoT time series persistence landscape topological data analysis unsupervised learning |
| url | https://www.mdpi.com/1999-5903/15/6/195 |
| work_keys_str_mv | AT renjiechen featureconstructionusingpersistencelandscapesforclusteringnoisyiottimeseries AT naliniravishanker featureconstructionusingpersistencelandscapesforclusteringnoisyiottimeseries |