Selective Ensemble Based on Extreme Learning Machine for Sensor-Based Human Activity Recognition
Sensor-based human activity recognition (HAR) has attracted interest both in academic and applied fields, and can be utilized in health-related areas, fitness, sports training, etc. With a view to improving the performance of sensor-based HAR and optimizing the generalizability and diversity of the...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2019-08-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/19/16/3468 |
| _version_ | 1818475029996765184 |
|---|---|
| author | Yiming Tian Jie Zhang Lingling Chen Yanli Geng Xitai Wang |
| author_facet | Yiming Tian Jie Zhang Lingling Chen Yanli Geng Xitai Wang |
| author_sort | Yiming Tian |
| collection | DOAJ |
| description | Sensor-based human activity recognition (HAR) has attracted interest both in academic and applied fields, and can be utilized in health-related areas, fitness, sports training, etc. With a view to improving the performance of sensor-based HAR and optimizing the generalizability and diversity of the base classifier of the ensemble system, a novel HAR approach (pairwise diversity measure and glowworm swarm optimization-based selective ensemble learning, DMGSOSEN) that utilizes ensemble learning with differentiated extreme learning machines (ELMs) is proposed in this paper. Firstly, the bootstrap sampling method is utilized to independently train multiple base ELMs which make up the initial base classifier pool. Secondly, the initial pool is pre-pruned by calculating the pairwise diversity measure of each base ELM, which can eliminate similar base ELMs and enhance the performance of HAR system by balancing diversity and accuracy. Then, glowworm swarm optimization (GSO) is utilized to search for the optimal sub-ensemble from the base ELMs after pre-pruning. Finally, majority voting is utilized to combine the results of the selected base ELMs. For the evaluation of our proposed method, we collected a dataset from different locations on the body, including chest, waist, left wrist, left ankle and right arm. The experimental results show that, compared with traditional ensemble algorithms such as Bagging, Adaboost, and other state-of-the-art pruning algorithms, the proposed approach is able to achieve better performance (96.7% accuracy and F1 from wrist) with fewer base classifiers. |
| first_indexed | 2024-04-14T04:45:08Z |
| format | Article |
| id | doaj.art-066223f14b234aa88dec162d32aee650 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-14T04:45:08Z |
| publishDate | 2019-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-066223f14b234aa88dec162d32aee6502022-12-22T02:11:29ZengMDPI AGSensors1424-82202019-08-011916346810.3390/s19163468s19163468Selective Ensemble Based on Extreme Learning Machine for Sensor-Based Human Activity RecognitionYiming Tian0Jie Zhang1Lingling Chen2Yanli Geng3Xitai Wang4School of Artificial Intelligence, Hebei University of Technology, Tianjin 300130, ChinaSchool of Engineering, Merz Court, Newcastle University, Newcastle upon Tyne NE1 7RU, UKSchool of Artificial Intelligence, Hebei University of Technology, Tianjin 300130, ChinaSchool of Artificial Intelligence, Hebei University of Technology, Tianjin 300130, ChinaSchool of Artificial Intelligence, Hebei University of Technology, Tianjin 300130, ChinaSensor-based human activity recognition (HAR) has attracted interest both in academic and applied fields, and can be utilized in health-related areas, fitness, sports training, etc. With a view to improving the performance of sensor-based HAR and optimizing the generalizability and diversity of the base classifier of the ensemble system, a novel HAR approach (pairwise diversity measure and glowworm swarm optimization-based selective ensemble learning, DMGSOSEN) that utilizes ensemble learning with differentiated extreme learning machines (ELMs) is proposed in this paper. Firstly, the bootstrap sampling method is utilized to independently train multiple base ELMs which make up the initial base classifier pool. Secondly, the initial pool is pre-pruned by calculating the pairwise diversity measure of each base ELM, which can eliminate similar base ELMs and enhance the performance of HAR system by balancing diversity and accuracy. Then, glowworm swarm optimization (GSO) is utilized to search for the optimal sub-ensemble from the base ELMs after pre-pruning. Finally, majority voting is utilized to combine the results of the selected base ELMs. For the evaluation of our proposed method, we collected a dataset from different locations on the body, including chest, waist, left wrist, left ankle and right arm. The experimental results show that, compared with traditional ensemble algorithms such as Bagging, Adaboost, and other state-of-the-art pruning algorithms, the proposed approach is able to achieve better performance (96.7% accuracy and F1 from wrist) with fewer base classifiers.https://www.mdpi.com/1424-8220/19/16/3468human activity recognitionselective ensemblewearable sensorextreme learning machinediversity measureglowworm swarm optimization |
| spellingShingle | Yiming Tian Jie Zhang Lingling Chen Yanli Geng Xitai Wang Selective Ensemble Based on Extreme Learning Machine for Sensor-Based Human Activity Recognition Sensors human activity recognition selective ensemble wearable sensor extreme learning machine diversity measure glowworm swarm optimization |
| title | Selective Ensemble Based on Extreme Learning Machine for Sensor-Based Human Activity Recognition |
| title_full | Selective Ensemble Based on Extreme Learning Machine for Sensor-Based Human Activity Recognition |
| title_fullStr | Selective Ensemble Based on Extreme Learning Machine for Sensor-Based Human Activity Recognition |
| title_full_unstemmed | Selective Ensemble Based on Extreme Learning Machine for Sensor-Based Human Activity Recognition |
| title_short | Selective Ensemble Based on Extreme Learning Machine for Sensor-Based Human Activity Recognition |
| title_sort | selective ensemble based on extreme learning machine for sensor based human activity recognition |
| topic | human activity recognition selective ensemble wearable sensor extreme learning machine diversity measure glowworm swarm optimization |
| url | https://www.mdpi.com/1424-8220/19/16/3468 |
| work_keys_str_mv | AT yimingtian selectiveensemblebasedonextremelearningmachineforsensorbasedhumanactivityrecognition AT jiezhang selectiveensemblebasedonextremelearningmachineforsensorbasedhumanactivityrecognition AT linglingchen selectiveensemblebasedonextremelearningmachineforsensorbasedhumanactivityrecognition AT yanligeng selectiveensemblebasedonextremelearningmachineforsensorbasedhumanactivityrecognition AT xitaiwang selectiveensemblebasedonextremelearningmachineforsensorbasedhumanactivityrecognition |