Multipopulation Whale Optimization-Based Feature Selection Algorithm and Its Application in Human Fall Detection Using Inertial Measurement Unit Sensors
Feature selection (FS) is a key process in many pattern-recognition tasks, which reduces dimensionality by eliminating redundant or irrelevant features. However, for complex high-dimensional issues, traditional FS methods cannot find the ideal feature combination. To overcome this disadvantage, this...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2024-12-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/24/24/7879 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850085154356199424 |
|---|---|
| author | Haolin Cao Bingshuo Yan Lin Dong Xianfeng Yuan |
| author_facet | Haolin Cao Bingshuo Yan Lin Dong Xianfeng Yuan |
| author_sort | Haolin Cao |
| collection | DOAJ |
| description | Feature selection (FS) is a key process in many pattern-recognition tasks, which reduces dimensionality by eliminating redundant or irrelevant features. However, for complex high-dimensional issues, traditional FS methods cannot find the ideal feature combination. To overcome this disadvantage, this paper presents a multispiral whale optimization algorithm (MSWOA) for feature selection. First, an Adaptive Multipopulation merging Strategy (AMS) is presented, which uses exponential variation and individual location information to divide the population, thus avoiding the premature aggregation of subpopulations and increasing candidate feature subsets. Second, a Double Spiral updating Strategy (DSS) is devised to break out of search stagnations by discovering new individual positions continuously. Last, to facilitate the convergence speed, a Baleen neighborhood Exploitation Strategy (BES) which mimics the behavior of whale tentacles is proposed. The presented algorithm is thoroughly compared with six state-of-the-art meta-heuristic methods and six promising WOA-based algorithms on 20 UCI datasets. Experimental results indicate that the proposed method is superior to other well-known competitors in most cases. In addition, the proposed method is utilized to perform feature selection in human fall-detection tasks, and extensive real experimental results further illustrate the superior ability of the proposed method in addressing practical problems. |
| format | Article |
| id | doaj-art-4689c505c9c344bf8a9f2d42c540ef8d |
| institution | DOAJ |
| issn | 1424-8220 |
| language | English |
| publishDate | 2024-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj-art-4689c505c9c344bf8a9f2d42c540ef8d2025-08-20T02:43:47ZengMDPI AGSensors1424-82202024-12-012424787910.3390/s24247879Multipopulation Whale Optimization-Based Feature Selection Algorithm and Its Application in Human Fall Detection Using Inertial Measurement Unit SensorsHaolin Cao0Bingshuo Yan1Lin Dong2Xianfeng Yuan3School of Mechanical Electrical and Information Engineering, Shandong University, Weihai 264209, ChinaSchool of Mechanical Electrical and Information Engineering, Shandong University, Weihai 264209, ChinaSchool of Mechanical Electrical and Information Engineering, Shandong University, Weihai 264209, ChinaSchool of Mechanical Electrical and Information Engineering, Shandong University, Weihai 264209, ChinaFeature selection (FS) is a key process in many pattern-recognition tasks, which reduces dimensionality by eliminating redundant or irrelevant features. However, for complex high-dimensional issues, traditional FS methods cannot find the ideal feature combination. To overcome this disadvantage, this paper presents a multispiral whale optimization algorithm (MSWOA) for feature selection. First, an Adaptive Multipopulation merging Strategy (AMS) is presented, which uses exponential variation and individual location information to divide the population, thus avoiding the premature aggregation of subpopulations and increasing candidate feature subsets. Second, a Double Spiral updating Strategy (DSS) is devised to break out of search stagnations by discovering new individual positions continuously. Last, to facilitate the convergence speed, a Baleen neighborhood Exploitation Strategy (BES) which mimics the behavior of whale tentacles is proposed. The presented algorithm is thoroughly compared with six state-of-the-art meta-heuristic methods and six promising WOA-based algorithms on 20 UCI datasets. Experimental results indicate that the proposed method is superior to other well-known competitors in most cases. In addition, the proposed method is utilized to perform feature selection in human fall-detection tasks, and extensive real experimental results further illustrate the superior ability of the proposed method in addressing practical problems.https://www.mdpi.com/1424-8220/24/24/7879feature selectionwhale optimization algorithmmultipopulationhuman fall detection |
| spellingShingle | Haolin Cao Bingshuo Yan Lin Dong Xianfeng Yuan Multipopulation Whale Optimization-Based Feature Selection Algorithm and Its Application in Human Fall Detection Using Inertial Measurement Unit Sensors Sensors feature selection whale optimization algorithm multipopulation human fall detection |
| title | Multipopulation Whale Optimization-Based Feature Selection Algorithm and Its Application in Human Fall Detection Using Inertial Measurement Unit Sensors |
| title_full | Multipopulation Whale Optimization-Based Feature Selection Algorithm and Its Application in Human Fall Detection Using Inertial Measurement Unit Sensors |
| title_fullStr | Multipopulation Whale Optimization-Based Feature Selection Algorithm and Its Application in Human Fall Detection Using Inertial Measurement Unit Sensors |
| title_full_unstemmed | Multipopulation Whale Optimization-Based Feature Selection Algorithm and Its Application in Human Fall Detection Using Inertial Measurement Unit Sensors |
| title_short | Multipopulation Whale Optimization-Based Feature Selection Algorithm and Its Application in Human Fall Detection Using Inertial Measurement Unit Sensors |
| title_sort | multipopulation whale optimization based feature selection algorithm and its application in human fall detection using inertial measurement unit sensors |
| topic | feature selection whale optimization algorithm multipopulation human fall detection |
| url | https://www.mdpi.com/1424-8220/24/24/7879 |
| work_keys_str_mv | AT haolincao multipopulationwhaleoptimizationbasedfeatureselectionalgorithmanditsapplicationinhumanfalldetectionusinginertialmeasurementunitsensors AT bingshuoyan multipopulationwhaleoptimizationbasedfeatureselectionalgorithmanditsapplicationinhumanfalldetectionusinginertialmeasurementunitsensors AT lindong multipopulationwhaleoptimizationbasedfeatureselectionalgorithmanditsapplicationinhumanfalldetectionusinginertialmeasurementunitsensors AT xianfengyuan multipopulationwhaleoptimizationbasedfeatureselectionalgorithmanditsapplicationinhumanfalldetectionusinginertialmeasurementunitsensors |