Recognizing salat activity using deep learning models via smartwatch sensors.
Saved in:
| Title: | Recognizing salat activity using deep learning models via smartwatch sensors. |
|---|---|
| Authors: | Vurgun, Yasin1 (AUTHOR), Kiran, Mustafa Servet2 (AUTHOR) mskiran@ktun.edu.tr |
| Source: | Neural Computing & Applications. Nov2024, Vol. 36 Issue 31, p19449-19467. 19p. |
| Subjects: | Linear acceleration, Deep learning, Human activity recognition, Magnetic sensors, Classification algorithms, Time series analysis |
| Abstract: | In this study, we focus on human activity recognition, particularly aiming to distinguish the activity of praying (salat) from other daily activities. To achieve this goal, we have created a new dataset named HAR-P (Human activity recognition for Praying), which includes eight different activities: walking, running, sitting, standing, walking upstairs, walking downstairs, typing with a keyboard, and praying (salat). The HAR-P dataset was collected from 50 male individuals, who wore smartwatches on their dominant wrists. We compare the activity classification performance using three state-of-the-art algorithms from the literature: Long Short-Term Memory, Convolutional Long Short-Term Memory, and Convolutional Neural Network—Long Short-Term Memory. To assess the influence of sensors, data from accelerometer, gyroscope, linear acceleration sensor, and magnetic field sensor were utilized. The impact of individual sensor data as well as combinations thereof was investigated. The highest classification accuracy within single sensor groups, reaching 95.7%, was achieved using the accelerometer data with the Convolutional Long Short-Term Memory method. Combining two sensor groups resulted in an increase in accuracy of up to 9%. The highest accuracy of 96.4% was obtained by utilizing three sensor groups together with the Convolutional Neural Network—Long Short-Term Memory method. Furthermore, the evaluation of sensor and model performance was conducted using the stratified k-fold cross-validation method with 5-folds. These findings contribute significantly to evaluating the performance of sensor combinations and different algorithms in activity classification. This study may provide an effective foundation for the automatic recognition and tracking of human activities and offer an applicable model, particularly for the recognition of religious practices such as praying. [ABSTRACT FROM AUTHOR] |
| Copyright of Neural Computing & Applications is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) | |
| Database: | Engineering Source |
|
Full text is not displayed to guests.
Login for full access.
|
|
| FullText | Links: – Type: pdflink Text: Availability: 1 |
|---|---|
| Header | DbId: egs DbLabel: Engineering Source An: 179969929 AccessLevel: 6 PubType: Academic Journal PubTypeId: academicJournal PreciseRelevancyScore: 0 |
| IllustrationInfo | |
| Items | – Name: Title Label: Title Group: Ti Data: Recognizing salat activity using deep learning models via smartwatch sensors. – Name: Author Label: Authors Group: Au Data: <searchLink fieldCode="AR" term="%22Vurgun%2C+Yasin%22">Vurgun, Yasin</searchLink><relatesTo>1</relatesTo> (AUTHOR)<br /><searchLink fieldCode="AR" term="%22Kiran%2C+Mustafa+Servet%22">Kiran, Mustafa Servet</searchLink><relatesTo>2</relatesTo> (AUTHOR)<i> mskiran@ktun.edu.tr</i> – Name: TitleSource Label: Source Group: Src Data: <searchLink fieldCode="JN" term="%22Neural+Computing+%26+Applications%22">Neural Computing & Applications</searchLink>. Nov2024, Vol. 36 Issue 31, p19449-19467. 19p. – Name: Subject Label: Subjects Group: Su Data: <searchLink fieldCode="DE" term="%22Linear+acceleration%22">Linear acceleration</searchLink><br /><searchLink fieldCode="DE" term="%22Deep+learning%22">Deep learning</searchLink><br /><searchLink fieldCode="DE" term="%22Human+activity+recognition%22">Human activity recognition</searchLink><br /><searchLink fieldCode="DE" term="%22Magnetic+sensors%22">Magnetic sensors</searchLink><br /><searchLink fieldCode="DE" term="%22Classification+algorithms%22">Classification algorithms</searchLink><br /><searchLink fieldCode="DE" term="%22Time+series+analysis%22">Time series analysis</searchLink> – Name: Abstract Label: Abstract Group: Ab Data: In this study, we focus on human activity recognition, particularly aiming to distinguish the activity of praying (salat) from other daily activities. To achieve this goal, we have created a new dataset named HAR-P (Human activity recognition for Praying), which includes eight different activities: walking, running, sitting, standing, walking upstairs, walking downstairs, typing with a keyboard, and praying (salat). The HAR-P dataset was collected from 50 male individuals, who wore smartwatches on their dominant wrists. We compare the activity classification performance using three state-of-the-art algorithms from the literature: Long Short-Term Memory, Convolutional Long Short-Term Memory, and Convolutional Neural Network—Long Short-Term Memory. To assess the influence of sensors, data from accelerometer, gyroscope, linear acceleration sensor, and magnetic field sensor were utilized. The impact of individual sensor data as well as combinations thereof was investigated. The highest classification accuracy within single sensor groups, reaching 95.7%, was achieved using the accelerometer data with the Convolutional Long Short-Term Memory method. Combining two sensor groups resulted in an increase in accuracy of up to 9%. The highest accuracy of 96.4% was obtained by utilizing three sensor groups together with the Convolutional Neural Network—Long Short-Term Memory method. Furthermore, the evaluation of sensor and model performance was conducted using the stratified k-fold cross-validation method with 5-folds. These findings contribute significantly to evaluating the performance of sensor combinations and different algorithms in activity classification. This study may provide an effective foundation for the automatic recognition and tracking of human activities and offer an applicable model, particularly for the recognition of religious practices such as praying. [ABSTRACT FROM AUTHOR] – Name: AbstractSuppliedCopyright Label: Group: Ab Data: <i>Copyright of Neural Computing & Applications is the property of Springer Nature and its content may not be copied or emailed to multiple sites without the copyright holder's express written permission. Additionally, content may not be used with any artificial intelligence tools or machine learning technologies. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract.</i> (Copyright applies to all Abstracts.) |
| PLink | https://search.ebscohost.com/login.aspx?direct=true&site=eds-live&db=egs&AN=179969929 |
| RecordInfo | BibRecord: BibEntity: Identifiers: – Type: doi Value: 10.1007/s00521-024-10195-1 Languages: – Code: eng Text: English PhysicalDescription: Pagination: PageCount: 19 StartPage: 19449 Subjects: – SubjectFull: Linear acceleration Type: general – SubjectFull: Deep learning Type: general – SubjectFull: Human activity recognition Type: general – SubjectFull: Magnetic sensors Type: general – SubjectFull: Classification algorithms Type: general – SubjectFull: Time series analysis Type: general Titles: – TitleFull: Recognizing salat activity using deep learning models via smartwatch sensors. Type: main BibRelationships: HasContributorRelationships: – PersonEntity: Name: NameFull: Vurgun, Yasin – PersonEntity: Name: NameFull: Kiran, Mustafa Servet IsPartOfRelationships: – BibEntity: Dates: – D: 01 M: 11 Text: Nov2024 Type: published Y: 2024 Identifiers: – Type: issn-print Value: 09410643 Numbering: – Type: volume Value: 36 – Type: issue Value: 31 Titles: – TitleFull: Neural Computing & Applications Type: main |
| ResultId | 1 |
