New method for evaluating artificial neural network algorithm with signal detection theory and full factorial design for detecting falls
Fall is one of the most critical accidents resulting in serious injuries and significant financial losses among people in allages. This paper presents the application of full factorial design (FFD) to investigate fall detection algorithms that have multiple hyperparameters which are very diffi...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Khon Kaen University
2023-01-01
|
| Series: | Engineering and Applied Science Research |
| Subjects: | |
| Online Access: | https://ph01.tci-thaijo.org/index.php/easr/article/view/250713/170318 |
| _version_ | 1827932333139820544 |
|---|---|
| author | Uttapon Khawnuan Teppakorn Sittiwanchai Nantakrit Yodpijit |
| author_facet | Uttapon Khawnuan Teppakorn Sittiwanchai Nantakrit Yodpijit |
| author_sort | Uttapon Khawnuan |
| collection | DOAJ |
| description | Fall is one of the most critical accidents resulting in serious injuries and significant financial losses among people in allages. This paper presents the application of full factorial design (FFD) to investigate fall detection algorithms that have multiple hyperparameters which are very difficult to identify the best values for the dataset. In this study, the algorithm factors are investigated from two motion sensors and six artifact neural network (ANN)parameters on seven possible outcomes of signal detection theory (SDT). It is found that only one accelerometer and one gyroscope and small size ANN with scaled conjugate gradient (SCG) and radial basis function (RBF) provide a higher performance classification with lowercomputationalcomplexity. Experimental outcomes show the new method using statistical theory for the selection of the most effective performance of fall detection algorithm parameters. Findings from the current study could be applied to various types of classification model problems in engineering applications, such as the design of products and systems. |
| first_indexed | 2024-03-13T07:07:08Z |
| format | Article |
| id | doaj.art-fe28fc73c3844bc7bbbf3ada89ed75ad |
| institution | Directory Open Access Journal |
| issn | 2539-6161 2539-6218 |
| language | English |
| last_indexed | 2024-03-13T07:07:08Z |
| publishDate | 2023-01-01 |
| publisher | Khon Kaen University |
| record_format | Article |
| series | Engineering and Applied Science Research |
| spelling | doaj.art-fe28fc73c3844bc7bbbf3ada89ed75ad2023-06-06T08:09:27ZengKhon Kaen UniversityEngineering and Applied Science Research2539-61612539-62182023-01-015013346New method for evaluating artificial neural network algorithm with signal detection theory and full factorial design for detecting fallsUttapon KhawnuanTeppakorn SittiwanchaiNantakrit YodpijitFall is one of the most critical accidents resulting in serious injuries and significant financial losses among people in allages. This paper presents the application of full factorial design (FFD) to investigate fall detection algorithms that have multiple hyperparameters which are very difficult to identify the best values for the dataset. In this study, the algorithm factors are investigated from two motion sensors and six artifact neural network (ANN)parameters on seven possible outcomes of signal detection theory (SDT). It is found that only one accelerometer and one gyroscope and small size ANN with scaled conjugate gradient (SCG) and radial basis function (RBF) provide a higher performance classification with lowercomputationalcomplexity. Experimental outcomes show the new method using statistical theory for the selection of the most effective performance of fall detection algorithm parameters. Findings from the current study could be applied to various types of classification model problems in engineering applications, such as the design of products and systems.https://ph01.tci-thaijo.org/index.php/easr/article/view/250713/170318falls detectionwearable sensorartifact neural network (ann)signal detection theory (sdt)full factorial design (ffd) |
| spellingShingle | Uttapon Khawnuan Teppakorn Sittiwanchai Nantakrit Yodpijit New method for evaluating artificial neural network algorithm with signal detection theory and full factorial design for detecting falls Engineering and Applied Science Research falls detection wearable sensor artifact neural network (ann) signal detection theory (sdt) full factorial design (ffd) |
| title | New method for evaluating artificial neural network algorithm with signal detection theory and full factorial design for detecting falls |
| title_full | New method for evaluating artificial neural network algorithm with signal detection theory and full factorial design for detecting falls |
| title_fullStr | New method for evaluating artificial neural network algorithm with signal detection theory and full factorial design for detecting falls |
| title_full_unstemmed | New method for evaluating artificial neural network algorithm with signal detection theory and full factorial design for detecting falls |
| title_short | New method for evaluating artificial neural network algorithm with signal detection theory and full factorial design for detecting falls |
| title_sort | new method for evaluating artificial neural network algorithm with signal detection theory and full factorial design for detecting falls |
| topic | falls detection wearable sensor artifact neural network (ann) signal detection theory (sdt) full factorial design (ffd) |
| url | https://ph01.tci-thaijo.org/index.php/easr/article/view/250713/170318 |
| work_keys_str_mv | AT uttaponkhawnuan newmethodforevaluatingartificialneuralnetworkalgorithmwithsignaldetectiontheoryandfullfactorialdesignfordetectingfalls AT teppakornsittiwanchai newmethodforevaluatingartificialneuralnetworkalgorithmwithsignaldetectiontheoryandfullfactorialdesignfordetectingfalls AT nantakrityodpijit newmethodforevaluatingartificialneuralnetworkalgorithmwithsignaldetectiontheoryandfullfactorialdesignfordetectingfalls |