Sensor Data Acquisition and Processing Parameters for Human Activity Classification
It is known that parameter selection for data sampling frequency and segmentation techniques (including different methods and window sizes) has an impact on the classification accuracy. For Ambient Assisted Living (AAL), no clear information to select these parameters exists, hence a wide variety an...
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2014-03-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | http://www.mdpi.com/1424-8220/14/3/4239 |
| _version_ | 1798035224529993728 |
|---|---|
| author | Sebastian D. Bersch Djamel Azzi Rinat Khusainov Ifeyinwa E. Achumba Jana Ries |
| author_facet | Sebastian D. Bersch Djamel Azzi Rinat Khusainov Ifeyinwa E. Achumba Jana Ries |
| author_sort | Sebastian D. Bersch |
| collection | DOAJ |
| description | It is known that parameter selection for data sampling frequency and segmentation techniques (including different methods and window sizes) has an impact on the classification accuracy. For Ambient Assisted Living (AAL), no clear information to select these parameters exists, hence a wide variety and inconsistency across today’s literature is observed. This paper presents the empirical investigation of different data sampling rates, segmentation techniques and segmentation window sizes and their effect on the accuracy of Activity of Daily Living (ADL) event classification and computational load for two different accelerometer sensor datasets. The study is conducted using an ANalysis Of VAriance (ANOVA) based on 32 different window sizes, three different segmentation algorithm (with and without overlap, totaling in six different parameters) and six sampling frequencies for nine common classification algorithms. The classification accuracy is based on a feature vector consisting of Root Mean Square (RMS), Mean, Signal Magnitude Area (SMA), Signal Vector Magnitude (here SMV), Energy, Entropy, FFTPeak, Standard Deviation (STD). The results are presented alongside recommendations for the parameter selection on the basis of the best performing parameter combinations that are identified by means of the corresponding Pareto curve. |
| first_indexed | 2024-04-11T20:54:18Z |
| format | Article |
| id | doaj.art-089177b4e6ed4250bd40eb74be3d3210 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-04-11T20:54:18Z |
| publishDate | 2014-03-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-089177b4e6ed4250bd40eb74be3d32102022-12-22T04:03:43ZengMDPI AGSensors1424-82202014-03-011434239427010.3390/s140304239s140304239Sensor Data Acquisition and Processing Parameters for Human Activity ClassificationSebastian D. Bersch0Djamel Azzi1Rinat Khusainov2Ifeyinwa E. Achumba3Jana Ries4School of Engineering, University of Portsmouth, Anglesea Building, Anglesea Road, Portsmouth PO1 3DJ, UKSchool of Engineering, University of Portsmouth, Anglesea Building, Anglesea Road, Portsmouth PO1 3DJ, UKSchool of Engineering, University of Portsmouth, Anglesea Building, Anglesea Road, Portsmouth PO1 3DJ, UKSchool of Engineering, University of Portsmouth, Anglesea Building, Anglesea Road, Portsmouth PO1 3DJ, UKPortsmouth Business School, University of Portsmouth, Richmond Building, Portland Street, Portsmouth PO1 3DE, UKIt is known that parameter selection for data sampling frequency and segmentation techniques (including different methods and window sizes) has an impact on the classification accuracy. For Ambient Assisted Living (AAL), no clear information to select these parameters exists, hence a wide variety and inconsistency across today’s literature is observed. This paper presents the empirical investigation of different data sampling rates, segmentation techniques and segmentation window sizes and their effect on the accuracy of Activity of Daily Living (ADL) event classification and computational load for two different accelerometer sensor datasets. The study is conducted using an ANalysis Of VAriance (ANOVA) based on 32 different window sizes, three different segmentation algorithm (with and without overlap, totaling in six different parameters) and six sampling frequencies for nine common classification algorithms. The classification accuracy is based on a feature vector consisting of Root Mean Square (RMS), Mean, Signal Magnitude Area (SMA), Signal Vector Magnitude (here SMV), Energy, Entropy, FFTPeak, Standard Deviation (STD). The results are presented alongside recommendations for the parameter selection on the basis of the best performing parameter combinations that are identified by means of the corresponding Pareto curve.http://www.mdpi.com/1424-8220/14/3/4239Ambient Assisted Living (AAL)data acquisitiondata samplingevent classificationoptimization |
| spellingShingle | Sebastian D. Bersch Djamel Azzi Rinat Khusainov Ifeyinwa E. Achumba Jana Ries Sensor Data Acquisition and Processing Parameters for Human Activity Classification Sensors Ambient Assisted Living (AAL) data acquisition data sampling event classification optimization |
| title | Sensor Data Acquisition and Processing Parameters for Human Activity Classification |
| title_full | Sensor Data Acquisition and Processing Parameters for Human Activity Classification |
| title_fullStr | Sensor Data Acquisition and Processing Parameters for Human Activity Classification |
| title_full_unstemmed | Sensor Data Acquisition and Processing Parameters for Human Activity Classification |
| title_short | Sensor Data Acquisition and Processing Parameters for Human Activity Classification |
| title_sort | sensor data acquisition and processing parameters for human activity classification |
| topic | Ambient Assisted Living (AAL) data acquisition data sampling event classification optimization |
| url | http://www.mdpi.com/1424-8220/14/3/4239 |
| work_keys_str_mv | AT sebastiandbersch sensordataacquisitionandprocessingparametersforhumanactivityclassification AT djamelazzi sensordataacquisitionandprocessingparametersforhumanactivityclassification AT rinatkhusainov sensordataacquisitionandprocessingparametersforhumanactivityclassification AT ifeyinwaeachumba sensordataacquisitionandprocessingparametersforhumanactivityclassification AT janaries sensordataacquisitionandprocessingparametersforhumanactivityclassification |