Hardware/Software Co-Design of Fractal Features Based Fall Detection System
Falls are a leading cause of death in older adults and result in high levels of mortality, morbidity and immobility. Fall Detection Systems (FDS) are imperative for timely medical aid and have been known to reduce death rate by 80%. We propose a novel wearable sensor FDS which exploits fractal dynam...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-04-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/20/8/2322 |
| _version_ | 1797570243778838528 |
|---|---|
| author | Ahsen Tahir Gordon Morison Dawn A. Skelton Ryan M. Gibson |
| author_facet | Ahsen Tahir Gordon Morison Dawn A. Skelton Ryan M. Gibson |
| author_sort | Ahsen Tahir |
| collection | DOAJ |
| description | Falls are a leading cause of death in older adults and result in high levels of mortality, morbidity and immobility. Fall Detection Systems (FDS) are imperative for timely medical aid and have been known to reduce death rate by 80%. We propose a novel wearable sensor FDS which exploits fractal dynamics of fall accelerometer signals. Fractal dynamics can be used as an irregularity measure of signals and our work shows that it is a key discriminant for classification of falls from other activities of life. We design, implement and evaluate a hardware feature accelerator for computation of fractal features through multi-level wavelet transform on a reconfigurable embedded System on Chip, Zynq device for evaluating wearable accelerometer sensors. The proposed FDS utilises a hardware/software co-design approach with hardware accelerator for fractal features and software implementation of Linear Discriminant Analysis on an embedded ARM core for high accuracy and energy efficiency. The proposed system achieves 99.38% fall detection accuracy, 7.3× speed-up and 6.53× improvements in power consumption, compared to the software only execution with an overall performance per Watt advantage of 47.6×, while consuming low reconfigurable resources at 28.67%. |
| first_indexed | 2024-03-10T20:23:08Z |
| format | Article |
| id | doaj.art-5eca6d9460234bdaa3faa787732102e1 |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T20:23:08Z |
| publishDate | 2020-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-5eca6d9460234bdaa3faa787732102e12023-11-19T22:02:39ZengMDPI AGSensors1424-82202020-04-01208232210.3390/s20082322Hardware/Software Co-Design of Fractal Features Based Fall Detection SystemAhsen Tahir0Gordon Morison1Dawn A. Skelton2Ryan M. Gibson3School of Computing, Engineering and Built Environment, Glasgow Caledonian University, Glasgow G4 0BA, UKSchool of Computing, Engineering and Built Environment, Glasgow Caledonian University, Glasgow G4 0BA, UKSchool of Health and Life Sciences, Glasgow Caledonian University, Glasgow G4 0BA, UKSchool of Computing, Engineering and Built Environment, Glasgow Caledonian University, Glasgow G4 0BA, UKFalls are a leading cause of death in older adults and result in high levels of mortality, morbidity and immobility. Fall Detection Systems (FDS) are imperative for timely medical aid and have been known to reduce death rate by 80%. We propose a novel wearable sensor FDS which exploits fractal dynamics of fall accelerometer signals. Fractal dynamics can be used as an irregularity measure of signals and our work shows that it is a key discriminant for classification of falls from other activities of life. We design, implement and evaluate a hardware feature accelerator for computation of fractal features through multi-level wavelet transform on a reconfigurable embedded System on Chip, Zynq device for evaluating wearable accelerometer sensors. The proposed FDS utilises a hardware/software co-design approach with hardware accelerator for fractal features and software implementation of Linear Discriminant Analysis on an embedded ARM core for high accuracy and energy efficiency. The proposed system achieves 99.38% fall detection accuracy, 7.3× speed-up and 6.53× improvements in power consumption, compared to the software only execution with an overall performance per Watt advantage of 47.6×, while consuming low reconfigurable resources at 28.67%.https://www.mdpi.com/1424-8220/20/8/2322fall detectionwearable sensorsclassificationmachine learningfractal featureshardware software co-design |
| spellingShingle | Ahsen Tahir Gordon Morison Dawn A. Skelton Ryan M. Gibson Hardware/Software Co-Design of Fractal Features Based Fall Detection System Sensors fall detection wearable sensors classification machine learning fractal features hardware software co-design |
| title | Hardware/Software Co-Design of Fractal Features Based Fall Detection System |
| title_full | Hardware/Software Co-Design of Fractal Features Based Fall Detection System |
| title_fullStr | Hardware/Software Co-Design of Fractal Features Based Fall Detection System |
| title_full_unstemmed | Hardware/Software Co-Design of Fractal Features Based Fall Detection System |
| title_short | Hardware/Software Co-Design of Fractal Features Based Fall Detection System |
| title_sort | hardware software co design of fractal features based fall detection system |
| topic | fall detection wearable sensors classification machine learning fractal features hardware software co-design |
| url | https://www.mdpi.com/1424-8220/20/8/2322 |
| work_keys_str_mv | AT ahsentahir hardwaresoftwarecodesignoffractalfeaturesbasedfalldetectionsystem AT gordonmorison hardwaresoftwarecodesignoffractalfeaturesbasedfalldetectionsystem AT dawnaskelton hardwaresoftwarecodesignoffractalfeaturesbasedfalldetectionsystem AT ryanmgibson hardwaresoftwarecodesignoffractalfeaturesbasedfalldetectionsystem |