Deep Neural Network for Slip Detection on Ice Surface
Slip-induced falls are among the most common causes of major occupational injuries and economic loss in Canada. Identifying the risk factors associated with slip events is key to developing preventive solutions to reduce falls. One factor is the slip-resistance quality of footwear, which is fundamen...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-12-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/20/23/6883 |
| _version_ | 1797545936589684736 |
|---|---|
| author | Kent Wu Suzy He Geoff Fernie Atena Roshan Fekr |
| author_facet | Kent Wu Suzy He Geoff Fernie Atena Roshan Fekr |
| author_sort | Kent Wu |
| collection | DOAJ |
| description | Slip-induced falls are among the most common causes of major occupational injuries and economic loss in Canada. Identifying the risk factors associated with slip events is key to developing preventive solutions to reduce falls. One factor is the slip-resistance quality of footwear, which is fundamental to reducing the number of falls. Measuring footwear slip resistance with the recently developed Maximum Achievable Angle (MAA) test requires a trained researcher to identify slip events in a simulated winter environment. The human capacity for information processing is limited and human error is natural, especially in a cold environment. Therefore, to remove conflicts associated with human errors, in this paper a deep three-dimensional convolutional neural network is proposed to detect the slips in real-time. The model has been trained by a new dataset that includes data from 18 different participants with various clothing, footwear, walking directions, inclined angles, and surface types. The model was evaluated on three types of slips: Maxi-slip, midi-slip, and mini-slip. This classification is based on the slip perception and recovery of the participants. The model was evaluated based on both 5-fold and Leave-One-Subject-Out (LOSO) cross validation. The best accuracy of 97% was achieved when identifying the maxi-slips. The minimum accuracy of 77% was achieved when classifying the no-slip and mini-slip trials. The overall slip detection accuracy was 86% with sensitivity and specificity of 81% and 91%, respectively. The overall accuracy dropped by about 2% in LOSO cross validation. The proposed slip detection algorithm is not only beneficial for footwear manufactures to improve their footwear slip resistance quality, but it also has other potential applications, such as improving the slip resistance properties of flooring in healthcare facilities, commercial kitchens, and oil drilling platforms. |
| first_indexed | 2024-03-10T14:22:59Z |
| format | Article |
| id | doaj.art-11ee189fdd1f4f92b41babaf8c79d89c |
| institution | Directory Open Access Journal |
| issn | 1424-8220 |
| language | English |
| last_indexed | 2024-03-10T14:22:59Z |
| publishDate | 2020-12-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj.art-11ee189fdd1f4f92b41babaf8c79d89c2023-11-20T23:12:08ZengMDPI AGSensors1424-82202020-12-012023688310.3390/s20236883Deep Neural Network for Slip Detection on Ice SurfaceKent Wu0Suzy He1Geoff Fernie2Atena Roshan Fekr3The Kite Research Institute, Toronto Rehabilitation Institute—University Health Network, University of Toronto, Toronto, ON M5G 2A2, CanadaThe Kite Research Institute, Toronto Rehabilitation Institute—University Health Network, University of Toronto, Toronto, ON M5G 2A2, CanadaThe Kite Research Institute, Toronto Rehabilitation Institute—University Health Network, University of Toronto, Toronto, ON M5G 2A2, CanadaThe Kite Research Institute, Toronto Rehabilitation Institute—University Health Network, University of Toronto, Toronto, ON M5G 2A2, CanadaSlip-induced falls are among the most common causes of major occupational injuries and economic loss in Canada. Identifying the risk factors associated with slip events is key to developing preventive solutions to reduce falls. One factor is the slip-resistance quality of footwear, which is fundamental to reducing the number of falls. Measuring footwear slip resistance with the recently developed Maximum Achievable Angle (MAA) test requires a trained researcher to identify slip events in a simulated winter environment. The human capacity for information processing is limited and human error is natural, especially in a cold environment. Therefore, to remove conflicts associated with human errors, in this paper a deep three-dimensional convolutional neural network is proposed to detect the slips in real-time. The model has been trained by a new dataset that includes data from 18 different participants with various clothing, footwear, walking directions, inclined angles, and surface types. The model was evaluated on three types of slips: Maxi-slip, midi-slip, and mini-slip. This classification is based on the slip perception and recovery of the participants. The model was evaluated based on both 5-fold and Leave-One-Subject-Out (LOSO) cross validation. The best accuracy of 97% was achieved when identifying the maxi-slips. The minimum accuracy of 77% was achieved when classifying the no-slip and mini-slip trials. The overall slip detection accuracy was 86% with sensitivity and specificity of 81% and 91%, respectively. The overall accuracy dropped by about 2% in LOSO cross validation. The proposed slip detection algorithm is not only beneficial for footwear manufactures to improve their footwear slip resistance quality, but it also has other potential applications, such as improving the slip resistance properties of flooring in healthcare facilities, commercial kitchens, and oil drilling platforms.https://www.mdpi.com/1424-8220/20/23/6883slip detectioninjury preventiondeep neural networkconvolutionspatiotemporal feature extraction |
| spellingShingle | Kent Wu Suzy He Geoff Fernie Atena Roshan Fekr Deep Neural Network for Slip Detection on Ice Surface Sensors slip detection injury prevention deep neural network convolution spatiotemporal feature extraction |
| title | Deep Neural Network for Slip Detection on Ice Surface |
| title_full | Deep Neural Network for Slip Detection on Ice Surface |
| title_fullStr | Deep Neural Network for Slip Detection on Ice Surface |
| title_full_unstemmed | Deep Neural Network for Slip Detection on Ice Surface |
| title_short | Deep Neural Network for Slip Detection on Ice Surface |
| title_sort | deep neural network for slip detection on ice surface |
| topic | slip detection injury prevention deep neural network convolution spatiotemporal feature extraction |
| url | https://www.mdpi.com/1424-8220/20/23/6883 |
| work_keys_str_mv | AT kentwu deepneuralnetworkforslipdetectiononicesurface AT suzyhe deepneuralnetworkforslipdetectiononicesurface AT geofffernie deepneuralnetworkforslipdetectiononicesurface AT atenaroshanfekr deepneuralnetworkforslipdetectiononicesurface |