There are approximately 131,800,000 (1.85% of world population) people in the world that have a physical disability and require a wheelchair. Musculoskeletal pain because of wheelchair use is very common amongst wheel...
详细信息
Drowsiness at the wheel continues to be one of the causes of road accidents with higher fatality rates and current solutions fail to mitigate the problem from a preventive viewpoint. This work contributes towards the ...
详细信息
There are approximately 131,800,000 (1.85% of world population) people in the world that have a physical disability and require a wheelchair. Musculoskeletal pain because of wheelchair use is very common amongst wheel...
详细信息
There are approximately 131,800,000 (1.85% of world population) people in the world that have a physical disability and require a wheelchair. Musculoskeletal pain because of wheelchair use is very common amongst wheelchair users. Optimal adjustment of seating position may prevent pain and other deceases, monitoring the seating position is an important tool to improve the quality of life for those who need use a wheelchair for long term. This information is important for the user who can receive instructions to improve the positioning of the chair and for the orthopedist who can more easily customize the wheelchair adjustments. Physical activity is important for the health and well-being of wheelchair users, using a wheelchair as a means of exercising will make an important contribution to the health status of its users. The creation of an integrated system that monitors and records the activity of the wheelchair, senses the wheelchair to carry out the monitoring, understands where to place the sensory devices and creates an intelligent system that, through the information collected, is able to classify the different positions of the wheelchair is essential for promoting the health and well-being of wheelchair users. This work shows the development of an monitoring system for wheelchair, the results indicate that the applied technology proved to be suitable and applicable for any type of wheelchair, manual or electric. The collected data allowed the development of a robust and highly accurate classification model, making it possible to classify the position of the wheelchair in real time, allowing the issue of alerts to the user. A mobile application was developed that concentrates all the information, making it available intuitively in two dimensions: wheelchair user and orthopedic surgeon.
Introduction: Sleep is a crucial biological need for all individuals, being reparative on a physical and mental level. Driving heavy vehicles is a task that requires constant attention and vigilance, and sleep depriva...
详细信息
Drowsiness at the wheel continues to be one of the causes of road accidents with higher fatality rates and current solutions fail to mitigate the problem from a preventive viewpoint. This work contributes towards the ...
详细信息
Drowsiness at the wheel continues to be one of the causes of road accidents with higher fatality rates and current solutions fail to mitigate the problem from a preventive viewpoint. This work contributes towards the development of a non-intrusive and low-cost system for drowsiness detection and prediction, using a wearable device and artificial intelligence for continuous and real-time monitoring and alert of the driver’s state. In particular, Machine Learning (ML) algorithms were used to classify drowsiness levels using Heart Rate Variability (HRV) data extracted from physiological signals collected during driving simulations, following data labeling considering three different sets of drowsiness levels’ distribution. Obtained results showed promising potential, with the Extra Trees, Random Forest and K-Nearest Neighbors (KNN) classifiers achieving overall good performance, with a relative capability of distinguishing between drowsiness levels and between alert and drowsy states. However, further analysis should be made to improve the performance of the models and deal with the existing data imbalance, as well as identify the best subset of features capable of detecting drowsiness. Ultimately, it was shown that drowsiness detection using physiological data from a standalone wrist-worn wearable device in combination with ML techniques is feasible. Henceforth, prediction and forecasting of the drowsiness state should be addressed, to achieve the preventive component of the system.
Drowsiness is one of the causes of road accidents with higher fatality rate and even though it has been studied over the years, there is still no solution that can mitigate this problem from a low cost perspective. Th...
Drowsiness is one of the causes of road accidents with higher fatality rate and even though it has been studied over the years, there is still no solution that can mitigate this problem from a low cost perspective. Thereby, artificial intelligence will be used to predict drowsiness and develop a non-intrusive and low-cost system using a wearable device that is capable of alerting the driver before they exhibit any signs. The aim of this work is to present the results achieved in the first stage, where driving simulations were conducted and video information, subjective reporting and physiological-based data were collected. Drowsiness levels and eye blinks were extracted from analysis of the participants’ videos, in addition to simulation based information, such as speed variations and road accidents, allowing to classify the driver’s state. Multivariate statistical process control was the method implemented, considering the Heart Rate Variability (HRV) and Electroencephalography (EEG) information. Using this methodology, it was able to detect the transition between the different drowsiness phases. Although the results are promising, there are still missing analyses, such as the application of Machine Learning (ML) techniques to classify the drowsy state and identify the best subset of features capable of detecting this state. Besides this, data analysis must be done to understand how drowsiness can be predicted. Finally, the proposed solution must be implemented in a real environment.
暂无评论