The rate of annual road accidents attributed to drowsy driving are significantly high. Due to this, researchers have proposed several methods aimed at detecting drivers' drowsiness. These methods include subjective, physiological, behavioral, vehicle-based, and hybrid methods. However, recent reports on road safety are still indicating drowsy driving as a major cause of road accidents. This is plausible because the current driver drowsiness detection (DDD) solutions are either intrusive or expensive, thus hindering their ubiquitous nature. This research serves to bridge this gap by providing a test-bed for achieving a non-intrusive and low-cost DDD solution. A behavioral DDD solution is proposed based on tracking the face and eye state of the driver. The aim is to make this research an inception to DDD pervasiveness. To achieve this, National Tsing Hua University (NTHU) Computer Vision Lab's driver drowsiness detection video dataset was utilized. Several video and image processing operations were performed on the videos so as to detect the drivers' eye state. From the eye states, three important drowsiness features were extracted: percentage of eyelid closure (PERCLOS), blink frequency (BF), and Maximum Closure Duration (MCD) of the eyes. These features were then fed as inputs into several machine learning models for drowsiness classification. Models from the K-nearest Neighbors (KNN), Support Vector Machine (SVM), Logistic Regression, and Artificial Neural Networks (ANN) machine learning algorithms were experimented. These models were evaluated by calculating their accuracy, sensitivity, specificity, miss rate, and false alarm rate values. Although these five metrics were evaluated, the focus was more on getting optimal accuracies and miss rates. The result shows that the best models were a KNN model when k = 31 and an ANN model that used an Adadelta optimizer with 3 hidden layer network of 3, 27, and 9 neurons respective. The KNN model obtained an accuracy of 72.25% with a miss rate of 16.67%, while the ANN model obtained 71.61% and 14.44% accuracy and miss rate respectively.
Fall is an increasing problem as people ageing. It may happen to anyone, but their incidence does increase with age. Hence, the elderly will be facing catastrophic consequences due to falls. Nevertheless, there are still vulnerable in its accuracy in categorizing and differentiating the Activities Daily Living (ADL) and falls as most of the existing systems cause false alarm. This paper presents the research and simulation of wearable device-based fall detection approach by addressing the building of wearable device-based fall detection system for elderly care by using mobile devices. Two main phases involve in this research: online phase and offline phase. Online phase covers in data acquisition step whereby the raw data of simulated fall by participants is collected via built-in-tri-axial accelerometer in a smartphone, then automatically sent towards the computer via wireless communication. Meanwhile, offline phase covers data pre-processing, feature extraction and selection and data classification where these steps are handled in offline mode. Support Vector Machine (SVM) classifier was employed, and evaluated in the analysis. Overall accuracy rate, sensitivity, specificity as well as False Positive Rate (FPR) and False Negative Rate (FNR) were calculated. The findings suggest that SVM with Polynomial (order 5) method which achieved 68.91% overall accuracy as well as producing only 24.46% FPR is the most precise model for fall detection system in this paper. This approach has the potential to be implemented and deploy in real mobile application in future.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.