SafeDrive

Abstract

Distracted driving causes a large number of fatalities every year and is now becoming an important issue in the traffic safety study. In this paper, we present SafeDrive, a driving safety system that leverages wearable wrist sensing techniques to detect and analyze driver distracted behaviors. Existing wrist-worn sensing approaches, however, do not address challenges under real driving environments, such as less distinguishable gesture patterns due to in-vehicle physical constraints, various gesture hallmarks produced by different drivers and significant noise introduced by various driving conditions. In response, SafeDrive adopts a semi-supervised machine learning model for in-vehicle distracting activity detection. To improve the detection accuracy, we provide online updated classifiers by collecting real-time gesture data, while at the same time utilize smartphone sensing to generate soft hints filtering out anomalies and non-distracted hand movements. In the evaluation, we conduct extensive real-road experiments involving 20 participants (10 males and 10 females) and 5 vehicles (a sedan, a minivan and three SUVs). Our approach can achieve an average classification accuracy of over 90% with a error rate of a few percent, which demonstrate that SafeDrive is robust to real driving environments, and has great potential to help drivers shape safe driving habits.

Systematic Review of Sleep Monitoring Systems for Babies: Research Issues, Current Status, and Future Challenges

“…Here in, the development of smart devices such as wearable sensors can bring intelligence to healthcare systems that can be useful in a variety of felds such as infant safety and health-tracking, care for the elderly, healthcare monitoring [10], military and law enforcement, sports, and preventive medicine [11]. Even these days, mental health disorders are being depicted in not only adults [12] but in children [13] and adolescents who have been taken into challenge to resolve using machine learning and deep learning algorithms. Wearable sensor-based technologies for infants have also been introduced to warn of lifethreatening situations [14].…”

Smartwatch-Based Information System as a Compliance Detector in Traffic

“…Users of this kind of information system can easily access driving safety information that is practical, easy to understand and access without being limited by location and time [2]. In this paper, we propose SafeDrive, an effective wrist-worn sensing-based application that detects most commonly occuring distracted driving events [5]. In this paper, we present Midtrack, a driver monitoring system that is based on tracking magnetic tags worn by the user.…”

Real-Time Driving Distraction Recognition Through a Wrist-Mounted Accelerometer

“…To date, different machine learning algorithms that are based on K-nearest neighbor (KNN), support vector machine (SVM), and deep neural networks (DNNs) have been developed and applied on wearable IMU data for human activity (Jiang et al, 2018; Voronin et al, 2012). Among these machine learning methods, KNN is less tolerant of noise and outliers (Kotsiantis et al, 2007).…”