Methodology for Predicting the Level of Drowsiness and Attention of Drivers Using the AI Waker App

• Grant number: 24/13300-7
• Support Opportunities: Research Grants - Innovative Research in Small Business - PIPE
• Start date: February 01, 2025
• End date: January 31, 2027
• Field of knowledge: Physical Sciences and Mathematics - Computer Science - Computer Systems
• Principal Investigator: Patrick Neri de Oliveira
• Grantee: Patrick Neri de Oliveira
• Company: Waker Inova Simples (IS)
• CNAE: Desenvolvimento de programas de computador sob encomenda ; Desenvolvimento e licenciamento de programas de computador não-customizáveis ; Tratamento de dados, provedores de serviços de aplicação e serviços de hospedagem na internet
• Principal investigators: Elaine Cristina Marqueze
• Associated researchers: Davi Duarte de Paula ; Felipe Pacheco de Almeida Euphrásio ; Pedro Augusto Borges dos Santos
• Associated research grant: 23/04821-0 - Traffic accident risk management plataform: Waker APP, AP.PIPE
• Associated scholarship(s): 25/01196-3 - Methodology for predicting drivers' drowsiness and attention levels using the AI Waker App, BP.PIPE

Abstract

The first phase of the São Paulo State Research Foundation (FAPESP) Innovative Research in Small Businesses (PIPE) program, process number 2023/04821-0, resulted in the development of Waker APP, an innovative system designed to identify drowsiness at the wheel in real time and on an individual level, using technological resources on Android or iOS cell phones. In Phase 2, the next stage of the research, we intend to investigate the physiological and behavioral aspects of the driver to develop not only the Waker application, but also an efficient methodology based on scientific data to predict the level of attention and drowsiness of drivers. The objective is to alert Waker APP users early whenever signs of drowsiness or a high probability of falling asleep at the wheel are detected. To achieve these objectives, we propose the formation of a multidisciplinary team composed of researchers and professionals experienced in sleep medicine, chronobiology, naturalistic driving studies, computer vision, electroencephalogram (EEG), data science, road safety, computer engineering and software engineering. The project will be divided into several stages, each led by team members with specific experience in the area. Initially, an extensive literature review and analysis of driving videos will be carried out to identify the main behaviors of distraction, stress, fatigue, drowsiness in traffic and others. In parallel, experiments will be conducted with driving simulators and drowsiness assessments to validate these recorded behaviors. With this information, the computer vision algorithm will be developed to extract data from images in real time and create a solid database to develop the proposed predictive model. This feature is expected to help drivers be alerted to their drowsiness and inattention when driving, contributing to the reduction of traffic accidents. Furthermore, we hope that Waker will provide data for studies in the area of road safety and help define targets for reducing accidents, in line with the second decade of action for road safety 2021-2030 proposed by the United Nations ( UN). (AU)