Banca de QUALIFICAÇÃO: LUISA CHRISTINA DE SOUZA

Uma banca de QUALIFICAÇÃO de DOUTORADO foi cadastrada pelo programa.
STUDENT : LUISA CHRISTINA DE SOUZA
DATE: 13/09/2024
TIME: 09:00
LOCAL: meet.google.com/ikd-brnx-ijk e no LANCE - nPITI
TITLE:

Inference of Driving Levels and Drivers' Mental State Using
Multimodal Signals and Machine Learning

KEY WORDS:

Fatigue detection, Driver behavior, Autonomous driving detection, Machine learning, Multimodal signals.

PAGES: 64
BIG AREA: Engenharias
AREA: Engenharia Elétrica
SUMMARY:

The human element is a critical determinant in automotive safety, as
the majority of accidents are attributable to driver error. In this
context, this study proposes analyzing driver behavior and conditions
using machine learning and exploratory data analysis techniques. By
employing physiological signals and driving simulation data,
multimodal signals are used to infer driver fatigue. The methodology
includes transforming physiological signals into visual
representations using Wavelet Transform, which are then analyzed to
distinguish between manual and autonomous driving modes. A model
demonstrated an accuracy of 93.34% in differentiating these
modes. Additionally, driver fatigue is assessed through unsupervised
learning techniques that cluster data based on driving behavior.
Fatigue detection relies on vehicle parameters and blink rate
analysis. Results indicate that radar chart areas, reflecting driving
behavior variations, can signal driver fatigue, though correlations
may vary among individuals. The study highlights that integrating
multiple parameters and methods can enhance fatigue detection
accuracy, emphasizing the need for personalized approaches.

COMMITTEE MEMBERS:
Presidente - 1837240 - MARCELO AUGUSTO COSTA FERNANDES
Interno - 1153006 - LUIZ AFFONSO HENDERSON GUEDES DE OLIVEIRA
Interna - ***.640.764-** - MARIANNE BATISTA DINIZ DA SILVA - UFRN
Externo ao Programa - 3083298 - RENAN CIPRIANO MOIOLI - UFRN