SIGNAL (programming language)

Linguistics

Philosophy

Generative model

Object detection

Feature learning

Computer science

Sensor fusion

Fusion

Generative grammar

Database

Pattern recognition (psychology)

Politics

Image (mathematics)

Political science

Long short term memory

Image fusion

Feature (linguistics)

Artificial intelligence

Representation (politics)

Programming language

Deep learning

Artificial neural network

Feature extraction

Recurrent neural network

Machine learning

Data modeling

Speech recognition

Computer vision

It is very dangerous for a driver to fall into a momentary drowsiness. Previous studies to prevent this have classified the driver's condition mainly by using features that appear when drowsiness occurs. At this time, there is insufficient information to judge the driver's condition by using only single data (physiological data, visual data). In this study, we propose a system based on Multimodal Deep Learning that recognizes both visual and physiological changes in drowsiness. Because using different kind of data, heterogeneity problem arise. So in order to eliminate heterogeneity between data, using generative model to representation. Since drowsiness is a change that occurs with time, we use a deep learning network consisting of Long Short-Term Memory (LSTM) to classify the driver's condition.

Driver Drowsiness Detection based on Multimodal using Fusion of Visual-feature and Bio-signal