TY - JOUR AV - public A1 - Siddiqui, Hafeez Ur Rehman A1 - Akmal, Ambreen A1 - Iqbal, Muhammad A1 - Saleem, Adil Ali A1 - Raza, Muhammad Amjad A1 - Zafar, Kainat A1 - Zaib, Aqsa A1 - Dudley, Sandra A1 - Arambarri, Jon A1 - Kuc Castilla, Ángel Gabriel A1 - Rustam, Furqan VL - 24 KW - drowsiness; ultra-wideband radar; convolutional neural network; spatial features; ensemble models N2 - Driving while drowsy poses significant risks, including reduced cognitive function and the potential for accidents, which can lead to severe consequences such as trauma, economic losses, injuries, or death. The use of artificial intelligence can enable effective detection of driver drowsiness, helping to prevent accidents and enhance driver performance. This research aims to address the crucial need for real-time and accurate drowsiness detection to mitigate the impact of fatigue-related accidents. Leveraging ultra-wideband radar data collected over five minutes, the dataset was segmented into one-minute chunks and transformed into grayscale images. Spatial features are retrieved from the images using a two-dimensional Convolutional Neural Network. Following that, these features were used to train and test multiple machine learning classifiers. The ensemble classifier RF-XGB-SVM, which combines Random Forest, XGBoost, and Support Vector Machine using a hard voting criterion, performed admirably with an accuracy of 96.6%. Additionally, the proposed approach was validated with a robust k-fold score of 97% and a standard deviation of 0.018, demonstrating significant results. The dataset is augmented using Generative Adversarial Networks, resulting in improved accuracies for all models. Among them, the RF-XGB-SVM model outperformed the rest with an accuracy score of 99.58%. JF - Sensors SN - 1424-8220 IS - 12 Y1 - 2024/06// TI - Ultra-Wide Band Radar Empowered Driver Drowsiness Detection with Convolutional Spatial Feature Engineering and Artificial Intelligence UR - http://doi.org/10.3390/s24123754 ID - uninimx12747 ER -