A Deep-Learning Approach to Driver Drowsiness Detection

Ahmed, Mohammed Imran Basheer; Alabdulkarem, Halah; Alomair, Fatimah; Aldossary, Dana; Alahmari, Manar; Alhumaidan, Munira; Alrassan, Shoog; Rahman, Atta; Youldash, Mustafa; Zaman, Gohar

doi:10.3390/safety9030065

Cited by 18 publications

(4 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Prior to utilizing the World Energy Consumption dataset, we employed a thorough pre-processing procedure to ensure the integrity and accuracy of the data [27][28][29][30][31][32]. Specifically, we removed any missing values by replacing them with a more appropriate constant value.…”

Section: Data Preprocessingmentioning

confidence: 99%

Predicting Global Energy Consumption Through Data Mining Techniques

Rahman,

Abahussin,

Alghamdi

et al. 2024

IJDNE

View full text Add to dashboard Cite

With the explosion of the global population and technological progress, the electricity demand has skyrocketed. To ensure a consistent flow of power, it's essential to accurately predict energy usage ahead of time. Failure to do so could lead to potential outages and disrupt our daily lives. This research reviews previous research in the field of using data mining techniques to analyze electricity consumption data, optimize energy performance of buildings, and predict energy consumption in various industries. The study also aims to uncover patterns, correlations, and rules in electricity consumption worldwide using data mining techniques. The analysis is performed using various data mining techniques, such as simple K-Means and Expectation Maximization (EM). This selection is based on their prominent applications for similar problems in literature. The simple K-Means and EM algorithms showed successful outcomes on the dataset, which is evident in the clustering plots. Further, the performance of the Hierarchical Clustering algorithm was not up to the desired standard. This is probably due to the nature of the available dataset. These outcomes of the analysis will provide a valuable resource for decision-makers and stakeholders in the energy sector, as it will provide a deeper understanding of electricity consumption patterns and trends. This could lead to a sustainable future.

show abstract

Section: Data Preprocessingmentioning

confidence: 99%

Predicting Global Energy Consumption Through Data Mining Techniques

Rahman,

Abahussin,

Alghamdi

et al. 2024

IJDNE

View full text Add to dashboard Cite

show abstract

“…The research study [8] proposed a method for detecting drivers' eye movements using deep learning models to mitigate road accidents. In this experiment, a drowsiness dataset, which is publicly available on Kaggle, was utilized.…”

Section: Literature Analysismentioning

confidence: 99%

“…Proposed Technique Performance Score [8] CNN 97% [12] Hybrid model 91% [13] ML model 80% [14] Bagging and boosting 89% [15] ML model 85% [31] YOLO network 73% [32] Yolo V3 98% [33] YOLO network 87% Our Novel VGLG 99%…”

Section: Refmentioning

confidence: 99%

Novel Transfer Learning Approach for Driver Drowsiness Detection Using Eye Movement Behavior

Madni,

Raza,

Sehar

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Driver drowsiness detection is a critical field of research within automotive safety, aimed at identifying signs of fatigue in drivers to prevent accidents. Drowsiness impairs a driver's reaction time, decision-making ability, and overall alertness, significantly increasing the risk of collisions. Nowadays, the challenge is to detect drowsiness using physiological signals, which often require direct contact with the driver's body. This can be uncomfortable and distracting. This study aimed at detecting driver drowsiness through eye movement behavior imagery of the driver. We utilized a standard image dataset based on the eye movement behavior of drivers to conduct this research experiment. We proposed a novel transfer learning-based features generation which combined the strengths of the Visual Geometry Group (VGG-16) and Light Gradient-Boosting Machine (LGBM) methods. The proposed VGLG (VGG16-LGBM) approach first extracts spatial features from input eye image data and then generates salient transfer features using LGBM. Experimental evaluations reveal that the k-neighbors classifier outperformed the state-of-the-art approach with a high-performance accuracy of 99%. The computational complexity analysis shows that the proposed approach detects driver drowsiness in 0.00829 seconds. We have enhanced the performance through hyperparameter tuning and validations using k-fold validation. This research has the potential to revolutionize driver drowsiness detection, aiming to prevent road accidents and save precious lives.

show abstract

“…Such efforts have facilitated the comparison of different methodologies and highlighted areas requiring further improvement [3,29]. Research integrating sensor data and utilizing semantic learning approaches to analyze driver fatigue more accurately are notable contributions to this area [30,31].…”

Section: Related Workmentioning

confidence: 99%

Processing and Integration of Multimodal Image Data Supporting the Detection of Behaviors Related to Reduced Concentration Level of Motor Vehicle Users

Smoliński,

Forczmański,

Nowosielski

2024

Electronics

View full text Add to dashboard Cite

This paper introduces a comprehensive framework for the detection of behaviors indicative of reduced concentration levels among motor vehicle operators, leveraging multimodal image data. By integrating dedicated deep learning models, our approach systematically analyzes RGB images, depth maps, and thermal imagery to identify driver drowsiness and distraction signs. Our novel contribution includes utilizing state-of-the-art convolutional neural networks (CNNs) and bidirectional long short-term memory (Bi-LSTM) networks for effective feature extraction and classification across diverse distraction scenarios. Additionally, we explore various data fusion techniques, demonstrating their impact on improving detection accuracy. The significance of this work lies in its potential to enhance road safety by providing more reliable and efficient tools for the real-time monitoring of driver attentiveness, thereby reducing the risk of accidents caused by distraction and fatigue. The proposed methods are thoroughly evaluated using a multimodal benchmark dataset, with results showing their substantial capabilities leading to the development of safety-enhancing technologies for vehicular environments. The primary challenge addressed in this study is the detection of driver states not relying on the lighting conditions. Our solution employs multimodal data integration, encompassing RGB, thermal, and depth images, to ensure robust and accurate monitoring regardless of external lighting variations

show abstract

A Deep-Learning Approach to Driver Drowsiness Detection

Cited by 18 publications

References 52 publications

Predicting Global Energy Consumption Through Data Mining Techniques

Predicting Global Energy Consumption Through Data Mining Techniques

Novel Transfer Learning Approach for Driver Drowsiness Detection Using Eye Movement Behavior

Processing and Integration of Multimodal Image Data Supporting the Detection of Behaviors Related to Reduced Concentration Level of Motor Vehicle Users

Contact Info

Product

Resources

About