Drowsiness Monitoring System Research Articles

Entropy-guided robust feature domain adaptation for electroencephalogram-based cross-dataset drowsiness recognition

To accurately identify driver drowsiness using Electroencephalogram (EEG), a significant amount of time is typically required to gather data from either the same subject or multiple subjects under the same experimental condition. The prolonged period required for data collection impedes the practical application of EEG. In this paper, we consider the challenging task of cross-dataset driver drowsiness recognition, where the EEG data collected by different devices are expected to be conveniently recognized by a classifier trained on an existing dataset. In order to solve the problem of distribution drift, we propose an Entropy-Guided Robust Feature (EGRF) adaptation framework. This framework utilizes the Entropy Minimization (EM) technique for domain alignment and an ensemble-like structure, consisting of multiple branch classifiers and a dropout layer, to enhance the robustness. The proposed method has been tested across two public datasets and achieves 2-class recognition accuracies of 77.4% and 85.9%. The innovative feature-robust block, combined with the EM loss, leads to substantial performance improvement, proving the effectiveness of our framework for cross-dataset driver drowsiness recognition. Our research demonstrates a promising direction for development of a calibration-free driver drowsiness monitoring system in the future.

SPARK: A High-Efficiency Black-Box Domain Adaptation Framework for Source Privacy-Preserving Drowsiness Detection.

Developing an effective and efficient electroencephalography (EEG)-based drowsiness monitoring system is crucial for enhancing road safety and reducing the risk of accidents. For general usage, cross-subject evaluation is indispensable. Despite progress in unsupervised domain adaptation (UDA) and source-free domain adaptation (SFDA) methods, these often rely on the availability of labeled source data or white-box source models, posing potential privacy risks. This study explores a more challenging setting of UDA for EEG-based drowsiness detection, termed black-box domain adaptation (BBDA). In BBDA, adaptation in the target domain relies solely on a black-box source model, without access to the source data or parameters of the source model. Specifically, we propose a framework called Self-distillation and Pseudo-labelling for Ensemble Deep Random Vector Functional Link (edRVFL)-based Black-box Knowledge Adaptation (SPARK). SPARK employs entropy-based selection of high-confidence samples, which are then pseudo-labeled to train a student edRVFL network. Subsequently, ensemble self-distillation is performed to extract knowledge by training the edRVFL using refined labels introduced by ensemble learning. This process further improves the robustness of the student edRVFL network. The features of the edRVFL are beneficial for improving the computational efficiency of the framework, making it more suitable for tasks involving small datasets. The proposed SPARK framework is evaluated on two publicly available driver drowsiness datasets. Experimental results demonstrate its superior performance over strong baselines, while significantly reducing training time. These findings underscore the potential for practical integration of the proposed framework into drowsiness monitoring systems, thereby contributing substantially to the privacy preservation of source subjects.

Driver Drowsiness Detection System

The Driver Drowsiness Monitoring System (DDMS) stands as a crucial advancement in automotive safety, specifically designed to mitigate accidents stemming from drowsy driving. Employing a sophisticated blend of sensors and advanced algorithms, it continuously monitors the driver's state, identifying signs of drowsiness in real-time. Key elements encompass infrared cameras, facial recognition technology, steering angle sensors, and biometric sensors such as heart rate monitors, collectively offering a comprehensive insight into the driver's behavior and physiological condition. The DDMS software meticulously analyzes data from these sensors, evaluating parameters like eye movement, blink frequency, facial expressions, and steering patterns. Upon detecting signs of drowsiness, the system promptly issues audible and visual alerts, thereby averting potential accidents caused by driver fatigue. Its adaptability to diverse vehicles and driving conditions establishes it as an indispensable tool for bolstering road safety, effectively curbing drowsy driving-related incidents.

Driver Drowsiness EEG Detection Based on Tree Federated Learning and Interpretable Network.

Accurate identification of driver's drowsiness state through Electroencephalogram (EEG) signals can effectively reduce traffic accidents, but EEG signals are usually stored in various clients in the form of small samples. This study attempts to construct an efficient and accurate privacy-preserving drowsiness monitoring system, and proposes a fusion model based on tree Federated Learning (FL) and Convolutional Neural Network (CNN), which can not only identify and explain the driver's drowsiness state, but also integrate the information of different clients under the premise of privacy protection. Each client uses CNN with the Global Average Pooling (GAP) layer and shares model parameters. The tree FL transforms communication relationships into a graph structure, and model parameters are transmitted in parallel along connected branches of the graph. Moreover, the Class Activation Mapping (CAM) is used to find distinctive EEG features for representing specific classes. On EEG data of 11 subjects, it is found that this method has higher average accuracy, F1-score and AUC than the traditional classification method, reaching 73.56%, 73.26% and 78.23%, respectively. Compared with the traditional FL algorithm, this method better protects the driver's privacy and improves communication efficiency.

Driver drowsiness monitoring system based on facial Landmark detection with convolutional neural network for prediction

Several factors often contribute to car accidents, most of them caused by human error, and the most notable are drowsiness, fatigue, distracted driving, and alcohol. Although self-driving cars are the best solution to save human lives and avoid car accidents, they are expensive. The roads in many countries are not prepared for the movement of this type of car. Scare new technologies included in modern cars, such as backup cameras and sensors, contributed to keeping drivers safer in this paper. A driver monitoring system is based on determining the driver’s face’s main points, which provide the required vital information for face analysis. The EfficientNet convolutional neural network (ConvNet) model is used for facial landmarks prediction, which is employed to detect face drowsiness and fatigue in real-time. The system is trained to detect multiple traits, including facial expressions, yawning and head poses. The results show that employing facial landmarks will assist in efficiently producing eyes and mouth features, which can assist in appropriately creating models to analyze drowsiness. Due to this, the proposed safety features are applicable and available in future vehicles.

Driving to safety: real-time danger spot and drowsiness monitoring system

Driving to safety: real-time danger spot and drowsiness monitoring system

EEG-based Safety Driving Performance Estimation and Alertness Using Support Vector Machine

Safety driving performance estimation and alertness (SDPEA) has drawn the attention of researchers in preventing traffic accidents caused by drowsiness while driving. Psychophysiological measures, such as electroencephalogram (EEG), are accurately investigated to be robust candidates for drivers’ drowsiness evaluation. This paper presents an effective EEG-based driver drowsiness monitoring system by analyzing the changes of brain activities in a simulator driving environment. The proposed SDPEA system can translate EEG signals into drowsiness level. Firstly, Independent component analysis (ICA) is performed on EEG data to remove artifacts. Then, eight EEG-band powers-related features: beta, alpha, theta, delta, (alpha plus theta)/beta, alpha / beta, (alpha plus theta)/(alpha plus beta) and theta / beta are extracted from the preprocessed EEG signals by employing the Fast Fourier Transform (FFT). Subsequently, fisher score technique selects the most descriptive features for further classification. Finally, Support Vector Machine (SVM) is employed as a classifier to distinguish drowsiness level. Experimental results show that the quantitative driving performance can be correctly estimated through analyzing driver’s EEG signals by the SDPEA system.

졸음 방지 시스템을 위한 눈 개폐 상태 판단 방법

졸음 방지 시스템을 위한 눈 개폐 상태 판단 방법

Driver fatigue and drowsiness monitoring system with embedded electrocardiogram sensor on steering wheel

Real time driver health condition monitoring system with drowsiness alertness was proposed. A new embedded electrocardiogram (ECG) sensor with electrically conductive fabric electrodes on the steering wheel of a car was designed to monitor the driver's health condition. The ECG signals were measured at a sampling rate of 100 Hz from the driver's palms as they stay on a pair of conductive fabric electrodes located on the steering wheel. Practical tests were conducted using an embedded ECG sensor with a wireless sensor node, and their performance was assessed under non-stop 2 h driving test. The ECG signals were measured and transmitted wirelessly to a base station connected to a server PC in personal area network environment. The driver's health condition such as the normal, fatigued and drowsy states was analysed by evaluating the heart rate variability in the time and frequency domains.

Drowsy Driving Detection by EEG Analysis Using Wavelet Transform and K-means Clustering

This research aims to develop a driver drowsiness monitoring system by analyzing the electroencephalographic (EEG) signals in a software scripted environment and using a driving simulator. These signals are captured by a multi-channel electrode system. Any muscle movement impacts the EEG signal recording which translates to artifacts. Therefore, noise from the recording is eliminated by subtracting the noisy signal from the original EEG recording. The actual EEG signals are then subjected to band pass filtering with cut-off frequencies 0.5Hz and 100Hz. The filtered signals are analyzed using a time-frequency technique known as the Discrete Wavelet Transform (DWT). A third order Debauchies’ wavelet and five level decomposition is utilized to segregate the signal into five sub-bands, namely, delta (0.5 – 4Hz), theta (4 – 8Hz), alpha (8 – 12Hz), beta (12 – 30Hz) and gamma (> 30Hz). First order statistical moments such as mean, median, variance, standard deviation and mode of the sub-bands are calculated and stored as features. These features serve as an input to the next stage of system classification. Unsupervised learning through K-means clustering is employed since the classes of the signals are unknown. This provides a strong decision making tool for a real-time drowsiness detection system. The algorithm developed in this work has been tested on twelve samples from the Physionet sleep-EDF database.

Assessment of Drowsiness Based on Ocular Parameters Detected by Infrared Reflectance Oculography

Numerous ocular parameters have been proposed as reliable physiological markers of drowsiness. A device that measures many of these parameters and then combines them into a single metric (the Johns Drowsiness Scale [JDS]) is being used commercially to assess drowsiness in professional drivers. Here, we examine how these parameters reflect changes in drowsiness, and how they relate to objective and subjective indices of the drowsy state in a controlled laboratory setting. A within subject prospective study. 29 healthy adults (18 males; mean age 23.3 ± 4.6 years; range 18-34 years). N/A. Over the course of a 30-h extended wake vigil under constant routine (CR) conditions, participants were monitored using infrared reflectance oculography (Optalert) and completed bi-hourly neurobehavioral tests, including the Karolinska Sleepiness Scale (KSS) and Psychomotor Vigilance Task (PVT). Ocular-defined increases in drowsiness were evident with extended time awake and during the biological night for all ocular parameters; JDS being the most sensitive marker of drowsiness induced by sleep regulatory processes (p < 0.0001). In addition, the associations between JDS in the preceding 10-min period and subsequent PVT lapses and KSS were stronger (AUC 0.74/0.80, respectively) than any other ocular metric, such that PVT lapses, mean response time (RT), and KSS increased in a dose-response manner as a function of prior JDS score (p < 0.0001). Ocular parameters captured by infrared reflectance oculography detected fluctuations in drowsiness due to time awake and during the biological night. The JDS outcome was the strongest predictor of drowsiness among those tested, and showed a clear association to objective and subjective measures of drowsiness. Our findings indicate this real-time objective drowsiness monitoring system is an effective tool for monitoring changes in alertness and performance along the alert-drowsy continuum in a controlled laboratory setting.