Drowsiness Detection using Forehead Electrophysiological Signals and CNN-MultiGRU Networks

2021 ◽  
Author(s):  
Mingwen Qu ◽  
Yue Ma ◽  
Shiming Zhou ◽  
Jiajun Wang ◽  
Nan Hu
Keyword(s):  
Drowsiness Detection ◽  
Electrophysiological Signals

Driver’s Drowsiness Detection Using Dlib and IOT

2020 ◽  
Vol 10 ◽  
Author(s):  
Prasanna Lakshmi Kompalli ◽  
Padma Vallakati ◽  
Ganapathi Raju Nadimpalli ◽  
Vinod Mahesh Jain ◽  
Samuel Annepogu
Keyword(s):  
Aspect Ratio ◽  
The Other ◽  
Human Intervention ◽  
Road Accidents ◽  
Online Content ◽  
Facial Landmarks ◽  
Drowsiness Detection ◽  
Rear Part ◽  
Cause Of Deaths ◽  
Published Paper

Background: Road accidents are major cause of deaths worldwide. This is enormously due to fatigue, drowsiness and microsleep of the drivers. This don’t just risk the life of driver and copassengers but also a great threat to the vehicles and humans moving around that vehicle. Methods: Research, online content and previously published paper related to drowsiness are reviewed. Using the facial landmarks DAT file, the prototype will locate and get the eye coordinates and it will calculate Eye Aspect Ratio (EAR). The EAR indicates whether the driver is drowsy or not based on the result various sensors gets activated such as Alarm generator, LED Indicators, LCD message scroll, message sent to owner and engine gets locked. Results: The prototype is able to locate eyes in the frame and detect whether the person is sleepy or not. Whenever the person is feeling drowsy alarm gets generated in the cabinet on further if the person is feeling drowsy, LED indicators will start glowing, messaging will be scrolling at the rear part of vehicle so that other vehicles and humans gets cautioned and vehicle slows down and engine gets locked. Conclusion: This prototype will help in reduction of road accidents due to human intervention. It is not only helpful to the person who install it in their vehicles but also for the other vehicles and humans moving around it.

Delamination-Resistant Imperceptible Bioelectrode for Robust Electrophysiological Signals Monitoring

2021 ◽  
pp. 1385-1393
Author(s):  
Wenjie Tang ◽  
Yuxuan Zhou ◽  
Shisheng Chen ◽  
Shancheng Yu ◽  
Yizhuo Yang ◽  
...  
Keyword(s):  
Electrophysiological Signals

scholarly journals Functionalization Strategies of PEDOT and PEDOT:PSS Films for Organic Bioelectronics Applications

Chemosensors ◽  
2021 ◽  
Vol 9 (8) ◽  
pp. 212
Author(s):  
Gonzalo E. Fenoy ◽  
Omar Azzaroni ◽  
Wolfgang Knoll ◽  
Waldemar A. Marmisollé
Keyword(s):  
Small Molecules ◽  
Conducting Polymer ◽  
Organic Semiconductors ◽  
Synthesis Method ◽  
Polymer Synthesis ◽  
Preparation Methods ◽  
Electrophysiological Signals ◽  
Organic Bioelectronics ◽  
Biological Interfaces ◽  
Living Organisms

Organic bioelectronics involves the connection of organic semiconductors with living organisms, organs, tissues, cells, membranes, proteins, and even small molecules. In recent years, this field has received great interest due to the development of all kinds of devices architectures, enabling the detection of several relevant biomarkers, the stimulation and sensing of cells and tissues, and the recording of electrophysiological signals, among others. In this review, we discuss recent functionalization approaches for PEDOT and PEDOT:PSS films with the aim of integrating biomolecules for the fabrication of bioelectronics platforms. As the choice of the strategy is determined by the conducting polymer synthesis method, initially PEDOT and PEDOT:PSS films preparation methods are presented. Later, a wide variety of PEDOT functionalization approaches are discussed, together with bioconjugation techniques to develop efficient organic-biological interfaces. Finally, and by making use of these approaches, the fabrication of different platforms towards organic bioelectronics devices is reviewed.

scholarly journals Dynamic relationships between spontaneous and evoked electrophysiological activity

2021 ◽  
Vol 4 (1) ◽  
Author(s):  
Soren Wainio-Theberge ◽  
Annemarie Wolff ◽  
Georg Northoff
Keyword(s):  
Neural Activity ◽  
Large Scale ◽  
Behavioral Outcomes ◽  
Low Frequencies ◽  
Scale Free ◽  
Non Invasive ◽  
Spontaneous Neural Activity ◽  
Electrophysiological Signals ◽  
Evoked Activity ◽  
Dynamic Relationships

AbstractSpontaneous neural activity fluctuations have been shown to influence trial-by-trial variation in perceptual, cognitive, and behavioral outcomes. However, the complex electrophysiological mechanisms by which these fluctuations shape stimulus-evoked neural activity remain largely to be explored. Employing a large-scale magnetoencephalographic dataset and an electroencephalographic replication dataset, we investigate the relationship between spontaneous and evoked neural activity across a range of electrophysiological variables. We observe that for high-frequency activity, high pre-stimulus amplitudes lead to greater evoked desynchronization, while for low frequencies, high pre-stimulus amplitudes induce larger degrees of event-related synchronization. We further decompose electrophysiological power into oscillatory and scale-free components, demonstrating different patterns of spontaneous-evoked correlation for each component. Finally, we find correlations between spontaneous and evoked time-domain electrophysiological signals. Overall, we demonstrate that the dynamics of multiple electrophysiological variables exhibit distinct relationships between their spontaneous and evoked activity, a result which carries implications for experimental design and analysis in non-invasive electrophysiology.

scholarly journals Driver Drowsiness Estimation Based on Factorized Bilinear Feature Fusion and a Long-Short-Term Recurrent Convolutional Network

Information ◽  
2020 ◽  
Vol 12 (1) ◽  
pp. 3
Author(s):  
Shuang Chen ◽  
Zengcai Wang ◽  
Wenxin Chen
Keyword(s):  
Short Term Memory ◽  
Feature Fusion ◽  
Detection Methods ◽  
Video Frame ◽  
Estimation Model ◽  
Short Term ◽  
Convolutional Network ◽  
Drowsiness Detection ◽  
Driver Drowsiness ◽  
Time Information

The effective detection of driver drowsiness is an important measure to prevent traffic accidents. Most existing drowsiness detection methods only use a single facial feature to identify fatigue status, ignoring the complex correlation between fatigue features and the time information of fatigue features, and this reduces the recognition accuracy. To solve these problems, we propose a driver sleepiness estimation model based on factorized bilinear feature fusion and a long- short-term recurrent convolutional network to detect driver drowsiness efficiently and accurately. The proposed framework includes three models: fatigue feature extraction, fatigue feature fusion, and driver drowsiness detection. First, we used a convolutional neural network (CNN) to effectively extract the deep representation of eye and mouth-related fatigue features from the face area detected in each video frame. Then, based on the factorized bilinear feature fusion model, we performed a nonlinear fusion of the deep feature representations of the eyes and mouth. Finally, we input a series of fused frame-level features into a long-short-term memory (LSTM) unit to obtain the time information of the features and used the softmax classifier to detect sleepiness. The proposed framework was evaluated with the National Tsing Hua University drowsy driver detection (NTHU-DDD) video dataset. The experimental results showed that this method had better stability and robustness compared with other methods.

Sign in / Sign up

Export Citation Format

Share Document