Driver Emotions Recognition Based on Improved Faster R-CNN and Neural Architectural Search Network

Symmetry, Journal Year: 2022, Volume and Issue: 14(4), P. 687 - 687

Published: March 26, 2022

It is critical for intelligent vehicles to be capable of monitoring the health and well-being drivers they transport on a continuous basis. This especially true in case autonomous vehicles. To address issue, an automatic system developed driver’s real emotion recognizer (DRER) using deep learning. The emotional values indoor are symmetrically mapped image design order investigate characteristics abstract expressions, expression principles, experimental evaluation conducted based existing research driver facial expressions products. By substituting custom-created CNN features learning block with base 11 layers model this paper development improved faster R-CNN face detector that detects at high frame per second (FPS). Transfer performed NasNet large recognize various emotions. Additionally, custom recognition dataset being as part task. proposed model, which combination transfer NasNet-Large architecture DER images, enables greater accuracy than previously possible images. outperforms some recently updated state-of-the-art techniques terms accuracy. achieved following benchmark datasets: JAFFE 98.48%, CK+ 99.73%, FER-2013 99.95%, AffectNet 95.28%, 99.15% custom-developed dataset.

Language: Английский

---

Evaluation of a New Lightweight EEG Technology for Translational Applications of Passive Brain-Computer Interfaces

Frontiers in Human Neuroscience, Journal Year: 2022, Volume and Issue: 16

Published: July 14, 2022

Technologies like passive brain-computer interfaces (BCI) can enhance human-machine interaction. Anyhow, there are still shortcomings in terms of easiness use, reliability, and generalizability that prevent passive-BCI from entering real-life situations. The current work aimed to technologically methodologically design a new gel-free system for out-of-the-lab employment. choice the water-based electrodes lightweight headset met need easy-to-wear, comfortable, highly acceptable technology. proposed showed high reliability both laboratory realistic settings, performing not significantly different gold standard based on gel electrodes. In cases, allowed effective discrimination (AUC > 0.9) between low levels workload, vigilance, stress even temporal resolution (<10 s). Finally, has been tested through cross-task calibration. calibrated with data recorded during tasks was able discriminate targeted human factors task reaching AUC values higher than 0.8 at 40 s case vigilance 20 monitoring. These results pave way ecologic use system, where calibration difficult obtain.

Language: Английский

---

Neurophysiological Assessment of An Innovative Maritime Safety System in Terms of Ship Operators’ Mental Workload, Stress, and Attention in the Full Mission Bridge Simulator

Brain Sciences, Journal Year: 2023, Volume and Issue: 13(9), P. 1319 - 1319

Published: Sept. 14, 2023

The current industrial environment relies heavily on maritime transportation. Despite the continuous technological advances for development of innovative safety software and hardware systems, there is a consistent gap in scientific literature regarding objective evaluation performance operators. human factor profoundly affected by changes or psychological state. difficulty lies fact that technology, tools, protocols investigating are not fully mature suitable experimental investigation. present research aims to integrate these two concepts (i) objectively characterizing state mariners, i.e., mental workload, stress, attention, through their electroencephalographic (EEG) signal analysis, (ii) validating an framework countermeasure, defined as Human Risk-Informed Design (HURID), aforementioned neurophysiological approach. proposed study involved 26 mariners within high-fidelity bridge simulator while encountering collision risk congested waters with without HURID. Subjective, behavioral, data, EEG, were collected throughout activities. results showed participants experienced statistically significant higher workload stress performing activities HURID, attention level was lower compared condition which they performed experiments HURID (all

Language: Английский

---

Neurophysiological mental fatigue assessment for developing user-centered Artificial Intelligence as a solution for autonomous driving

Frontiers in Neurorobotics, Journal Year: 2023, Volume and Issue: 17

Published: Nov. 30, 2023

The human factor plays a key role in the automotive field since most accidents are due to drivers' unsafe and risky behaviors. industry is now pursuing two main solutions deal with this concern: short term, there development of systems monitoring psychophysical states, such as inattention fatigue, medium-long fully autonomous driving. This second solution promoted by recent technological progress terms Artificial Intelligence sensing aimed at making vehicles more accurately aware their "surroundings." However, even an vehicle, driver should be able take control vehicle when needed, especially during current transition from lower (SAE < 3) highest level = 5) In scenario, has not only its "surroundings" but also driver's state, i.e., user-centered Intelligence. neurophysiological approach one effective detecting improper mental states. particularly true if considering that automatic driving will be, less available vehicular data related style. present study employing holistic approach, simultaneously several parameters, particular, electroencephalographic, electrooculographic, photopletismographic, electrodermal activity assess fatigue real time detect onset increasing. would ideally work information/trigger channel for AI. all, 26 professional drivers were engaged 45-min-lasting realistic task simulated conditions, which previously listed biosignals recorded. Behavioral (reaction times) subjective measures collected validate experimental design support results discussion. Results showed sensitive timely parameters those brain activity. To lesser extent, ocular delayed effect. other investigated did significantly change session.

Language: Английский

---

The impact of traffic congestion, aggression and driving anger on driver stress: A structural equation modelling approach

Journal of Transportation Safety & Security, Journal Year: 2025, Volume and Issue: unknown, P. 1 - 22

Published: Feb. 27, 2025

Language: Английский

---

Method to avert vehicle collision based on driver’s attention lapse predicted using BCI

Multimedia Tools and Applications, Journal Year: 2025, Volume and Issue: unknown

Published: April 12, 2025

Language: Английский

---

EEG Dataset for natural image recognition through Visual Stimuli

Data in Brief, Journal Year: 2025, Volume and Issue: unknown, P. 111639 - 111639

Published: May 1, 2025

Language: Английский

---

Listening Effort in Tinnitus: A Pilot Study Employing a Light EEG Headset and Skin Conductance Assessment during the Listening to a Continuous Speech Stimulus under Different SNR Conditions

Brain Sciences, Journal Year: 2023, Volume and Issue: 13(7), P. 1084 - 1084

Published: July 17, 2023

Background noise elicits listening effort. What else is tinnitus if not an endogenous background noise? From such reasoning, we hypothesized the occurrence of increased effort in patients during tasks. Such a hypothesis was tested by investigating some indices through electroencephalographic and skin conductance, particularly parietal frontal alpha electrodermal activity (EDA). Furthermore, distress questionnaires (THI TQ12-I) were employed. Parietal values positively correlated to TQ12-I scores, both negatively EDA; Pre-stimulus with THI score our pilot study; finally, results showed general trend group comparison control group. stimuli, TQ12-I, appears reflect higher perception symptoms. The negative correlation between (parietal alpha) symptoms (TQ12-I scores) EDA levels could be explained less responsive sympathetic nervous system prepare body expend energy “fight or flight” response, due pauperization from perception.

Language: Английский

---

Frontal cortex cooling and modulation of brain frequencies using a wearable Peltier device

Physica B Condensed Matter, Journal Year: 2023, Volume and Issue: 652, P. 414641 - 414641

Published: Jan. 9, 2023

Language: Английский

---

A Neuroergonomic Approach Fostered by Wearable EEG for the Multimodal Assessment of Drivers Trainees

Sensors, Journal Year: 2023, Volume and Issue: 23(20), P. 8389 - 8389

Published: Oct. 11, 2023

When assessing trainees’ progresses during a driving training program, instructors can only rely on the evaluation of trainee’s explicit behavior and their performance, without having any insight about effects at cognitive level. However, being able to drive does not imply knowing how safely in complex scenario such as road traffic. Indeed, latter point involves mental aspects, ability manage allocate one’s effort appropriately, which are difficult assess objectively. In this scenario, study investigates validity deploying an electroencephalographic neurometric effort, obtained through wearable device, improve assessment trainee. The engaged 22 young people, or with limited experience. They were asked along five different but similar urban routes, while brain activity was recorded electroencephalography. Moreover, subjective reaction times measures collected for multimodal analysis. terms performance measures, no improvement could be detected either driver’s performance. On other side, it possible catch decrease experienced demand after three repetitions tasks. These results confirmed by analysis times, that significantly improved from third repetition well. Therefore, measure when task is less mentally demanding, so more automatic, allows deduce degree users training, becoming capable handling additional tasks reacting unexpected events.

Language: Английский

---