Machine learning of electroencephalography signals and eye movements to classify work-in-progress risk at construction sites DOI Creative Commons
Jui‐Sheng Chou,

Pin‐Chao Liao,

Chi‐Yun Liu

et al.

Journal of Civil Engineering and Management, Journal Year: 2024, Volume and Issue: 0(0), P. 1 - 16

Published: Dec. 10, 2024

The construction industry has consistently faced high accident rates and delays in recognizing hazards, posing significant risks to onsite personnel. Traditional hazard detection methods are often reactive rather than proactive, emphasizing a pressing need for innovative solutions. Despite advances safety technology, considerable gap remains real-time, accurate recognition at sites. Current technologies do not fully leverage physiological data predict mitigate risks. This research introduces groundbreaking approach by employing machine learning analyze electroencephalography (EEG) signals eye movement data, enabling real-time differentiation of safe, warning, hazardous visual cues. A Random Forest model with an impressive classification accuracy 99.04% been developed, marking enhancement identifying potential hazards. possible impact integrating EEG analyses into wearable devices or sensors is substantial, as it could revolutionize protocols the industry, fostering safer future.

Language: Английский

The fundamentals of eye tracking part 4: Tools for conducting an eye tracking study DOI Creative Commons
Diederick C. Niehorster, Marcus Nyström, Roy S. Hessels

et al.

Behavior Research Methods, Journal Year: 2025, Volume and Issue: 57(1)

Published: Jan. 6, 2025

Abstract Researchers using eye tracking are heavily dependent on software and hardware tools to perform their studies, from recording data visualizing it, processing analyzing it. This article provides an overview of available for research trackers discusses considerations make when choosing which adopt one’s study.

Language: Английский

Citations

3
Cognitive Assessment and Training in Extended Reality: Multimodal Systems, Clinical Utility, and Current Challenges DOI Creative Commons

Palmira Victoria González-Erena,

Sara Fernández‐Guinea,

Panagiotis Kourtesis

et al.

Encyclopedia, Journal Year: 2025, Volume and Issue: 5(1), P. 8 - 8

Published: Jan. 13, 2025

Extended reality (XR) technologies—encompassing virtual (VR), augmented (AR), and mixed (MR)—are transforming cognitive assessment training by offering immersive, interactive environments that simulate real-world tasks. XR enhances ecological validity while enabling real-time, multimodal data collection through tools such as galvanic skin response (GSR), electroencephalography (EEG), eye tracking (ET), hand tracking, body tracking. This allows for a more comprehensive understanding of emotional processes, well adaptive, personalized interventions users. Despite these advancements, current applications often underutilize the full potential integration, relying primarily on visual auditory inputs. Challenges cybersickness, usability concerns, accessibility barriers further limit widespread adoption in science clinical practice. review examines XR-based training, focusing its advantages over traditional methods, including validity, engagement, adaptability. It also explores unresolved challenges system usability, cost, need feedback integration. The concludes identifying opportunities optimizing to improve evaluation rehabilitation outcomes, particularly diverse populations, older adults individuals with impairments.

Language: Английский

Citations

0
Assessing Cognitive Load in Distraction and Task Switching: Implications for Developing Realistic Clinical XR Training DOI
Adrian Vulpe-Grigorasi, Benedikt Gollan, Vanessa Leung

et al.

Lecture notes in computer science, Journal Year: 2025, Volume and Issue: unknown, P. 84 - 98

Published: Jan. 1, 2025

Language: Английский

Citations

0
A system for periodometric analysis of data on brain electrical activity in subjects in virtual space DOI
Denis S. Chernyshov, Alexander Yu. Tychkov,

O. S. Simakova

et al.

Biomedical Engineering, Journal Year: 2025, Volume and Issue: unknown

Published: March 25, 2025

Language: Английский

Citations

0
Parallel collaboration and closed-loop control of a cursor using multimodal physiological signals DOI Creative Commons
Zeqi Ye, Yang Yu,

Yiyun Zhang

et al.

Journal of Applied Biomedicine, Journal Year: 2024, Volume and Issue: 44(3), P. 470 - 480

Published: July 1, 2024

This paper explores the parallel collaboration of multimodal physiological signals, combining eye tracker output motor imagery, and error-related potentials to control a computer mouse. Specifically, working mechanism is implemented in decision layer, where manages cursor movements, imagery click functions. Meanwhile, signals are integrated with electroencephalography data detect idle state for asynchronous control. Additionally, evoked by visual feedback, detected reduce cost error corrections. To efficiently collect provide continuous evaluations, we performed offline training online testing designed paradigm. further validate practicability, conducted experiments on real-world computer, focusing scenario opening closing files. The involved seventeen subjects. results showed that stability was optimized from 67.6% 95.2% filter, providing support accuracy simultaneously fixations reached 93.41 ± 2.91%, proving feasibility Furthermore, took 45.86 14.94 s complete three movements clicks, significant improvement compared baseline experiment without automatic correction, validating practicability system efficacy detection. Moreover, this freed users stimulus paradigm, enabling more natural interaction. sum up, novel feasible, mouse practical promising.

Language: Английский

Citations

0
Call with eyes: A robust interface based on ANN to assist people with locked-in syndrome DOI Creative Commons

Roberto Alan Beltrán-Vargas,

Jorge Arturo Sandoval-Espino, José Salgado

et al.

SoftwareX, Journal Year: 2024, Volume and Issue: 27, P. 101883 - 101883

Published: Sept. 1, 2024

Language: Английский

Citations

0
Machine learning of electroencephalography signals and eye movements to classify work-in-progress risk at construction sites DOI Creative Commons
Jui‐Sheng Chou,

Pin‐Chao Liao,

Chi‐Yun Liu

et al.

Journal of Civil Engineering and Management, Journal Year: 2024, Volume and Issue: 0(0), P. 1 - 16

Published: Dec. 10, 2024

The construction industry has consistently faced high accident rates and delays in recognizing hazards, posing significant risks to onsite personnel. Traditional hazard detection methods are often reactive rather than proactive, emphasizing a pressing need for innovative solutions. Despite advances safety technology, considerable gap remains real-time, accurate recognition at sites. Current technologies do not fully leverage physiological data predict mitigate risks. This research introduces groundbreaking approach by employing machine learning analyze electroencephalography (EEG) signals eye movement data, enabling real-time differentiation of safe, warning, hazardous visual cues. A Random Forest model with an impressive classification accuracy 99.04% been developed, marking enhancement identifying potential hazards. possible impact integrating EEG analyses into wearable devices or sensors is substantial, as it could revolutionize protocols the industry, fostering safer future.

Language: Английский

Citations

0