Investigating the self-explaining performance of visual guidance facilities in extra-long spiral tunnels based on drivers' spatial perception and visual attention distribution.

Accid Anal Prev

Jiangsu Key Laboratory of Urban ITS, School of Transportation, Southeast University, Nanjing 211189, China; Jiangsu Province Collaborative Innovation Center of Modem Urban Traffic Technologies, Southeast University, Nanjing 211189, China.

Published: July 2025


Category Ranking

98%

Total Visits

921

Avg Visit Duration

2 minutes

Citations

20

Article Abstract

Enhancing the weak visual reference system is crucial for improving drivers' spatial perception in extra-long spiral tunnels, which require continuous turns and uphill/downhill maneuvers. Using the Midicun Tunnel as a prototype, we tested three common visual guidance facilities-horizontal stripes, retroreflective rings, and edge markers-by constructing scenarios with each facility individually and in combinations of these facilities. A comprehensive indicator framework was developed to assess the impact of these facilities on drivers' spatial perception and attention distribution. The self-explaining performance of each facility was evaluated using the matter-element model combined with the entropy weight method. Additionally, drivers' subjective acceptance of each facility was measured using the Technology Acceptance Model (TAM), which offered insights into their internal expectations and cognitive state. The results reveal that drivers tend to drive close to the inside wall of the curve in the continuous curved section of a spiral tunnel. Installing edge markers improves the self-explaining performance of the tunnel's horizontal right-of-way, increasing the distance between the vehicle and the tunnel wall. Installing the retroreflective ring guides drivers' attention to the central area ahead, enhancing the longitudinal right-of-way. However, when used alone, it can lead to longer fixation durations and lower saccade frequencies, an issue that can be mitigated by combining them with other features. Comprehensive evaluations and subjective acceptance surveys indicate that scenarios with multiple facilities provide optimal self-explaining performance and best meet drivers' psychological expectations. Among individual installations, edge markers are the most effective, followed by retroreflective rings, with horizontal stripes showing the weakest performance. Based on these findings, specific recommendations for optimizing visual guidance in spiral tunnels are provided, offering valuable insights for improving tunnel environments.

Download full-text PDF

Source
http://dx.doi.org/10.1016/j.aap.2025.108040DOI Listing

Publication Analysis

Top Keywords

self-explaining performance
16
visual guidance
12
spiral tunnels
12
drivers' spatial
12
spatial perception
12
extra-long spiral
8
attention distribution
8
retroreflective rings
8
subjective acceptance
8
edge markers
8

Similar Publications

Investigating the self-explaining performance of visual guidance facilities in extra-long spiral tunnels based on drivers' spatial perception and visual attention distribution.

Accid Anal Prev

July 2025

Jiangsu Key Laboratory of Urban ITS, School of Transportation, Southeast University, Nanjing 211189, China; Jiangsu Province Collaborative Innovation Center of Modem Urban Traffic Technologies, Southeast University, Nanjing 211189, China.

Enhancing the weak visual reference system is crucial for improving drivers' spatial perception in extra-long spiral tunnels, which require continuous turns and uphill/downhill maneuvers. Using the Midicun Tunnel as a prototype, we tested three common visual guidance facilities-horizontal stripes, retroreflective rings, and edge markers-by constructing scenarios with each facility individually and in combinations of these facilities. A comprehensive indicator framework was developed to assess the impact of these facilities on drivers' spatial perception and attention distribution.

View Article and Find Full Text PDF

Toward explainable AI (XAI) for mental health detection based on language behavior.

Front Psychiatry

December 2023

Institute for Logic, Language and Computation, University of Amsterdam, Amsterdam, Netherlands.

Advances in artificial intelligence (AI) in general and Natural Language Processing (NLP) in particular are paving the new way forward for the automated detection and prediction of mental health disorders among the population. Recent research in this area has prioritized predictive accuracy over model interpretability by relying on deep learning methods. However, prioritizing predictive accuracy over model interpretability can result in a lack of transparency in the decision-making process, which is critical in sensitive applications such as healthcare.

View Article and Find Full Text PDF

Oral demonstration of knowledge is an effective learning and assessment strategy. It has been shown that generating explanations to oneself, or self-explaining, can improve student understanding of information. This can be achieved via student-generated videos.

View Article and Find Full Text PDF

Enhanced survival prediction using explainable artificial intelligence in heart transplantation.

Sci Rep

November 2022

Department of Translational Medicine, Artificial Intelligence and Bioinformatics in Cardiothoracic Sciences, Lund University, Lund, Sweden.

The most limiting factor in heart transplantation is the lack of donor organs. With enhanced prediction of outcome, it may be possible to increase the life-years from the organs that become available. Applications of machine learning to tabular data, typical of clinical decision support, pose the practical question of interpretation, which has technical and potential ethical implications.

View Article and Find Full Text PDF

Nowadays Artificial Intelligence (AI) has become a fundamental component of healthcare applications, both clinical and remote, but the best performing AI systems are often too complex to be self-explaining. Explainable AI (XAI) techniques are defined to unveil the reasoning behind the system's predictions and decisions, and they become even more critical when dealing with sensitive and personal health data. It is worth noting that XAI has not gathered the same attention across different research areas and data types, especially in healthcare.

View Article and Find Full Text PDF