Brain activity patterns reflecting security perceptions of female cyclists in virtual reality experiments

Abstract

Active transportation, such as cycling, improves mobility and general health. However, statistics reveal that in low- and middle-income countries, male and female cycling participation rates differ significantly. Existing literature highlights that women's willingness to use bicycles is significantly influenced by their perception of security. This study employs virtual reality (VR) cycling simulation and electroencephalography (EEG) analysis to investigate factors influencing female cyclists' perceptions of security in Tehran. A total of 52 female participants took part in four scenarios within a VR bicycle simulator, which simulates various environmental settings. In this experiment, participants' brainwave signals are gathered through an EEG device, and a questionnaire with their stated preferences is filled out. The Gaussian mixture approach is used to cluster brainwave patterns based on security perception from EEG data. Subsequently, four supervised machine learning methods, random forest, support vector machine, logistic regression, and multilayer perceptron, are utilized to classify influential factors on security perception using clustered EEG data. Consequently, the support vector machine model, with an F1 score of 0.74, appears to be the most effective technique for the classification of environmental and surveillance factors. Furthermore, the SelectKBest algorithm determines that factors such as the presence of obstacles like kiosks, cycling routes passing through tunnels and underpasses, the level of incivility in the urban cycling environment, and the presence of informal surveillance have the biggest impact on female cyclists' security perception.

Fig. 1

Schematic representation of the framework used in this article to analyze the female cyclists’ perceived security.

Fig. 2

Participants’ (a) demographic profile and (b) transportation characteristics.

Fig. 3

Modeling framework.

Fig. 4

(a) EEG data recording of a participant riding a VR-based bicycle simulator. (b) Locations and labels of 21 channels of EEG device. (c) A sample of recorded brainwave signals.

Fig. 5

Channel spectra of EEG data of a respondent’s brainwave signals over 21 channels.

Fig. 6

Sample distributions within the five security perception categories for EEG clustering and participants’ stated preferences.

Fig. 7

EEG power analysis on women’s security perception in the alpha frequency band for mean selected channels.

Fig. 8

Confusion matrix for classification models for brainwave power representing perceived security; (a) RF, (b) LR, (c) SVM, and (d) MLP.

Fig. 9

Relative influence of environmental and surveillance factors on female cyclist’s perceived security.

Fig. 10

Spatiotemporal analysis in Laleh Park and Keshavarz Boulevard in Tehran on August 30, 2022. Maps generated in the ArcGIS Pro 2.8.6 software (www.esri.com): (a) Tehran city and the location of the two cycling routes considered in this study; (b) location of the stations; (c) classification heatmap of women’s perceived security of Route 1 at Keshavarz boulevard between 19:15 and 19:30; and (d) classification heatmap of women’s perceived security of Route 2 at Laleh Park between 21:45 and 22:00.