Dataset and Interactive Visualization for the article: 'Modeling Women Cyclists' Perceived Security: A Comparison of Machine Learning Techniques'

This dataset supports the study "Modeling Women Cyclists' Perceived Security: A Comparison of Machine Learning Techniques." It includes data from 55 female participants assessing perceived security in 16 VR scenarios at the University of Tehran, Iran, with 208 samples after outlier removal. Features include crowdedness (1-4), incivility (1-3), lighting (1-3), obstruction of visibility (1-4), surveillance (0-1), and perceived security (1=low, 2=medium, 3=high). The dataset is provided as a CSV file for analysis and an HTML file offering a dynamic 3D visualization of key features. See README.txt for file details and usage instructions. This supports the DNN-stack2 model (84.07% accuracy) and future research in cyclist security and urban planning.