Answers are grounded in this paper and cite their sources.
The implementation of facial recognition technology in railway transportation services represents an effort to improve passenger identification and service efficiency through biometric technology. This study aims to analyze and predict passenger readiness for the implementation of a face recognition system at Medan Railway Station using an artificial neural network based on the Perceptron model. A quantitative approach was employed by collecting questionnaire responses from 207 participants. The study examined eight input variables, including previous experience, understanding of the technology, trust in identity recognition, perceived accuracy, biometric data security, registration convenience, boarding efficiency, and support for elderly passengers. The collected data were processed through binary encoding, dataset splitting, model training, and testing. A total of 165 observations were used for training and 42 for testing, with a learning rate of 0.1 and a maximum of 200 epochs. The questionnaire results indicated that 188 respondents (90.82%) were classified as ready, while 19 respondents (9.18%) were classified as not ready. Model evaluation produced an accuracy of 90.48%, with 38 correct classifications and 4 incorrect classifications. This study also developed a web-based application to support data management, model training, testing, prediction, and result visualization. The findings suggest that most respondents demonstrated readiness to adopt the face recognition system, although further improvements are needed to achieve more balanced classification performance.
No takes yet. Share an insight, caveat, or question.
Mufakhrasy et al. (2026) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: