Predictive RFID Tour Monitoring Dashboard Integrating Multimodal Machine Learning and Contextual Data

Traditional tourism monitoring systems rely on manual tracking and overlook dynamic factors influencing travel duration. To address this limitation, this research presents an intelligent web dashboard integrating RFID infrastructure and multimodal machine learning to assess the risk of delay in tourist activities. The project encompasses the design and physical prototyping of a Radio Frequency Identification (RFID) based checkpoint system. This prototype demonstrated functional detection of members upon entry and exit, providing an automated identification layer. To predict delays, the system processes two diverse datasets. A biometric gait dataset facilitates human speed prediction utilizing age, gender, body mass, body size, and shoe size. Simultaneously, a vehicle dataset provides environmental context through travel distance, weather ratings, traffic conditions, and vehicle classification. The study evaluates Ridge Regression, Random Forest, and Gradient Boosting Regressor algorithms for human speed prediction, while Random Forest, Gradient Boosting Regressor, and Long Short-Term Memory (LSTM) networks are utilized for vehicle speed prediction. Evaluation revealed that the Gradient Boosting Regressor achieved the lowest error metrics across both datasets. This superior model was exported and implemented into a Python Flask backend to generate live transit time estimations. The dashboard provides live visibility into member locations and implements automated missing member notifications. This allows tour organizers to respond promptly to movement irregularities without manual tracking. Overall, the results demonstrated the feasibility of the proposed automated tour group monitoring system. However, the current prototype was validated through controlled functional testing, and further multi-user and field-based evaluation is required to establish its scalability and generalizability for larger smart tourism environments.

@article{Koey2026,
  title     = {Predictive RFID Tour Monitoring Dashboard Integrating Multimodal Machine Learning and Contextual Data},
  journal   = {International Journal of Advanced Computer Science and Applications},
  volume    = {17},
  number    = {9},
  year      = {2026},
  publisher = {The Science and Information Organization},
  author    = {Heng Jin Koey and Siti Zuraidah Ibrahim and Ismahayati Adam and Megat Syahirul Amin Megat Ali and Rashidah Che Yob and Sugchai Tantiviwat and Sazwan Syafiq Mazlan},
  doi       = {10.14569/IJACSA.2026.0170963},
  url       = {https://doi.org/10.14569/IJACSA.2026.0170963}
}