Radio frequency identification technology (RFID) and time series forecasts are used to create a dependable IoT-based traffic system. The system regulates city traffic. The suggested method estimates junction traffic volume over time using LSTM neural networks. RFID technology improves data collection accuracy and reliability. Data preparation includes outlier identification to remove anomalies. Training the LSTM model on preprocessed data reveals traffic volume trends. The trained model predicts traffic volume using historical data. Prediction performance is quantified by MAE, MAPE, and R2. The proposed approach is tested using four intersection traffic data. Results indicate that LSTM-based traffic volume estimation works. The optimal design is determined by evaluating system performance for 12-to-168-time steps. The experimental findings suggest that the proposed method can accurately anticipate traffic volume, helping traffic managers enhance flow. RFID and time series projections bolster traffic system reliability.
Authors: Binay Kumar Pandey, Vinay Kumar Nassa, Mukundan Appadurai Paramashivan, Darshan A. Mahajan, Digvijay Pandey, A. Shaji George, Pankaj Dadheech
DOI: https://doi.org/10.4018/979-8-3693-1335-0.ch009
Publish Year: 2024
