Smart City Technical Planning Based on Time Series Forecasting of IOT Data

• Published in: 2023 International Conference on Sustainable Emerging Innovations in Engineering and Technology (ICSEIET) pp. 646 - 651
• Main Authors: Venkateshwari, P., Veeraiah, Vivek, Talukdar, Veera, Gupta, Deena Nath, Anand, Rohit, Gupta, Ankur
• Format: Conference Proceeding
• Language: English
• Published: IEEE 14.09.2023
• Subjects: Data analysis; Machine learning; Predictive models; Smart cities; Soft sensors; Solid modeling; Technical planning; Time series analysis; Traffic prediction; Traffic volume; Transportation
• ISBN: 9798350329186
• DOI: 10.1109/ICSEIET58677.2023.10303480

The research focuses on smart city technical planning based on IoT data time series forecasting. The study use machine learning techniques, notably random forest regression and decision tree regression, to anticipate the number of vehicles at various smart city intersections. The forecasting models are built using past IoT data obtained from municipal sensors. To prepare the data for model training and evaluation, data preprocessing techniques such as feature extraction and normalisation are used. Metrics such as mean absolute error, mean absolute percentage error, and R2 score are used to evaluate the models' performance. The results are visualised using graphs and tables to provide insights into the forecasting models' accuracy and efficacy. This study's findings contribute to the subject of smart city planning by presenting a data-driven strategy to anticipating traffic patterns and optimising urban infrastructure.