IoT-Enabled Traffic Management System Using Vehicle Count Prediction in a Semantic Communication Framework

An effective traffic management system is crucial to smart city growth. Consequently, the significance of IoT devices is increasing. Numerous IoT devices, including cameras, are commonly positioned along major roads in a smart city. These IoT devices, embedded with computing and transmitting capabilities, collect data from cameras and then relay it to the central traffic controller (CTC) responsible for managing traffic flow. In our study, we introduce a novel framework termed semantic communication (SemCom), which integrates a Convolutional Neural Network (CNN) with a Long Short-Term Memory (LSTM) network. The SemCom model employs a semantic encoder within each IoT device to extract pertinent information from raw images. This encoded data is transmitted to the CTC as symbols by the transmitter of the IoT device. Subsequently, the CTC’s semantic decoder utilizes this sequence of symbols to predict vehicle counts on respective roads and devise traffic management strategies accordingly. To enhance the quality of experience (QoE), we formulate an optimization problem considering vehicle user safety, IoT device transmission power, prediction accuracy, and semantic entropy. Through numerical analysis, we demonstrate that the SemCom model significantly reduces overhead by 54.42% compared to conventional source encoder/decoder models. Moreover, simulation results showcase the superiority of our proposed model in terms of mean absolute error (MAE) and QoE metrics over existing state-of-the-art approaches. Since vehicle count prediction is pivotal in traffic management, our SemCom framework offers a promising avenue for efficient and accurate vehicle count prediction, contributing to more effective traffic management in smart cities.