| Abstrakt: |
Effective traffic management is critical in the modern age of smart cities to guarantee seamless transit, lessen traffic, and protect the environment. Therefore, to enhance road traffic monitoring, this research presents a novel Quantum Optimized LSTM (QO-LSTM) framework that leverages Quantum Machine Learning techniques with Long Short-Term Memory in an edge cloud environment. The quantum circuit is used to improve predictions via quantum-enhanced optimization, while the LSTM network is utilized to extract temporal relationships from traffic data. The use of this hybrid approach in edge cloud infrastructure offers low latency and great scalability, making it ideal for real-time applications in smart city contexts. The QO-LSTM model's performance was assessed using several measures, yielding results such as a 99.32% Coefficient of Determination (R2), a 1.96% Root Mean Squared Error (RMSE), and a 0.97% Mean Absolute Error (MAE) which are far better when compared with other models like GRU, LSTM and SAE. Additionally, the model showed great prediction accuracy and reliability with an Explained Variance Score (EVS) of 99.33% and a Mean Absolute Percentage Error (MAPE) of 1.07%. Traffic peaks were also identified followed by the peak durations to gain an understanding of traffic congestion patterns. Moreover, by integrating these innovations, the findings reveal that the model considerably improves the accuracy and responsiveness of traffic predictions, allowing for more effective traffic management approaches and real-time decision-making. [ABSTRACT FROM AUTHOR] |
Full text from SpringerLink