Real-time Driving Ability Prediction Model Based on GWO-LSTM

With the development of intelligent transportation system, accurate prediction of driver’s real-time driving ability has become the key to ensure road traffic safety and improve driving efficiency. This paper proposes a real-time driving ability prediction model based on grey wolf optimization algorithm (GWO) and long short-term memory neural network (LSTM). The model optimizes the network parameters of LSTM through GWO, improves the prediction accuracy and generalization ability, and compares it with support vector regression (SVR) and classification regression tree (CART) prediction models. The experimental results show that the average coefficient of determination of the GWO-LSTM model is 0.9949, which is greater than 0.9840 of the SVR model and 0.9602 of the CART model. The model has good performance in real-time driving ability prediction and provides strong support for the development of intelligent transportation systems.