An Hybridization of LSTM and Random Forest Model to Predict Road Situation - Archive ouverte HAL Accéder directement au contenu
Communication Dans Un Congrès Année : 2023

An Hybridization of LSTM and Random Forest Model to Predict Road Situation

Résumé

Intelligent transport systems (ITS) play a pivotal role in enhancing safety, efficiency, and sustainability in modern transportation. Deep learning, a subfield of machine learning, has emerged as a powerful tool for tackling complex problems in intelligent transport applications. In this paper, we first provide a comprehensive overview of the advancements and future prospects of deep learning in intelligent transport systems. It explores various deep learning techniques, their applications, challenges, and potential solutions, contributing to the development of efficient and intelligent transportation networks. We created a hybrid prediction model based on LSTM with a Random forest algorithm to inform drivers' real-time road situations. To evaluate our proposed model, we developed a web application in which the user should subscribe to access the different services and know the real-time situation of his current used road. In the final, we showed the performance of our model by calculating the different metrics of evaluation, which are accuracy and F1_Score.
Fichier non déposé

Dates et versions

hal-04530169 , version 1 (03-04-2024)

Identifiants

Citer

Olfa Souki, Raoudha Ben Djemaa, Ikram Amous, Florence Sèdes. An Hybridization of LSTM and Random Forest Model to Predict Road Situation. 31th IEEE International Conference on Enabling Technologies: Infrastructure for Collaborative Enterprises (WETICE 2023), IEEE, Dec 2023, Paris, France. pp.1--7, ⟨10.1109/WETICE57085.2023.10477806⟩. ⟨hal-04530169⟩
0 Consultations
0 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More