A carregar...
Publicação
Driving Behavior Classification Using a ConvLSTM
| Nome: | Descrição: | Tamanho: | Formato: | |
|---|---|---|---|---|
| 3.75 MB | Adobe PDF |
Orientador(es)
Resumo(s)
This work explores the classification of driving behaviors using a hybrid deep learning model that combines Convolutional Neural Networks (CNNs) with Long Short-Term Memory (LSTM) networks (ConvLSTM). Sensor data are collected from a smartphone application and undergo a preprocessing pipeline, including data normalization, labeling, and feature extraction, to enhance the model’s performance. By capturing temporal and spatial dependencies within driving patterns, the proposed ConvLSTM model effectively differentiates between normal and aggressive driving behaviors. The model is trained and evaluated against traditional stacked LSTM and Bidirectional LSTM (BiLSTM) architectures, demonstrating superior accuracy and robustness. Experimental results confirm that the preprocessing techniques improve classification performance, ensuring high reliability in driving behavior recognition. The novelty of this work lies in a simple data preprocessing methodology combined with the specific application scenario. By enhancing data quality before feeding it into the AI model, we improve classification accuracy and robustness. The proposed framework not only optimizes model performance but also demonstrates practical feasibility, making it a strong candidate for real-world deployment.
Descrição
Article number - 52
This article belongs to the Special Issue Autonomous Vehicles and Urban Evolution: Technological, Social and Environmental Perspectives
This article belongs to the Special Issue Autonomous Vehicles and Urban Evolution: Technological, Social and Environmental Perspectives
Palavras-chave
Artificial intelligence Neural networks LSTM RNN Driving classification
Contexto Educativo
Citação
Pingo, A.; Castro, J.; Loureiro, P.; Mendes, S.; Bernardino, A.; Miragaia, R.; Husyeva, I. Driving Behavior Classification Using a ConvLSTM. Future Transp. 2025, 5, 52. https://doi.org/10.3390/ futuretransp5020052
Editora
MDPI