Combining discrete choice models and neural networks through embeddings: Formulation, interpretability and performance

Arkoudi, Ioanna; Azevedo, Carlos Lima; Pereira, Francisco C.

doi:10.1016/j.trb.2023.102783

Cited by 8 publications

(2 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Embedding techniques can be employed to represent categorical data as continuous-valued vectors in a lowerdimensional space, effectively mitigating memory overhead, especially when dealing with a large number of categorical features [76]. Traditional algorithms require numerical inputs, leading to the utilization of encoding methods to transform categorical values into numerical ones [33].…”

Section: A Embedding Techniquesmentioning

confidence: 99%

“…Another advanced method is the embeddings technique, which is used to represent categorical data as continuous-valued vectors in a lower-dimensional space. These continuous-valued vectors are called embeddings [76]. Additionally, this method enables models to comprehend the connections, parallels, and associations between various categories that the one-hot encoding method does not.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Road Crash Injury Severity Prediction Using a Graph Neural Network Framework

Sattar,

Ishak,

Affendey

et al. 2024

IEEE Access

View full text Add to dashboard Cite

Crash severity prediction is a challenging research area, where the objective is to accurately assess the extent of severity of an injury resulting from road traffic accidents. The main aim of existing studies is to precisely assess the potential severity of crashes under diverse circumstances, such as weather conditions, vehicle attributes, road characteristics and layout, and traffic control factors. This effort aids authorities in establishing effective emergency response systems. The novelty and objective of our work involve contributing to this research area by employing a graph architecture to capture relationships among various crash records to uncover any hidden patterns that traditional ML models might overlook. The current study extends existing knowledge by leveraging Graph Neural Networks (GNN) and comparing their performance to popular ensemble-based models, which include Extreme Gradient Boosting (XGBoost) and Random Forest (RF) and Artificial Neural Networks (ANNs). Real data from the United Kingdom (UK) was employed to achieve our goal. All models underwent training using the training dataset, followed by performance evaluation using diverse metrics such as the accuracy, precision, recall, f1-score, Matthews Correlation Coefficient (MCC), confusion matrix, and computational cost on the test dataset. Overall, our proposed GNN-based model demonstrated better performance when compared to other models. Specifically, the GNN model outperformed all other models across all metrics. For instance, the accuracy stood at 85.55% for GNN as compared to 83.36%, 83.18%, and 83.27% for XGBoost, RF, and ANNs models, respectively. The GNN model assisted in identifying hidden patterns by considering non-linear relationships among crash records. Thus, the model had the potential to improve its ability to predict severe accidents, which could in turn significantly improve emergency response efforts and reduce the likelihood of severe accidents resulting in fatalities.

show abstract

Section: A Embedding Techniquesmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%