Application of various machine learning architectures for crash prediction, considering different depths and processing layers

Abstract

Over a million people die every year as a result of road crashes. A significant proportion of all road fatalities are related to vulnerable road users, including motorcyclist and pedestrian. Artificial intelligent can proactively act to identify those drivers as higher risk of crashes. However, an accurate predictive model is essential for the safety of the road users. High accuracy could be achieved by implementing a reliable method with an optimal architecture and structure being able to identify and flag the risky drivers before a crash occurs. Over the last decade, extensive research has been conducted to achieve a higher accuracy by adjusting the depth of various machine learning algorithms or staking different processing layers. The literature highlights that having a higher algorithm complexity or blindly stacking up layers would not necessarily enhance the model accuracy. Despite the extensive efforts being made about the impacts of depth and various processing layers in the literture, not much research has been conducted on transportation problems to investigate the importance of those factors on the accuracy of crash prediction. In this context, this study aims to implement and compare various deep learning architectures in predicting motorists' crash severity. Various processing layers and depths are considered and compared. Long short‐term memory (LSTM) models have extensively been used in the literature for different types of sequential datasets. However, a comprehensive application of this method for non‐sequential data is still missing. Different processing layers of LSTM and deep neural network (DNN)‐based models with various depths and combinations are here considered and compared. The results indicate that a simple LSTM outperforms an LSTM model with higher depths, and a model with DNN stacked on top of the LSTM model. This study discusses in detail the methodological approach to stacking various layers and hyperparameters tuning.

Human injury-based safety decision of automated vehicles

“…The following references appear in the Supplemental information: Alkheder et al., 2017 , Assi, 2020 , Chen et al., 2015 , Chen et al., 2016 , He et al., 2018 , Ji and Levinson, 2020 , Liu et al., 2020 , Lubbe and Kiuchi, 2015 , Mansoor et al., 2020 , Rezapour et al., 2020 , Rezapour and Ksaibati, 2020 , Sameen and Pradhan, 2017 , Tang et al., 2019 , Wahab and Jiang, 2020 , Wang and Kim, 2019 , Zheng et al., 2019 .…”

Sentiment classification of skewed shoppers' reviews using machine learning techniques, examining the textual features

“…After conducting n‐grams, the bag of words was used to break words into individual word counts variables. The machine learning algorithms have been used in all areas of day‐to‐day life, from anomaly detection, 21 and crash prediction, 22 to sentiment analysis of the investors 23 . The below sections discuss the machine learning techniques have been used for training and evaluation of model accuracy.…”

El comportamiento, los conflictos de tráfico y los factores asociados con la accidentalidad de los motociclistas en las intersecciones de las vías de Cartagena

“…Estudios por Rezapour, et al [139], Wahab y Jiang [160], Wahab y Jiang [161] , Kumar y Toshniwal [162], Kashani, et al [159] y Rezapour, et al [163] aplicaron las técnicas de random forest, support vector machine, árboles de decisión, reglas de clasificación, redes neuronales y regresión avanzadas. Adicionalmente, estudios por Das, et al [164] y Rezapour y Ksaibati [165] aplicaron la técnica de deep learning.…”