Travel Time Prediction and Explanation with Spatio-Temporal Features: A Comparative Study

Travel time information is used as input or auxiliary data for tasks such as dynamic navigation, infrastructure planning, congestion control, and accident detection. Various data-driven Travel Time Prediction (TTP) methods have been proposed in recent years. One of the most challenging tasks in TTP is developing and selecting the most appropriate prediction algorithm. The existing studies that empirically compare different TTP models only use a few models with specific features. Moreover, there is a lack of research on explaining TTPs made by black-box models. Such explanations can help to tune and apply TTP methods successfully. To fill these gaps in the current TTP literature, using three data sets, we compare three types of TTP methods (ensemble tree-based learning, deep neural networks, and hybrid models) and ten different prediction algorithms overall. Furthermore, we apply XAI (Explainable Artificial Intelligence) methods (SHAP and LIME) to understand and interpret models’ predictions. The prediction accuracy and reliability for all models are evaluated and compared. We observed that the ensemble learning methods, i.e., XGBoost and LightGBM, are the best performing models over the three data sets, and XAI methods can adequately explain how various spatial and temporal features influence travel time.

An Accident Detection and Classification System Using Internet of Things and Machine Learning towards Smart City

Daily traffic accidents increase annually, causing a significant number of death and disability cases. Most of fatalities occur because of the late response to these emergency cases. The time after the traumatic injury is called the golden hour, where providing essential medical and surgical aid at that time increases the probability of saving human lives by one-third an average. Thus, the focus of this paper was to develop a system based on IoT for accident detection and classification. The system detects and classifies vehicle accidents based on severity level and reports the essential information about the accident to emergency services providers. The system consists of a microcontroller, GPS, and a group of sensors to determine different physical parameters related to vehicle motion. In addition, different types of machine learning classifiers were examined with the developed system to determine the most accurate classifier for the system. The classifiers are the Gaussian Mixture Model (GMM), Naive-Bayes Tree (NB), Decision Tree (DT), and Classification and Regression Trees (CART). The implementation of the system showed that GMM and CART models were better in terms of precision and recall. It was also shown that the severity of accidents depends mainly on the g-force value and fire occurrence.

Truck-Lifting Prevention System Based on Vision Tracking for Container-Lifting Operation

Truck-lifting accidents are common in container-lifting operations. Previously, the operation sites are needed to arrange workers for observation and guidance. However, with the development of automated equipment in container terminals, an automated accident detection method is required to replace manual workers. Considering the development of vision detection and tracking algorithms, this study designed a vision-based truck-lifting prevention system. This system uses a camera to detect and track the movement of the truck wheel hub during the operation to determine whether the truck chassis is being lifted. The hardware device of this system is easy to install and has good versatility for most container-lifting equipment. The accident detection algorithm combines convolutional neural network detection, traditional image processing, and a multitarget tracking algorithm to calculate the displacement and posture information of the truck during the operation. The experiments show that the measurement accuracy of this system reaches 52 mm, and it can effectively distinguish the trajectories of different wheel hubs, meeting the requirements for detecting lifting accidents.