Abstract
Short-term traffic state prediction has become an integral component of an advanced traveler information system (ATIS) in intelligent transportation systems (ITS). Accurate modeling and short-term traffic prediction are quite challenging due to its intricate characteristics, stochastic, and dynamic traffic processes. Existing works in this area follow different modeling approaches that are focused to fit speed, density, or the volume data. However, the accuracy of such modeling approaches has been frequently questioned, thereby traffic state prediction over the short-term from such methods inflicts an overfitting issue. We address this issue to accurately model short-term future traffic state prediction using state-of-the-art models via hyperparameter optimization. To do so, we focused on different machine learning classifiers such as local deep support vector machine (LD-SVM), decision jungles, multi-layers perceptron (MLP), and CN2 rule induction. Moreover, traffic states are evaluated using traffic attributes such as level of service (LOS) horizons and simple if–then rules at different time intervals. Our findings show that hyperparameter optimization via random sweep yielded superior results. The overall prediction performances obtained an average improvement by over 95%, such that the decision jungle and LD-SVM achieved an accuracy of 0.982 and 0.975, respectively. The experimental results show the robustness and superior performances of decision jungles (DJ) over other methods.
Highlights
Smart cities have emerged at the heart of “ stage urbanization” as they are equipped with fully digital infrastructure and communication technologies to facilitate efficient urban mobility
In recent years, following rapid diversification, navigation technologies and traffic information services enable a large amount of data to be collected from the different devices such as loop detectors, on-board equipment, speed sensors, remote microwave traffic sensors (RTMS), and road-side surveillance cameras etc., that have been proactively used for monitoring of traffic conditions in the intelligent transportation systems (ITS) domain [5,6,7,8,9]
We extend the exploration of decision jungles and locally deep SVM (LD-SVM) for short term traffic state prediction using hyperparameter optimization
Summary
Smart cities have emerged at the heart of “ stage urbanization” as they are equipped with fully digital infrastructure and communication technologies to facilitate efficient urban mobility. Three factors affect the quality of prediction in real-time traffic information These factors include: (i) variation in data collected from various sources like sensors and other sources;. Non-parametric approaches provide several advantages such as the ability to avoid model’s strong assumptions and learn from the implicit dynamic traffic characteristics through archived traffic data These models have the benefit of being able to manage non-linear, dynamic tasks, and can utilize spatial–temporal relationships, whereas non-parametric methods require a large amount of historical data and training processes. Since non-parametric techniques yield better prediction accuracy compared to ordinary parametric techniques like time series as they require significantly high computational effort Their prediction accuracy is largely dependent on the quantity and quality of training data [32].
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
