EO-CNN: An Enhanced CNN Model Trained by Equilibrium Optimization for Traffic Transportation Prediction

Abstract Time-ordered data are widely available in many real-life areas like traffic transportation, economic growth, weather prediction, as well as in monitoring and distributed system workloads and many more. Recently, deep learning models are often applied to solve time-series prediction due to their quality. While deep learning models such as recurrent neural networks are the most well-known in this direction, convolutional neural networks (CNNs) is more known for image processing. However, CNNs are also a strong candidate for sequence modeling as well as time-series forecasting. In general, deep learning models are often trained by backpropagation using an optimization algorithm like gradient descent. In this paper, we design a novel variant for training CNN based on meta-heuristic algorithm Equilibrium Optimization (EO). The proposed model, therefore, is called by EO-CNN is consequently applied to traffic transportation envisioning. To evaluate our model, we employ real-time road traffic data, including occupancy, speed, and travel time datasets collected from specialized traffic sensors at the Twin Cities Metro area in Minnesota. The experimental results proved that our design works effectively in application domains such as transportation with excellent performance in comparison with existing well-known approaches.