Dynamic Bus Arrival Time Prediction with Artificial Neural Networks

A Hybrid Model Based on Support Vector Machine for Bus Travel-Time Prediction

“…The past decades have witnessed an increasing passion for the research of bus running time prediction. The literature focuses on time series [1] artificial neural network or support vector machine (SVM) [2][3][4][5][6][7][8] and Kalman filtering techniques [9,10], etc.…”

Estimation of Bus Arrival Times Using APC Data

“…A variety of prediction models developed in previous studies were reviewed and they can be classified into univariate and multivariate forecasting models (Chien, Ding, and Wei 2002). Univariate forecasting models are designed to predict a dependent variable by describing the intrinsic relationship with its historical data mathematically.…”

“…These models are developed using path-based data (e.g., travel time between two stops along the route), and the travel times are defined as a function of ridership and other external independent factors. Nonetheless, regression is not the only pos-sible estimation approach and other methods, such as artificial neural networks, have been explored (Chien, Ding, and Wei 2002).…”

“…Previous studies (Abdelfattah and Khan 1998;Chien, Ding, and Wei 2002) indicated that bus travel times might be affected by a number of factors such as route length, ridership (which, in turn, depends on population density and major trip generators), the number of stops and intersections, and the geometry of the route. To develop a meaningful model, data collected from the study route should have substantial variability in the aforementioned factors.…”

Traffic Signal Control with Swarm Intelligence

“…Some major conventional traffic signal control systems, such as TRANSYT (traffic network study tool) [1], SCOOT (split, cycle and offset optimization technique) [2], and SCATS (Sydney coordinated adaptive traffic system) [3], select the best pre-calculated off-line timing plan based the current traffic conditions on the road. Some latest developments on traffic signal control employ artificial intelligence technology, such as neural networks [4] and fuzzy logic [5]. Algorithms using Petri nets [6] and Markov decision control [7] have also been investigated in recent years.…”