Informed driving is becoming a key feature to increase the sustainability of taxi companies. The sensors installed in each vehicle are providing new opportunities to automatically discover knowledge, which in return deliver information for realtime decision making. Intelligent transportation systems for taxi dispatching and time-saving route finding are already exploring this sensing data. In this paper, we introduce a novel methodology to predict the spatial distribution of taxi-passenger in a shortterm time horizon using streaming data. We have done so by firstly aggregating the information into a histogram time series. Then, we combined three time series forecasting techniques to output our prediction. Experimental tests were done using the online data transmitted by 441 vehicles of a fleet running in the city of Porto, Portugal. Our results demonstrated that the proposed framework can provide an effective insight into the spatiotemporal distribution of taxi-passenger demand in a 30 minutes horizon. Index Terms-taxi-passenger demand, mobility intelligence, GPS data, data streams,time series forecasting, auto-regressive integrated moving average (ARIMA), time-varying Poisson models, ensemble learning.

The goal of ensemble regression is to combine several models in order to improve the prediction accuracy in learning problems with a numerical target variable. The process of ensemble learning can be divided into three phases: the generation phase, the pruning phase, and the integration phase. We discuss different approaches to each of these phases that are able to deal with the regression problem, categorizing them in terms of their relevant characteristics and linking them to contributions from different fields. Furthermore, this work makes it possible to identify interesting areas for future research.

The goal is to forecast time series of traffic intervals between vehicles on the main street under different conditions within one week and try to predict the intervals between vehicles for the future. To accomplish this goal it is decided to apply the modern computer Software R.

a b s t r a c tRecent advances in telecommunications created new opportunities for monitoring public transport operations in real-time. This paper presents an automatic control framework to mitigate the Bus Bunching phenomenon in real-time. The framework depicts a powerful combination of distinct Machine Learning principles and methods to extract valuable information from raw location-based data. State-of-the-art tools and methodologies such as Regression Analysis, Probabilistic Reasoning and Perceptron's learning with Stochastic Gradient Descent constitute building blocks of this predictive methodology. The prediction's output is then used to select and deploy a corrective action to automatically prevent Bus Bunching. The performance of the proposed method is evaluated using data collected from 18 bus routes in Porto, Portugal over a period of one year. Simulation results demonstrate that the proposed method can potentially reduce bunching by 68% and decrease average passenger waiting times by 4.5%, without prolonging in-vehicle times. The proposed system could be embedded in a decision support system to improve control room operations.