Luis Moreira-Matias

Predicting Taxi–Passenger Demand Using Streaming Data

Informed driving is increasingly becoming a key feature for increasing the sustainability of taxi companies. The sensors that are installed in each vehicle are providing new opportunities for automatically discovering knowledge, which, in return, delivers information for real-time decision making. Intelligent transportation systems for taxi dispatching and for finding time-saving routes are already exploring these sensing data. This paper introduces a novel methodology for predicting the spatial distribution of taxi-passengers for a short-term time horizon using streaming data. First, the information was aggregated into a histogram time series. Then, three time-series forecasting techniques were combined to originate a prediction. Experimental tests were conducted using the online data that are transmitted by 441 vehicles of a fleet running in the city of Porto, Portugal. The results demonstrated that the proposed framework can provide effective insight into the spatiotemporal distribution of taxi-passenger demand for a 30-min horizon.

Improving Mass Transit Operations by Using AVL-Based Systems: A Survey

Intelligent transportation systems based on automated data collection frameworks are widely used by the major transit companies around the globe. This paper describes the current state of the art on improving both planning and control on public road transportation companies using automatic vehicle location (AVL) data. By surveying this topic, the expectation is to help develop a better understanding of the nature, approaches, challenges, and opportunities with regard to these problems. This paper starts by presenting a brief review on improving the network definition based on historical location-based data. Second, it presents a comprehensive review on AVL-based evaluation techniques of the schedule plan (SP) reliability, discussing the existing metrics. Then, the different dimensions on improving the SP reliability are presented in detail, as well as the works addressing such problem. Finally, the automatic control strategies are also revised, along with the research employed over the location-based data. A comprehensive discussion on the techniques employed is provided to encourage those who are starting research on this topic. It is important to highlight that there are still gaps in AVL-based literature, such as the following: 1) long-term travel time prediction; 2) finding optimal slack time; or 3) choosing the best control strategy to apply in each situation in the event of schedule instability. Hence, this paper includes introductory model formulations, reference surveys, formal definitions, and an overview of a promising area, which is of interest to any researcher, regardless of the level of expertise.

On Predicting the Taxi-Passenger Demand: A Real-Time Approach

Informed driving is becoming a key feature to increase the sustainability of taxi companies. Some recent works are exploring the data broadcasted by each vehicle to provide live information for decision making. In this paper, we propose a method to employ a learning model based on historical GPS data in a real-time environment. Our goal is to predict the spatiotemporal distribution of the Taxi-Passenger demand in a short time horizon. We did so by using learning concepts originally proposed to a well-known online algorithm: the perceptron [1]. The results were promising: we accomplished a satisfactory performance to output the next prediction using a short amount of resources.

An Incremental Probabilistic Model to Predict Bus Bunching in Real-Time

In this paper, we presented a probabilistic framework to predict Bus Bunching (BB) occurrences in real-time. It uses both historical and real-time data to approximate the headway distributions on the further stops of a given route by employing both offline and online supervised learning techniques. Such approximations are incrementally calculated by reusing the latest prediction residuals to update the further ones. These update rules extend the Perceptron’s delta rule by assuming an adaptive beta value based on the current context. These distributions are then used to compute the likelihood of forming a bus platoon on a further stop - which may trigger an threshold-based BB alarm. This framework was evaluated using real-world data about the trips of 3 bus lines throughout an year running on the city of Porto, Portugal. The results are promising.

A predictive model for the passenger demand on a taxi network

In the last decade, the real-time vehicle location systems attracted everyone attention for the new kind of rich spatio-temporal information. The fast processing of this large amount of information is a growing and explosive challenge. Taxi companies are already exploring such information in efficient taxi dispatching and time-saving route finding. In this paper, we propose a novel methodology to produce online short term predictions on the passenger demand spatial distribution over 63 taxi stands in the city of Porto, Portugal. We did so using time series forecasting techniques to the processed events constantly communicated for 441 taxi vehicles. Our tests - using 4 months of real data - demonstrated that this model is a true major contribution to the driver mobility intelligence: 76% of the 86411 demanded taxi services were accurately forecasted in a 30 minutes time horizon.

An online recommendation system for the taxi stand choice problem (Poster)

Nowadays, Informed Driving is crucial to the transportation industry. We present an online recommendation model to help the driver to decide about the best stand to head in each moment, minimizing the waiting time. Our approach uses time series forecasting techniques to predict the spatiotemporal distribution in real-time. Then, we combine this information with the live current network status to produce our output. Our online test-beds were carried out using data obtained from a fleet of 441 vehicles running in the city of Porto, Portugal. We demonstrate that our approach can be a major contribution to this industry: 395.361/506.873 of the services dispatched were correctly predicted. Our tests also highlighted that a fleet equipped with such framework surpassed a fleet that is not: they experienced an average waiting time to pick-up a passenger 5% lower than its competitor.

Text categorization using an ensemble classifier based on a mean co-association matrix

Text Categorization (TC) has attracted the attention of the research community in the last decade. Algorithms like Support Vector Machines, Naive Bayes or k Nearest Neighbors have been used with good performance, confirmed by several comparative studies. Recently, several ensemble classifiers were also introduced in TC. However, many of those can only provide a category for a given new sample. Instead, in this paper, we propose a methodology --- MECAC --- to build an ensemble of classifiers that has two advantages to other ensemble methods: 1) it can be run using parallel computing, saving processing time and 2) it can extract important statistics from the obtained clusters. It uses the mean co-association matrix to solve binary TC problems. Our experiments revealed that our framework performed, on average, 2.04% better than the best individual classifier on the tested datasets. These results were statistically validated for a significance level of 0.05 using the Friedman Test.

Using Exit Time Predictions to Optimize Self Automated Parking Lots

Private car commuting is heavily dependent on the subsidisation that exists in the form of available free parking. However, the public funding policy of such free parking has been changing over the last years, with a substantial increase of meter-charged parking areas in many cities. To help to increase the sustainability of car transportation, a novel concept of a self-automated parking lot has been recently proposed, which leverages on a collaborative mobility of parked cars to achieve the goal of parking twice as many cars in the same area, as compared to a conventional parking lot. This concept, known as self-automated parking lots, can be improved if a reasonable prediction of the exit time of each car that enters the parking lot is used to try to optimize its initial placement, in order to reduce the mobility necessary to extract blocked cars. In this paper we show that the exit time prediction can be done with a relatively small error, and that this prediction can be used to reduce the collaborative mobility in a self-automated parking lot.

Online predictive model for taxi services

In recent years, both companies and researchers have been exploring intelligent data analysis to increase the profitability of the taxi industry. Intelligent systems for online taxi dispatching and time saving route finding have been built to do so. In this paper, we propose a novel methodology to produce online predictions regarding the spatial distribution of passenger demand throughout taxi stand networks. We have done so by assembling two well-known time series short-term forecast models: the time-varying Poisson models and ARIMA models. Our tests were performed using data gathered over a period of 6 months and collected from 63 taxi stands within the city of Porto, Portugal. Our results demonstrate that this model is a true major contribution to the driver mobility intelligence: 78% of the 253745 demanded taxi services were correctly forecasted in a 30 minutes horizon.

Vehicular Sensing: Emergence of a Massive Urban Scanner

Vehicular sensing is emerging as a powerful mean to collect information using the variety of sensors that equip modern vehicles. These sensors range from simple speedometers to complex video capturing systems capable of performing image recognition. The advent of connected vehicles makes such information accessible nearly in real-time and creates a sensing network with a massive reach, amplified by the inherent mobility of vehicles. In this paper we discuss several applications that rely on vehicular sensing, using sensors such as the GPS receiver, windshield cameras, or specific sensors in special vehicles, such as a taximeter in taxi cabs. We further discuss connectivity issues related to the mobility and limited wireless range of an infrastructure-less network based only on vehicular nodes.