Luís Damas

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.

The yap prolog system

Yet Another Prolog (YAP) is a Prolog system originally developed in the mid-eighties and that has been under almost constant development since then. This paper presents the general structure and design of the YAP system, focusing on three important contributions to the Logic Programming community. First, it describes the main techniques used in YAP to achieve an efficient Prolog engine. Second, most Logic Programming systems have a rather limited indexing algorithm. YAP contributes to this area by providing a dynamic indexing mechanism, or just-in-time indexer. Third, a important contribution of the YAP system has been the integration of both or-parallelism and tabling in a single Logic Programming system.

Large-scale simulation of V2V environments

Providing vehicles with enhanced ability to communicate and exchange real-time data with neighboring vehicles opens up a variety of complex challenges that can only be met by combining different research fronts such as wireless communications, information processing, self-organization protocols and collaborative optimization. The difficulty in performing real tests in this area forces the use of computer simulation. In this paper we introduce an efficient simulation framework for large scale vehicle-to-vehicle (V2V) networks in urban environments. Our main contribution is a sophisticated traffic simulator, which is oriented towards simulating car-to-car communications, and relies on a global positioning server in order to convey location information for micro-simulated vehicles. To illustrate the various studies made possible by our simulation system, we provide a preliminary characterization of how the wireless transmission range in an urban-like environment affects the freshness and inter-vehicle propagation characteristics of real-time mobility information.

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.

WAM Local Analysis

The abstract interpretation framework has been used mainly in the global analysis of programs. Most often also, this interpretation is applied to the source Prolog program. In this paper we present an abstract interpretation of more local nature, and applied to the intermediate code (WAM). The purpose of obtaining a more efficient specialized version of the program remains the same as in global analysis approaches. Our specialization is multiple, meaning that we generate a different version for each entry pattern detected by analysis. This poly-variant unfolding of predicates allows the local (predicate level) analysis to propagate inter-procedurally relevant information. Besides time and complexity reduction of local versus global analysis, our approach is suited for goal-independent specialization, and for the partial selection of predicates to specialize. The evaluation of this more general specialization of programs in a full compiler shows that it is an alternative to global and goal-dependent methods.

Self-automated parking lots for autonomous vehicles based on vehicular ad hoc networking

Parking is a major problem of car transportation, with important implications in traffic congestion and urban landscape. Reducing the space needed to park cars has led to the development of fully automated and mechanical parking systems. These systems are, however, limitedly deployed because of their construction and maintenance costs. Leveraging on semi and fully-autonomous vehicular technology, as well as on the electric propulsion paradigm and in vehicular ad hoc networking, we propose a new parking concept where the mobility of parked vehicles is managed by a parking lot controller to create space for cars entering or exiting the parking lot, in a collaborative manner. We show that the space needed to park such vehicles can be reduced to half the space needed with conventional parking lot designs. We also show that the total travelled distance of vehicles in this new parking lot paradigm can be 30% less than in conventional parking lots. Our proposal can have important consequences in parking costs and in urban landscape.

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.

CLG: A Grammar Formalism Based on Constraint Reslution

We present the design and implementation of a powerful grammar formalism based on constraint resolution. Constraints are expressed in a full first order language with equality allowing on top of the expression of equational, disjunctive, conunctive, negative, implicative and if-then-else constraints. CLG has been implemented in Prolog and tested with relatively large grammars of Danish, English and German. We also report on the efficiency of the implementation and the expressive adequacy of the formalism.

On Long Normal Inhabitants of a Type

In this paper we give a complete, formal definition of the formula-tree proof method, prove its correctness and illustrate its adequateness for research in the area of inhabitation of simple types.

Driver-centric VANET simulation

Inter-vehicle communication is becoming increasingly relevant in the research and development of novel, innovative vehicular applications. To support the driver in his/her primary driving task in an effective non distracting way, these applications need to be evaluated in a realistic context from a drivers perspective of the VANET environment. In this paper we propose an innovative driver-centric simulation tool that integrates a VANET simulator with a driving simulator using communication technologies to relay information about the vehicle to the VANET environment and vice versa. The driver behavior is reflected in the VANET simulation system affecting the mobility of the cars in the vicinity and providing the intelligent driving model with new realistic features.