Browsing by Author "Fernandes, Pedro Afonso"
Now showing 1 - 10 of 13
Results Per Page
Sort Options
- Combining space syntax with machine learning to predict seating places: the case of Gulbenkian estate in PortugalPublication . Fernandes, Pedro AfonsoA recent trend in space syntax is the application of machine learning (ML) techniques to extend the analyses traditionally performed with methods from graph theory. The goal of this paper is to explore the relationship between visual syntactic measures and the location of seating places in a grid with the resort of ML methods. As far as a public housing estate (Bairro Gulbenkian) located in Odivelas, near Lisbon, Portugal, is concerned, we found that the location of benches can be predicted accurately from visual connectivity, clustering, control, controllability, integration and through vision using partial least squares or random forests. In fact, these two methods provide a better balance between sensitivity (the proportion of seating places classified as such) and specificity (the proportion of other places classified as such) than logistic regression, least absolute shrinkage operator (LASSO), decision trees, support vector machines and neural networks. In addition, we found that visual clustering, integration, control and through vision may be the key measures to predict seating places.
- Introduction of non-topological costs in syntactic analyses: the case of Gulbenkian estatePublication . Fernandes, Pedro AfonsoSpace syntax is a set of theories and techniques for analysing urban settlements and buildings. Focused on the study of the configuration of convex spaces, space syntax is based on the concept of topological depth, that is, in the number of steps to go from some space (or axial line) to every other space in a spatial complex. Typically, non-topological costs like stairs, ramps, accentuated slopes or walls are not considered in space syntax analyses, or are incorporated in an insufficient fashion, namely, with the arbitrary introduction of axial lines in order to increase depth. This article proposes an innovative method to deal with these costs that uses logic programming with Prolog language. In this way, it is possible to better understand the relative segregation of the Gulbenkian estate within its urban environment, the city of Odivelas near Lisbon (Portugal), noting that it was the largest public housing estate built within the scope of the resettlement plan for those displaced by the great floods of November 25-26, 1967, established by the Ministry of Public Works and the Calouste Gulbenkian Foundation in the late 1960s.
- Nowcasting GDP: an application to PortugalPublication . Assunção, João B.; Fernandes, Pedro AfonsoForecasting the state of an economy is important for policy makers and business leaders. When this is conducted in real-time, it is called nowcasting. In this paper, we present a method that shows how forecasting errors decline as additional contemporaneous information unfolds and becomes available. When the economic environment changes fast, as has happened often in the last decades across most developed economies, it is important to use forecasting methods that are both flexible and robust. This can be achieved with bridge equations and non-parametric estimates of the trend growth using only publicly available information. The method presented in this paper achieves, by the end of a quarter, an accuracy that is equivalent to the methods used by official entities.
- Nowcasting the Portuguese GDP with monthly dataPublication . Assunção, João B.; Fernandes, Pedro AfonsoIn this article, we present a method to forecast the Portuguese gross domestic product (GDP) in each current quarter (nowcasting). It combines bridge equations of the real GDP on readily available monthly data like the Economic Sentiment Indicator (ESI), industrial production index, cement sales or exports and imports, with forecasts for the jagged missing values computed with the well-known Hodrick and Prescott (HP) filter. As shown, this simple multivariate approach can perform as well as a Targeted Diffusion Index (TDI) model and slightly better thanthe univariate Theta method in terms of out-of-sample mean errors.
- Programming the logic of space: a new approach to space syntaxPublication . Fernandes, Pedro AfonsoSpace syntax is a set of theories and techniques for analysing urban settlements and buildings. It is a relevant approach for spatial studies concerned with the scientific understanding of and intervention in public open spaces. It requires a previous convex/line/segment map of the area in question designed with the aid of CAD or GIS. Such preparatory task may be laborious and more difficult for social researchers than for architects or urban planners. A new approach to syntactic analyses is proposed here; it requires only setting the connections between axial lines or convex spaces in a computer program. We performed a settlement (alpha) analysis of the Areeiro neighbourhood in Lisbon by computing connectivity, control, depth, integration, ringiness and other syntactic measures, using Prolog predicates. Prolog is a logic programming language used in Artificial Intelligence and a powerful tool to describe the patterns of urban systems as socially knowable due to its declarative nature. In fact, a Prolog program represents a certain amount of knowledge, in this case, of an urban settlement such Areeiro, which is used to answer queries about the social and economic consequences of the spatial design. This approach revealed the intelligibility but also the weaknesses of Areeiro, a remarkable milestone for Portuguese urbanism from the mid-20th century.
- Prospective scenarios for water sustainability in the São Francisco River BasinPublication . Bettencourt, Pedro; Fernandes, Pedro Afonso; Fulgêncio, Cláudia; Canas, Ângela; Wasserman, Julio CesarExpanding water demands and increasing uncertainties associate with water availability in the context of climate change are drivers of future development scenarios in water management of river basins. Water limitations can be particularly important in developing countries, where agriculture and livestock constitute the basis of the economy. Although many researchers have dealt with quantification of water, the application of methods to evaluate the relationship between demand and availability is still scarce in the literature. In the present research, water demand prospective scenarios for the São Francisco River Basin, Brazil were developed, allowing the determination of management procedures to spare this resource. Starting from the present situation, three distinct future evolution scenarios were drawn for water withdrawal flows for the years 2025 and 2035 based on sub-basin water use sectors (farming, industry, human supply—urban and rural, and water diversion for external use): a tendential scenario (B) drawn from the present water uses; a moderate water consumption scenario (A), associated with smaller economic and social development; and a stronger development scenario (C), with increases in water demand. Sustainability of water demand is assessed by comparing water availability, as the ratio between the water demand and observed flows. Regardless of the complexity and extent of the region, applied geographic information system was able to depict the water availability and determine management procedures. The main water withdrawal is associated with irrigated agriculture. For the three prospective scenarios, it is expected that the situation tends to get worse, leading to severe water scarcity in most sub-basins and posing several challenges for the water resources management. Management actions are proposed, in order to equilibrate the water availability in the basin.
- Robust filtering with quantile regressionPublication . Assunção, João Borges; Fernandes, Pedro AfonsoThis working paper proposes a new, practical method to compute the non-linear Mosheiov-Raveh (MR) filter using least absolute deviations (LAD) instead of the linear programming approach proposed by these two authors. This paper is embodied with an implementation in the R programming language of the proposed method which facilitates the computation of the MR filter in current applications to produce a robust estimate, namely, of the GDP trend growth. This technique may be appropriate to deal with non linear time series or structural changes.
- A robust method to date recessions and compute output gaps: the portuguese casePublication . Assunção, João B.; Fernandes, Pedro AfonsoThe application of the Hodrick-Prescott (HP) and other linear filters to remove trend and extract business cycles in macroeconomic time series is a common practice despite its limitations, namely, in signaling recessions. Median filters and other nonlinear techniques can perform better by accommodating sharp but fundamental changes in the growth trend and passing only the relevant information to the cycle component, a possible measure of the output gap of an economy. An application to the Portuguese relevant macroeconomic series confirmed the robustness of nonlinear filters in signaling the recessions and recoveries. In particular, the Mosheiov-Raveh (MR) filter estimates piecewise trend growth paths that naturally date the specific periods of the Portuguese economy since 1977.
- Space syntax with logic programming: an application to a modern EstatePublication . Fernandes, Pedro AfonsoSpace syntax is a set of theories and techniques for analysing urban settlements and buildings. Here, we propose a new approach to perform syntactic analyses that requires only the declaration in a computer program of the connections between axial lines or convex spaces using Prolog, a logic programming language concerned with artificial intelligence. With this new tool, we found that the deep tree nature of modern estates can be mitigated with a concentric structure similar to the famous Bororo village. In fact, Portela, a high-rise settlement near Lisbon (Portugal), is structured around a central open space (green park) equipped with noninterchangeable facilities (mall, sports centre and church), which are highly synchronised with the surrounding buildings (towers and blocks). The transpatial relations between housing estates and the central zone are maximised either by a distributive ringy network or by a smart grid of pedestrian paths. The result is a compact and integrated settlement with a strong identity and sense of belonging. Nevertheless, this kind of concentric dual system is potentially unstable, a problem that was minimised by forcing a clear opposition with a popular neighbourhood at Portela's vicinity. With this case study, we show how logic programming is a useful tool to describe the patterns of discrete systems as social knowables due to its declarative nature. In fact, a Prolog program represents a certain amount of knowledge, namely, concerned with the structure of an urban settlement (or building), which could be used to answer queries about the social and economic consequences of certain spatial designs.
- Space Syntax with PrologPublication . Fernandes, Pedro AfonsoThis paper introduces a new way to perform space syntax analyses using Prolog, a Logic Programming language concerned with Artificial Intelligence. Developed in the 1970’s to process natural languages, Prolog can deal easily with simple declarations of facts like the connection (or permeability) between convex spaces or axial lines. Readily available on-line through the SWISH platform, in a fancy format inspired by Jupyter Notebooks, Prolog may help to understand the recursive nature of urban processes, given some elementary generators, or to describe or even check the structure (e.g. concentric) of some village. Mostly important, Prolog can compute space syntax measures such connectivity, control or integration in a comprehensive, transparent and attractive way, namely, for students and researchers on space syntax. The experience suggests that Prolog may be appropriate for gamma-analysis of small buildings like the Ashanti’s shrine, acting as flexible and easily replicable calculator of syntactic measures. This flexibility is reinforced by the free and open-source nature of the code stored in the SWISH platform, as well as by the declarative nature of Logic Programming, which facilitates the description of the patterns of discrete systems as social knowables. In fact, a Prolog program represents a certain amount of knowledge, which is used to answer queries about the social and economic consequences of some spatial design.