No abstract

No abstract

Pattern recognition in financial time series is not a trivial task, due to level of noise, volatile context, lack of formal definitions and high number of pattern variants. A current research trend involves machine learning techniques and online computing. However, medium-term trading is still based on humancentric heuristics, and the integration with machine learning support remains relatively unexplored. The purpose of this study is to investigate potential and perspectives of a novel architectural topology providing modularity, scalability and personalization capabilities. The proposed architecture is based on the concept of Receptive Fields (RF), i.e., sub-modules focusing on specific patterns, that can be connected to further levels of processing to analyze the price dynamics on different granularities and different abstraction levels. Both Multilayer Perceptrons (MLP) and Support Vector Machines (SVM) have been experimented as a RF. Early experiments have been carried out over the FTSE-MIB index.

<p>Forest biodiversity is one of the seven thematic programmes established by the Conference of the Parties within the Convention on Biological Diversity. The topic of identification, monitoring, definition of indicators and assessment of biodiversity is one of the cross-cutting issues  of the Convention to collect, maitain and organize biodiversity information.</p> <p>The huge amount, spectral diversity, regular and dense acquisition plan of current Earth Observation spaceborne missions provides a means to monitor and evaluate the vegetation biodiversity. In this work we present the results of an application of multispectral, hyperspectral and SAR satellite images to map the vegetation biodiversity in National Parks of Gargano, Alta Murgia, Cilento-Vallo di Diano-Alburni, Appennino Lucano Val D’Agri Lagonegrese and Pollino, all located in Southern Italy. For each of the aforementioned parks, study areas have been selected. Sentinel-2 and PRISMA images have been used to compute different vegetation indeces to analyze the different phenological properties of plants and the impact of the interaction soil-vegetation on the reflection coefficient measured by the sensors. Furthermore, Sentinel-1 images have been used to compute the radar vegetation index and the interferometric Synthetic Aperture Radar (SAR) coherence.</p> <p>The maps of all the above multi- and hypespectral indeces and SAR products have been analyzed in terms of two abundance-based metrics and used within a agent-based model to quantify vegetation biodiversity. The Shannon entropy and Rao’s Q metrics haven been implemented and applied to the matrices of vegetation indeces and SAR products. These two computational tools are compared in terms of their ability to describe the diversity of the agro-forestry landspace. Furthermore, the landscape heterogeneity has been modelled by intelligent agents that move through the selected areas in a simulated environment and collect information on vegetation indices in order to measure their diversity. The output of the agent-based model has been compared to the results obtained by the abundance-based metrics to identify mathematical tools useful for the conservation planning of critical habitats.</p>