The risk of exposure to Lyme disease in the province of Trento, Italian Alps, was predicted through the analysis of the distribution of Ixodes ricinus (L.) nymphs infected with Borrelia burgdorferi s.l. with a model based on bootstrap aggregation (bagging) of tree-based classifiers within a Geographical Information System. Data on I. ricinus density assessed by dragging the vegetation in 438 sites during 1996 were cross-correlated with the digital cartography of a GIS which included the variables altitude, exposure and slope, substratum, vegetation type and roe deer density. Ticks resulted more abundant at altitudes below 1,300 m a.s.l., in the presence of limestone and vegetation cover with thermophile deciduous forests with high densities of roe deer. A bootstrap aggregation procedure (bagging) was used to produce a model for the prediction of tick occurrence, which accuracy was tested on actual tick counts assessed by a further dragging campaign carried out during 1997 to determine infection prevalence and resulted in average 77%. Other tests of the model were made on other additional and independent data set. The prevalence of infection with Borrelia burgdorferi s.l, determined by PCR on 2,208 nymphs collected by dragging the vegetation during 1997 in 245 transects selected randomly within 8 areas where I. ricinus was predicted to occur by the model, was 17.5% and was positively correlated to tick abundance and roe deer density. These findings were used to relate the output of the bagged model (probability of tick occurrence) to the density of infected nymphs through a stepwise model selection procedure and thus to produce a GIS digital map of the probability distribution of infected nymphs in the Province of Trento at high resolution scale (50 m× 50 m cell resolution).The application of the bagging procedure increased the accuracy of the prediction made by a single classification tree, a well known classification method for the analysis of epidemiological data.

We present a technology for the accurate and fast geo-location of medical data and the creation of central data archives, specifically designed for the development of disease risk maps and of other functions for modern epidemiology and surveillance. A WEBGIS system is configured as an Internet web service integrated with connectivity to a Geographical Information System (GIS). We developed for the ULSS Belluno a WEBGIS for the accurate mapping of tick-borne diseases, with specific attention to Lyme borreliosis, which may cause cardiac manifestations as atrioventricular conduction abnormalities, complete atrioventricular block, myocarditis and dilated cardiomiopathy. A first tree-based predictive model has been developed for risk classification of tick bites from 256 samples (data gathered through the Belluno Lyme WEBGIS), with a descriptive error of 81.9% and a predictive error of 75.1% . An experimental risk GIS map was therefore obtained from the model by considering altitude, week of sampling and vegetation type as predictor variables.

The dynamical evolution of weights in the Adaboost algorithm contains useful information about the rôle that the associated data points play in the built of the Adaboost model. In particular, the dynamics induces a bipartition of the data set into two (easy/hard) classes. Easy points are ininfluential in the making of the model, while the varying relevance of hard points can be gauged in terms of an entropy value associated to their evolution. Smooth approximations of entropy highlight regions where classification is most uncertain. Promising results are obtained when methods proposed are applied in the Optimal Sampling framework.

Open Source Software is one of the most striking innovations in software development in the 1990s. It has been stimulated by the success of LINUX and the Internet which facilitated global communication as well as data and software exchange. The Geographical Information System GRASS (Geographical Resources Analysis Support System) is the largest Free Software GIS Project and by the size of the code it belongs to the top ten list of all Open Source Projects worldwide. Open Source GIS: A GRASS GIS Approach was written for experienced GIS users, who want to learn GRASS, as well as for the Open Source software users who are GIS newcomers. Following the Open Source model of GRASS, the book includes links to sites where the GRASS system and on-line reference manuals can be downloaded and additional applications can be viewed. The project's web site can be reached at http://grass.itc.it and a number of mirror sites worldwide. Open Source GIS: A GRASS GIS Approach, provides basic information about the use of GRASS from setting up the spatial database, through working with raster, vector and site data, to image processing and hands-on applications. This book also contains a brief introduction to programming within GRASS encouraging the new GRASS development. The power of computing within Open Source environment is illustrated by examples of the GRASS usage with other Open Source software tools, such as GSTAT, R statistical language, and linking GRASS to MapServer. Open Source GIS: A GRASS GIS Approach is designed to meet the needs of a professional audience composed of researchers and practitioners in industry and graduate level students in Computer Science and Geosciences. http://mpa.itc.it/grassbook/open_source_gis2002.pdf

Keywords: GIS, Geographic Information Systems, Open Source, Software