1,721,077 research outputs found
AIDA: A Spatial Data Augmentation Tool for Machine Learning Dataset Preparation
Full text linkThe use of machine and deep learning techniques for dealing with spatial data is progressively increasing as the amount of such kind of information consistently grows. At the same time, the quality of the obtained results strictly depends on the quality of the training data. In regression and classification tasks, the balancing of the training set with respect to both the characteristics of the input data and the ground truth values is essential to correctly capture all the eventualities and cases in the right way. However, as already pointed out in the literature, producing balanced training sets is not simple, even when they are synthetically generated. This demonstration presents a tool for producing balanced training sets for spatial operation estimation, which starts from the synthetic generation of spatial datasets resembling real-world situations, with respect to distribution and other spatial characteristics, and then apply spatial queries for obtaining a first collection on which balancing analysis and spatial augmentation techniques are applied to obtain a final balanced collection with respect to specific metrics. This tool is a step towards the generation of good-quality training sets for different spatial query optimization and evaluation models
Modeling Time in Archaeological Data: the Verona Case Study
Full text linkTime and space are two important characteristics of archaeological data. As regards to the first aspect, in literature many time dimensions for archaeol- ogy have been defined which extend from the excavation time, to the dating of archaeological objects. Standard ISO 19018 describes temporal character- istics of geographical information in terms of both geometric and topological primitives. The first aim of this report is to analyse the applicability of such Standard for representing archaeological data, referring to the model adopted by the city of Verona (Italy) as case study. However, since archaeo- logical dates are often subjective, estimated and imprecise, one of the main lack in the Standard is the inability to incorporate such vagueness in date representation. Therefore, the second contribution of this report is the exten- sion of the Standard in order to represent fuzzy dates and fuzzy relationships among them. Finally, considering the process through which objects are usu- ally manually dated by archeologists, some existing automatic techniques for time reasoning may be successfully applied in this context in order to guide the dating process. For this purpose, the last report contribution regards the translation of some archaeological temporal data into a Fuzzy Temporal Constraint Network (FTCN) for checking the overall data consistency and reducing the vagueness of some dates based on their relationships with other ones
A Spatio-Temporal Framework for Managing Archeological Data
Full text linkSpace and time are two important characteristics of data in many domains. This is particularly true in the archaeological context where informa- tion concerning the discovery location of objects allows one to derive important relations between findings of a specific survey or even of different surveys, and time aspects extend from the excavation time, to the dating of archaeological objects. In recent years, several attempts have been performed to develop a spatio-temporal information system tailored for archaeological data. The first aim of this paper is to propose a model, called Star, for repre- senting spatio-temporal data in archaeology. In particular, since in this domain dates are often subjective, estimated and imprecise, Star has to incorporate such vague representation by using fuzzy dates and fuzzy relationships among them. Moreover, besides to the topological relations, another kind of spatial relations is particularly useful in archeology: the stratigraphic ones. There- fore, this paper defines a set of rules for deriving temporal knowledge from the topological and stratigraphic relations existing between two findings. Finally, considering the process through which objects are usually manually dated by archeologists, some existing automatic reasoning techniques may be success- fully applied to guide such process. For this purpose, the last contribution regards the translation of archaeological temporal data into a Fuzzy Temporal Constraint Network for checking the overall data consistency and reducing the vagueness of some dates based on their relationships with other ones
Mereological Inheritance
No full textIn questo articolo si propone una classificazione delle formule spaziali basate su relazioni mereologiche. La classificazione si basa sul comportamento delle formule rispetto alla proprietà di ereditarietà della verità della formula da una regione verso le regioni che essa contiene e verso le regioni che la contengono
Internationalizing Data-Intensive Web Applications
No full textNowadays a considerable amount of web sites are data-intensive web sites, meaning that web pages are generated by extracting their content on the fly from a database system. Systems of this type are often the result of an integration process between intranet legacy systems and Internet web applications that represent the front end of the organization towards the rest of the world. The globalization process, that influences the activities of any organization (company, public agencies, etc.), makes it necessary to provide information in different languages in order to enlarge the audience of the information presented through the web. Therefore, it is often required to extend the web system for handling information in more than one language. This process is called internationalization of an application or system. Another important requirement in this process is that it should be applied without a strong reorganization of the web applications that implements the web site, so that the main cost would regard the translation of the web contents. We propose a general framework for the internationalization of data-intensive web application based on the MVC-2 paradigm and a relational database system. Moreover it can be applied to existing web applications with a low impact on code restructuring. This framework has been applied at the University of Verona (Italy) for the internationalization of the web sites of all departments and faculties of this university
Self Spatial Join Selectivity Estimation Using Fractal Concepts
No full textThe problem of selectivity estimation for queries of nontraditional databases is still an open issue. In this article, we examine the problem of selectivity estimation for some types of spatial queries in databases containing real data. We have shown earlier [Faloutsos and Kamel 1994] that real point sets typically have a nonuniform distribution, violating consistently the uniformity and independence assumptions. Moreover, we demonstrated that the theory of fractals can help to describe real point sets. In this article we show how the concept of fractal dimension, i.e., (noninteger) dimension, can lead to the solution for the selectivity estimation problem in spatial databases. Among the infinite family of fractal dimensions, we consider here the Hausdorff fractal dimension D0 and the “Correlation” fractal dimension D2. Specifically, we show that (a) the average number of neighbors for a given point set follows a power law, with D2 as exponent, and (b) the average number of nonempty range queries follows a power law with E − D0 as exponent (E is the dimension of the embedding space). We present the formulas to estimate the selectivity for “biased” range queries, for self-spatial joins, and for the average number of nonempty range queries. The result of some experiments on real and synthetic point sets are shown. Our formulas achieve very low relative errors, typically about 10%, versus 40%–100% of the formulas that are based on the uniformity and independence assumptions
Integrating Multi-Accuracy Spatial Data
Full text linkIn recent years the integration of spatial data coming from different sources has become a crucial issue for many geographical applications, in particular in the process of building and maintaining a Spatial Data Infrastructure (SDI). In such context new methodologies are necessary in order to acquire and update spatial datasets by collecting new measurements from different sources. The traditional approach implemented in GIS systems for updating spatial data does not usually consider the accuracy of these data, but just replaces the old geometries with the new ones. The application of such approach in the case of an SDI, where continuous and incremental updates occur, will lead very soon to an inconsistent spatial dataset with respect to spatial relations and relative distances among objects. In this report we address this problem and we propose a framework for representing multiaccuracy spatial databases, based on a statistical representation of the objects geometry, together with a method for the incremental and consistent update of the database objects, that applies a customized version of the Kalman filter. Moreover, in the framework we consider also the spatial relations among objects, since they represent a particular kind of observation, that could be derived from geometries or be observed independently in the real world. Therefore, also spatial relations among objects coming from different sources need to be compared and we show that they are necessary in order to obtain a correct result in objects geometry integration
Distributed Integration of Spatial Data with Different Positional Accuracies
No full textSpatial Data Infrastructures (SDIs) have been developed in many countries, determining the need for new techniques able to efficiently integrate spatial data in a distributed context. In order to preserve coherence and consistency of the integrated data, such techniques cannot ignore the positional accuracy of both the source datasets and the new computed data. Considering accuracy information during the integration process inevitably increases the complexity of such operation in terms of time and space required to compute and store the updated data. This paper presents a novel integration technique based on a multi-accuracy spatial data model, which includes a distributed update phase performed by each SDI member, and a centralized recombination phase performed by an SDI manager. Moreover, some optimizations are proposed for efficiently storing and transferring accuracy information. These two aspects make the technique applicable in a distributed context, even in presence of huge among of data
- …
