Visualization of clusters in geo-referenced data using three-dimensional self-organizing maps

Dissertação apresentada como requisito parcial para obtenção do grau de Mestre em Estatística e Gestão de Informação

Advanced data driven visualisation for geo-spatial data

Most current 3D landscape visualisation systems either use bespoke hardware solutions, or offer a limited amount of interaction and detail when used in realtime mode. We are developing a modular, data driven 3D visualisation system that can be readily customised to specific requirements. By utilising the latest software engineering methods and bringing a dynamic data driven approach to geo-spatial data visualisation we will deliver an unparalleled level of customisation in near-photo realistic, realtime 3D landscape visualisation. In this paper we show the system framework and describe how this employs data driven techniques. In particular we discuss how data driven approaches are applied to the spatiotemporal management aspect of the application framework, and describe the advantages these convey.

Advanced data driven visualisation for geo-spatial data

Most current 3D landscape visualisation systems either use bespoke hardware solutions, or offer a limited amount of interaction and detail when used in realtime mode. We are developing a modular, data driven 3D visualisation system that can be readily customised to specific requirements. By utilising the latest software engineering methods and bringing a dynamic data driven approach to geo-spatial data visualisation we will deliver an unparalleled level of customisation in near-photo realistic, realtime 3D landscape visualisation. In this paper we show the system framework and describe how this employs data driven techniques. In particular we discuss how data driven approaches are applied to the spatiotemporal management aspect of the application framework, and describe the advantages these convey. © Springer-Verlag Berlin Heidelberg 2006.

ToPI - uma abordagem online para identificar locais de interesse utilizando fotografias geo-referenciadas

Due to the growing use of social networks people no longer just consume data, they also produce and share it. Geo-tagged information, i.e., data with geographical location, have been used in many attempts to identify popular places and help tourists that will visit unfamiliar cities. This Master Thesis presents an online strategy that uses geo-tagged photos and their metadata in order to identify places of interest inside a given geographical area and retrieve relevant related information. The whole process runs automatically in real time, returning updated information about places. The proposed strategy takes into account the inherent dynamism of social media, and thus is robust under inconsistencies and/or outdated information, a common issue in solutions that rely on previously stored data. The analysis of the results showed that our approach is very promising, returning places that present high agreement with those from a popular travel website.

A geographic opportunistic forwarding strategy for vehicular named data networking

Studies in Computational Intelligence, 616

Understanding U.S. regional linguistic variation with Twitter data analysis

We analyze a Big Data set of geo-tagged tweets for a year (Oct. 2013–Oct. 2014) to understand the regional linguistic variation in the U.S. Prior work on regional linguistic variations usually took a long time to collect data and focused on either rural or urban areas. Geo-tagged Twitter data offers an unprecedented database with rich linguistic representation of fine spatiotemporal resolution and continuity. From the one-year Twitter corpus, we extract lexical characteristics for twitter users by summarizing the frequencies of a set of lexical alternations that each user has used. We spatially aggregate and smooth each lexical characteristic to derive county-based linguistic variables, from which orthogonal dimensions are extracted using the principal component analysis (PCA). Finally a regionalization method is used to discover hierarchical dialect regions using the PCA components. The regionalization results reveal interesting linguistic regional variations in the U.S. The discovered regions not only confirm past research findings in the literature but also provide new insights and a more detailed understanding of very recent linguistic patterns in the U.S.

Multilayer perceptron with local constraint as an emerging method in spatial data analysis

The use of Geographic Information Systems has revolutionalized the handling and the visualization of geo-referenced data and has underlined the critic role of spatial analysis. The usual tools for such a purpose are geostatistics which are widely used in Earth science. Geostatistics are based upon several hypothesis which are not always verified in practice. On the other hand, Artificial Neural Network (ANN) a priori can be used without special assumptions and are known to be flexible. This paper proposes to discuss the application of ANN in the case of the interpolation of a geo-referenced variable.

Machine learning algorithms for spatial data. Case studies: Environmental pollution, natural hazards, renewable resources

This paper presents general problems and approaches for the spatial data analysis using machine learning algorithms. Machine learning is a very powerful approach to adaptive data analysis, modelling and visualisation. The key feature of the machine learning algorithms is that they learn from empirical data and can be used in cases when the modelled environmental phenomena are hidden, nonlinear, noisy and highly variable in space and in time. Most of the machines learning algorithms are universal and adaptive modelling tools developed to solve basic problems of learning from data: classification/pattern recognition, regression/mapping and probability density modelling. In the present report some of the widely used machine learning algorithms, namely artificial neural networks (ANN) of different architectures and Support Vector Machines (SVM), are adapted to the problems of the analysis and modelling of geo-spatial data. Machine learning algorithms have an important advantage over traditional models of spatial statistics when problems are considered in a high dimensional geo-feature spaces, when the dimension of space exceeds 5. Such features are usually generated, for example, from digital elevation models, remote sensing images, etc. An important extension of models concerns considering of real space constrains like geomorphology, networks, and other natural structures. Recent developments in semi-supervised learning can improve modelling of environmental phenomena taking into account on geo-manifolds. An important part of the study deals with the analysis of relevant variables and models' inputs. This problem is approached by using different feature selection/feature extraction nonlinear tools. To demonstrate the application of machine learning algorithms several interesting case studies are considered: digital soil mapping using SVM, automatic mapping of soil and water system pollution using ANN; natural hazards risk analysis (avalanches, landslides), assessments of renewable resources (wind fields) with SVM and ANN models, etc. The dimensionality of spaces considered varies from 2 to more than 30. Figures 1, 2, 3 demonstrate some results of the studies and their outputs. Finally, the results of environmental mapping are discussed and compared with traditional models of geostatistics.

Discriminating among earth composition models using geo-antineutrinos

It has been estimated that the entire Earth generates heat corresponding to about 40 TW (equivalent to 10,000 nuclear power plants) which is considered to originate mainly from the radioactive decay of elements like U, Th and K, deposited in the crust and mantle of the Earth. Radioactivity of these elements produce not only heat but also antineutrinos (called geo-antineutrinos) which can be observed by terrestrial detectors. We investigate the possibility of discriminating among Earth composition models predicting different total radiogenic heat generation, by observing such geo-antineutrinos at Kamioka and Gran Sasso, assuming KamLAND and Borexino (type) detectors, respectively, at these places. By simulating the future geo-antineutrino data as well as reactor antineutrino background contributions, we try to establish to which extent we can discriminate among Earth composition models for given exposures (in units of kt · yr) at these two sites on our planet. We use also information on neutrino mixing parameters coming from solar neutrino data as well as KamLAND reactor antineutrino data, in order to estimate the number of geo-antineutrino induced events. © SISSA/ISAS 2003.

Ancient Greek harbours used as geo-archives for palaeotsunami research : case studies from Krane (Cefalonia), Lechaion (Gulf of Corinth) and Kyllini (Peloponnese)

Since historical times, coastal areas throughout the eastern Mediterranean are exposed to tsunami hazard. For many decades the knowledge about palaeotsunamis was solely based on historical accounts. However, results from timeline analyses reveal different characteristics affecting the quality of the dataset (i.e. distribution of data, temporal thinning backward of events, local periodization phenomena) that emphasize the fragmentary character of the historical data. As an increasing number of geo-scientific studies give convincing examples of well dated tsunami signatures not reported in catalogues, the non-existing record is a major problem to palaeotsunami research. While the compilation of historical data allows a first approach in the identification of areas vulnerable to tsunamis, it must not be regarded as reliable for hazard assessment. Considering the increasing economic significance of coastal regions (e.g. for mass tourism) and the constantly growing coastal population, our knowledge on the local, regional and supraregional tsunami hazard along Mediterranean coasts has to be improved. For setting up a reliable tsunami risk assessment and developing risk mitigation strategies, it is of major importance (i) to identify areas under risk and (ii) to estimate the intensity and frequency of potential events. This approach is most promising when based on the analysis of palaeotsunami research seeking to detect areas of high palaeotsunami hazard, to calculate recurrence intervals and to document palaeotsunami destructiveness in terms of wave run-up, inundation and long-term coastal change. Within the past few years, geo-scientific studies on palaeotsunami events provided convincing evidence that throughout the Mediterranean ancient harbours were subject to strong tsunami-related disturbance or destruction. Constructed to protect ships from storm and wave activity, harbours provide especially sheltered and quiescent environments and thus turned out to be valuable geo-archives for tsunamigenic high-energy impacts on coastal areas. Directly exposed to the Hellenic Trench and extensive local fault systems, coastal areas in the Ionian Sea and the Gulf of Corinth hold a considerably high risk for tsunami events, respectively.Geo-scientific and geoarcheaological studies carried out in the environs of the ancient harbours of Krane (Cefalonia Island), Lechaion (Corinth, Gulf of Corinth) and Kyllini (western Peloponnese) comprised on-shore and near-shore vibracoring and subsequent sedimentological, geochemical and microfossil analyses of the recovered sediments. Geophysical methods like electrical resistivity tomography and ground penetrating radar were applied in order to detect subsurface structures and to verify stratigraphical patterns derived from vibracores over long distances. The overall geochronological framework of each study area is based on radiocarbon dating of biogenic material and age determination of diagnostic ceramic fragments. Results presented within this study provide distinct evidence of multiple palaeotsunami landfalls for the investigated areas. Tsunami signatures encountered in the environs of Krane, Lechaion and Kyllini include (i) coarse-grained allochthonous marine sediments intersecting silt-dominated quiescent harbour deposits and/or shallow marine environments, (ii) disturbed microfaunal assemblages and/or (iii) distinct geochemical fingerprints as well as (iv) geo-archaeological destruction layers and (v) extensive units of beachrock-type calcarenitic tsunamites. For Krane, geochronological data yielded termini ad or post quem (maximum ages) for tsunami event generations dated to 4150 ± 60 cal BC, ~ 3200 ± 110 cal BC, ~ 650 ± 110 cal BC, and ~ 930 ± 40 cal AD, respectively. Results for Lechaion suggest that the harbour was hit by strong tsunami impacts in the 8th-6th century BC, the 1st-2nd century AD and in the 6th century AD. At Kyllini, the harbour site was affected by tsunami impact in between the late 7th and early 4th cent. BC and between the 4th and 6th cent. AD. In case of Lechaion and Kyllini, the final destruction of the harbour facilities also seems to be related to the tsunami impact. Comparing the tsunami signals obtained for each study areas with geo-scientific data from palaeotsunami events from other sites indicates that the investigated harbour sites represent excellent geo-archives for supra-regional mega-tsunamis.

Algorithms for Geometric Matching, Clustering, and Covering

With the popularization of GPS-enabled devices such as mobile phones, location data are becoming available at an unprecedented scale. The locations may be collected from many different sources such as vehicles moving around a city, user check-ins in social networks, and geo-tagged micro-blogging photos or messages. Besides the longitude and latitude, each location record may also have a timestamp and additional information such as the name of the location. Time-ordered sequences of these locations form trajectories, which together contain useful high-level information about people's movement patterns.

The first part of this thesis focuses on a few geometric problems motivated by the matching and clustering of trajectories. We first give a new algorithm for computing a matching between a pair of curves under existing models such as dynamic time warping (DTW). The algorithm is more efficient than standard dynamic programming algorithms both theoretically and practically. We then propose a new matching model for trajectories that avoids the drawbacks of existing models. For trajectory clustering, we present an algorithm that computes clusters of subtrajectories, which correspond to common movement patterns. We also consider trajectories of check-ins, and propose a statistical generative model, which identifies check-in clusters as well as the transition patterns between the clusters.

The second part of the thesis considers the problem of covering shortest paths in a road network, motivated by an EV charging station placement problem. More specifically, a subset of vertices in the road network are selected to place charging stations so that every shortest path contains enough charging stations and can be traveled by an EV without draining the battery. We first introduce a general technique for the geometric set cover problem. This technique leads to near-linear-time approximation algorithms, which are the state-of-the-art algorithms for this problem in either running time or approximation ratio. We then use this technique to develop a near-linear-time algorithm for this

shortest-path cover problem.

A Dynamic Analysis of Tuberculosis Dissemination to Improve Control and Surveillance

Background: Detailed analysis of the dynamic interactions among biological, environmental, social, and economic factors that favour the spread of certain diseases is extremely useful for designing effective control strategies. Diseases like tuberculosis that kills somebody every 15 seconds in the world, require methods that take into account the disease dynamics to design truly efficient control and surveillance strategies. The usual and well established statistical approaches provide insights into the cause-effect relationships that favour disease transmission but they only estimate risk areas, spatial or temporal trends. Here we introduce a novel approach that allows figuring out the dynamical behaviour of the disease spreading. This information can subsequently be used to validate mathematical models of the dissemination process from which the underlying mechanisms that are responsible for this spreading could be inferred. Methodology/Principal Findings: The method presented here is based on the analysis of the spread of tuberculosis in a Brazilian endemic city during five consecutive years. The detailed analysis of the spatio-temporal correlation of the yearly geo-referenced data, using different characteristic times of the disease evolution, allowed us to trace the temporal path of the aetiological agent, to locate the sources of infection, and to characterize the dynamics of disease spreading. Consequently, the method also allowed for the identification of socio-economic factors that influence the process. Conclusions/Significance: The information obtained can contribute to more effective budget allocation, drug distribution and recruitment of human skilled resources, as well as guiding the design of vaccination programs. We propose that this novel strategy can also be applied to the evaluation of other diseases as well as other social processes.

GIS capacity building for risk management to help developing countries:Case of climate change problem in Amhara rural region (Ethiopia)

Dissertation submitted in partial fulfillment of the requirements for the Degree of Master of Science in Geospatial Technologies.

Spatio-temporal analyses of the relationship between armed conflict and climate change in the eastern Africa

Dissertation submitted in partial fulfillment of the requirements for the Degree of Master of Science in Geospatial Technologies.

ISEGI-NOVA AR Project - Augmented Reality Aplied to the Universidade Nova de Lisboa

Project work presented as a partial requirement to obtain a Master Degree in Information Management