Integration of heterogeneous data sources and automated reasoning in healthcare and domotic IoT systems

In recent years, IoT technology has radically transformed many crucial industrial and service sectors such as healthcare. The multi-facets heterogeneity of the devices and the collected information provides important opportunities to develop innovative systems and services. However, the ubiquitous presence of data silos and the poor semantic interoperability in the IoT landscape constitute a significant obstacle in the pursuit of this goal. Moreover, achieving actionable knowledge from the collected data requires IoT information sources to be analysed using appropriate artificial intelligence techniques such as automated reasoning. In this thesis work, Semantic Web technologies have been investigated as an approach to address both the data integration and reasoning aspect in modern IoT systems. In particular, the contributions presented in this thesis are the following: (1) the IoT Fitness Ontology, an OWL ontology that has been developed in order to overcome the issue of data silos and enable semantic interoperability in the IoT fitness domain; (2) a Linked Open Data web portal for collecting and sharing IoT health datasets with the research community; (3) a novel methodology for embedding knowledge in rule-defined IoT smart home scenarios; and (4) a knowledge-based IoT home automation system that supports a seamless integration of heterogeneous devices and data sources.

Cost effectiveness of OptiMal (R) rapid diagnostic test for malaria in remote areas of the Amazon Region, Brazil

Background: In areas with limited structure in place for microscopy diagnosis, rapid diagnostic tests (RDT) have been demonstrated to be effective. Method: The cost-effectiveness of the Optimal (R) and thick smear microscopy was estimated and compared. Data were collected on remote areas of 12 municipalities in the Brazilian Amazon. Data sources included the National Malaria Control Programme of the Ministry of Health, the National Healthcare System reimbursement table, hospitalization records, primary data collected from the municipalities, and scientific literature. The perspective was that of the Brazilian public health system, the analytical horizon was from the start of fever until the diagnostic results provided to patient and the temporal reference was that of year 2006. The results were expressed in costs per adequately diagnosed cases in 2006 U. S. dollars. Sensitivity analysis was performed considering key model parameters. Results: In the case base scenario, considering 92% and 95% sensitivity for thick smear microscopy to Plasmodium falciparum and Plasmodium vivax, respectively, and 100% specificity for both species, thick smear microscopy is more costly and more effective, with an incremental cost estimated at US$ 549.9 per adequately diagnosed case. In sensitivity analysis, when sensitivity and specificity of microscopy for P. vivax were 0.90 and 0.98, respectively, and when its sensitivity for P. falciparum was 0.83, the RDT was more cost-effective than microscopy. Conclusion: Microscopy is more cost-effective than OptiMal (R) in these remote areas if high accuracy of microscopy is maintained in the field. Decision regarding use of rapid tests for diagnosis of malaria in these areas depends on current microscopy accuracy in the field.

Evaluation of a real time DGPS data server

The goal of the this paper is to show that the DGPS data Internet service we designed and developed provides campus-wide real time access to Differential GPS (DGPS) data and, thus, supports precise outdoor navigation. First we describe the developed distributed system in terms of architecture (a three tier client/server application), services provided (real time DGPS data transportation from remote DGPS sources and campus wide data dissemination) and transmission modes implemented (raw and frame mode over TCP and UDP). Then we present and discuss the results obtained and, finally, we draw some conclusions.

A Distributed System for the Dissemination of DGPS Data through the Internet

In this paper we describe a low cost distributed system intended to increase the positioning accuracy of outdoor navigation systems based on the Global Positioning System (GPS). Since the accuracy of absolute GPS positioning is insufficient for many outdoor navigation tasks, another GPS based methodology – the Differential GPS (DGPS) – was developed in the nineties. The differential or relative positioning approach is based on the calculation and dissemination of the range errors of the received GPS satellites. GPS/DGPS receivers correlate the broadcasted GPS data with the DGPS corrections, granting users increased accuracy. DGPS data can be disseminated using terrestrial radio beacons, satellites and, more recently, the Internet. Our goal is to provide mobile platforms within our campus with DGPS data for precise outdoor navigation. To achieve this objective, we designed and implemented a three-tier client/server distributed system that, first, establishes Internet links with remote DGPS sources and, then, performs campus-wide dissemination of the obtained data. The Internet links are established between data servers connected to remote DGPS sources and the client, which is the data input module of the campus-wide DGPS data provider. The campus DGPS data provider allows the establishment of both Intranet and wireless links within the campus. This distributed system is expected to provide adequate support for accurate outdoor navigation tasks.

Domain Adaptation in remote sensing: increasing the portability of land-cover classifiers

Among the types of remote sensing acquisitions, optical images are certainly one of the most widely relied upon data sources for Earth observation. They provide detailed measurements of the electromagnetic radiation reflected or emitted by each pixel in the scene. Through a process termed supervised land-cover classification, this allows to automatically yet accurately distinguish objects at the surface of our planet. In this respect, when producing a land-cover map of the surveyed area, the availability of training examples representative of each thematic class is crucial for the success of the classification procedure. However, in real applications, due to several constraints on the sample collection process, labeled pixels are usually scarce. When analyzing an image for which those key samples are unavailable, a viable solution consists in resorting to the ground truth data of other previously acquired images. This option is attractive but several factors such as atmospheric, ground and acquisition conditions can cause radiometric differences between the images, hindering therefore the transfer of knowledge from one image to another. The goal of this Thesis is to supply remote sensing image analysts with suitable processing techniques to ensure a robust portability of the classification models across different images. The ultimate purpose is to map the land-cover classes over large spatial and temporal extents with minimal ground information. To overcome, or simply quantify, the observed shifts in the statistical distribution of the spectra of the materials, we study four approaches issued from the field of machine learning. First, we propose a strategy to intelligently sample the image of interest to collect the labels only in correspondence of the most useful pixels. This iterative routine is based on a constant evaluation of the pertinence to the new image of the initial training data actually belonging to a different image. Second, an approach to reduce the radiometric differences among the images by projecting the respective pixels in a common new data space is presented. We analyze a kernel-based feature extraction framework suited for such problems, showing that, after this relative normalization, the cross-image generalization abilities of a classifier are highly increased. Third, we test a new data-driven measure of distance between probability distributions to assess the distortions caused by differences in the acquisition geometry affecting series of multi-angle images. Also, we gauge the portability of classification models through the sequences. In both exercises, the efficacy of classic physically- and statistically-based normalization methods is discussed. Finally, we explore a new family of approaches based on sparse representations of the samples to reciprocally convert the data space of two images. The projection function bridging the images allows a synthesis of new pixels with more similar characteristics ultimately facilitating the land-cover mapping across images.

Rockfall susceptibility assessment and remote geological mapping with LiDAR point clouds

Characterizing the geological features and structures in three dimensions over inaccessible rock cliffs is needed to assess natural hazards such as rockfalls and rockslides and also to perform investigations aimed at mapping geological contacts and building stratigraphy and fold models. Indeed, the detailed 3D data, such as LiDAR point clouds, allow to study accurately the hazard processes and the structure of geologic features, in particular in vertical and overhanging rock slopes. Thus, 3D geological models have a great potential of being applied to a wide range of geological investigations both in research and applied geology projects, such as mines, tunnels and reservoirs. Recent development of ground-based remote sensing techniques (LiDAR, photogrammetry and multispectral / hyperspectral images) are revolutionizing the acquisition of morphological and geological information. As a consequence, there is a great potential for improving the modeling of geological bodies as well as failure mechanisms and stability conditions by integrating detailed remote data. During the past ten years several large rockfall events occurred along important transportation corridors where millions of people travel every year (Switzerland: Gotthard motorway and railway; Canada: Sea to sky highway between Vancouver and Whistler). These events show that there is still a lack of knowledge concerning the detection of potential rockfalls, making mountain residential settlements and roads highly risky. It is necessary to understand the main factors that destabilize rocky outcrops even if inventories are lacking and if no clear morphological evidences of rockfall activity are observed. In order to increase the possibilities of forecasting potential future landslides, it is crucial to understand the evolution of rock slope stability. Defining the areas theoretically most prone to rockfalls can be particularly useful to simulate trajectory profiles and to generate hazard maps, which are the basis for land use planning in mountainous regions. The most important questions to address in order to assess rockfall hazard are: Where are the most probable sources for future rockfalls located? What are the frequencies of occurrence of these rockfalls? I characterized the fracturing patterns in the field and with LiDAR point clouds. Afterwards, I developed a model to compute the failure mechanisms on terrestrial point clouds in order to assess the susceptibility to rockfalls at the cliff scale. Similar procedures were already available to evaluate the susceptibility to rockfalls based on aerial digital elevation models. This new model gives the possibility to detect the most susceptible rockfall sources with unprecented detail in the vertical and overhanging areas. The results of the computation of the most probable rockfall source areas in granitic cliffs of Yosemite Valley and Mont-Blanc massif were then compared to the inventoried rockfall events to validate the calculation methods. Yosemite Valley was chosen as a test area because it has a particularly strong rockfall activity (about one rockfall every week) which leads to a high rockfall hazard. The west face of the Dru was also chosen for the relevant rockfall activity and especially because it was affected by some of the largest rockfalls that occurred in the Alps during the last 10 years. Moreover, both areas were suitable because of their huge vertical and overhanging cliffs that are difficult to study with classical methods. Limit equilibrium models have been applied to several case studies to evaluate the effects of different parameters on the stability of rockslope areas. The impact of the degradation of rockbridges on the stability of large compartments in the west face of the Dru was assessed using finite element modeling. In particular I conducted a back-analysis of the large rockfall event of 2005 (265'000 m3) by integrating field observations of joint conditions, characteristics of fracturing pattern and results of geomechanical tests on the intact rock. These analyses improved our understanding of the factors that influence the stability of rock compartments and were used to define the most probable future rockfall volumes at the Dru. Terrestrial laser scanning point clouds were also successfully employed to perform geological mapping in 3D, using the intensity of the backscattered signal. Another technique to obtain vertical geological maps is combining triangulated TLS mesh with 2D geological maps. At El Capitan (Yosemite Valley) we built a georeferenced vertical map of the main plutonio rocks that was used to investigate the reasons for preferential rockwall retreat rate. Additional efforts to characterize the erosion rate were made at Monte Generoso (Ticino, southern Switzerland) where I attempted to improve the estimation of long term erosion by taking into account also the volumes of the unstable rock compartments. Eventually, the following points summarize the main out puts of my research: The new model to compute the failure mechanisms and the rockfall susceptibility with 3D point clouds allows to define accurately the most probable rockfall source areas at the cliff scale. The analysis of the rockbridges at the Dru shows the potential of integrating detailed measurements of the fractures in geomechanical models of rockmass stability. The correction of the LiDAR intensity signal gives the possibility to classify a point cloud according to the rock type and then use this information to model complex geologic structures. The integration of these results, on rockmass fracturing and composition, with existing methods can improve rockfall hazard assessments and enhance the interpretation of the evolution of steep rockslopes. -- La caractérisation de la géologie en 3D pour des parois rocheuses inaccessibles est une étape nécessaire pour évaluer les dangers naturels tels que chutes de blocs et glissements rocheux, mais aussi pour réaliser des modèles stratigraphiques ou de structures plissées. Les modèles géologiques 3D ont un grand potentiel pour être appliqués dans une vaste gamme de travaux géologiques dans le domaine de la recherche, mais aussi dans des projets appliqués comme les mines, les tunnels ou les réservoirs. Les développements récents des outils de télédétection terrestre (LiDAR, photogrammétrie et imagerie multispectrale / hyperspectrale) sont en train de révolutionner l'acquisition d'informations géomorphologiques et géologiques. Par conséquence, il y a un grand potentiel d'amélioration pour la modélisation d'objets géologiques, ainsi que des mécanismes de rupture et des conditions de stabilité, en intégrant des données détaillées acquises à distance. Pour augmenter les possibilités de prévoir les éboulements futurs, il est fondamental de comprendre l'évolution actuelle de la stabilité des parois rocheuses. Définir les zones qui sont théoriquement plus propices aux chutes de blocs peut être très utile pour simuler les trajectoires de propagation des blocs et pour réaliser des cartes de danger, qui constituent la base de l'aménagement du territoire dans les régions de montagne. Les questions plus importantes à résoudre pour estimer le danger de chutes de blocs sont : Où se situent les sources plus probables pour les chutes de blocs et éboulement futurs ? Avec quelle fréquence vont se produire ces événements ? Donc, j'ai caractérisé les réseaux de fractures sur le terrain et avec des nuages de points LiDAR. Ensuite, j'ai développé un modèle pour calculer les mécanismes de rupture directement sur les nuages de points pour pouvoir évaluer la susceptibilité au déclenchement de chutes de blocs à l'échelle de la paroi. Les zones sources de chutes de blocs les plus probables dans les parois granitiques de la vallée de Yosemite et du massif du Mont-Blanc ont été calculées et ensuite comparés aux inventaires des événements pour vérifier les méthodes. Des modèles d'équilibre limite ont été appliqués à plusieurs cas d'études pour évaluer les effets de différents paramètres sur la stabilité des parois. L'impact de la dégradation des ponts rocheux sur la stabilité de grands compartiments de roche dans la paroi ouest du Petit Dru a été évalué en utilisant la modélisation par éléments finis. En particulier j'ai analysé le grand éboulement de 2005 (265'000 m3), qui a emporté l'entier du pilier sud-ouest. Dans le modèle j'ai intégré des observations des conditions des joints, les caractéristiques du réseau de fractures et les résultats de tests géoméchaniques sur la roche intacte. Ces analyses ont amélioré l'estimation des paramètres qui influencent la stabilité des compartiments rocheux et ont servi pour définir des volumes probables pour des éboulements futurs. Les nuages de points obtenus avec le scanner laser terrestre ont été utilisés avec succès aussi pour produire des cartes géologiques en 3D, en utilisant l'intensité du signal réfléchi. Une autre technique pour obtenir des cartes géologiques des zones verticales consiste à combiner un maillage LiDAR avec une carte géologique en 2D. A El Capitan (Yosemite Valley) nous avons pu géoréferencer une carte verticale des principales roches plutoniques que j'ai utilisé ensuite pour étudier les raisons d'une érosion préférentielle de certaines zones de la paroi. D'autres efforts pour quantifier le taux d'érosion ont été effectués au Monte Generoso (Ticino, Suisse) où j'ai essayé d'améliorer l'estimation de l'érosion au long terme en prenant en compte les volumes des compartiments rocheux instables. L'intégration de ces résultats, sur la fracturation et la composition de l'amas rocheux, avec les méthodes existantes permet d'améliorer la prise en compte de l'aléa chute de pierres et éboulements et augmente les possibilités d'interprétation de l'évolution des parois rocheuses.

Modelling ecological values in heterogeneous and dynamic landscapes with geospatial data

Our surrounding landscape is in a constantly dynamic state, but recently the rate of changes and their effects on the environment have considerably increased. In terms of the impact on nature, this development has not been entirely positive, but has rather caused a decline in valuable species, habitats, and general biodiversity. Regardless of recognizing the problem and its high importance, plans and actions of how to stop the detrimental development are largely lacking. This partly originates from a lack of genuine will, but is also due to difficulties in detecting many valuable landscape components and their consequent neglect. To support knowledge extraction, various digital environmental data sources may be of substantial help, but only if all the relevant background factors are known and the data is processed in a suitable way. This dissertation concentrates on detecting ecologically valuable landscape components by using geospatial data sources, and applies this knowledge to support spatial planning and management activities. In other words, the focus is on observing regionally valuable species, habitats, and biotopes with GIS and remote sensing data, using suitable methods for their analysis. Primary emphasis is given to the hemiboreal vegetation zone and the drastic decline in its semi-natural grasslands, which were created by a long trajectory of traditional grazing and management activities. However, the applied perspective is largely methodological, and allows for the application of the obtained results in various contexts. Models based on statistical dependencies and correlations of multiple variables, which are able to extract desired properties from a large mass of initial data, are emphasized in the dissertation. In addition, the papers included combine several data sets from different sources and dates together, with the aim of detecting a wider range of environmental characteristics, as well as pointing out their temporal dynamics. The results of the dissertation emphasise the multidimensionality and dynamics of landscapes, which need to be understood in order to be able to recognise their ecologically valuable components. This not only requires knowledge about the emergence of these components and an understanding of the used data, but also the need to focus the observations on minute details that are able to indicate the existence of fragmented and partly overlapping landscape targets. In addition, this pinpoints the fact that most of the existing classifications are too generalised as such to provide all the required details, but they can be utilized at various steps along a longer processing chain. The dissertation also emphases the importance of landscape history as an important factor, which both creates and preserves ecological values, and which sets an essential standpoint for understanding the present landscape characteristics. The obtained results are significant both in terms of preserving semi-natural grasslands, as well as general methodological development, giving support to science-based framework in order to evaluate ecological values and guide spatial planning.

An intercomparison of bio-optical techniques for detecting dominant phytoplankton size class from satellite remote sensing

Satellite remote sensing of ocean colour is the only method currently available for synoptically measuring wide-area properties of ocean ecosystems, such as phytoplankton chlorophyll biomass. Recently, a variety of bio-optical and ecological methods have been established that use satellite data to identify and differentiate between either phytoplankton functional types (PFTs) or phytoplankton size classes (PSCs). In this study, several of these techniques were evaluated against in situ observations to determine their ability to detect dominant phytoplankton size classes (micro-, nano- and picoplankton). The techniques are applied to a 10-year ocean-colour data series from the SeaWiFS satellite sensor and compared with in situ data (6504 samples) from a variety of locations in the global ocean. Results show that spectral-response, ecological and abundance-based approaches can all perform with similar accuracy. Detection of microplankton and picoplankton were generally better than detection of nanoplankton. Abundance-based approaches were shown to provide better spatial retrieval of PSCs. Individual model performance varied according to PSC, input satellite data sources and in situ validation data types. Uncertainty in the comparison procedure and data sources was considered. Improved availability of in situ observations would aid ongoing research in this field. (C) 2010 Elsevier B.V. All rights reserved.

Wavelets and decision trees for target detection over sea surface using cosmo-skymed SAR data

We are investigating the combination of wavelets and decision trees to detect ships and other maritime surveillance targets from medium resolution SAR images. Wavelets have inherent advantages to extract image descriptors while decision trees are able to handle different data sources. In addition, our work aims to consider oceanic features such as ship wakes and ocean spills. In this incipient work, Haar and Cohen-Daubechies-Feauveau 9/7 wavelets obtain detailed descriptors from targets and ocean features and are inserted with other statistical parameters and wavelets into an oblique decision tree. © 2011 Springer-Verlag.

Cost effectiveness of OptiMal® rapid diagnostic test for malaria in remote areas of the Amazon Region, Brazil

Abstract Background In areas with limited structure in place for microscopy diagnosis, rapid diagnostic tests (RDT) have been demonstrated to be effective. Method The cost-effectiveness of the Optimal® and thick smear microscopy was estimated and compared. Data were collected on remote areas of 12 municipalities in the Brazilian Amazon. Data sources included the National Malaria Control Programme of the Ministry of Health, the National Healthcare System reimbursement table, hospitalization records, primary data collected from the municipalities, and scientific literature. The perspective was that of the Brazilian public health system, the analytical horizon was from the start of fever until the diagnostic results provided to patient and the temporal reference was that of year 2006. The results were expressed in costs per adequately diagnosed cases in 2006 U.S. dollars. Sensitivity analysis was performed considering key model parameters. Results In the case base scenario, considering 92% and 95% sensitivity for thick smear microscopy to Plasmodium falciparum and Plasmodium vivax, respectively, and 100% specificity for both species, thick smear microscopy is more costly and more effective, with an incremental cost estimated at US$549.9 per adequately diagnosed case. In sensitivity analysis, when sensitivity and specificity of microscopy for P. vivax were 0.90 and 0.98, respectively, and when its sensitivity for P. falciparum was 0.83, the RDT was more cost-effective than microscopy. Conclusion Microscopy is more cost-effective than OptiMal® in these remote areas if high accuracy of microscopy is maintained in the field. Decision regarding use of rapid tests for diagnosis of malaria in these areas depends on current microscopy accuracy in the field.

A graph theoretic approach to testing associations between disparate sources of functional genomic data

The last few years have seen the advent of high-throughput technologies to analyze various properties of the transcriptome and proteome of several organisms. The congruency of these different data sources, or lack thereof, can shed light on the mechanisms that govern cellular function. A central challenge for bioinformatics research is to develop a unified framework for combining the multiple sources of functional genomics information and testing associations between them, thus obtaining a robust and integrated view of the underlying biology. We present a graph theoretic approach to test the significance of the association between multiple disparate sources of functional genomics data by proposing two statistical tests, namely edge permutation and node label permutation tests. We demonstrate the use of the proposed tests by finding significant association between a Gene Ontology-derived "predictome" and data obtained from mRNA expression and phenotypic experiments for Saccharomyces cerevisiae. Moreover, we employ the graph theoretic framework to recast a surprising discrepancy presented in Giaever et al. (2002) between gene expression and knockout phenotype, using expression data from a different set of experiments.

Nesting In The Clouds: Evaluating And Predicting Sea Turtle Nesting Beach Parameters From Lidar Data

Humans' desire for knowledge regarding animal species and their interactions with the natural world have spurred centuries of studies. The relatively new development of remote sensing systems using satellite or aircraft-borne sensors has opened up a wide field of research, which unfortunately largely remains dependent on coarse-scale image spatial resolution, particularly for habitat modeling. For habitat-specialized species, such data may not be sufficient to successfully capture the nuances of their preferred areas. Of particular concern are those species for which topographic feature attributes are a main limiting factor for habitat use. Coarse spatial resolution data can smooth over details that may be essential for habitat characterization. Three studies focusing on sea turtle nesting beaches were completed to serve as an example of how topography can be a main deciding factor for certain species. Light Detection and Ranging (LiDAR) data were used to illustrate that fine spatial scale data can provide information not readily captured by either field work or coarser spatial scale sources. The variables extracted from the LiDAR data could successfully model nesting density for loggerhead (Caretta caretta), green (Chelonia mydas), and leatherback (Dermochelys coriacea) sea turtle species using morphological beach characteristics, highlight beach changes over time and their correlations with nesting success, and provide comparisons for nesting density models across large geographic areas. Comparisons between the LiDAR dataset and other digital elevation models (DEMs) confirmed that fine spatial scale data sources provide more similar habitat information than those with coarser spatial scales. Although these studies focused solely on sea turtles, the underlying principles are applicable for many other wildlife species whose range and behavior may be influenced by topographic features.

An Investigation of Ozone Related Data and Development of a Model to Evaluate Ozone Episodes for Exceptional Event Criteria

The EPA promulgated the Exceptional Events Rule codifying guidance regarding exclusion of monitoring data from compliance decisions due to uncontrollable natural or exceptional events. This capstone examines documentation systems utilized by agencies requesting data be excluded from compliance decisions due to exceptional events. A screening tool is developed to determine whether an event would meet exceptional event criteria. New data sources are available to enhance analysis but evaluation shows many are unusable in their current form. The EPA and States must collaborate to develop consistent evaluation methodologies documenting exceptional events to improve the efficiency and effectiveness of the new rule. To utilize newer sophisticated data, consistent, user-friendly translation systems must be developed.

The integration of multi-source data to improve the classification of remotely sensed images

The number of remote sensing platforms and sensors rises almost every year, yet much work on the interpretation of land cover is still carried out using either single images or images from the same source taken at different dates. Two questions could be asked of this proliferation of images: can the information contained in different scenes be used to improve the classification accuracy and, what is the best way to combine the different imagery? Two of these multiple image sources are MODIS on the Terra platform and ETM+ on board Landsat7, which are suitably complementary. Daily MODIS images with 36 spectral bands in 250-1000 m spatial resolution and seven spectral bands of ETM+ with 30m and 16 days spatial and temporal resolution respectively are available. In the UK, cloud cover may mean that only a few ETM+ scenes may be available for any particular year and these may not be at the time of year of most interest. The MODIS data may provide information on land cover over the growing season, such as harvest dates, that is not present in the ETM+ data. Therefore, the primary objective of this work is to develop a methodology for the integration of medium spatial resolution Landsat ETM+ image, with multi-temporal, multi-spectral, low-resolution MODIS \Terra images, with the aim of improving the classification of agricultural land. Additionally other data may also be incorporated such as field boundaries from existing maps. When classifying agricultural land cover of the type seen in the UK, where crops are largely sown in homogenous fields with clear and often mapped boundaries, the classification is greatly improved using the mapped polygons and utilising the classification of the polygon as a whole as an apriori probability in classifying each individual pixel using a Bayesian approach. When dealing with multiple images from different platforms and dates it is highly unlikely that the pixels will be exactly co-registered and these pixels will contain a mixture of different real world land covers. Similarly the different atmospheric conditions prevailing during the different days will mean that the same emission from the ground will give rise to different sensor reception. Therefore, a method is presented with a model of the instantaneous field of view and atmospheric effects to enable different remote sensed data sources to be integrated.

Knowledge discovery using multiple sources of biological data

The primary aim of this dissertation is to develop data mining tools for knowledge discovery in biomedical data when multiple (homogeneous or heterogeneous) sources of data are available. The central hypothesis is that, when information from multiple sources of data are used appropriately and effectively, knowledge discovery can be better achieved than what is possible from only a single source. ^ Recent advances in high-throughput technology have enabled biomedical researchers to generate large volumes of diverse types of data on a genome-wide scale. These data include DNA sequences, gene expression measurements, and much more; they provide the motivation for building analysis tools to elucidate the modular organization of the cell. The challenges include efficiently and accurately extracting information from the multiple data sources; representing the information effectively, developing analytical tools, and interpreting the results in the context of the domain. ^ The first part considers the application of feature-level integration to design classifiers that discriminate between soil types. The machine learning tools, SVM and KNN, were used to successfully distinguish between several soil samples. ^ The second part considers clustering using multiple heterogeneous data sources. The resulting Multi-Source Clustering (MSC) algorithm was shown to have a better performance than clustering methods that use only a single data source or a simple feature-level integration of heterogeneous data sources. ^ The third part proposes a new approach to effectively incorporate incomplete data into clustering analysis. Adapted from K-means algorithm, the Generalized Constrained Clustering (GCC) algorithm makes use of incomplete data in the form of constraints to perform exploratory analysis. Novel approaches for extracting constraints were proposed. For sufficiently large constraint sets, the GCC algorithm outperformed the MSC algorithm. ^ The last part considers the problem of providing a theme-specific environment for mining multi-source biomedical data. The database called PlasmoTFBM, focusing on gene regulation of Plasmodium falciparum, contains diverse information and has a simple interface to allow biologists to explore the data. It provided a framework for comparing different analytical tools for predicting regulatory elements and for designing useful data mining tools. ^ The conclusion is that the experiments reported in this dissertation strongly support the central hypothesis.^