Machine learning for geospatial data : algorithms, software tools and case studies

Résumé Cette thèse est consacrée à l'analyse, la modélisation et la visualisation de données environnementales à référence spatiale à l'aide d'algorithmes d'apprentissage automatique (Machine Learning). L'apprentissage automatique peut être considéré au sens large comme une sous-catégorie de l'intelligence artificielle qui concerne particulièrement le développement de techniques et d'algorithmes permettant à une machine d'apprendre à partir de données. Dans cette thèse, les algorithmes d'apprentissage automatique sont adaptés pour être appliqués à des données environnementales et à la prédiction spatiale. Pourquoi l'apprentissage automatique ? Parce que la majorité des algorithmes d'apprentissage automatiques sont universels, adaptatifs, non-linéaires, robustes et efficaces pour la modélisation. Ils peuvent résoudre des problèmes de classification, de régression et de modélisation de densité de probabilités dans des espaces à haute dimension, composés de variables informatives spatialisées (« géo-features ») en plus des coordonnées géographiques. De plus, ils sont idéaux pour être implémentés en tant qu'outils d'aide à la décision pour des questions environnementales allant de la reconnaissance de pattern à la modélisation et la prédiction en passant par la cartographie automatique. Leur efficacité est comparable au modèles géostatistiques dans l'espace des coordonnées géographiques, mais ils sont indispensables pour des données à hautes dimensions incluant des géo-features. Les algorithmes d'apprentissage automatique les plus importants et les plus populaires sont présentés théoriquement et implémentés sous forme de logiciels pour les sciences environnementales. Les principaux algorithmes décrits sont le Perceptron multicouches (MultiLayer Perceptron, MLP) - l'algorithme le plus connu dans l'intelligence artificielle, le réseau de neurones de régression généralisée (General Regression Neural Networks, GRNN), le réseau de neurones probabiliste (Probabilistic Neural Networks, PNN), les cartes auto-organisées (SelfOrganized Maps, SOM), les modèles à mixture Gaussiennes (Gaussian Mixture Models, GMM), les réseaux à fonctions de base radiales (Radial Basis Functions Networks, RBF) et les réseaux à mixture de densité (Mixture Density Networks, MDN). Cette gamme d'algorithmes permet de couvrir des tâches variées telle que la classification, la régression ou l'estimation de densité de probabilité. L'analyse exploratoire des données (Exploratory Data Analysis, EDA) est le premier pas de toute analyse de données. Dans cette thèse les concepts d'analyse exploratoire de données spatiales (Exploratory Spatial Data Analysis, ESDA) sont traités selon l'approche traditionnelle de la géostatistique avec la variographie expérimentale et selon les principes de l'apprentissage automatique. La variographie expérimentale, qui étudie les relations entre pairs de points, est un outil de base pour l'analyse géostatistique de corrélations spatiales anisotropiques qui permet de détecter la présence de patterns spatiaux descriptible par une statistique. L'approche de l'apprentissage automatique pour l'ESDA est présentée à travers l'application de la méthode des k plus proches voisins qui est très simple et possède d'excellentes qualités d'interprétation et de visualisation. Une part importante de la thèse traite de sujets d'actualité comme la cartographie automatique de données spatiales. Le réseau de neurones de régression généralisée est proposé pour résoudre cette tâche efficacement. Les performances du GRNN sont démontrées par des données de Comparaison d'Interpolation Spatiale (SIC) de 2004 pour lesquelles le GRNN bat significativement toutes les autres méthodes, particulièrement lors de situations d'urgence. La thèse est composée de quatre chapitres : théorie, applications, outils logiciels et des exemples guidés. Une partie importante du travail consiste en une collection de logiciels : Machine Learning Office. Cette collection de logiciels a été développée durant les 15 dernières années et a été utilisée pour l'enseignement de nombreux cours, dont des workshops internationaux en Chine, France, Italie, Irlande et Suisse ainsi que dans des projets de recherche fondamentaux et appliqués. Les cas d'études considérés couvrent un vaste spectre de problèmes géoenvironnementaux réels à basse et haute dimensionnalité, tels que la pollution de l'air, du sol et de l'eau par des produits radioactifs et des métaux lourds, la classification de types de sols et d'unités hydrogéologiques, la cartographie des incertitudes pour l'aide à la décision et l'estimation de risques naturels (glissements de terrain, avalanches). Des outils complémentaires pour l'analyse exploratoire des données et la visualisation ont également été développés en prenant soin de créer une interface conviviale et facile à l'utilisation. Machine Learning for geospatial data: algorithms, software tools and case studies Abstract The thesis is devoted to the analysis, modeling and visualisation of spatial environmental data using machine learning algorithms. In a broad sense machine learning can be considered as a subfield of artificial intelligence. It mainly concerns with the development of techniques and algorithms that allow computers to learn from data. In this thesis machine learning algorithms are adapted to learn from spatial environmental data and to make spatial predictions. Why machine learning? In few words most of machine learning algorithms are universal, adaptive, nonlinear, robust and efficient modeling tools. They can find solutions for the classification, regression, and probability density modeling problems in high-dimensional geo-feature spaces, composed of geographical space and additional relevant spatially referenced features. They are well-suited to be implemented as predictive engines in decision support systems, for the purposes of environmental data mining including pattern recognition, modeling and predictions as well as automatic data mapping. They have competitive efficiency to the geostatistical models in low dimensional geographical spaces but are indispensable in high-dimensional geo-feature spaces. The most important and popular machine learning algorithms and models interesting for geo- and environmental sciences are presented in details: from theoretical description of the concepts to the software implementation. The main algorithms and models considered are the following: multi-layer perceptron (a workhorse of machine learning), general regression neural networks, probabilistic neural networks, self-organising (Kohonen) maps, Gaussian mixture models, radial basis functions networks, mixture density networks. This set of models covers machine learning tasks such as classification, regression, and density estimation. Exploratory data analysis (EDA) is initial and very important part of data analysis. In this thesis the concepts of exploratory spatial data analysis (ESDA) is considered using both traditional geostatistical approach such as_experimental variography and machine learning. Experimental variography is a basic tool for geostatistical analysis of anisotropic spatial correlations which helps to understand the presence of spatial patterns, at least described by two-point statistics. A machine learning approach for ESDA is presented by applying the k-nearest neighbors (k-NN) method which is simple and has very good interpretation and visualization properties. Important part of the thesis deals with a hot topic of nowadays, namely, an automatic mapping of geospatial data. General regression neural networks (GRNN) is proposed as efficient model to solve this task. Performance of the GRNN model is demonstrated on Spatial Interpolation Comparison (SIC) 2004 data where GRNN model significantly outperformed all other approaches, especially in case of emergency conditions. The thesis consists of four chapters and has the following structure: theory, applications, software tools, and how-to-do-it examples. An important part of the work is a collection of software tools - Machine Learning Office. Machine Learning Office tools were developed during last 15 years and was used both for many teaching courses, including international workshops in China, France, Italy, Ireland, Switzerland and for realizing fundamental and applied research projects. Case studies considered cover wide spectrum of the real-life low and high-dimensional geo- and environmental problems, such as air, soil and water pollution by radionuclides and heavy metals, soil types and hydro-geological units classification, decision-oriented mapping with uncertainties, natural hazards (landslides, avalanches) assessments and susceptibility mapping. Complementary tools useful for the exploratory data analysis and visualisation were developed as well. The software is user friendly and easy to use.

Publication bias in animal research: a systematic review protocol.

BACKGROUND: Systematic reviews and meta-analyses of pre-clinical studies, in vivo animal experiments in particular, can influence clinical care. Publication bias is one of the major threats of validity in systematic reviews and meta-analyses. Previous empirical studies suggested that systematic reviews and meta-analyses have become more prevalent until 2010 and found evidence for compromised methodological rigor with a trend towards improvement. We aim to comprehensively summarize and update the evidence base on systematic reviews and meta-analyses of animal studies, their methodological quality and assessment of publication bias in particular. METHODS/DESIGN: The objectives of this systematic review are as follows: âeuro¢To investigate the epidemiology of published systematic reviews of animal studies until present. âeuro¢To examine methodological features of systematic reviews and meta-analyses of animal studies with special attention to the assessment of publication bias. âeuro¢To investigate the influence of systematic reviews of animal studies on clinical research by examining citations of the systematic reviews by clinical studies. Eligible studies for this systematic review constitute systematic reviews and meta-analyses that summarize in vivo animal experiments with the purpose of reviewing animal evidence to inform human health. We will exclude genome-wide association studies and animal experiments with the main purpose to learn more about fundamental biology, physical functioning or behavior. In addition to the inclusion of systematic reviews and meta-analyses identified by other empirical studies, we will systematically search Ovid Medline, Embase, ToxNet, and ScienceDirect from 2009 to January 2013 for further eligible studies without language restrictions. Two reviewers working independently will assess titles, abstracts, and full texts for eligibility and extract relevant data from included studies. Data reporting will involve a descriptive summary of meta-analyses and systematic reviews. DISCUSSION: Results are expected to be publicly available later in 2013 and may form the basis for recommendations to improve the quality of systematic reviews and meta-analyses of animal studies and their use with respect to clinical care.

Nondeclarative learning in children with Specific Language Impairment: Predicting regularities in the visuomotor, phonological, and cognitive domains.

Ullman (2004) suggested that Specific Language Impairment (SLI) results from a general procedural learning deficit. In order to test this hypothesis, we investigated children with SLI via procedural learning tasks exploring the verbal, motor, and cognitive domains. Results showed that compared with a Control Group, the children with SLI (a) were unable to learn a phonotactic learning task, (b) were able but less efficiently to learn a motor learning task and (c) succeeded in a cognitive learning task. Regarding the motor learning task (Serial Reaction Time Task), reaction times were longer and learning slower than in controls. The learning effect was not significant in children with an associated Developmental Coordination Disorder (DCD), and future studies should consider comorbid motor impairment in order to clarify whether impairments are related to the motor rather than the language disorder. Our results indicate that a phonotactic learning but not a cognitive procedural deficit underlies SLI, thus challenging Ullmans' general procedural deficit hypothesis, like a few other recent studies.

Auditory stimulation does not induce implicit memory during anaesthesia

Background and aim of the study: Formation of implicit memory during general anaesthesia is still debated. Perceptual learning is the ability to learn to perceive. In this study, an auditory perceptual learning paradigm, using frequency discrimination, was performed to investigate the implicit memory. It was hypothesized that auditory stimulation would successfully induce perceptual learning. Thus, initial thresholds of the frequency discrimination postoperative task should be lower for the stimulated group (group S) compared to the control group (group C). Material and method: Eighty-seven patients ASA I-III undergoing visceral and orthopaedic surgery during general anaesthesia lasting more than 60 minutes were recruited. The anaesthesia procedure was standardized (BISR monitoring included). Group S received auditory stimulation (2000 pure tones applied for 45 minutes) during the surgery. Twenty-four hours after the operation, both groups performed ten blocks of the frequency discrimination task. Mean of the thresholds for the first three blocks (T1) were compared between groups. Results: Mean age and BIS value of group S and group C are respectively 40 } 11 vs 42 } 11 years (p = 0,49) and 42 } 6 vs 41 } 8 (p = 0.87). T1 is respectively 31 } 33 vs 28 } 34 (p = 0.72) in group S and C. Conclusion: In our study, no implicit memory during general anaesthesia was demonstrated. This may be explained by a modulation of the auditory evoked potentials caused by the anaesthesia, or by an insufficient longer time of repetitive stimulation to induce perceptual learning.

Evaluation of Work Zone Speed Reduction Measures, 2000

The Iowa Department of Transportation (DOT) has made improving work zone (WZ) safety a high priority. Managing vehicle speeds through work zones is perceived to be an important factor in achieving this goal. A number of speed reduction techniques are currently used by transportation agencies throughout the country to control speeds and reduce speed variation at work zones. The purpose of this project is to study these and other applicable work zone speed reduction strategies. Furthermore, this research explores transportation agencies' policies regarding managing speeds in long-term, short-term, and moving work zones. This report consists of three chapters. The first chapter, a literature review, examines the current speed reduction practices at work zones and provides a review of the relevant literature. The speed control strategies reviewed in this chapter range from posting regulatory and advisory speed limit signs to using the latest radar technologies to reduce speeds at work zones. The second chapter includes a short write-up for each identified speed control technique. The write-up includes a description, the results of any field tests, the benefits and the costs of the technology or technique. To learn more about other state policies regarding work zone speed reduction and management, the Center for Transportation Research and Education conducted a survey. The survey consists of six multipart questions. The third chapter provides summaries of the response to each question.

Neural networks complemented with genetic algorithms and fuzzy systems for predicting nitrogenous effluent variables in wastewater treatment plants

This work focuses on the prediction of the two main nitrogenous variables that describe the water quality at the effluent of a Wastewater Treatment Plant. We have developed two kind of Neural Networks architectures based on considering only one output or, in the other hand, the usual five effluent variables that define the water quality: suspended solids, biochemical organic matter, chemical organic matter, total nitrogen and total Kjedhal nitrogen. Two learning techniques based on a classical adaptative gradient and a Kalman filter have been implemented. In order to try to improve generalization and performance we have selected variables by means genetic algorithms and fuzzy systems. The training, testing and validation sets show that the final networks are able to learn enough well the simulated available data specially for the total nitrogen

Correlations between Vocal Input and Visual Response Apparently Enhance Presence in a Virtual Environment

This work investigates novel alternative means of interaction in a virtual environment (VE).We analyze whether humans can remap established body functions to learn to interact with digital information in an environment that is cross-sensory by nature and uses vocal utterances in order to influence (abstract) virtual objects. We thus establish a correlation among learning, control of the interface, and the perceived sense of presence in the VE. The application enables intuitive interaction by mapping actions (the prosodic aspects of the human voice) to a certain response (i.e., visualization). A series of single-user and multiuser studies shows that users can gain control of the intuitive interface and learn to adapt to new and previously unseen tasks in VEs. Despite the abstract nature of the presented environment, presence scores were generally very high.

Ibotenate Lesions of Hippocampus and/or Subiculum: Dissociating Components of Allocentric Spatial Learning

This study examined the effects of ibotenic acid-induced lesions of the hippocampus, subiculum and hippocampus +/- subiculum upon the capacity of rats to learn and perform a series of allocentric spatial learning tasks in an open-field water maze. The lesions were made by infusing small volumes of the neurotoxin at a total of 26 (hippocampus) or 20 (subiculum) sites intended to achieve complete target cell loss but minimal extratarget damage. The regional extent and axon-sparing nature of these lesions was evaluated using both cresyl violet and Fink - Heimer stained sections. The behavioural findings indicated that both the hippocampus and subiculum lesions caused impairment to the initial postoperative acquisition of place navigation but did not prevent eventual learning to levels of performance almost as effective as those of controls. However, overtraining of the hippocampus + subiculum lesioned rats did not result in significant place learning. Qualitative observations of the paths taken to find a hidden escape platform indicated that different strategies were deployed by hippocampal and subiculum lesioned groups. Subsequent training on a delayed matching to place task revealed a deficit in all lesioned groups across a range of sample choice intervals, but the subiculum lesioned group was less impaired than the group with the hippocampal lesion. Finally, unoperated control rats given both the initial training and overtraining were later given either a hippocampal lesion or sham surgery. The hippocampal lesioned rats were impaired during a subsequent retention/relearning phase. Together, these findings suggest that total hippocampal cell loss may cause a dual deficit: a slower rate of place learning and a separate navigational impairment. The prospect of unravelling dissociable components of allocentric spatial learning is discussed.

Synthesis of polyhydroxyalkanoate in the peroxisome of Saccharomyces cerevisiae by using intermediates of fatty acid beta-oxidation.

Medium-chain-length polyhydroxyalkanoates (PHAs) are polyesters having properties of biodegradable thermoplastics and elastomers that are naturally produced by a variety of pseudomonads. Saccharomyces cerevisiae was transformed with the Pseudomonas aeruginosa PHAC1 synthase modified for peroxisome targeting by the addition of the carboxyl 34 amino acids from the Brassica napus isocitrate lyase. The PHAC1 gene was put under the control of the promoter of the catalase A gene. PHA synthase expression and PHA accumulation were found in recombinant S. cerevisiae growing in media containing fatty acids. PHA containing even-chain monomers from 6 to 14 carbons was found in recombinant yeast grown on oleic acid, while odd-chain monomers from 5 to 15 carbons were found in PHA from yeast grown on heptadecenoic acid. The maximum amount of PHA accumulated was 0.45% of the dry weight. Transmission electron microscopy of recombinant yeast grown on oleic acid revealed the presence of numerous PHA inclusions found within membrane-bound organelles. Together, these data show that S. cerevisiae expressing a peroxisomal PHA synthase produces PHA in the peroxisome using the 3-hydroxyacyl coenzyme A intermediates of the beta-oxidation of fatty acids present in the media. S. cerevisiae can thus be used as a powerful model system to learn how fatty acid metabolism can be modified in order to synthesize high amounts of PHA in eukaryotes, including plants.

Spatial prediction of monthly wind speeds in complex terrain with adaptive general regression neural networks

This paper presents the general regression neural networks (GRNN) as a nonlinear regression method for the interpolation of monthly wind speeds in complex Alpine orography. GRNN is trained using data coming from Swiss meteorological networks to learn the statistical relationship between topographic features and wind speed. The terrain convexity, slope and exposure are considered by extracting features from the digital elevation model at different spatial scales using specialised convolution filters. A database of gridded monthly wind speeds is then constructed by applying GRNN in prediction mode during the period 1968-2008. This study demonstrates that using topographic features as inputs in GRNN significantly reduces cross-validation errors with respect to low-dimensional models integrating only geographical coordinates and terrain height for the interpolation of wind speed. The spatial predictability of wind speed is found to be lower in summer than in winter due to more complex and weaker wind-topography relationships. The relevance of these relationships is studied using an adaptive version of the GRNN algorithm which allows to select the useful terrain features by eliminating the noisy ones. This research provides a framework for extending the low-dimensional interpolation models to high-dimensional spaces by integrating additional features accounting for the topographic conditions at multiple spatial scales. Copyright (c) 2012 Royal Meteorological Society.

Quality of Learners' Time and Learning Performance Beyond Quantitative Time-on-Task

Peer-reviewed

Rakentava ongelmanratkaisudialogi - tärkeä taito, joka tuntuu vaikealta oppia

Summary: Constructive problem solving dialogue - and important skill, but hard to learn

Personas adultas mayores y comunicación móvil: voz y SMS

Todavía sabemos poco sobre las formas de adopción, o rechazo, de la comunicación móvil por parte de las personas adultas mayores. ¿De qué manera utilizan la telefonía móvil? ¿Cuáles son los motivos de rechazo de este tipo de telefonía, si los hay?Discutimos los resultados de un caso de estudio cualitativo con personas adultas mayores (60 años o más), desarrollado en el área metropolitana de Montevideo en 2012. Los y las participantes valoran la conectividad permanente que brinda el teléfono móvil. Lo utilizan en combinación con otros canales, como el teléfono fijo, para una diversidad de objetivos y con diferentes interlocutores. Además de las llamadas de voz, los SMS son de uso habitual. Entre los no usuarios encontramos tanto el discurso del rechazo como el de la indiferencia hacia el celular. Finalmente, todos los usuarios de Internet son, también, usuarios de teléfono celular.

SiMR: A simulator for learning computer architecture

This paper presents SiMR, a simulator of the Rudimentary Machine designed to be used in a first course of computer architecture of Software Engineering and Computer Engineering programmes. The Rudimentary Machine contains all the basic elements in a RISC computer, and SiMR allows editing, assembling and executing programmes for this processor. SiMR is used at the Universitat Oberta de Catalunya as one of the most important resources in the Virtual Computing Architecture and Organisation Laboratory, since students work at home with the simulator and reports containing their work are automatically generated to be evaluated by lecturers. The results obtained from a survey show that most of the students consider SiMR as a highly necessary or even an indispensable resource to learn the basic concepts about computer architecture.

Drosophila rely on learning while foraging under semi-natural conditions

Learning is predicted to affect manifold ecological and evolutionary processes, but the extent to which animals rely on learning in nature remains poorly known, especially for short-lived non-social invertebrates. This is in particular the case for Drosophila, a favourite laboratory system to study molecular mechanisms of learning. Here we tested whether Drosophila melanogaster use learned information to choose food while free-flying in a large greenhouse emulating the natural environment. In a series of experiments flies were first given an opportunity to learn which of two food odours was associated with good versus unpalatable taste; subsequently, their preference for the two odours was assessed with olfactory traps set up in the greenhouse. Flies that had experienced palatable apple-flavoured food and unpalatable orange-flavoured food were more likely to be attracted to the odour of apple than flies with the opposite experience. This was true both when the flies first learned in the laboratory and were then released and recaptured in the greenhouse, and when the learning occurred under free-flying conditions in the greenhouse. Furthermore, flies retained the memory of their experience while exploring the greenhouse overnight in the absence of focal odours, pointing to the involvement of consolidated memory. These results support the notion that even small, short lived insects which are not central-place foragers make use of learned cues in their natural environments.