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.

Training Diaries during Altitude Training Camp in Two Olympic Champions: An Observational Case Study.

Traditionally, Live High-Train High (LHTH) interventions were adopted when athletes trained and lived at altitude to try maximising the benefits offered by hypoxic exposure and improving sea level performance. Nevertheless, scientific research has proposed that the possible benefits of hypoxia would be offset by the inability to maintain high training intensity at altitude. However, elite athletes have been rarely recruited as an experimental sample, and training intensity has almost never been monitored during altitude research. This case study is an attempt to provide a practical example of successful LHTH interventions in two Olympic gold medal athletes. Training diaries were collected and total training volumes, volumes at different intensities, and sea level performance recorded before, during and after a 3-week LHTH camp. Both athletes successfully completed the LHTH camp (2090 m) maintaining similar absolute training intensity and training volume at high-intensity (> 91% of race pace) compared to sea level. After the LHTH intervention both athletes obtained enhancements in performance and they won an Olympic gold medal. In our opinion, LHTH interventions can be used as a simple, yet effective, method to maintain absolute, and improve relative training intensity in elite endurance athletes. Key PointsElite endurance athletes, with extensive altitude training experience, can maintain similar absolute intensity during LHTH compared to sea level.LHTH may be considered as an effective method to increase relative training intensity while maintaining the same running/walking pace, with possible beneficial effects on sea level performance.Training intensity could be the key factor for successful high-level LHTH camp.

Workforce Training and Economic Development Fund Annual Progress Report, 2014 December 9, 2014

The Department of Education, Division of Community Colleges, will annually provide the State Board of Education with the Workforce Training and Economic Development Fund Annual Progress Report. Administration and oversight responsibility for the fund was transferred from the Iowa Economic Development Authority to the Iowa Department of Education effective July 1, 2013 (FY 2014). This report is the first annual progress report produced and distributed by the Iowa Department of Education. The full report outlines the programs, projects, and initiatives that the community colleges have implemented during the past fiscal year.

TFC-J2EE: Web Training Diary

Els present document te com objectiu detallar el procés que s¿ha dut a terme per la implementació d¿una aplicació que permeti a un esportista l¿enregistrament tant de entrenaments com competicions. Per la implementació de dita aplicació s¿ha escollit Java com a llenguatge de programació i concretament J2EE com la arquitectura a utilitzar.

Effect of an 8-weeks aerobic training program in elderly on oxidative stress and HSP72 expression in leukocytes during antioxidant supplementation.

OBJECTIVE: To investigate the effect of aerobic training in the context of antioxidant supplementation on systemic oxidative stress and leukocytes heat shock protein (Hsp)72 expression in the elderly. DESIGN: Sixteen septuagenarians (8 males and 8 females, mean age 74.6) were supplemented with Vitamin C and E (respectively 500 and 100mg per day) and randomly assigned either to sedentary (AS) or individualized aerobically trained (AT) group for 8 weeks. METHODS: Plasma Vitamin C and E concentrations and aerobic fitness, as well as resting and post graded exercise (GXT) Hsp72 expression in leukocytes, plasma levels of thiobarbituric acid reactive substances (TBARS) and advanced oxidation protein product (AOPP) were measured pre and post training / supplementation. RESULTS: At the end of the intervention, the two groups showed a significant increase in resting plasma vitamin C and E (approximately 50 and 20% increase respectively) and a significant decrease in both resting and post GXT plasma TBARS and AOPP (approximately 25 and 20% decrease respectively). These changes were of similar magnitude in the two groups. The reduced oxidative stress was concomitant with a 15% decreased expression of Hsp72 in monocytes and granulocytes in both groups. CONCLUSION: This study provides evidence that in elderly, increased concentration of antioxidant vitamins C and E is associated with a reduction in oxidative stress and leukocytes Hsp72. In this context, 8 weeks of aerobic training has no impact on oxidative stress or leukocytes Hsp72 expression in elderly people.

Developing an Effective Construction Training Program for Hispanic and American Supervisors and Craft Workers, 2007

Hispanics are a large and growing part of the United States workforce. Projections of the U.S. Census Bureau (2001) state that, by the year 2050, Hispanics will account for 25% of the population. For the Midwest in particular, the Hispanic population is expected to increase 35% by the year 2025. The construction industry is expected to experience a greater percentage increase of its Hispanic population, due to the labor-intensive nature of the industry. This study addresses the expected increase of Hispanic workers in the construction industry by testing the best approaches for delivering training to construction crews with Hispanic workers as well as American supervisors and laborers in the state of Iowa. The research methodology consisted of assessing the effects on communication, safety, work environment, and productivity as a result of the integration training. Results show that integration on-site training decreases workers’ desire to move and increases quality of work and productivity. Most importantly, experimental design was used to show the increasing levels of direct construction communication due to the Toolbox Integration Course for Hispanic Workers and American Supervisors (TICHA) designed as part of this project. This study recommends the creation of a quasi-governmental or association program that can offer continuous research and training that can benefit the construction industry as well as society as a whole. The industry involvement in this process is crucial for contractors. Not only do contractors benefit from reduced insurance premiums when workers act safely, but workers with better communication skills are more productive.

Developing an Effective Construction Training Program for American Supervisors with Hispanic Craft Workers, 2005

In the construction industry, Hispanics have the highest rate of fatal work injuries among the racial/ethnic groups, and productivity in the field is limited by the language barrier between Hispanic workers and their supervisors and the level of education of many Hispanic craft workers. This research developed a training program designed to facilitate the integration process between American supervisors and Hispanic craft workers in a practical and cost-effective way, thus improving productivity and lowering fatality rates. The Iowa State University research team conducted a survey of 38 American supervisors, representing 14 Iowa construction companies. Survey results confirm that communication is the main problem experienced by American supervisors in the job site. Many American supervisors also use or depend on a link-person (an individual who interprets tasks to the rest of the Hispanic crew) to communicate to the Hispanic crew members. Research findings show that language differences affect productivity and workplace safety in the construction industry. Additionally, the educational levels of Hispanic workers indicate that they may not have the literacy skills necessary to understand training materials. This research developed two training courses designed to expand the Spanish communication skills of American supervisors. The research team modified the English-as-a-second-language course developed in Phase I into the Spanish as a Second Language (SSL) Survival Course. A series of technical training courses were also developed, titled Concrete Pavement Construction Basics (CPCB), that cover general practices in concrete pavement construction. They are much shorter and more specialized than the SSL course. The CPCB courses provide American supervisors simple and practical communication tools on a variety of topics to choose from according to their specific needs.

Diurnal and exercise-related variability of haemoglobin and reticulocytes in athletes.

Haemoglobin (Hb) and Reticulocytes (Ret) are measured as indirect markers of doping in athletes. We studied the diurnal variation, the impact of exercise, fluid intake and ambient temperature in athletes on these parameters. Hourly venous blood samples were obtained from 36 male athletes of different disciplines (endurance (END) and non-endurance (NON-END)) over 12 h during a typical training day. Seven inactive subjects served as controls (CON). Hb and Ret were determined. A mixed model procedure was used to analyse the data. At baseline, Hb was similar for all groups, END showed lower Ret than NON-END and CON. Exercise showed a significant impact on Hb (+0.46 g/dl, p<0.001), the effect disappeared approximately 2 h after exercise. Hb decreased over the day by approximately 0.55 g/dl (p<0.01). There was no relevant effect on Ret. Fluid intake and ambient temperature had no significant effect. Hb shows significant diurnal- and exercise related variations. In an anti-doping context, most of these variations are in favour of the athlete. Blood samples taken after exercise might therefore provide reliable results and thus be used for the longitudinal monitoring of athletes if a timeframe for the re-equilibration of vascular volumes is respected.

Camp Dodge Joint Maneuver Training, February 10, 2012

Th e Warrior Ready is an offi cial publication authorized under the provisions of AR 360-1. It is published electronically by the Iowa National Guard State Public Aff airs Offi ce on a monthly basis. News and opinions expressed in this publication are not necessarily those of the Adjutant General of Iowa, the National Guard, or the Department of Defense.

Communication skills training in oncology: it works!

While the previous chapter by L. Fallowfield and V. Jenkins focuses on different communication skills training (CST) concepts currently being utilized, this chapter reviews and comments the scientific evidence of the impact of CST on improving communication skills. The aim of this chapter is not to provide a complete review of the evidence-this has already been done in systematic reviews-but to discuss the scientific evidence and reflect on the available results and relevant topics for further investigations.

Maltraitance: une formation évaluée à dix ans: Une démarche originale [Abuse: training evaluated at 10 years: an original approach]

[Introduction (extrait)] Il existe de nombreuses formations destinées à prévenir la maltraitance envers les personnes âgées. A ce jour, leur efficacité n'est cependant pas prouvée, faute d'évaluation de leur impact sur les pratiques professionnelles. La formation PREMALPA, qui existe depuis 2003, a fait l'objet d'une évaluation en 2013.

A course on collaboration between social workers and general practitioners during their vocational training

The educational programme reported was an experiment in the vocational training scheme of the department of General Practice, Erasmus University, Rotterdam, Holland, and is now part of the course. The programme focused on the training in team function (co-operation) given to trainee GPs and social workers. It became clear that both groups during their professional training develop markedly different attitudes and views about patient (client) care. These differences form a fundamental handicap in any discussion about teamwork. During the programme the students were made aware of this divergence of viewpoint and were taught how to handle these resulting handicaps and, if possible, to eliminate them.

Learning in the working place: the educational potential of a multihead microscope in pathology postgraduate training.

Training future pathologists is an important mission of many hospital anatomic pathology departments. Apprenticeship-a process in which learning and teaching tightly intertwine with daily work, is one of the main educational methods in use in postgraduate medical training. However, patient care, including pathological diagnosis, often comes first, diagnostic priorities prevailing over educational ones. Recognition of the unique educational opportunities is a prerequisite for enhancing the postgraduate learning experience. The aim of this paper is to draw attention of senior pathologists with a role as supervisor in postgraduate training on the potential educational value of a multihead microscope, a common setting in pathology departments. After reporting on an informal observation of senior and junior pathologists' meetings around the multihead microscope in our department, we review the literature on current theories of learning to provide support to the high potential educational value of these meetings for postgraduate training in pathology. We also draw from the literature on learner-centered teaching some recommendations to better support learning in this particular context. Finally, we propose clues for further studies and effective instruction during meetings around a multihead microscope.