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.

A genome-wide screen for interactions reveals a new locus on 4p15 modifying the effect of waist-to-hip ratio on total cholesterol.

Recent genome-wide association (GWA) studies described 95 loci controlling serum lipid levels. These common variants explain ∼25% of the heritability of the phenotypes. To date, no unbiased screen for gene-environment interactions for circulating lipids has been reported. We screened for variants that modify the relationship between known epidemiological risk factors and circulating lipid levels in a meta-analysis of genome-wide association (GWA) data from 18 population-based cohorts with European ancestry (maximum N = 32,225). We collected 8 further cohorts (N = 17,102) for replication, and rs6448771 on 4p15 demonstrated genome-wide significant interaction with waist-to-hip-ratio (WHR) on total cholesterol (TC) with a combined P-value of 4.79×10(-9). There were two potential candidate genes in the region, PCDH7 and CCKAR, with differential expression levels for rs6448771 genotypes in adipose tissue. The effect of WHR on TC was strongest for individuals carrying two copies of G allele, for whom a one standard deviation (sd) difference in WHR corresponds to 0.19 sd difference in TC concentration, while for A allele homozygous the difference was 0.12 sd. Our findings may open up possibilities for targeted intervention strategies for people characterized by specific genomic profiles. However, more refined measures of both body-fat distribution and metabolic measures are needed to understand how their joint dynamics are modified by the newly found locus.

Quantification of Myocardial Perfusion Using 13N-ammonia PET: a Cross-Comparison Study on Analysis Software Packages - Carimas, PMOD and FlowQuant

Aim. Several software packages (SWP) and models have been released for quantification of myocardial perfusion (MP). Although they all are validated against something, the question remains how well their values agree. The present analysis focused on cross-comparison of three SWP for MP quantification of 13N-ammonia PET studies. Materials & Methods. 48 rest and stress MP 13N-ammonia PET studies of hypertrophic cardiomyopathy (HCM) patients (Sciagrà et al., 2009) were analysed with three SW packages - Carimas, PMOD, and FlowQuant - by three observers blinded to the results of each other. All SWP implement the one-tissue-compartment model (1TCM, DeGrado et al. 1996), and first two - the two-tissue-compartment model (2TCM, Hutchins et al. 1990) as well. Linear mixed model for the repeated measures was fitted to the data. Where appropriate we used Bland-Altman plots as well. The reproducibility was assessed on global, regional and segmental levels. Intraclass correlation coefficients (ICC), differences between the SWPs and between models were obtained. ICC≥0.75 indicated excellent reproducibility, 0.4≤ICC<0.75 indicated fair to good reproducibility, ICC<0.4 - poor reproducibility (Rosner, 2010). Results. When 1TCM MP values were compared, the SW agreement on global and regional levels was excellent, except for Carimas vs. PMOD at RCA: ICC=0.715 and for PMOD vs. FlowQuant at LCX:ICC=0.745 which were good. In segmental analysis in five segments: 7,12,13, 16, and 17 the agreement between all SWP was excellent; in the remaining 12 segments the agreement varied between the compared SWP. Carimas showed excellent agreement with FlowQuant in 13 segments and good in four - 1, 5, 6, 11: 0.687≤ICCs≤0.73; Carimas had excellent agreement with PMOD in 11 segments, good in five_4, 9, 10, 14, 15: 0.682≤ICCs≤0.737, and poor in segment 3: ICC=0.341. PMOD had excellent agreement with FlowQuant in eight segments and substantial-to-good in nine_1, 2, 3, 5, 6,8-11: 0.585≤ICCs≤0.738. Agreement between Carimas and PMOD for 2TCM was good at a global level: ICC=0.745, excellent at LCX (0.780) and RCA (0.774), good at LAD (0.662); agreement was excellent for ten segments, fair-to-substantial for segments 2, 3, 8, 14, 15 (0.431≤ICCs≤0.681), poor for segments 4 (0.384) and 17 (0.278). Conclusions. The three SWP used by different operators to analyse 13N-ammonia PET MP studies provide results that agree well at a global level, regional levels, and mostly well even at a segmental level. Agreement is better for 1TCM. Poor agreement at segments 4 and 17 for 2TCM needs further clarification.

Monitoring of noninvasive ventilation by built-in software of home bilevel ventilators: a bench study.

BACKGROUND: Current bilevel positive-pressure ventilators for home noninvasive ventilation (NIV) provide physicians with software that records items important for patient monitoring, such as compliance, tidal volume (Vt), and leaks. However, to our knowledge, the validity of this information has not yet been independently assessed. METHODS: Testing was done for seven home ventilators on a bench model adapted to simulate NIV and generate unintentional leaks (ie, other than of the mask exhalation valve). Five levels of leaks were simulated using a computer-driven solenoid valve (0-60 L/min) at different levels of inspiratory pressure (15 and 25 cm H(2)O) and at a fixed expiratory pressure (5 cm H(2)O), for a total of 10 conditions. Bench data were compared with results retrieved from ventilator software for leaks and Vt. RESULTS: For assessing leaks, three of the devices tested were highly reliable, with a small bias (0.3-0.9 L/min), narrow limits of agreement (LA), and high correlations (R(2), 0.993-0.997) when comparing ventilator software and bench results; conversely, for four ventilators, bias ranged from -6.0 L/min to -25.9 L/min, exceeding -10 L/min for two devices, with wide LA and lower correlations (R(2), 0.70-0.98). Bias for leaks increased markedly with the importance of leaks in three devices. Vt was underestimated by all devices, and bias (range, 66-236 mL) increased with higher insufflation pressures. Only two devices had a bias < 100 mL, with all testing conditions considered. CONCLUSIONS: Physicians monitoring patients who use home ventilation must be aware of differences in the estimation of leaks and Vt by ventilator software. Also, leaks are reported in different ways according to the device used.

HIV-1 capture and transmission by dendritic cells: the role of viral glycolipids and the cellular receptor Siglec-1.

Dendritic cells (DCs) are essential in order to combat invading viruses and trigger antiviral responses. Paradoxically, in the case of HIV-1, DCs might contribute to viral pathogenesis through trans-infection, a mechanism that promotes viral capture and transmission to target cells, especially after DC maturation. In this review, we highlight recent evidence identifying sialyllactose-containing gangliosides in the viral membrane and the cellular lectin Siglec-1 as critical determinants for HIV-1 capture and storage by mature DCs and for DC-mediated trans-infection of T cells. In contrast, DC-SIGN, long considered to be the main receptor for DC capture of HIV-1, plays a minor role in mature DC-mediated HIV-1 capture and trans-infection.

Targeted sequence capture and Ultra High Throughput sequencing for gene discovery in inherited diseases

L'introduction des technologies de séquençage de nouvelle génération est en vue de révolutionner la médecine moderne. L'impact de ces nouveaux outils a déjà contribué à la découverte de nouveaux gènes et de voies cellulaires impliqués dans la pathologie de maladies génétiques rares ou communes. En revanche, l'énorme quantité de données générées par ces systèmes ainsi que la complexité des analyses bioinformatiques nécessaires, engendre un goulet d'étranglement pour résoudre les cas les plus difficiles. L'objectif de cette thèse a été d'identifier les causes génétiques de deux maladies héréditaires utilisant ces nouvelles techniques de séquençage, couplées à des technologies d'enrichissement de gènes. Dans ce cadre, nous avons développé notre propre méthode de travail (pipeline) pour l'alignement des fragments de séquence (reads). Suite à l'identification de gènes, nous avons réalisé une analyse fonctionnelle pour élucider leur rôle dans la maladie. Dans un premier temps, nous avons étudié et identifié des mutations impliquées dans une forme récessive de la rétinite pigmentaire qui est à ce jour la dégénérescence rétinienne héréditaire la plus fréquente. En particulier, nous avons constaté que des mutations faux-sens dans le gène FAM161A étaient la cause de la rétinite pigmentaire préalablement associé avec le locus RP28. De plus, nous avons démontré que ce gène avait des fonctions au niveau du cil du photorécepteur, complétant le large spectre des cilliopathies rétiniennes héréditaires. Dans un second temps, nous avons exploré la possibilité qu'un syndrome, relativement fréquent en pédiatrie de fièvre récurrente, appelé PFAPA (acronyme de fièvre périodique avec adénite stomatite, pharyngite et cervical aphteuse) puisse avoir une origine génétique. L'étiologie de cette maladie n'étant pas claire, nous avons tenté d'identifier le spectre génétique de patients PFAPA. Comme nous n'avons pas pu mettre à jour un nouveau gène unique muté et responsable de la maladie chez tous les individus dépistés, il semblerait qu'un modèle génétique plus complexe suggérant l'implication de plusieurs gènes dans la pathologie ait été identifié chez les patients touchés. Ces gènes seraient notamment impliqués dans des processus liés à l'inflammation ce qui élargirait l'impact de ces études à d'autres maladies auto-inflammatoires.

Improving globally distributed software development and support processes - A workflow view

We propose a new approach and related indicators for globally distributed software support and development based on a 3-year process improvement project in a globally distributed engineering company. The company develops, delivers and supports a complex software system with tailored hardware components and unique end-customer installations. By applying the domain knowledge from operations management on lead time reduction and its multiple benefits to process performance, the workflows of globally distributed software development and multitier support processes were measured and monitored throughout the company. The results show that the global end-to-end process visibility and centrally managed reporting at all levels of the organization catalyzed a change process toward significantly better performance. Due to the new performance indicators based on lead times and their variation with fixed control procedures, the case company was able to report faster bug-fixing cycle times, improved response times and generally better customer satisfaction in its global operations. In all, lead times to implement new features and to respond to customer issues and requests were reduced by 50%.

The business model ontology a proposition in a design science approach

The goal of this dissertation is to find and provide the basis for a managerial tool that allows a firm to easily express its business logic. The methodological basis for this work is design science, where the researcher builds an artifact to solve a specific problem. In this case the aim is to provide an ontology that makes it possible to explicit a firm's business model. In other words, the proposed artifact helps a firm to formally describe its value proposition, its customers, the relationship with them, the necessary intra- and inter-firm infrastructure and its profit model. Such an ontology is relevant because until now there is no model that expresses a company's global business logic from a pure business point of view. Previous models essentially take an organizational or process perspective or cover only parts of a firm's business logic. The four main pillars of the ontology, which are inspired by management science and enterprise- and processmodeling, are product, customer interface, infrastructure and finance. The ontology is validated by case studies, a panel of experts and managers. The dissertation also provides a software prototype to capture a company's business model in an information system. The last part of the thesis consists of a demonstration of the value of the ontology in business strategy and Information Systems (IS) alignment. Structure of this thesis: The dissertation is structured in nine parts: Chapter 1 presents the motivations of this research, the research methodology with which the goals shall be achieved and why this dissertation present a contribution to research. Chapter 2 investigates the origins, the term and the concept of business models. It defines what is meant by business models in this dissertation and how they are situated in the context of the firm. In addition this chapter outlines the possible uses of the business model concept. Chapter 3 gives an overview of the research done in the field of business models and enterprise ontologies. Chapter 4 introduces the major contribution of this dissertation: the business model ontology. In this part of the thesis the elements, attributes and relationships of the ontology are explained and described in detail. Chapter 5 presents a case study of the Montreux Jazz Festival which's business model was captured by applying the structure and concepts of the ontology. In fact, it gives an impression of how a business model description based on the ontology looks like. Chapter 6 shows an instantiation of the ontology into a prototype tool: the Business Model Modelling Language BM2L. This is an XML-based description language that allows to capture and describe the business model of a firm and has a large potential for further applications. Chapter 7 is about the evaluation of the business model ontology. The evaluation builds on literature review, a set of interviews with practitioners and case studies. Chapter 8 gives an outlook on possible future research and applications of the business model ontology. The main areas of interest are alignment of business and information technology IT/information systems IS and business model comparison. Finally, chapter 9 presents some conclusions.

False normal Lung Clearance Index in infants with cystic fibrosis due to software algorithms.

BACKGROUND: Lung clearance index (LCI), a marker of ventilation inhomogeneity, is elevated early in children with cystic fibrosis (CF). However, in infants with CF, LCI values are found to be normal, although structural lung abnormalities are often detectable. We hypothesized that this discrepancy is due to inadequate algorithms of the available software package. AIM: Our aim was to challenge the validity of these software algorithms. METHODS: We compared multiple breath washout (MBW) results of current software algorithms (automatic modus) to refined algorithms (manual modus) in 17 asymptomatic infants with CF, and 24 matched healthy term-born infants. The main difference between these two analysis methods lies in the calculation of the molar mass differences that the system uses to define the completion of the measurement. RESULTS: In infants with CF the refined manual modus revealed clearly elevated LCI above 9 in 8 out of 35 measurements (23%), all showing LCI values below 8.3 using the automatic modus (paired t-test comparing the means, P < 0.001). Healthy infants showed normal LCI values using both analysis methods (n = 47, paired t-test, P = 0.79). The most relevant reason for false normal LCI values in infants with CF using the automatic modus was the incorrect recognition of the end-of-test too early during the washout. CONCLUSION: We recommend the use of the manual modus for the analysis of MBW outcomes in infants in order to obtain more accurate results. This will allow appropriate use of infant lung function results for clinical and scientific purposes. Pediatr Pulmonol. 2015; 50:970-977. © 2015 Wiley Periodicals, Inc.

MRI/TRUS fusion software-based targeted biopsy: the new standard of care?

The advent of multiparametric MRI has made it possible to change the way in which prostate biopsy is done, allowing to direct biopsies to suspicious lesions rather than randomly. The subject of this review relates to a computer-assisted strategy, the MRI/US fusion software-based targeted biopsy, and to its performance compared to the other sampling methods. Different devices with different methods to register MR images to live TRUS are currently in use to allow software-based targeted biopsy. Main clinical indications of MRI/US fusion software-based targeted biopsy are re-biopsy in men with persistent suspicious of prostate cancer after first negative standard biopsy and the follow-up of patients under active surveillance. Some studies have compared MRI/US fusion software-based targeted versus standard biopsy. In men at risk with MRI-suspicious lesion, targeted biopsy consistently detects more men with clinically significant disease as compared to standard biopsy; some studies have also shown decreased detection of insignificant disease. Only two studies directly compared MRI/US fusion software-based targeted biopsy with MRI/US fusion visual targeted biopsy, and the diagnostic ability seems to be in favor of the software approach. To date, no study comparing software-based targeted biopsy against in-bore MRI biopsy is available. The new software-based targeted approach seems to have the characteristics to be added in the standard pathway for achieving accurate risk stratification. Once reproducibility and cost-effectiveness will be verified, the actual issue will be to determine whether MRI/TRUS fusion software-based targeted biopsy represents anadd-on test or a replacement to standard TRUS biopsy.

Cardiovascular risk among hypertensive adolescents and the potential benefit of a screen-and-treat strategy.

To evaluate whether screening for hypertension should start early in life, information on the risk of diseases associated with the level of blood pressure in childhood or adolescence is needed. The study by Leiba et al. that is reported in the current issue of Pediatric Nephrology demonstrates convincingly that hypertensive adolescents are at higher risk of cardiovascular death than normotensive adolescents. Nevertheless, it can be shown that this excess risk is not sufficient to justify a screen-and-treat strategy. Since the large majority of cardiovascular deaths occur among normotensive adolescents, measures for primordial prevention of cardiovascular diseases could have a much larger impact at the population level.

Enhanced capture of healthcare-related harms and injuries in the 11th revision of the International Classification of Diseases (ICD-11).

The World Health Organization (WHO) plans to submit the 11th revision of the International Classification of Diseases (ICD) to the World Health Assembly in 2018. The WHO is working toward a revised classification system that has an enhanced ability to capture health concepts in a manner that reflects current scientific evidence and that is compatible with contemporary information systems. In this paper, we present recommendations made to the WHO by the ICD revision's Quality and Safety Topic Advisory Group (Q&S TAG) for a new conceptual approach to capturing healthcare-related harms and injuries in ICD-coded data. The Q&S TAG has grouped causes of healthcare-related harm and injuries into four categories that relate to the source of the event: (a) medications and substances, (b) procedures, (c) devices and (d) other aspects of care. Under the proposed multiple coding approach, one of these sources of harm must be coded as part of a cluster of three codes to depict, respectively, a healthcare activity as a 'source' of harm, a 'mode or mechanism' of harm and a consequence of the event summarized by these codes (i.e. injury or harm). Use of this framework depends on the implementation of a new and potentially powerful code-clustering mechanism in ICD-11. This new framework for coding healthcare-related harm has great potential to improve the clinical detail of adverse event descriptions, and the overall quality of coded health data.