Automatic Mapping and Classification of Spatial Environmental Data

The paper deals with the development and application of the generic methodology for automatic processing (mapping and classification) of environmental data. General Regression Neural Network (GRNN) is considered in detail and is proposed as an efficient tool to solve the problem of spatial data mapping (regression). The Probabilistic Neural Network (PNN) is considered as an automatic tool for spatial classifications. The automatic tuning of isotropic and anisotropic GRNN/PNN models using cross-validation procedure is presented. Results are compared with the k-Nearest-Neighbours (k-NN) interpolation algorithm using independent validation data set. Real case studies are based on decision-oriented mapping and classification of radioactively contaminated territories.

Multitask learning of environmental spatial data

The present research deals with an application of artificial neural networks for multitask learning from spatial environmental data. The real case study (sediments contamination of Geneva Lake) consists of 8 pollutants. There are different relationships between these variables, from linear correlations to strong nonlinear dependencies. The main idea is to construct a subsets of pollutants which can be efficiently modeled together within the multitask framework. The proposed two-step approach is based on: 1) the criterion of nonlinear predictability of each variable ?k? by analyzing all possible models composed from the rest of the variables by using a General Regression Neural Network (GRNN) as a model; 2) a multitask learning of the best model using multilayer perceptron and spatial predictions. The results of the study are analyzed using both machine learning and geostatistical tools.

Data-driven clustering : new methods and applications

Abstract : This work is concerned with the development and application of novel unsupervised learning methods, having in mind two target applications: the analysis of forensic case data and the classification of remote sensing images. First, a method based on a symbolic optimization of the inter-sample distance measure is proposed to improve the flexibility of spectral clustering algorithms, and applied to the problem of forensic case data. This distance is optimized using a loss function related to the preservation of neighborhood structure between the input space and the space of principal components, and solutions are found using genetic programming. Results are compared to a variety of state-of--the-art clustering algorithms. Subsequently, a new large-scale clustering method based on a joint optimization of feature extraction and classification is proposed and applied to various databases, including two hyperspectral remote sensing images. The algorithm makes uses of a functional model (e.g., a neural network) for clustering which is trained by stochastic gradient descent. Results indicate that such a technique can easily scale to huge databases, can avoid the so-called out-of-sample problem, and can compete with or even outperform existing clustering algorithms on both artificial data and real remote sensing images. This is verified on small databases as well as very large problems. Résumé : Ce travail de recherche porte sur le développement et l'application de méthodes d'apprentissage dites non supervisées. Les applications visées par ces méthodes sont l'analyse de données forensiques et la classification d'images hyperspectrales en télédétection. Dans un premier temps, une méthodologie de classification non supervisée fondée sur l'optimisation symbolique d'une mesure de distance inter-échantillons est proposée. Cette mesure est obtenue en optimisant une fonction de coût reliée à la préservation de la structure de voisinage d'un point entre l'espace des variables initiales et l'espace des composantes principales. Cette méthode est appliquée à l'analyse de données forensiques et comparée à un éventail de méthodes déjà existantes. En second lieu, une méthode fondée sur une optimisation conjointe des tâches de sélection de variables et de classification est implémentée dans un réseau de neurones et appliquée à diverses bases de données, dont deux images hyperspectrales. Le réseau de neurones est entraîné à l'aide d'un algorithme de gradient stochastique, ce qui rend cette technique applicable à des images de très haute résolution. Les résultats de l'application de cette dernière montrent que l'utilisation d'une telle technique permet de classifier de très grandes bases de données sans difficulté et donne des résultats avantageusement comparables aux méthodes existantes.

Viscoelasticity in Achilles Tendonopathy: Quantitative Assessment by Using Real-time Shear-Wave Elastography.

Purpose To investigate the differences in viscoelastic properties between normal and pathologic Achilles tendons ( AT Achilles tendon s) by using real-time shear-wave elastography ( SWE shear-wave elastography ). Materials and Methods The institutional review board approved this study, and written informed consent was obtained from 25 symptomatic patients and 80 volunteers. One hundred eighty ultrasonographic (US) and SWE shear-wave elastography studies of AT Achilles tendon s without tendonopathy and 30 studies of the middle portion of the AT Achilles tendon in patients with tendonopathy were assessed prospectively. Each study included data sets acquired at B-mode US (tendon morphology and cross-sectional area) and SWE shear-wave elastography (axial and sagittal mean velocity and relative anisotropic coefficient) for two passively mobilized ankle positions. The presence of AT Achilles tendon tears at B-mode US and signal-void areas at SWE shear-wave elastography were noted. Results Significantly lower mean velocity was shown in tendons with tendonopathy than in normal tendons in the relaxed position at axial SWE shear-wave elastography (P < .001) and in the stretched position at sagittal (P < .001) and axial (P = .0026) SWE shear-wave elastography . Tendon softening was a sign of tendonopathy in relaxed AT Achilles tendon s when the mean velocity was less than or equal to 4.06 m · sec(-1) at axial SWE shear-wave elastography (sensitivity, 54.2%; 95% confidence interval [ CI confidence interval ]: 32.8, 74.4; specificity, 91.5%; 95% CI confidence interval : 86.3, 95.1) and less than or equal to 5.70 m · sec(-1) at sagittal SWE shear-wave elastography (sensitivity, 41.7%; 95% CI confidence interval : 22.1, 63.3; specificity, 81.8%; 95% CI confidence interval : 75.3, 87.2) and in stretched AT Achilles tendon s, when the mean velocity was less than or equal to 4.86 m · sec(-1) at axial SWE shear-wave elastography (sensitivity, 66.7%; 95% CI confidence interval : 44.7, 84.3; specificity, 75.6%; 95% CI confidence interval : 68.5, 81.7) and less than or equal to 14.58 m · sec(-1) at sagittal SWE shear-wave elastography (sensitivity, 58.3%; 95% CI confidence interval : 36.7, 77.9; specificity, 83.5%; 95% CI confidence interval : 77.2, 88.7). Anisotropic results were not significantly different between normal and pathologic AT Achilles tendon s. Six of six (100%) partial-thickness tears appeared as signal-void areas at SWE shear-wave elastography . Conclusion Whether the AT Achilles tendon was relaxed or stretched, SWE shear-wave elastography helped to confirm and quantify pathologic tendon softening in patients with tendonopathy in the midportion of the AT Achilles tendon and did not reveal modifications of viscoelastic anisotropy in the tendon. Tendon softening assessed by using SWE shear-wave elastography appeared to be highly specific, but sensitivity was relatively low. © RSNA, 2014.

Monitoring network optimisation for spatial data classification using support vector machines

The paper presents a novel method for monitoring network optimisation, based on a recent machine learning technique known as support vector machine. It is problem-oriented in the sense that it directly answers the question of whether the advised spatial location is important for the classification model. The method can be used to increase the accuracy of classification models by taking a small number of additional measurements. Traditionally, network optimisation is performed by means of the analysis of the kriging variances. The comparison of the method with the traditional approach is presented on a real case study with climate data.

Multiple Kernel Learning of Environmental Data. Case study: Analysis and Mapping of Wind Fields

The paper presents the Multiple Kernel Learning (MKL) approach as a modelling and data exploratory tool and applies it to the problem of wind speed mapping. Support Vector Regression (SVR) is used to predict spatial variations of the mean wind speed from terrain features (slopes, terrain curvature, directional derivatives) generated at different spatial scales. Multiple Kernel Learning is applied to learn kernels for individual features and thematic feature subsets, both in the context of feature selection and optimal parameters determination. An empirical study on real-life data confirms the usefulness of MKL as a tool that enhances the interpretability of data-driven models.

Using Scanning Lasers for Real-Time Pavement Thickness Measurement, TR-538, 2006

Due to limited budgets and reduced inspection staff, state departments of transportation (DOTs) are in need of innovative approaches for providing more efficient quality assurance on concrete paving projects. The goal of this research was to investigate and test new methods that can determine pavement thickness in real time. Three methods were evaluated: laser scanning, ultrasonic sensors, and eddy current sensors. Laser scanning, which scans the surface of the base prior to paving and then scans the surface after paving, can determine the thickness at any point. Also, scanning lasers provide thorough data coverage that can be used to calculate thickness variance accurately and identify any areas where the thickness is below tolerance. Ultrasonic and eddy current sensors also have the potential to measure thickness nondestructively at discrete points and may result in an easier method of obtaining thickness. There appear to be two viable approaches for measuring concrete pavement thickness during the paving operation: laser scanning and eddy current sensors. Laser scanning has proved to be a reliable technique in terms of its ability to provide virtual core thickness with low variability. Research is still required to develop a prototype system that integrates point cloud data from two scanners. Eddy current sensors have also proved to be a suitable alternative, and are probably closer to field implementation than the laser scanning approach. As a next step for this research project, it is suggested that a pavement thickness measuring device using eddy current sensors be created, which would involve both a handheld and paver-mounted version of the device.

Evaluating effects of spectral training data distribution on continuous field mapping performance

Continuous field mapping has to address two conflicting remote sensing requirements when collecting training data. On one hand, continuous field mapping trains fractional land cover and thus favours mixed training pixels. On the other hand, the spectral signature has to be preferably distinct and thus favours pure training pixels. The aim of this study was to evaluate the sensitivity of training data distribution along fractional and spectral gradients on the resulting mapping performance. We derived four continuous fields (tree, shrubherb, bare, water) from aerial photographs as response variables and processed corresponding spectral signatures from multitemporal Landsat 5 TM data as explanatory variables. Subsequent controlled experiments along fractional cover gradients were then based on generalised linear models. Resulting fractional and spectral distribution differed between single continuous fields, but could be satisfactorily trained and mapped. Pixels with fractional or without respective cover were much more critical than pure full cover pixels. Error distribution of continuous field models was non-uniform with respect to horizontal and vertical spatial distribution of target fields. We conclude that a sampling for continuous field training data should be based on extent and densities in the fractional and spectral, rather than the real spatial space. Consequently, adequate training plots are most probably not systematically distributed in the real spatial space, but cover the gradient and covariate structure of the fractional and spectral space well. (C) 2009 International Society for Photogrammetry and Remote Sensing, Inc. (ISPRS). Published by Elsevier B.V. All rights reserved.

Data-driven topo-climatic mapping with machine learning methods

Automatic environmental monitoring networks enforced by wireless communication technologies provide large and ever increasing volumes of data nowadays. The use of this information in natural hazard research is an important issue. Particularly useful for risk assessment and decision making are the spatial maps of hazard-related parameters produced from point observations and available auxiliary information. The purpose of this article is to present and explore the appropriate tools to process large amounts of available data and produce predictions at fine spatial scales. These are the algorithms of machine learning, which are aimed at non-parametric robust modelling of non-linear dependencies from empirical data. The computational efficiency of the data-driven methods allows producing the prediction maps in real time which makes them superior to physical models for the operational use in risk assessment and mitigation. Particularly, this situation encounters in spatial prediction of climatic variables (topo-climatic mapping). In complex topographies of the mountainous regions, the meteorological processes are highly influenced by the relief. The article shows how these relations, possibly regionalized and non-linear, can be modelled from data using the information from digital elevation models. The particular illustration of the developed methodology concerns the mapping of temperatures (including the situations of Föhn and temperature inversion) given the measurements taken from the Swiss meteorological monitoring network. The range of the methods used in the study includes data-driven feature selection, support vector algorithms and artificial neural networks.

Machine learning for spatial environmental data. Theory, applications and software

The book presents the state of the art in machine learning algorithms (artificial neural networks of different architectures, support vector machines, etc.) as applied to the classification and mapping of spatially distributed environmental data. Basic geostatistical algorithms are presented as well. New trends in machine learning and their application to spatial data are given, and real case studies based on environmental and pollution data are carried out. The book provides a CD-ROM with the Machine Learning Office software, including sample sets of data, that will allow both students and researchers to put the concepts rapidly to practice.

A Smartphone-Based Prototype System for Incident/Work Zone Management Driven by Crowd-Sourced Data, 2015

This project develops a smartphone-based prototype system that supplements the 511 system to improve its dynamic traffic routing service to state highway users under non-recurrent congestion. This system will save considerable time to provide crucial traffic information and en-route assistance to travelers for them to avoid being trapped in traffic congestion due to accidents, work zones, hazards, or special events. It also creates a feedback loop between travelers and responsible agencies that enable the state to effectively collect, fuse, and analyze crowd-sourced data for next-gen transportation planning and management. This project can result in substantial economic savings (e.g. less traffic congestion, reduced fuel wastage and emissions) and safety benefits for the freight industry and society due to better dissemination of real-time traffic information by highway users. Such benefits will increase significantly in future with the expected increase in freight traffic on the network. The proposed system also has the flexibility to be integrated with various transportation management modules to assist state agencies to improve transportation services and daily operations.

Navigator-gated and real-time motion corrected free-breathing MR Imaging of myocardial late enhancement.

PURPOSE: A new magnetic resonance imaging approach for detection of myocardial late enhancement during free-breathing was developed. METHODS AND RESULTS: For suppression of respiratory motion artifacts, a prospective navigator technology including real-time motion correction and a local navigator restore was implemented. Subject specific inversion times were defined from images with incrementally increased inversion times acquired during a single dynamic scout navigator-gated and real-time motion corrected free-breathing scan. Subsequently, MR-imaging of myocardial late enhancement was performed with navigator-gated and real-time motion corrected adjacent short axis and long axis (two, three and four chamber) views. This alternative approach was investigated in 7 patients with history of myocardial infarction 12 min after i. v. administration of 0.2 mmol/kg body weight gadolinium-DTPA. CONCLUSION: With the presented navigator-gated and real-time motion corrected sequence for MR-imaging of myocardial late enhancement data can be completely acquired during free-breathing. Time constraints of a breath-hold technique are abolished and optimized patient specific inversion time is ensured.

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.

Identification of reference genes for expression analysis by real-time quantitative PCR in drought-stressed soybean

The objective of this work was to validate, by quantitative PCR in real time (RT-qPCR), genes to be used as reference in studies of gene expression in soybean in drought-stressed trials. Four genes commonly used in soybean were evaluated: Gmβ-actin, GmGAPDH, GmLectin and GmRNAr18S. Total RNA was extracted from six samples: three from roots in a hydroponic system with different drought intensities (0, 25, 50, 75 and 100 minutes of water stress), and three from leaves of plants grown in sand with different soil moistures (15, 5 and 2.5% gravimetric humidity). The raw cycle threshold (Ct) data were analyzed, and the efficiency of each primer was calculated for an overall analysis of the Ct range among the different samples. The GeNorm application was used to evaluate the best reference gene, according to its stability. The GmGAPDH was the least stable gene, with the highest mean values of expression stability (M), and the most stable genes, with the lowest M values, were the Gmβ-actin and GmRNAr18S, when both root and leaves samples were tested. These genes can be used in RT-qPCR as reference gene for expression analysis.

Addressing current treatment challenges in Crohn's disease in real life: A physician's survey.

BACKGROUND: In recent years several trials have addressed treatment challenges in Crohn's disease. Clinical trials however, represent a very special situation. AIMS: To perform a cross-sectional survey among gastroenterologists on the current clinical real life therapeutic approach focussing on the use of biologics. METHODS: A survey including six main questions on clinical management of loss of response, diagnostic evaluation prior to major treatment changes, preference for anti-tumour necrosis factor (TNF) agent, (de-)escalation strategies as well as a basic section regarding personal information was sent by mail to all gastroenterologists in Switzerland (n=318). RESULTS: In total, 120 questionnaires were analysed (response rate 37.7%). 90% of gastroenterologists in Switzerland use a thiopurine as the first step-up strategy (anti-TNF alone 7.5%, combination 2.5%). To address loss of response, most physicians prefer shortening the interval of anti-TNF administration followed by dose increase, switching the biologic and adding a thiopurine. In case of prolonged remission on combination therapy, the thiopurine is stopped first (52.6%) after a mean treatment duration of 15.7 months (biologic first in 41.4%). CONCLUSIONS: Everyday clinical practice in Crohn's disease patients appears to be incongruent with clinical data derived from major trials. Studies investigating reasons underlying these discrepancies are of need to optimize and harmonize treatment.