Machine learning algorithms for spatial data. Case studies: Environmental pollution, natural hazards, renewable resources

This paper presents general problems and approaches for the spatial data analysis using machine learning algorithms. Machine learning is a very powerful approach to adaptive data analysis, modelling and visualisation. The key feature of the machine learning algorithms is that they learn from empirical data and can be used in cases when the modelled environmental phenomena are hidden, nonlinear, noisy and highly variable in space and in time. Most of the machines learning algorithms are universal and adaptive modelling tools developed to solve basic problems of learning from data: classification/pattern recognition, regression/mapping and probability density modelling. In the present report some of the widely used machine learning algorithms, namely artificial neural networks (ANN) of different architectures and Support Vector Machines (SVM), are adapted to the problems of the analysis and modelling of geo-spatial data. Machine learning algorithms have an important advantage over traditional models of spatial statistics when problems are considered in a high dimensional geo-feature spaces, when the dimension of space exceeds 5. Such features are usually generated, for example, from digital elevation models, remote sensing images, etc. An important extension of models concerns considering of real space constrains like geomorphology, networks, and other natural structures. Recent developments in semi-supervised learning can improve modelling of environmental phenomena taking into account on geo-manifolds. An important part of the study deals with the analysis of relevant variables and models' inputs. This problem is approached by using different feature selection/feature extraction nonlinear tools. To demonstrate the application of machine learning algorithms several interesting case studies are considered: digital soil mapping using SVM, automatic mapping of soil and water system pollution using ANN; natural hazards risk analysis (avalanches, landslides), assessments of renewable resources (wind fields) with SVM and ANN models, etc. The dimensionality of spaces considered varies from 2 to more than 30. Figures 1, 2, 3 demonstrate some results of the studies and their outputs. Finally, the results of environmental mapping are discussed and compared with traditional models of geostatistics.

Optimization of treatment with interferon beta in multiple sclerosis. Usefulness of automatic system application criteria

Background. A software based tool has been developed (Optem) to allow automatize the recommendations of the Canadian Multiple Sclerosis Working Group for optimizing MS treatment in order to avoid subjective interpretation. METHODS: Treatment Optimization Recommendations (TORs) were applied to our database of patients treated with IFN beta1a IM. Patient data were assessed during year 1 for disease activity, and patients were assigned to 2 groups according to TOR: "change treatment" (CH) and "no change treatment" (NCH). These assessments were then compared to observed clinical outcomes for disease activity over the following years. RESULTS: We have data on 55 patients. The "change treatment" status was assigned to 22 patients, and "no change treatment" to 33 patients. The estimated sensitivity and specificity according to last visit status were 73.9% and 84.4%. During the following years, the Relapse Rate was always higher in the "change treatment" group than in the "no change treatment" group (5 y; CH: 0.7, NCH: 0.07; p < 0.001, 12 m - last visit; CH: 0.536, NCH: 0.34). We obtained the same results with the EDSS (4 y; CH: 3.53, NCH: 2.55, annual progression rate in 12 m - last visit; CH: 0.29, NCH: 0.13). CONCLUSION: Applying TOR at the first year of therapy allowed accurate prediction of continued disease activity in relapses and disability progression.

Overview of coded light projection techniques for automatic 3D profiling

Obtaining automatic 3D profile of objects is one of the most important issues in computer vision. With this information, a large number of applications become feasible: from visual inspection of industrial parts to 3D reconstruction of the environment for mobile robots. In order to achieve 3D data, range finders can be used. Coded structured light approach is one of the most widely used techniques to retrieve 3D information of an unknown surface. An overview of the existing techniques as well as a new classification of patterns for structured light sensors is presented. This kind of systems belong to the group of active triangulation method, which are based on projecting a light pattern and imaging the illuminated scene from one or more points of view. Since the patterns are coded, correspondences between points of the image(s) and points of the projected pattern can be easily found. Once correspondences are found, a classical triangulation strategy between camera(s) and projector device leads to the reconstruction of the surface. Advantages and constraints of the different patterns are discussed

Who we are and who can join us: National identity content and entry criteria for new immigrants

We argue that attitudes about immigration can be better understood by paying closer attention to the various ways in which national group boundaries are demarcated. We describe two related lines of work that address this. The first deals with national group definitions and, based on evidence from studies carried out in England and analyses of international survey data, argues that the relationship between national identification and prejudice toward immigrants is contingent on the extent to which ethnic or civic definitions of nationality are endorsed. The second, which uses European survey data, examines support for ascribed and acquired criteria that can be applied when determining who is permitted to migrate to one's country, and the various forms of national and individual threat that affect support for these criteria. We explain how the research benefits from a multilevel approach and also suggest how these findings relate to some current policy debates.

Segmentation and grid generation for numerical simulations of vad connections with patient-specific data

Objectives: We are interested in the numerical simulation of the anastomotic region comprised between outflow canula of LVAD and the aorta. Segmenta¬tion, geometry reconstruction and grid generation from patient-specific data remain an issue because of the variable quality of DICOM images, in particular CT-scan (e.g. metallic noise of the device, non-aortic contrast phase). We pro¬pose a general framework to overcome this problem and create suitable grids for numerical simulations.Methods: Preliminary treatment of images is performed by reducing the level window and enhancing the contrast of the greyscale image using contrast-limited adaptive histogram equalization. A gradient anisotropic diffusion filter is applied to reduce the noise. Then, watershed segmentation algorithms and mathematical morphology filters allow reconstructing the patient geometry. This is done using the InsightToolKit library (www.itk.org). Finally the Vascular Model¬ing ToolKit (www.vmtk.org) and gmsh (www.geuz.org/gmsh) are used to create the meshes for the fluid (blood) and structure (arterial wall, outflow canula) and to a priori identify the boundary layers. The method is tested on five different patients with left ventricular assistance and who underwent a CT-scan exam.Results: This method produced good results in four patients. The anastomosis area is recovered and the generated grids are suitable for numerical simulations. In one patient the method failed to produce a good segmentation because of the small dimension of the aortic arch with respect to the image resolution.Conclusions: The described framework allows the use of data that could not be otherwise segmented by standard automatic segmentation tools. In particular the computational grids that have been generated are suitable for simulations that take into account fluid-structure interactions. Finally the presented method features a good reproducibility and fast application.

Modelling the cardiovascular system for automatic interpretation of the blood pressure curve

A four compartment model of the cardiovascular system is developed. To allow for easy interpretation and to minimise the number of parameters, an effort was made to keep the model as simple as possible. A sensitivity analysis is first carried out to determine which are the most important model parameters to characterise the blood pressure signal. A four stage process is then described which accurately determines all parameter values. This process is applied to data from three patients and good agreement is shown in all cases.

Gender differences in premorbid, entry, treatment, and outcome characteristics in a treated epidemiological sample of 661 patients with first episode psychosis.

OBJECTIVES: Gender differences in psychotic disorder have been observed in terms of illness onset and course; however, past research has been limited by inconsistencies between studies and the lack of epidemiological representative of samples assessed. Thus, the aim of this study was to elucidate gender differences in a treated epidemiological sample of patients with first episode psychosis (FEP). METHODS: A medical file audit was used to collect data on premorbid, entry, treatment and 18-month outcome characteristics of 661 FEP consecutive patients treated at the Early Psychosis Prevention and Intervention Centre (EPPIC), Melbourne, Australia. RESULTS: Prior to onset of psychosis, females were more likely to have a history of suicide attempts (p=.011) and depression (p=.001). At service entry, females were more likely to have depressive symptoms (p=.007). Conversely, males had marked substance use problems that were evident prior to admission (p<.001) and persisted through treatment (p<.001). At service entry, males also experienced more severe psychopathology (p<.001) and lower levels of functioning (GAF, p=.008; unemployment/not studying p=.004; living with family, p=.003). Treatment non-compliance (p<.001) and frequent hospitalisations (p=.047) were also common for males with FEP. At service discharge males had significantly lower levels of functioning (GAF, p=.008; unemployment/not studying p=.040; living with family, p=.001) compared to females with FEP. CONCLUSIONS: Gender differences are evident in illness course of patients with FEP, particularly with respect to past history of psychopathology and functioning at presentation and at service discharge. Strategies to deal with these gender differences need to be considered in early intervention programs.

Incorporating features of distribution and progression for automatic Makam classification

Automatic classification of makams from symbolic data is a rarely studied topic. In this paper, first a review of an n-gram based approach is presented using various representations of the symbolic data. While a high degree of precision can be obtained, confusion happens mainly for makams using (almost) the same scale and pitch hierarchy but differ in overall melodic progression, seyir. To further improve the system, first n-gram based classification is tested for various sections of the piece to take into account a feature of the seyir that melodic progression starts in a certain region of the scale. In a second test, a hierarchical classification structure is designed which uses n-grams and seyir features in different levels to further improve the system.

Red tape and delayed entry

Does cutting red tape foster entrepreneurship in industries with the potential to expand? We address this question by combining the time needed to comply with government entry procedures in 45 countries with industry-level data on employment growth and growth in the number of establishments during the 1980s. Our main empirical finding is that countries where it takes less time to register new businesses have seen more entry in industries that experienced expansionary global demand and technology shifts. Our estimates take into account that proxying global industry shifts using data from only one country or group of countries with similar entry regulations will in general yield biased results.

Mapping of Environmental Data Using Kernel-Based Methods

Recently, kernel-based Machine Learning methods have gained great popularity in many data analysis and data mining fields: pattern recognition, biocomputing, speech and vision, engineering, remote sensing etc. The paper describes the use of kernel methods to approach the processing of large datasets from environmental monitoring networks. Several typical problems of the environmental sciences and their solutions provided by kernel-based methods are considered: classification of categorical data (soil type classification), mapping of environmental and pollution continuous information (pollution of soil by radionuclides), mapping with auxiliary information (climatic data from Aral Sea region). The promising developments, such as automatic emergency hot spot detection and monitoring network optimization are discussed as well.

Generic entry into a regulated pharmaceutical market

The aim of this paper is to analyse empirically entry decisions by generic firms intomarkets with tough regulation. Generic drugs might be a key driver of competitionand cost containment in pharmaceutical markets. The dynamics of reforms ofpatents and pricing across drug markets in Spain are useful to identify the impact ofregulations on generic entry. Estimates from a count data model using a panel of 86active ingredients during the 1999 2005 period show that the drivers of genericentry in markets with price regulations are similar to less regulated markets: genericfirms entries are positively affected by the market size and time trend, and negativelyaffected by the number of incumbent laboratories and the number of substitutesactive ingredients. We also find that contrary to what policy makers expected, thesystem of reference pricing restrains considerably the generic entry. Short run brandname drug price reductions are obtained by governments at the cost of long runbenefits from fostering generic entry and post-patent competition into the markets.

Automatic classification of MR scans in Alzheimer's disease.

To be diagnostically useful, structural MRI must reliably distinguish Alzheimer's disease (AD) from normal aging in individual scans. Recent advances in statistical learning theory have led to the application of support vector machines to MRI for detection of a variety of disease states. The aims of this study were to assess how successfully support vector machines assigned individual diagnoses and to determine whether data-sets combined from multiple scanners and different centres could be used to obtain effective classification of scans. We used linear support vector machines to classify the grey matter segment of T1-weighted MR scans from pathologically proven AD patients and cognitively normal elderly individuals obtained from two centres with different scanning equipment. Because the clinical diagnosis of mild AD is difficult we also tested the ability of support vector machines to differentiate control scans from patients without post-mortem confirmation. Finally we sought to use these methods to differentiate scans between patients suffering from AD from those with frontotemporal lobar degeneration. Up to 96% of pathologically verified AD patients were correctly classified using whole brain images. Data from different centres were successfully combined achieving comparable results from the separate analyses. Importantly, data from one centre could be used to train a support vector machine to accurately differentiate AD and normal ageing scans obtained from another centre with different subjects and different scanner equipment. Patients with mild, clinically probable AD and age/sex matched controls were correctly separated in 89% of cases which is compatible with published diagnosis rates in the best clinical centres. This method correctly assigned 89% of patients with post-mortem confirmed diagnosis of either AD or frontotemporal lobar degeneration to their respective group. Our study leads to three conclusions: Firstly, support vector machines successfully separate patients with AD from healthy aging subjects. Secondly, they perform well in the differential diagnosis of two different forms of dementia. Thirdly, the method is robust and can be generalized across different centres. This suggests an important role for computer based diagnostic image analysis for clinical practice.

Activation of Transient Receptor Potential Canonical 3 (TRPC3)-mediated Ca2+ Entry by A1 Adenosine Receptor in Cardiomyocytes Disturbs Atrioventricular Conduction.

Although the activation of the A(1)-subtype of the adenosine receptors (A(1)AR) is arrhythmogenic in the developing heart, little is known about the underlying downstream mechanisms. The aim of this study was to determine to what extent the transient receptor potential canonical (TRPC) channel 3, functioning as receptor-operated channel (ROC), contributes to the A(1)AR-induced conduction disturbances. Using embryonic atrial and ventricular myocytes obtained from 4-day-old chick embryos, we found that the specific activation of A(1)AR by CCPA induced sarcolemmal Ca(2+) entry. However, A(1)AR stimulation did not induce Ca(2+) release from the sarcoplasmic reticulum. Specific blockade of TRPC3 activity by Pyr3, by a dominant negative of TRPC3 construct, or inhibition of phospholipase Cs and PKCs strongly inhibited the A(1)AR-enhanced Ca(2+) entry. Ca(2+) entry through TRPC3 was activated by the 1,2-diacylglycerol (DAG) analog OAG via PKC-independent and -dependent mechanisms in atrial and ventricular myocytes, respectively. In parallel, inhibition of the atypical PKCζ by myristoylated PKCζ pseudosubstrate inhibitor significantly decreased the A(1)AR-enhanced Ca(2+) entry in both types of myocytes. Additionally, electrocardiography showed that inhibition of TRPC3 channel suppressed transient A(1)AR-induced conduction disturbances in the embryonic heart. Our data showing that A(1)AR activation subtly mediates a proarrhythmic Ca(2+) entry through TRPC3-encoded ROC by stimulating the phospholipase C/DAG/PKC cascade provide evidence for a novel pathway whereby Ca(2+) entry and cardiac function are altered. Thus, the A(1)AR-TRPC3 axis may represent a potential therapeutic target.

Globally aligned photomosaic of the Lucky Strike hydrothermal vent field (Mid-Atlantic Ridge, 37°18.5’N): Release of georeferenced data, mosaic construction, and viewing software

We present a georeferenced photomosaic of the Lucky Strike hydrothermal vent field (Mid-Atlantic Ridge, 37°18’N). The photomosaic was generated from digital photographs acquired using the ARGO II seafloor imaging system during the 1996 LUSTRE cruise, which surveyed a ~1 km2 zone and provided a coverage of ~20% of the seafloor. The photomosaic has a pixel resolution of 15 mm and encloses the areas with known active hydrothermal venting. The final mosaic is generated after an optimization that includes the automatic detection of the same benthic features across different images (feature-matching), followed by a global alignment of images based on the vehicle navigation. We also provide software to construct mosaics from large sets of images for which georeferencing information exists (location, attitude, and altitude per image), to visualize them, and to extract data. Georeferencing information can be provided by the raw navigation data (collected during the survey) or result from the optimization obtained from imatge matching. Mosaics based solely on navigation can be readily generated by any user but the optimization and global alignment of the mosaic requires a case-by-case approach for which no universally software is available. The Lucky Strike photomosaics (optimized and navigated-only) are publicly available through the Marine Geoscience Data System (MGDS, http://www.marine-geo.org). The mosaic-generating and viewing software is available through the Computer Vision and Robotics Group Web page at the University of Girona (http://eia.udg.es/_rafa/mosaicviewer.html)

Analysis, modelling and classification of geospatial data using machine learning

The research considers the problem of spatial data classification using machine learning algorithms: probabilistic neural networks (PNN) and support vector machines (SVM). As a benchmark model simple k-nearest neighbor algorithm is considered. PNN is a neural network reformulation of well known nonparametric principles of probability density modeling using kernel density estimator and Bayesian optimal or maximum a posteriori decision rules. PNN is well suited to problems where not only predictions but also quantification of accuracy and integration of prior information are necessary. An important property of PNN is that they can be easily used in decision support systems dealing with problems of automatic classification. Support vector machine is an implementation of the principles of statistical learning theory for the classification tasks. Recently they were successfully applied for different environmental topics: classification of soil types and hydro-geological units, optimization of monitoring networks, susceptibility mapping of natural hazards. In the present paper both simulated and real data case studies (low and high dimensional) are considered. The main attention is paid to the detection and learning of spatial patterns by the algorithms applied.