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.

UOC Algorithms

Aplicació per a iPad a mode de repositori de continguts relacionats amb l'ensenyament d'assignatures d'informàtica.

Evaluation of organ-specific peripheral doses after 2-dimensional, 3-dimensional and hybrid intensity modulated radiation therapy for breast cancer based on Monte Carlo and convolution/superposition algorithms: implications for secondary cancer risk assessment.

To make a comprehensive evaluation of organ-specific out-of-field doses using Monte Carlo (MC) simulations for different breast cancer irradiation techniques and to compare results with a commercial treatment planning system (TPS). Three breast radiotherapy techniques using 6MV tangential photon beams were compared: (a) 2DRT (open rectangular fields), (b) 3DCRT (conformal wedged fields), and (c) hybrid IMRT (open conformal+modulated fields). Over 35 organs were contoured in a whole-body CT scan and organ-specific dose distributions were determined with MC and the TPS. Large differences in out-of-field doses were observed between MC and TPS calculations, even for organs close to the target volume such as the heart, the lungs and the contralateral breast (up to 70% difference). MC simulations showed that a large fraction of the out-of-field dose comes from the out-of-field head scatter fluence (>40%) which is not adequately modeled by the TPS. Based on MC simulations, the 3DCRT technique using external wedges yielded significantly higher doses (up to a factor 4-5 in the pelvis) than the 2DRT and the hybrid IMRT techniques which yielded similar out-of-field doses. In sharp contrast to popular belief, the IMRT technique investigated here does not increase the out-of-field dose compared to conventional techniques and may offer the most optimal plan. The 3DCRT technique with external wedges yields the largest out-of-field doses. For accurate out-of-field dose assessment, a commercial TPS should not be used, even for organs near the target volume (contralateral breast, lungs, heart).

Synchronization of EEG: bivariate and multivariate measures.

Synchronization behavior of electroencephalographic (EEG) signals is important for decoding information processing in the human brain. Modern multichannel EEG allows a transition from traditional measurements of synchronization in pairs of EEG signals to whole-brain synchronization maps. The latter can be based on bivariate measures (BM) via averaging over pair-wise values or, alternatively, on multivariate measures (MM), which directly ascribe a single value to the synchronization in a group. In order to compare BM versus MM, we applied nine different estimators to simulated multivariate time series with known parameters and to real EEGs.We found widespread correlations between BM and MM, which were almost frequency-independent for all the measures except coherence. The analysis of the behavior of synchronization measures in simulated settings with variable coupling strength, connection probability, and parameter mismatch showed that some of them, including S-estimator, S-Renyi, omega, and coherence, aremore sensitive to linear interdependences,while others, like mutual information and phase locking value, are more responsive to nonlinear effects. Onemust consider these properties together with the fact thatMM are computationally less expensive and, therefore, more efficient for the large-scale data sets than BM while choosing a synchronization measure for EEG analysis.

Abnormal EEG Synchronization Correlates with Demyelination in Alzheimer's Disease

Introduction : The pathological processes caused by Alzheimer's disease (AD) supposedly disrupt communication between and within the distributed cortical networks due to the dysfunction/loss of synapses and myelination breakdown. Indeed, recently (Knyazeva et al. 2008), we have revealed the whole-head topography of EEG synchronization specific to AD. Here we analyze whether and how these abnormalities of synchronization are related to the demyelination of cortico-cortical fibers. Methods : Fifteen newly diagnosed AD patients (CDR 0.5-1) and 15 controls matched for age, participated in the study. Their multichannel (128) EEGs were recorded during 3-5 min at rest. They were submitted to the multivariate phase synchronization (MPS) analysis for mapping regional synchronization. To obtain individual whole-head maps, the MPS was computed for each sensor considering its 2nd nearest topographical neighbors. Separate calculations were performed for the delta, theta, alpha-1/−2, and beta-1/−2 EEG bands. The same subjects were scanned on a 3 Tesla Philips scanner. The protocol included a high-resolution T1-weighted sequence and a Magnetization Transfer Imaging (MTI) acquisition. For each subject, we defined a 3mm thick layer of white matter exactly below the cortical gray matter. The magnetization transfer ratio (MTR) - an estimator of myelination - was calculated for this layer in 39 Brodmann-defined ROIs per hemisphere. To assess the between-group differences, we used a permutation version of Hotelling's T2 test or two-sample T-test (Pcorrected <0.05). For correlation analysis, Spearman Rank Correlation was calculated. Results : In AD patients, we have found an abnormal landscape of synchronization characterized by a decrease in MPS over the fronto-temporal region of the left hemisphere and an increase over the temporo-parieto-occipital regions bilaterally. Also, we have shown a widespread decrease in regional MTR in the AD patients for all the areas excluding motor, premotor, and primary sensory ones. Assuming that AD-related changes in synchronization are associated with demyelination, we hypothesized a correlation between the regional MTR values and MPS values in the hypo- and hyper-synchronized clusters. We found that MPS in the left fronto-temporal hypo-synchronized cluster directly correlates with myelination in BA42-46 of the left hemisphere: the lower the myelination in individual patients, the lower the EEG synchronization. By contrast, in the posterior hyper-synchronized cluster, MPS inversely correlated with myelination, i.e., the lower the myelination, the higher the synchronization. This posterior hyper-synchronization, more characteristic for early-onset AD, probably, results from the initial effect of the disease on cortical inhibition, reducing cortical capacity for decoupling irrelevant connections. Remarkably, it showed different topography of correlations in early- vs. late-onset patients. In the early-onset patients, hyper-synchronization was mainly related to demyelination in posterior BAs, the effect being significant in all the EEG frequency bands. In the late-onset patients, widely distributed correlations were significant for the EEG delta band, suggesting an interaction between the cerebral manifestations of AD and the age of its onset, i.e., topographically selective impairment of cortical inhibition in early-onset AD vs. its wide-spread weakening in old age. Conclusions : Overall, our results document that the degradation of white matter is a significant factor of AD pathogenesis leading to functional dysconnection, the latter being reflected in EEG synchronization abnormalities.

Neonatal and adult ICU ventilators to provide ventilation in neonates, infants, and children: a bench model study.

BACKGROUND: Using a bench test model, we investigated the hypothesis that neonatal and/or adult ventilators equipped with neonatal/pediatric modes currently do not reliably administer pressure support (PS) in neonatal or pediatric patient groups in either the absence or presence of air leaks. METHODS: PS was evaluated in 4 neonatal and 6 adult ventilators using a bench model to evaluate triggering, pressurization, and cycling in both the absence and presence of leaks. Delivered tidal volumes were also assessed. Three patients were simulated: a preterm infant (resistance 100 cm H2O/L/s, compliance 2 mL/cm H2O, inspiratory time of the patient [TI] 400 ms, inspiratory effort 1 and 2 cm H2O), a full-term infant (resistance 50 cm H2O/L/s, compliance 5 mL/cm H2O, TI 500 ms, inspiratory effort 2 and 4 cm H2O), and a child (resistance 30 cm H2O/L/s, compliance 10 mL/cm H2O, TI 600 ms, inspiratory effort 5 and 10 cm H2O). Two PS levels were tested (10 and 15 cm H2O) with and without leaks and with and without the leak compensation algorithm activated. RESULTS: Without leaks, only 2 neonatal ventilators and one adult ventilator had trigger delays under a given predefined acceptable limit (1/8 TI). Pressurization showed high variability between ventilators. Most ventilators showed TI in excess high enough to seriously impair patient-ventilator synchronization (> 50% of the TI of the subject). In some ventilators, leaks led to autotriggering and impairment of ventilation performance, but the influence of leaks was generally lower in neonatal ventilators. When a noninvasive ventilation algorithm was available, this was partially corrected. In general, tidal volume was calculated too low by the ventilators in the presence of leaks; the noninvasive ventilation algorithm was able to correct this difference in only 2 adult ventilators. CONCLUSIONS: No ventilator performed equally well under all tested conditions for all explored parameters. However, neonatal ventilators tended to perform better in the presence of leaks. These findings emphasize the need to improve algorithms for assisted ventilation modes to better deal with situations of high airway resistance, low pulmonary compliance, and the presence of leaks.

Enhancing fault management performance of two-step QoS routing algorithms in GMPLS networks

In this paper a novel methodology aimed at minimizing the probability of network failure and the failure impact (in terms of QoS degradation) while optimizing the resource consumption is introduced. A detailed study of MPLS recovery techniques and their GMPLS extensions are also presented. In this scenario, some features for reducing the failure impact and offering minimum failure probabilities at the same time are also analyzed. Novel two-step routing algorithms using this methodology are proposed. Results show that these methods offer high protection levels with optimal resource consumption

Enhancing MPLS QoS routing algorithms by using the network protection degree paradigm

IP based networks still do not have the required degree of reliability required by new multimedia services, achieving such reliability will be crucial in the success or failure of the new Internet generation. Most of existing schemes for QoS routing do not take into consideration parameters concerning the quality of the protection, such as packet loss or restoration time. In this paper, we define a new paradigm to develop new protection strategies for building reliable MPLS networks, based on what we have called the network protection degree (NPD). This NPD consists of an a priori evaluation, the failure sensibility degree (FSD), which provides the failure probability and an a posteriori evaluation, the failure impact degree (FID), to determine the impact on the network in case of failure. Having mathematical formulated these components, we point out the most relevant components. Experimental results demonstrate the benefits of the utilization of the NPD, when used to enhance some current QoS routing algorithms to offer a certain degree of protection

Improving Clustering Algorithms for Image Segmentation using Contour and Region Information

In image segmentation, clustering algorithms are very popular because they are intuitive and, some of them, easy to implement. For instance, the k-means is one of the most used in the literature, and many authors successfully compare their new proposal with the results achieved by the k-means. However, it is well known that clustering image segmentation has many problems. For instance, the number of regions of the image has to be known a priori, as well as different initial seed placement (initial clusters) could produce different segmentation results. Most of these algorithms could be slightly improved by considering the coordinates of the image as features in the clustering process (to take spatial region information into account). In this paper we propose a significant improvement of clustering algorithms for image segmentation. The method is qualitatively and quantitative evaluated over a set of synthetic and real images, and compared with classical clustering approaches. Results demonstrate the validity of this new approach

Comparison of topography- and aperture-dependent motion compensation algorithms for airborne SAR

This letter presents a comparison between threeFourier-based motion compensation (MoCo) algorithms forairborne synthetic aperture radar (SAR) systems. These algorithmscircumvent the limitations of conventional MoCo, namelythe assumption of a reference height and the beam-center approximation.All these approaches rely on the inherent time–frequencyrelation in SAR systems but exploit it differently, with the consequentdifferences in accuracy and computational burden. Aftera brief overview of the three approaches, the performance ofeach algorithm is analyzed with respect to azimuthal topographyaccommodation, angle accommodation, and maximum frequencyof track deviations with which the algorithm can cope. Also, ananalysis on the computational complexity is presented. Quantitativeresults are shown using real data acquired by the ExperimentalSAR system of the German Aerospace Center (DLR).

Using free data mining software and clustering algorithms to find predictors from student qualifications

In this project a research both in finding predictors via clustering techniques and in reviewing the Data Mining free software is achieved. The research is based in a case of study, from where additionally to the KDD free software used by the scientific community; a new free tool for pre-processing the data is presented. The predictors are intended for the e-learning domain as the data from where these predictors have to be inferred are student qualifications from different e-learning environments. Through our case of study not only clustering algorithms are tested but also additional goals are proposed.

Glutathione Precursor, N-Acetyl-Cysteine, Modulates EEG Synchronization in Schizophrenia Patients

Background: Glutathione (GSH) dysregulation at the gene, protein and functional levels observed in schizophrenia patients, and schizophrenia-like anomalies in GSH deficit experimental models, suggest that genetic glutathione synthesis impairments represent one major risk factor for the disease (Do et al., 2009). In a randomized, double blind, placebo controlled, add-on clinical trial of 140 patients, the GSH precursor N-Acetyl-Cysteine (NAC, 2g/day, 6 months) significantly improved the negative symptoms and reduced sideeffects due to antipsychotics (Berk et al., 2008). In a subset of patients (n=7), NAC (2g/day, 2 months, cross-over design) also improved auditory evoked potentials, the NMDA-dependent mismatch negativity (Lavoie et al, 2008). Methods: To determine whether increased GSH levels would modulate the topography of functional brain connectivity, we applied a multivariate phase synchronization (MPS) estimator (Knyazeva et al, 2008) to dense-array EEGs recorded during rest with eyes closed at the protocol onset, the point of crossover, and at its end. Results: The whole-head imaging revealed a specific synchronization landscape in NAC compared to placebo condition. In particular, NAC increased MPS over frontal and left temporal regions in a frequency-specific manner. The topography and direction of MPS changes were similar and robust in all 7 patients. Moreover, these changes correlated with the changes in the Liddle's score of disorganization, thus linking EEG synchronization to the improvement of the clinical picture. Conclusions: The data suggest an important pathway towards new therapeutic strategies that target GSH dysregulation in schizophrenia. They also show the utility of MPS mapping as a marker of treatment efficacy.