Active learning methods for remote sensing image classification

In this paper, we propose two active learning algorithms for semiautomatic definition of training samples in remote sensing image classification. Based on predefined heuristics, the classifier ranks the unlabeled pixels and automatically chooses those that are considered the most valuable for its improvement. Once the pixels have been selected, the analyst labels them manually and the process is iterated. Starting with a small and nonoptimal training set, the model itself builds the optimal set of samples which minimizes the classification error. We have applied the proposed algorithms to a variety of remote sensing data, including very high resolution and hyperspectral images, using support vector machines. Experimental results confirm the consistency of the methods. The required number of training samples can be reduced to 10% using the methods proposed, reaching the same level of accuracy as larger data sets. A comparison with a state-of-the-art active learning method, margin sampling, is provided, highlighting advantages of the methods proposed. The effect of spatial resolution and separability of the classes on the quality of the selection of pixels is also discussed.

Software per al cronometratge de temps mitjançant sensors digitals

L’Slot, conegut per tots amb el nom d’Scalextric, s’ha implantat com a una forma d’oci habitual, la pràctica del qual no queda restringida als més petits, sinó que cada vegada crea més afició entre els grans. El fet que l’Slot s’hagi extès entre els adults n’ha revolucionat la pràctica. L’entrada al mercat de l’Slot de gent adulta, i amb poder adquisitiu molt superior als adolescents, ha provocat que les marques especialitzades vagin evolucionant els seus productes cada vegada més. Totes les marques s’han vist obligades a desenvolupar vehicles més competitius i alhora treure al mercat accessoris que augmentin la realitat del joc. Una de les necessitats que s’ha creat és la de competir entre jugadors. Aquesta competició tan pot ser en forma de carrera entre diversos participants, com de forma individual, cronometrant el temps de cada participant en un circuit. L’objectiu principal del projecte és crear un sistema capaç de realitzar cronometratges en temps real mitjançant sensors digitals ja existents en el mercat de l’Slot i poder controlar i visualitzar la informació des d’un PC. Per a poder captar els senyals dels sensors s’ha utilitzat un sistema microcontrolat, que garanteix gran velocitat d’adquisició, processament de dades i transmissió. La comunicació del Microcontrolador amb el PC s’ha realizat mitjançant el bus USB. El PC serà el controlador del sistema i donarà les ordres al Microcontrolador, podent així tenir control total sobre el funcionament del programa. També serà el PC el que tractarà els crocometratges enregistrats i els mostrarà per pantalla

Regulation of glucagon secretion by glucose transporter type 2 (glut2) and astrocyte-dependent glucose sensors.

Ripglut1;glut2-/- mice have no endogenous glucose transporter type 2 (glut2) gene expression but rescue glucose-regulated insulin secretion. Control of glucagon plasma levels is, however, abnormal, with fed hyperglucagonemia and insensitivity to physiological hypo- or hyperglycemia, indicating that GLUT2-dependent sensors control glucagon secretion. Here, we evaluated whether these sensors were located centrally and whether GLUT2 was expressed in glial cells or in neurons. We showed that ripglut1;glut2-/- mice failed to increase plasma glucagon levels following glucoprivation induced either by i.p. or intracerebroventricular 2-deoxy-D-glucose injections. This was accompanied by failure of 2-deoxy-D-glucose injections to activate c-Fos-like immunoreactivity in the nucleus of the tractus solitarius and the dorsal motor nucleus of the vagus. When glut2 was expressed by transgenesis in glial cells but not in neurons of ripglut1;glut2-/- mice, stimulated glucagon secretion was restored as was c-Fos-like immunoreactive labeling in the brainstem. When ripglut1;glut2-/- mice were backcrossed into the C57BL/6 genetic background, fed plasma glucagon levels were also elevated due to abnormal autonomic input to the alpha cells; glucagon secretion was, however, stimulated by hypoglycemic stimuli to levels similar to those in control mice. These studies identify the existence of central glucose sensors requiring glut2 expression in glial cells and therefore functional coupling between glial cells and neurons. These sensors may be activated at different glycemic levels depending on the genetic background.

A system to measure the kinematics during the entire ski jump sequence using inertial sensors.

Three-dimensional analysis of the entire sequence in ski jumping is recommended when studying the kinematics or evaluating performance. Camera-based systems which allow three-dimensional kinematics measurement are complex to set-up and require extensive post-processing, usually limiting ski jumping analyses to small numbers of jumps. In this study, a simple method using a wearable inertial sensors-based system is described to measure the orientation of the lower-body segments (sacrum, thighs, shanks) and skis during the entire jump sequence. This new method combines the fusion of inertial signals and biomechanical constraints of ski jumping. Its performance was evaluated in terms of validity and sensitivity to different performances based on 22 athletes monitored during daily training. The validity of the method was assessed by comparing the inclination of the ski and the slope at landing point and reported an error of -0.2±4.8°. The validity was also assessed by comparison of characteristic angles obtained with the proposed system and reference values in the literature; the differences were smaller than 6° for 75% of the angles and smaller than 15° for 90% of the angles. The sensitivity to different performances was evaluated by comparing the angles between two groups of athletes with different jump lengths and by assessing the association between angles and jump lengths. The differences of technique observed between athletes and the associations with jumps length agreed with the literature. In conclusion, these results suggest that this system is a promising tool for a generalization of three-dimensional kinematics analysis in ski jumping.

Direct Fourier Tomographic Reconstruction Image-To-Image Filter

We present an open-source ITK implementation of a directFourier method for tomographic reconstruction, applicableto parallel-beam x-ray images. Direct Fourierreconstruction makes use of the central-slice theorem tobuild a polar 2D Fourier space from the 1D transformedprojections of the scanned object, that is resampled intoa Cartesian grid. Inverse 2D Fourier transform eventuallyyields the reconstructed image. Additionally, we providea complex wrapper to the BSplineInterpolateImageFunctionto overcome ITKâeuro?s current lack for image interpolatorsdealing with complex data types. A sample application ispresented and extensively illustrated on the Shepp-Loganhead phantom. We show that appropriate input zeropaddingand 2D-DFT oversampling rates together with radial cubicb-spline interpolation improve 2D-DFT interpolationquality and are efficient remedies to reducereconstruction artifacts.

Web semàntica aplicada a la gestió i caracterització de dades, sensors i accés a serveis per a vaixells d'investigació oceanogràfica

Amb el present projecte es proposa fer un estudi de la web semàntica aplicada a la descripció i modelització de la instrumentació marina operada en el context de campanyes d'investigació oceanogràfica.

Creating large and accurate mosaics of the mid-atlantic ridge

We present an approach for creating image mosaics using navigation data consisting on 3D position estimates provided by sensors such as LBL available in deep water surveys. A central issue with acoustic 3D positioning is that the accuracy is far too low compositing the images within reasonable accuracy

Weight status, body image and bullying among adolescents in the Seychelles.

We investigated the relationship between being bullied and measured body weight and perceived body weight among adolescents of a middle-income sub Saharan African country. Our data originated from the Global School-based Health Survey, which targets adolescents aged 13-15 years. Student weights and heights were measured before administrating the questionnaire which included questions about personal data, health behaviors and being bullied. Standard criteria were used to assess thinness, overweight and obesity. Among 1,006 participants who had complete data, 16.5% (95%CI 13.3-20.2) reported being bullied ≥ 3 days during the past 30 days; 13.4% were thin, 16.8% were overweight and 7.6% were obese. Categories of actual weight and of perceived weight correlated only moderately (Spearman correlation coefficient 0.37 for boys and 0.57 for girls; p < 0.001). In univariate analysis, both actual obesity (OR 1.76; p = 0.051) and perception of high weight (OR 1.63 for "slightly overweight"; OR 2.74 for "very overweight", both p < 0.05) were associated with being bullied. In multivariate analysis, ORs for categories of perceived overweight were virtually unchanged while ORs for actual overweight and obesity were substantially attenuated, suggesting a substantial role of perceived weight in the association with being bullied. Actual underweight and perceived thinness also tended to be associated with being bullied, although not significantly. Our findings suggest that more research attention be given to disentangling the significant association between body image, overweight and bullying among adolescents. Further studies in diverse populations are warranted.

Three-dimensional magnetic resonance myocardial motion tracking from a single image plane.

Three-dimensional imaging for the quantification of myocardial motion is a key step in the evaluation of cardiac disease. A tagged magnetic resonance imaging method that automatically tracks myocardial displacement in three dimensions is presented. Unlike other techniques, this method tracks both in-plane and through-plane motion from a single image plane without affecting the duration of image acquisition. A small z-encoding gradient is subsequently added to the refocusing lobe of the slice-selection gradient pulse in a slice following CSPAMM acquisition. An opposite polarity z-encoding gradient is added to the orthogonal tag direction. The additional z-gradients encode the instantaneous through plane position of the slice. The vertical and horizontal tags are used to resolve in-plane motion, while the added z-gradients is used to resolve through-plane motion. Postprocessing automatically decodes the acquired data and tracks the three-dimensional displacement of every material point within the image plane for each cine frame. Experiments include both a phantom and in vivo human validation. These studies demonstrate that the simultaneous extraction of both in-plane and through-plane displacements and pathlines from tagged images is achievable. This capability should open up new avenues for the automatic quantification of cardiac motion and strain for scientific and clinical purposes.

Bayesian image reconstruction with space-variant noise suppression

In this paper we present a Bayesian image reconstruction algorithm with entropy prior (FMAPE) that uses a space-variant hyperparameter. The spatial variation of the hyperparameter allows different degrees of resolution in areas of different statistical characteristics, thus avoiding the large residuals resulting from algorithms that use a constant hyperparameter. In the first implementation of the algorithm, we begin by segmenting a Maximum Likelihood Estimator (MLE) reconstruction. The segmentation method is based on using a wavelet decomposition and a self-organizing neural network. The result is a predetermined number of extended regions plus a small region for each star or bright object. To assign a different value of the hyperparameter to each extended region and star, we use either feasibility tests or cross-validation methods. Once the set of hyperparameters is obtained, we carried out the final Bayesian reconstruction, leading to a reconstruction with decreased bias and excellent visual characteristics. The method has been applied to data from the non-refurbished Hubble Space Telescope. The method can be also applied to ground-based images.

Single-trial topographic analysis of human EEG: A new image of event-related potentials

We present a novel approach for analyzing single-trial electroencephalography (EEG) data, using topographic information. The method allows for visualizing event-related potentials using all the electrodes of recordings overcoming the problem of previous approaches that required electrode selection and waveforms filtering. We apply this method to EEG data from an auditory object recognition experiment that we have previously analyzed at an ERP level. Temporally structured periods were statistically identified wherein a given topography predominated without any prior information about the temporal behavior. In addition to providing novel methods for EEG analysis, the data indicate that ERPs are reliably observable at a single-trial level when examined topographically.