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.

Four 13-lipoxygenases contribute to rapid jasmonate synthesis in wounded Arabidopsis thaliana leaves: a role for lipoxygenase 6 in responses to long-distance wound signals.

Damage-inducible defenses in plants are controlled in part by jasmonates, fatty acid-derived regulators that start to accumulate within 30 s of wounding a leaf. Using liquid chromatography-tandem mass spectrometry, we sought to identify the 13-lipoxygenases (13-LOXs) that initiate wound-induced jasmonate synthesis within a 190-s timeframe in Arabidopsis thaliana in 19 single, double, triple and quadruple mutant combinations derived from the four 13-LOX genes in this plant. All four 13-LOXs were found to contribute to jasmonate synthesis in wounded leaves: among them LOX6 showed a unique behavior. The relative contribution of LOX6 to jasmonate synthesis increased with distance from a leaf tip wound, and LOX6 was the only 13-LOX necessary for the initiation of early jasmonate synthesis in leaves distal to the wounded leaf. Herbivory assays that compared Spodoptera littoralis feeding on the lox2-1 lox3B lox4A lox6A quadruple mutant and the lox2-1 lox3B lox4A triple mutant revealed a role for LOX6 in defense of the shoot apical meristem. Consistent with this, we found that LOX6 promoter activity was strong in the apical region of rosettes. The LOX6 promoter was active in and near developing xylem cells and in expression domains we term subtrichomal mounds.

Synthesis of polyhydroxyalkanoate in the peroxisome of Pichia pastoris.

Polyhydroxyalkanoates (PHAs) are polyesters naturally produced by bacteria that have properties of biodegradable plastics and elastomers. A PHA synthase from Pseudomonas aeruginosa modified at the carboxy-end for peroxisomal targeting was transformed in Pichia pastoris. The PHA synthase was expressed under the control of the promoter of the P. pastoris acyl-CoA oxidase gene. Synthesis of up to 1% medium-chain-length PHA per g dry weight was dependent on both the expression of the PHA synthase and the presence of oleic acid in the medium. PHA accumulated as inclusions within the peroxisomes. P. pastoris could be used as a model system to study how peroxisomal metabolism needs to be modified to increase PHA production in other eukaryotes, such as plants.

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.

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.

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.

An index of 5-HT synthesis changes during early antidepressant treatment: α-[11C]methyl-l-tryptophan PET study

The antidepressant selective serotonin transporter inhibitors (SSRIs) are clinically active after a delay of several weeks. Indeed, the rapid increase of serotonin (5-HT) caused by SSRIs, stimulates the 5-HT1A autoreceptors, which exert a negative feedback on the 5-HT neurotransmission. Only when autoreceptors are desensitized, can SSRIs exert their therapeutic activity. The 5-HT1A receptor antagonist pindolol has been used to accelerate the clinical effects of antidepressant by preventing the negative feedback. Using the a-[11C]methyl-L-tryptophan/positron emission tomography (PET), the goal of the present double-blind, randomized study was to compare the changes in a-[11C]methyl-L-tryptophan trapping, an index of serotonin synthesis, in patients suffering from unipolar depression treated with the SSRI citalopram (20 mg/day) plus placebo versus patients treated with citalopram plus pindol (7.5 mg/day). PET and Hamilton depression rating scale (HDRS-17) were performed at baseline, and after 10 and 24 days of antidepressant treatment. Results show that the combination citalopram plus pindol, compared to citalopram alone shows a more rapid and greater increase of an index of 5-HT synthesis in prefrontal cortex (BA 9). This research is the first human PET study demonstrating that, after 24 days, the combination SSRIs plus pindolol produces a greater increase of the metabolism of serotonin in the prefrontal cortex, an area associated to depressive symptoms.

Semi-supervised remote sensing image classification with cluster kernels

A semisupervised support vector machine is presented for the classification of remote sensing images. The method exploits the wealth of unlabeled samples for regularizing the training kernel representation locally by means of cluster kernels. The method learns a suitable kernel directly from the image and thus avoids assuming a priori signal relations by using a predefined kernel structure. Good results are obtained in image classification examples when few labeled samples are available. The method scales almost linearly with the number of unlabeled samples and provides out-of-sample predictions.