Text classification using compression-based dissimilarity measures

Arguably, the most difficult task in text classification is to choose an appropriate set of features that allows machine learning algorithms to provide accurate classification. Most state-of-the-art techniques for this task involve careful feature engineering and a pre-processing stage, which may be too expensive in the emerging context of massive collections of electronic texts. In this paper, we propose efficient methods for text classification based on information-theoretic dissimilarity measures, which are used to define dissimilarity-based representations. These methods dispense with any feature design or engineering, by mapping texts into a feature space using universal dissimilarity measures; in this space, classical classifiers (e.g. nearest neighbor or support vector machines) can then be used. The reported experimental evaluation of the proposed methods, on sentiment polarity analysis and authorship attribution problems, reveals that it approximates, sometimes even outperforms previous state-of-the-art techniques, despite being much simpler, in the sense that they do not require any text pre-processing or feature engineering.

Structured Light System Calibration for Perception in Underwater Tanks

The process of visually exploring underwater environments is still a complex problem. Underwater vision systems require complementary means of sensor information to help overcome water disturbances. This work proposes the development of calibration methods for a structured light based system consisting on a camera and a laser with a line beam. Two different calibration procedures that require only two images from different viewpoints were developed and tested in dry and underwater environments. Results obtained show, an accurate calibration for the camera/projector pair with errors close to 1 mm even in the presence of a small stereos baseline.

Spatial point pattern analysis of gorilla nest sites in the Kagwene Sanctuary, Cameroon: Towards understanding the nesting behavior of a critically endangered subspecies

Dissertation submitted in partial fulfillment of the requirements for the Degree of Master of Science in Geospatial Technologies.

Time series morphological analysis applied to biomedical signals events detection

Dissertation submitted in the fufillment of the requirements for the Degree of Master in Biomedical Engineering

Modeling sequencing errors by combining Hidden Markov models.

Among the largest resources for biological sequence data is the large amount of expressed sequence tags (ESTs) available in public and proprietary databases. ESTs provide information on transcripts but for technical reasons they often contain sequencing errors. Therefore, when analyzing EST sequences computationally, such errors must be taken into account. Earlier attempts to model error prone coding regions have shown good performance in detecting and predicting these while correcting sequencing errors using codon usage frequencies. In the research presented here, we improve the detection of translation start and stop sites by integrating a more complex mRNA model with codon usage bias based error correction into one hidden Markov model (HMM), thus generalizing this error correction approach to more complex HMMs. We show that our method maintains the performance in detecting coding sequences.

Generating controlled image sets in cognitive neuroscience research.

The investigation of perceptual and cognitive functions with non-invasive brain imaging methods critically depends on the careful selection of stimuli for use in experiments. For example, it must be verified that any observed effects follow from the parameter of interest (e.g. semantic category) rather than other low-level physical features (e.g. luminance, or spectral properties). Otherwise, interpretation of results is confounded. Often, researchers circumvent this issue by including additional control conditions or tasks, both of which are flawed and also prolong experiments. Here, we present some new approaches for controlling classes of stimuli intended for use in cognitive neuroscience, however these methods can be readily extrapolated to other applications and stimulus modalities. Our approach is comprised of two levels. The first level aims at equalizing individual stimuli in terms of their mean luminance. Each data point in the stimulus is adjusted to a standardized value based on a standard value across the stimulus battery. The second level analyzes two populations of stimuli along their spectral properties (i.e. spatial frequency) using a dissimilarity metric that equals the root mean square of the distance between two populations of objects as a function of spatial frequency along x- and y-dimensions of the image. Randomized permutations are used to obtain a minimal value between the populations to minimize, in a completely data-driven manner, the spectral differences between image sets. While another paper in this issue applies these methods in the case of acoustic stimuli (Aeschlimann et al., Brain Topogr 2008), we illustrate this approach here in detail for complex visual stimuli.

Structural Analysis of Networks

Network analysis naturally relies on graph theory and, more particularly, on the use of node and edge metrics to identify the salient properties in graphs. When building visual maps of networks, these metrics are turned into useful visual cues or are used interactively to filter out parts of a graph while querying it, for instance. Over the years, analysts from different application domains have designed metrics to serve specific needs. Network science is an inherently cross-disciplinary field, which leads to the publication of metrics with similar goals; different names and descriptions of their analytics often mask the similarity between two metrics that originated in different fields. Here, we study a set of graph metrics and compare their relative values and behaviors in an effort to survey their potential contributions to the spatial analysis of networks.

MAMOT: hidden Markov modeling tool.

Hidden Markov models (HMMs) are probabilistic models that are well adapted to many tasks in bioinformatics, for example, for predicting the occurrence of specific motifs in biological sequences. MAMOT is a command-line program for Unix-like operating systems, including MacOS X, that we developed to allow scientists to apply HMMs more easily in their research. One can define the architecture and initial parameters of the model in a text file and then use MAMOT for parameter optimization on example data, decoding (like predicting motif occurrence in sequences) and the production of stochastic sequences generated according to the probabilistic model. Two examples for which models are provided are coiled-coil domains in protein sequences and protein binding sites in DNA. A wealth of useful features include the use of pseudocounts, state tying and fixing of selected parameters in learning, and the inclusion of prior probabilities in decoding. AVAILABILITY: MAMOT is implemented in C++, and is distributed under the GNU General Public Licence (GPL). The software, documentation, and example model files can be found at http://bcf.isb-sib.ch/mamot

Innate signaling promotes formation of regulatory nitric oxide-producing dendritic cells limiting T-cell expansion in experimental autoimmune myocarditis.

BACKGROUND: Activation of innate pattern-recognition receptors promotes CD4+ T-cell-mediated autoimmune myocarditis and subsequent inflammatory cardiomyopathy. Mechanisms that counterregulate exaggerated heart-specific autoimmunity are poorly understood. METHODS AND RESULTS: Experimental autoimmune myocarditis was induced in BALB/c mice by immunization with α-myosin heavy chain peptide and complete Freund's adjuvant. Together with interferon-γ, heat-killed Mycobacterium tuberculosis, an essential component of complete Freund's adjuvant, converted CD11b(hi)CD11c(-) monocytes into tumor necrosis factor-α- and nitric oxide synthase 2-producing dendritic cells (TipDCs). Heat-killed M. tuberculosis stimulated production of nitric oxide synthase 2 via Toll-like receptor 2-mediated nuclear factor-κB activation. TipDCs limited antigen-specific T-cell expansion through nitric oxide synthase 2-dependent nitric oxide production. Moreover, they promoted nitric oxide synthase 2 production in hematopoietic and stromal cells in a paracrine manner. Consequently, nitric oxide synthase 2 production by both radiosensitive hematopoietic and radioresistant stromal cells prevented exacerbation of autoimmune myocarditis in vivo. CONCLUSIONS: Innate Toll-like receptor 2 stimulation promotes formation of regulatory TipDCs, which confine autoreactive T-cell responses in experimental autoimmune myocarditis via nitric oxide. Therefore, activation of innate pattern-recognition receptors is critical not only for disease induction but also for counterregulatory mechanisms, protecting the heart from exaggerated autoimmunity.

Representing diffusion MRI in 5D for segmentation of white matter tracts with a level set method.

We present a method for segmenting white matter tracts from high angular resolution diffusion MR. images by representing the data in a 5 dimensional space of position and orientation. Whereas crossing fiber tracts cannot be separated in 3D position space, they clearly disentangle in 5D position-orientation space. The segmentation is done using a 5D level set method applied to hyper-surfaces evolving in 5D position-orientation space. In this paper we present a methodology for constructing the position-orientation space. We then show how to implement the standard level set method in such a non-Euclidean high dimensional space. The level set theory is basically defined for N-dimensions but there are several practical implementation details to consider, such as mean curvature. Finally, we will show results from a synthetic model and a few preliminary results on real data of a human brain acquired by high angular resolution diffusion MRI.

Early processing in the human lateral occipital complex is highly responsive to illusory contours but not to salient regions.

Human electrophysiological studies support a model whereby sensitivity to so-called illusory contour stimuli is first seen within the lateral occipital complex. A challenge to this model posits that the lateral occipital complex is a general site for crude region-based segmentation, based on findings of equivalent hemodynamic activations in the lateral occipital complex to illusory contour and so-called salient region stimuli, a stimulus class that lacks the classic bounding contours of illusory contours. Using high-density electrical mapping of visual evoked potentials, we show that early lateral occipital cortex activity is substantially stronger to illusory contour than to salient region stimuli, whereas later lateral occipital complex activity is stronger to salient region than to illusory contour stimuli. Our results suggest that equivalent hemodynamic activity to illusory contour and salient region stimuli probably reflects temporally integrated responses, a result of the poor temporal resolution of hemodynamic imaging. The temporal precision of visual evoked potentials is critical for establishing viable models of completion processes and visual scene analysis. We propose that crude spatial segmentation analyses, which are insensitive to illusory contours, occur first within dorsal visual regions, not the lateral occipital complex, and that initial illusory contour sensitivity is a function of the lateral occipital complex.

Low Mannan-binding lectin serum levels are associated with complicated Crohn's disease and reactivity to oligomannan (ASCA).

OBJECTIVES: Mannan-binding lectin (MBL) acts as a pattern-recognition molecule directed against oligomannan, which is part of the cell wall of yeasts and various bacteria. We have previously shown an association between MBL deficiency and anti-Saccharomyces cerevisiae mannan antibody (ASCA) positivity. This study aims at evaluating whether MBL deficiency is associated with distinct Crohn's disease (CD) phenotypes. METHODS: Serum concentrations of MBL and ASCA were measured using ELISA (enzyme-linked immunosorbent assay) in 427 patients with CD, 70 with ulcerative colitis, and 76 healthy controls. CD phenotypes were grouped according to the Montreal Classification as follows: non-stricturing, non-penetrating (B1, n=182), stricturing (B2, n=113), penetrating (B3, n=67), and perianal disease (p, n=65). MBL was classified as deficient (<100 ng/ml), low (100-500 ng/ml), and normal (500 ng/ml). RESULTS: Mean MBL was lower in B2 and B3 CD patients (1,503+/-1,358 ng/ml) compared with that in B1 phenotypes (1,909+/-1,392 ng/ml, P=0.013). B2 and B3 patients more frequently had low or deficient MBL and ASCA positivity compared with B1 patients (P=0.004 and P<0.001). Mean MBL was lower in ASCA-positive CD patients (1,562+/-1,319 ng/ml) compared with that in ASCA-negative CD patients (1,871+/-1,320 ng/ml, P=0.038). In multivariate logistic regression modeling, low or deficient MBL was associated significantly with B1 (negative association), complicated disease (B2+B3), and ASCA. MBL levels did not correlate with disease duration. CONCLUSIONS: Low or deficient MBL serum levels are significantly associated with complicated (stricturing and penetrating) CD phenotypes but are negatively associated with the non-stricturing, non-penetrating group. Furthermore, CD patients with low or deficient MBL are significantly more often ASCA positive, possibly reflecting delayed clearance of oligomannan-containing microorganisms by the innate immune system in the absence of MBL.

Association between IL-18 gene polymorphisms and biopsy-proven giant cell

INTRODUCTION: The objective was to investigate the potential implication of the IL18 gene promoter polymorphisms in the susceptibility to giant-cell arteritis GCA). METHODS: In total, 212 patients diagnosed with biopsy-proven GCA were included in this study. DNA from patients and matched controls was obtained from peripheral blood. Samples were genotyped for the IL18-137 G>C (rs187238), the IL18-607 C>A (rs1946518), and the IL18-1297 T>C (rs360719) gene polymorphisms with polymerase chain reaction, by using a predesigned TaqMan allele discrimination assay. RESULTS: No significant association between the IL18-137 G>C polymorphism and GCA was found. However, the IL18 -607 allele A was significantly increased in GCA patients compared with controls (47.8% versus 40.9% in patients and controls respectively; P = 0.02; OR, 1.32; 95% CI, 1.04 to 1.69). It was due to an increased frequency of homozygosity for the IL18 -607 A/A genotype in patients with GCA (20.4%) compared with controls (13.4%) (IL18 -607 A/A versus IL18 -607 A/C plus IL18 -607 C/C genotypes: P = 0.04; OR, 1.59; 95% CI, 1.02 to 2.46). Also, the IL18-1297 allele C was significantly increased in GCA patients (30.7%) compared with controls (23.0%) (P = 0.003; OR, 1.48; 95% CI, 1.13 to 1.95). In this regard, an increased susceptibility to GCA was observed in individuals carrying the IL18-1297 C/C or the IL18-1297 C/T genotypes compared with those carrying the IL18-1297 T/T genotype (IL18-1297 C/C plus IL18-1297 T/C versus IL18-1297 T/T genotype in GCA patients compared with controls: P = 0.005; OR, 1.61; 95% CI, 1.15 to 2.25). We also found an additive effect of the IL18 -1297 and -607 polymorphisms with TLR4 Asp299Gly polymorphism. The OR for GCA was 1.95 for combinations of genotypes with one or two risk alleles, whereas carriers of three or more risk alleles have an OR of 3.7. CONCLUSIONS: Our results show for the first time an implication of IL18 gene-promoter polymorphisms in the susceptibility to biopsy-proven GCA. In addition, an additive effect between the associated IL18 and TLR4 genetic variants was observed.

Monocular-based 3-D seafloor reconstruction and ortho-mosaicing by piecewise planar representation

Photo-mosaicing techniques have become popular for seafloor mapping in various marine science applications. However, the common methods cannot accurately map regions with high relief and topographical variations. Ortho-mosaicing borrowed from photogrammetry is an alternative technique that enables taking into account the 3-D shape of the terrain. A serious bottleneck is the volume of elevation information that needs to be estimated from the video data, fused, and processed for the generation of a composite ortho-photo that covers a relatively large seafloor area. We present a framework that combines the advantages of dense depth-map and 3-D feature estimation techniques based on visual motion cues. The main goal is to identify and reconstruct certain key terrain feature points that adequately represent the surface with minimal complexity in the form of piecewise planar patches. The proposed implementation utilizes local depth maps for feature selection, while tracking over several views enables 3-D reconstruction by bundle adjustment. Experimental results with synthetic and real data validate the effectiveness of the proposed approach

A new approach to real time traffic sign recognition based on colour information

The automatic interpretation of conventional traffic signs is very complex and time consuming. The paper concerns an automatic warning system for driving assistance. It does not interpret the standard traffic signs on the roadside; the proposal is to incorporate into the existing signs another type of traffic sign whose information will be more easily interpreted by a processor. The type of information to be added is profuse and therefore the most important object is the robustness of the system. The basic proposal of this new philosophy is that the co-pilot system for automatic warning and driving assistance can interpret with greater ease the information contained in the new sign, whilst the human driver only has to interpret the "classic" sign. One of the codings that has been tested with good results and which seems to us easy to implement is that which has a rectangular shape and 4 vertical bars of different colours. The size of these signs is equivalent to the size of the conventional signs (approximately 0.4 m2). The colour information from the sign can be easily interpreted by the proposed processor and the interpretation is much easier and quicker than the information shown by the pictographs of the classic signs