Distance learning for similarity estimation

In this paper, we present a general guideline to find a better distance measure for similarity estimation based on statistical analysis of distribution models and distance functions. A new set of distance measures are derived from the harmonic distance, the geometric distance, and their generalized variants according to the Maximum Likelihood theory. These measures can provide a more accurate feature model than the classical Euclidean and Manhattan distances. We also find that the feature elements are often from heterogeneous sources that may have different influence on similarity estimation. Therefore, the assumption of single isotropic distribution model is often inappropriate. To alleviate this problem, we use a boosted distance measure framework that finds multiple distance measures which fit the distribution of selected feature elements best for accurate similarity estimation. The new distance measures for similarity estimation are tested on two applications: stereo matching and motion tracking in video sequences. The performance of boosted distance measure is further evaluated on several benchmark data sets from the UCI repository and two image retrieval applications. In all the experiments, robust results are obtained based on the proposed methods.     

ECOC-DRF: Discriminative random fields based on error correcting output codes

We present ECOC-DRF, a framework where potential functions for Discriminative Random Fields are formulated as an ensemble of classifiers. We introduce the label trick, a technique to express transitions in the pairwise potential as meta-classes. This allows to independently learn any possible transition between labels without assuming any pre-defined model. The Error Correcting Output Codes matrix is used as ensemble framework for the combination of margin classifiers. We apply ECOC-DRF to a large set of classification problems, covering synthetic, natural and medical images for binary and multi-class cases, outperforming state-of-the art in almost all the experiments.     

Personalization and user verification in wearable systems using biometric walking patterns

In this article, a novel technique for user’s authentication and verification using gait as a biometric unobtrusive pattern is proposed. The method is based on a two stages pipeline. First, a general activity recognition classifier is personalized for an specific user using a small sample of her/his walking pattern. As a result, the system is much more selective with respect to the new walking pattern. A second stage verifies whether the user is an authorized one or not. This stage is defined as a one-class classification problem. In order to solve this problem, a four-layer architecture is built around the geometric concept of convex hull. This architecture allows to improve robustness to outliers, modeling non-convex shapes, and to take into account temporal coherence information. Two different scenarios are proposed as validation with two different wearable systems. First, a custom high-performance wearable system is built and used in a free environment. A second dataset is acquired from an Android-based commercial device in a ‘wild’ scenario with rough terrains, adversarial conditions, crowded places and obstacles. Results on both systems and datasets are very promising, reducing the verification error rates by an order of magnitude with respect to the state-of-the-art technologies.     

One Question,Multiple Answers: Biochemical and Biophysical Screening Methods Retrieve Deviating Fragment Hit Lists

Fragment‐based lead discovery is gaining momentum in drug development. Typically, a hierarchical cascade of several screening techniques is consulted to identify fragment hits which are then analyzed by crystallography. Because crystal structures with bound fragments are essential for the subsequent hit‐to‐lead‐to‐drug optimization, the screening process should distinguish reliably between binders and non‐binders. We therefore investigated whether different screening methods would reveal similar collections of putative binders. First we used a biochemical assay to identify fragments that bind to endothiapepsin, a surrogate for disease‐relevant aspartic proteases. In a comprehensive screening approach, we then evaluated our 361‐entry library by using a reporter‐displacement assay, saturation‐transfer difference NMR, native mass spectrometry, thermophoresis, and a thermal shift assay. While the combined results of these screening methods retrieve 10 of the 11 crystal structures originally predicted by the biochemical assay, the mutual overlap of individual hit lists is surprisingly low, highlighting that each technique operates on different biophysical principles and conditions.     

Traffic sign recognition system with β -correction

Traffic sign classification represents a classical application of multi-object recognition processing in uncontrolled adverse environments. Lack of visibility, illumination changes, and partial occlusions are just a few problems. In this paper, we introduce a novel system for multi-class classification of traffic signs based on error correcting output codes (ECOC). ECOC is based on an ensemble of binary classifiers that are trained on bi-partition of classes. We classify a wide set of traffic signs types using robust error correcting codings. Moreover, we introduce the novel β-correction decoding strategy that outperforms the state-of-the-art decoding techniques, classifying a high number of classes with great success.     

Intravascular Ultrasound Tissue Characterization with Sub-class Error-Correcting Output Codes

Intravascular ultrasound (IVUS) represents a powerful imaging technique to explore coronary vessels and to study their morphology and histologic properties. In this paper, we characterize different tissues based on radial frequency, texture-based, and combined features. To deal with the classification of multiple tissues, we require the use of robust multi-class learning techniques. In this sense, error-correcting output codes (ECOC) show to robustly combine binary classifiers to solve multi-class problems. In this context, we propose a strategy to model multi-class classification tasks using sub-classes information in the ECOC framework. The new strategy splits the classes into different sub-sets according to the applied base classifier. Complex IVUS data sets containing overlapping data are learnt by splitting the original set of classes into sub-classes, and embedding the binary problems in a problem-dependent ECOC design. The method automatically characterizes different tissues, showing performance improvements over the state-of-the-art ECOC techniques for different base classifiers. Furthermore, the combination of RF and texture-based features also shows improvements over the state-of-the-art approaches.     

Elastic wave fields in a half-plane with free-surface relief,tunnels and multiple buried inclusions

In this work, we study the elastic wave fields that develop in an isotropic half-plane which contains different types of heterogeneities such as free-surface relief, unlined and lined tunnels, as well as multiple buried inclusions. The half-plane is swept by traveling harmonic waves, namely pressure waves, vertically polarized shear waves and Rayleigh waves, as well as by waves emanating from an embedded source. The computational tool used is the direct boundary element method (BEM) with sub-structuring capabilities. Following development and numerical implementation of the BEM, two stages of work are performed, namely a detailed verification study followed by extensive parametric investigations. These last numerical simulations help determine the dependence of the elastic waves that develop along the surface of the half-plane, as well as of the dynamic stress concentration factors in the different types of buried inclusions, to the following key factors: geometry of the free-surface relief, geometry, depth of burial and separation distance of the inclusions, wavelength to inclusion diameter ratio and dynamic interaction phenomena between the multiple heterogeneities. In closing, the potential of the enhanced BEM formulation to treat dynamic soil-structure-interaction problems with the kind of complexity expected in realistic engineering applications is discussed.     

Preparation of copolymers of p-Isopropenylcalix[8]arene and Styrene

Summary p-Isopropenylcalix[n]arenes are useful building blocks for the design of novel polymer architectures. This paper is the first report on copolymerization of p-isopropenylcalix[8]arene and styrene by free radical polymerization. An extensive study on the optimization of the reaction conditions (especially monomer to initiator ratio, initiator concentration, and duration of the process) was performed in order to prepare high molecular weight copolymers in good yield. Homopolymerizations were also carried out for comparison. The products obtained by homopolymerization of the monomers and their copolymerization were fractionated and each fraction was characterized by chromatographic (GPC and HLPC) and spectroscopic methods as UV, IR and ¹H NMR and analytical methods. Considering the molecular weight, spectroscopic and analytical data the most probable structure of the copolymer was proposed. Extraction of metal picrates from water into organic solvent was used to evaluate the ion binding capabilities of p-isopropenylcalix[8]arenestyrene and O-acetylated p-isopropenycalix[8]arenestyrene copolymers.