Parallel implementation of vertex component analysis for hyperspectral endmember extraction

International Conference with Peer Review 2012 IEEE International Conference in Geoscience and Remote Sensing Symposium (IGARSS), 22-27 July 2012, Munich, Germany

An Evaluation of Local Feature Combiners for Robot Visual Localization

In the last decade, local image features have been widely used in robot visual localization. To assess image similarity, a strategy exploiting these features compares raw descriptors extracted from the current image to those in the models of places. This paper addresses the ensuing step in this process, where a combining function must be used to aggregate results and assign each place a score. Casting the problem in the multiple classifier systems framework, we compare several candidate combiners with respect to their performance in the visual localization task. A deeper insight into the potential of the sum and product combiners is provided by testing two extensions of these algebraic rules: threshold and weighted modifications. In addition, a voting method, previously used in robot visual localization, is assessed. All combiners are tested on a visual localization task, carried out on a public dataset. It is experimentally demonstrated that the sum rule extensions globally achieve the best performance. The voting method, whilst competitive to the algebraic rules in their standard form, is shown to be outperformed by both their modified versions.

Feature selection for clustering categorical data with an embedded modelling approach

Research on the problem of feature selection for clustering continues to develop. This is a challenging task, mainly due to the absence of class labels to guide the search for relevant features. Categorical feature selection for clustering has rarely been addressed in the literature, with most of the proposed approaches having focused on numerical data. In this work, we propose an approach to simultaneously cluster categorical data and select a subset of relevant features. Our approach is based on a modification of a finite mixture model (of multinomial distributions), where a set of latent variables indicate the relevance of each feature. To estimate the model parameters, we implement a variant of the expectation-maximization algorithm that simultaneously selects the subset of relevant features, using a minimum message length criterion. The proposed approach compares favourably with two baseline methods: a filter based on an entropy measure and a wrapper based on mutual information. The results obtained on synthetic data illustrate the ability of the proposed expectation-maximization method to recover ground truth. An application to real data, referred to official statistics, shows its usefulness.

Reconhecimento de língua gestual

Trabalho Final de Mestrado para obtenção do grau de Mestre em Engenharia Informática e Computadores

Coding mode decision algorithm for binary descriptor coding

In visual sensor networks, local feature descriptors can be computed at the sensing nodes, which work collaboratively on the data obtained to make an efficient visual analysis. In fact, with a minimal amount of computational effort, the detection and extraction of local features, such as binary descriptors, can provide a reliable and compact image representation. In this paper, it is proposed to extract and code binary descriptors to meet the energy and bandwidth constraints at each sensing node. The major contribution is a binary descriptor coding technique that exploits the correlation using two different coding modes: Intra, which exploits the correlation between the elements that compose a descriptor; and Inter, which exploits the correlation between descriptors of the same image. The experimental results show bitrate savings up to 35% without any impact in the performance efficiency of the image retrieval task. © 2014 EURASIP.

Enhancing Multimodal Silent Speech Interfaces With Feature Selection

In research on Silent Speech Interfaces (SSI), different sources of information (modalities) have been combined, aiming at obtaining better performance than the individual modalities. However, when combining these modalities, the dimensionality of the feature space rapidly increases, yielding the well-known "curse of dimensionality". As a consequence, in order to extract useful information from this data, one has to resort to feature selection (FS) techniques to lower the dimensionality of the learning space. In this paper, we assess the impact of FS techniques for silent speech data, in a dataset with 4 non-invasive and promising modalities, namely: video, depth, ultrasonic Doppler sensing, and surface electromyography. We consider two supervised (mutual information and Fisher's ratio) and two unsupervised (meanmedian and arithmetic mean geometric mean) FS filters. The evaluation was made by assessing the classification accuracy (word recognition error) of three well-known classifiers (knearest neighbors, support vector machines, and dynamic time warping). The key results of this study show that both unsupervised and supervised FS techniques improve on the classification accuracy on both individual and combined modalities. For instance, on the video component, we attain relative performance gains of 36.2% in error rates. FS is also useful as pre-processing for feature fusion. Copyright © 2014 ISCA.

Incremental filter and wrapper approaches for feature discretization

Discrete data representations are necessary, or at least convenient, in many machine learning problems. While feature selection (FS) techniques aim at finding relevant subsets of features, the goal of feature discretization (FD) is to find concise (quantized) data representations, adequate for the learning task at hand. In this paper, we propose two incremental methods for FD. The first method belongs to the filter family, in which the quality of the discretization is assessed by a (supervised or unsupervised) relevance criterion. The second method is a wrapper, where discretized features are assessed using a classifier. Both methods can be coupled with any static (unsupervised or supervised) discretization procedure and can be used to perform FS as pre-processing or post-processing stages. The proposed methods attain efficient representations suitable for binary and multi-class problems with different types of data, being competitive with existing methods. Moreover, using well-known FS methods with the features discretized by our techniques leads to better accuracy than with the features discretized by other methods or with the original features. (C) 2013 Elsevier B.V. All rights reserved.

Optimal location of supports in beam structures using genetic algorithms

Real structures can be thought as an assembly of components, as for instances plates, shells and beams. This later type of component is very commonly found in structures like frames which can involve a significant degree of complexity or as a reinforcement element of plates or shells. To obtain the desired mechanical behavior of these components or to improve their operating conditions when rehabilitating structures, one of the eventual parameters to consider for that purpose, when possible, is the location of the supports. In the present work, a beam-type structure is considered, and for a set of cases concerning different number and types of supports, as well as different load cases, the authors optimize the location of the supports in order to obtain minimum values of the maximum transverse deflection. The optimization processes are carried out using genetic algorithms. The results obtained, clearly show a good performance of the approach proposed. © 2014 IEEE.

Chemical composition and antioxidante activity of Tunisian Origanum glandulosum Desf. essential oil and volatile oil obtain by supercritical CO2 extraction

Dried flowers and leaves of Origanum glandulosum Desf. were submitted to hydrodistillation (HD) and supercritical fluid extraction with CO2 (SFE). The essential oils isolated by HD and volatile oils obtained by SFE were analysed by GC and GC/MS. Total phenolics content and antioxidant effectiveness were performed. The main components of the essential oils from Bargou and Nefza were: p-cymene (40.4% and 39%), thymol (38.7% and 34.4%) and γ- terpinene (12.3% and 19.2%), respectively. The major components obtain by SFE in the volatile oil, from Bargou and Nefza, were: p-cymene (32.3% and 36.2%), thymol (41% and 40%) and γ-terpinene (20.3% and 13.3%). Total phenolic content, expressed in gallic acid equivalent (GAE) g kg-1 dry weight, varied from 12 to 27 g kg-1 dw, and the ability to scavenge the DPPH radicals, expressed by IC50 ranged from 44 to143 mg L-1.

Efficient feature selection filters for high-dimensional data

Feature selection is a central problem in machine learning and pattern recognition. On large datasets (in terms of dimension and/or number of instances), using search-based or wrapper techniques can be cornputationally prohibitive. Moreover, many filter methods based on relevance/redundancy assessment also take a prohibitively long time on high-dimensional. datasets. In this paper, we propose efficient unsupervised and supervised feature selection/ranking filters for high-dimensional datasets. These methods use low-complexity relevance and redundancy criteria, applicable to supervised, semi-supervised, and unsupervised learning, being able to act as pre-processors for computationally intensive methods to focus their attention on smaller subsets of promising features. The experimental results, with up to 10(5) features, show the time efficiency of our methods, with lower generalization error than state-of-the-art techniques, while being dramatically simpler and faster.

Hyperspectral unmixing based on mixtures of Dirichlet components

This paper introduces a new unsupervised hyperspectral unmixing method conceived to linear but highly mixed hyperspectral data sets, in which the simplex of minimum volume, usually estimated by the purely geometrically based algorithms, is far way from the true simplex associated with the endmembers. The proposed method, an extension of our previous studies, resorts to the statistical framework. The abundance fraction prior is a mixture of Dirichlet densities, thus automatically enforcing the constraints on the abundance fractions imposed by the acquisition process, namely, nonnegativity and sum-to-one. A cyclic minimization algorithm is developed where the following are observed: 1) The number of Dirichlet modes is inferred based on the minimum description length principle; 2) a generalized expectation maximization algorithm is derived to infer the model parameters; and 3) a sequence of augmented Lagrangian-based optimizations is used to compute the signatures of the endmembers. Experiments on simulated and real data are presented to show the effectiveness of the proposed algorithm in unmixing problems beyond the reach of the geometrically based state-of-the-art competitors.

Extraction of volatile oil from aromatic plants with supercritical carbon dioxide: experiments and modeling

An overview of the studies carried out in our laboratories on supercritical fluid extraction (SFE) of volatile oils from seven aromatic plants: pennyroyal (Mentha pulegium L.), fennel seeds (Foeniculum vulgare Mill.), coriander (Coriandrum sativum L.), savory (Satureja fruticosa Beguinot), winter savory (Satureja montana L.), cotton lavender (Santolina chamaecyparisus) and thyme (Thymus vulgaris), is presented. A flow apparatus with a 1 L extractor and two 0.27 L separators was built to perform studies at temperatures ranging from 298 to 353 K and pressures up to 30.0 MPa. The best compromise between yield and composition compared with hydrodistillation (HD) was achieved selecting the optimum experimental conditions of extraction and fractionation. The major differences between HD and SFE oils is the presence of a small percentage of cuticular waxes and the relative amount of thymoquinone, an oxygenated monoterpene with important biological properties, which is present in the oils from thyme and winter savory. On the other hand, the modeling of our data on supercritical extraction of volatile oil from pennyroyal is discussed using Sovova's models. These models have been applied successfully to the other volatile oil extractions. Furthermore, other experimental studies involving supercritical CO2 carried out in our laboratories are also mentioned.

Comparison between monopolar and bipolar microsecond range pulsed electric fields in enhancement of apple juice extraction

The effect of monopolar and bipolar shaped pulses in additional yield of apple juice extraction is evaluated. The applied electric field strength, pulsewidth, and number of pulses are assessed for both pulse types, and divergences are analyzed. Variation of electric field strength is ranged from 100 to 1300 V/cm, pulsewidth from 20 to 300 mu s, and the number of pulses from 10 to 200, at a frequency of 200 Hz. Two pulse trains separated by 1 s are applied to apple cubes. Results are plotted against reference untreated samples for all assays. Specific energy consumption is calculated for each experiment as well as qualitative indicators for apple juice of total soluble dry matter and absorbance at 390-nm wavelength. Bipolar pulses demonstrated higher efficiency, and specific energetic consumption has a threshold where higher inputs of energy do not result in higher juice extraction when electric field variation is applied. Total soluble dry matter and absorbance results do not illustrate significant differences between application of monopolar and bipolar pulses, but all values are inside the limits proposed for apple juice intended for human consumption.

Pulsed electric field pre-treatment for apple juice extraction: Evaluation of monopolar and bipolar pulses effects

Additional apple juice extraction with pulsed electric field pretreated apple cubes towards control samples is evaluated. Monopolar and bipolar shaped pulses are compared and their effect is studied with variation of electric field, pulse width and number of pulses. Variation of electric field strength is ranged from 100 V/cm to 1300 V/cm, pulse width from 20 mu s to 300 mu s and number of pulses from 10 to 200, at frequency of 200Hz. Two pulse trains separated by 1 second are applied to all samples. Bipolar pulses showed higher apple juice yields with all studied parameters. Calculation of specific energies consumed was assessed and a threshold where higher energy inputs do not increase juice yield is found for a number of used parameters. Qualitative parameters of total soluble matter (Brix) and absorbance at 390 nm wavelength were determined for each sample and results show that no substantial differences are found for PEF pre-treated and control samples.

Robot visual localization through local feature fusion: an evaluation of multiple classifiers combination approaches

In the last decade, local image features have been widely used in robot visual localization. In order to assess image similarity, a strategy exploiting these features compares raw descriptors extracted from the current image with those in the models of places. This paper addresses the ensuing step in this process, where a combining function must be used to aggregate results and assign each place a score. Casting the problem in the multiple classifier systems framework, in this paper we compare several candidate combiners with respect to their performance in the visual localization task. For this evaluation, we selected the most popular methods in the class of non-trained combiners, namely the sum rule and product rule. A deeper insight into the potential of these combiners is provided through a discriminativity analysis involving the algebraic rules and two extensions of these methods: the threshold, as well as the weighted modifications. In addition, a voting method, previously used in robot visual localization, is assessed. Furthermore, we address the process of constructing a model of the environment by describing how the model granularity impacts upon performance. All combiners are tested on a visual localization task, carried out on a public dataset. It is experimentally demonstrated that the sum rule extensions globally achieve the best performance, confirming the general agreement on the robustness of this rule in other classification problems. The voting method, whilst competitive with the product rule in its standard form, is shown to be outperformed by its modified versions.