Nonstationary feature extraction techniques for automatic classification of impact acoustic signals

Condition monitoring of wooden railway sleepers applications are generallycarried out by visual inspection and if necessary some impact acoustic examination iscarried out intuitively by skilled personnel. In this work, a pattern recognition solutionhas been proposed to automate the process for the achievement of robust results. Thestudy presents a comparison of several pattern recognition techniques together withvarious nonstationary feature extraction techniques for classification of impactacoustic emissions. Pattern classifiers such as multilayer perceptron, learning cectorquantization and gaussian mixture models, are combined with nonstationary featureextraction techniques such as Short Time Fourier Transform, Continuous WaveletTransform, Discrete Wavelet Transform and Wigner-Ville Distribution. Due to thepresence of several different feature extraction and classification technqies, datafusion has been investigated. Data fusion in the current case has mainly beeninvestigated on two levels, feature level and classifier level respectively. Fusion at thefeature level demonstrated best results with an overall accuracy of 82% whencompared to the human operator.

Benchmark Evaluation of HOG Descriptors as Features for Classification of Traffic Signs

The purpose of this paper is to analyze the performance of the Histograms of Oriented Gradients (HOG) as descriptors for traffic signs recognition. The test dataset consists of speed limit traffic signs because of their high inter-class similarities.   HOG features of speed limit signs, which were extracted from different traffic scenes, were computed and a Gentle AdaBoost classifier was invoked to evaluate the different features. The performance of HOG was tested with a dataset consisting of 1727 Swedish speed signs images. Different numbers of HOG features per descriptor, ranging from 36 features up 396 features, were computed for each traffic sign in the benchmark testing. The results show that HOG features perform high classification rate as the Gentle AdaBoost classification rate was 99.42%, and they are suitable to real time traffic sign recognition. However, it is found that changing the number of orientation bins has insignificant effect on the classification rate. In addition to this, HOG descriptors are not robust with respect to sign orientation.

O trabalho policial: estudo da Polícia Cívil do Estado do Rio Grande do Sul

A tese apresenta um estudo do trabalho policial, tendo por referência empírica a Polícia Civil do Estado do Rio Grande do Sul. O trabalho policial é analisado a partir das relações sociais no campo de poder jurídico, que engloba, além da Polícia Civil, a Polícia Militar, o Ministério Público e o Poder Judiciário. Apresenta-se e analisa-se o processo de mudança quanto aos métodos de recrutamento e de formação dos novos policiais. Apresenta-se também uma análise das mudanças ocorridas no perfil sócio-demográfico dos policiais civis ao longo do período entre 1970 e 2004. Detalham-se as atividades desenvolvidas nas delegacias de polícia, apresentando os seguintes setores: o plantão, a investigação, o cartório e a secretaria. Discutem-se as formas através das quais, no desempenho das atividades policiais, ocorrem lutas pela classificação e pelo reconhecimento, que constituem múltiplas oposições, tais como entre "operacional" e "burocrata" e agente e delegado, entre outras. A abordagem das conexões entre trabalho policial e relações de gênero se faz presente ao longo do desenvolvimento da análise Considera-se que no estudo do trabalho policial civil, as questões de gênero remetem às representações e práticas de violência policial. Em outros termos, argumenta-se acerca da importância das relações de gênero na análise do trabalho policial, especialmente no que diz respeito às concepções de masculinidade, constitutivas classicamente da cultura policial, e às novas formas de expressão dessas relações sociais a partir da crescente presença feminina nos quadros da Polícia Civil do Estado do Rio Grande do Sul. A tese propicia a reflexão sobre as formas que assumem, hoje, as carreiras na Polícia Civil do Rio Grande do Sul, apontando avanços, embora em ritmo que inclui tempos de parada e espera, em direção ao uso de critérios públicos abrangentes na condução de seu agir.

Ontology-based metadata for e-learning content

Nowadays, the popularity of the Web encourages the development of Hypermedia Systems dedicated to e-learning. Nevertheless, most of the available Web teaching systems apply the traditional paper-based learning resources presented as HTML pages making no use of the new capabilities provided by the Web. There is a challenge to develop educative systems that adapt the educative content to the style of learning, context and background of each student. Another research issue is the capacity to interoperate on the Web reusing learning objects. This work presents an approach to address these two issues by using the technologies of the Semantic Web. The approach presented here models the knowledge of the educative content and the learner’s profile with ontologies whose vocabularies are a refinement of those defined on standards situated on the Web as reference points to provide semantics. Ontologies enable the representation of metadata concerning simple learning objects and the rules that define the way that they can feasibly be assembled to configure more complex ones. These complex learning objects could be created dynamically according to the learners’ profile by intelligent agents that use the ontologies as the source of their beliefs. Interoperability issues were addressed by using an application profile of the IEEE LOM- Learning Object Metadata standard.

How national culture on consumers' decision-making styles: a comparative study among Americans, Brazilians, Chinese, and japanese in the purchase of cell phones.

The influence of the national culture on consumer decision-making styles is investigated using a sample of Americans, Brazilians, Chinese, and Japanese consumers who have purchased a cell phone in the past three years. To make the research possible, a survey was used as a method of data collection. It relates Hofstede’s cultural classification typology with Sproles and Kendall’s consumer style inventory (CSI). The multivariate analysis of variance (MANOVA) results indicate six decision-making styles together with other consumer behavioral characteristics that can be used to distinguish and profile consumers who purchase cell phones. Empirical findings reveal that among Americans, Brazilians, and Japanese; Americans are the most quality conscious, brand conscious, innovative, and hedonistic shoppers; Brazilians are the most loyal, and Japanese, the most confused by overchoice consumers. Conceptual contributions and managerial implications are discussed.

Aquatic weed automatic classification using machine learning techniques

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

Vibrational spectroscopy applied to the study of archeological ceramic artifacts from Guarani culture in Brazil

An archeological artifact can be seen as a chronological element, which helps to determine the age of certain society and to understand the thinking, values and the way of life of this society. Thus, the classification of archeological artifacts is one of the approaches used to study the cultural system of antique societies trying to reconstruct their history. The "Centro de Museologia, Antropologia e Argueologia (CEMAARQ)" of the "Unesp Univ Estadual Paulista" in Presidente Prudente, São Paulo state, Brazil, develops projects within this context (identification and preservation). This is the case of the archeological site named "Lagoa São Paulo-02" discovered in 1993 at the margins of the Parana river in the region of Presidente Epitacio city, São Paulo state, Brazil. This site has ceramic fragments of different shapes and sizes that have a strong influence of traces of the Guarani culture, which is one of the Brazilian native populations. These samples were basically characterized via micro-Raman scattering and Fourier transform infrared absorption (FTIR) spectroscopies. The main objective was to identify the pigments used in the manufacture of the ceramic artifacts and to analyze the composition of the ceramic body to understand how the artifacts were made. Three pigments were found: red, black and white. For the red pigment were identified characteristic bands of hematite, an iron oxide found in the red rocks of the river banks that were eroded by water. The black pigment, probably, is due to the use of vegetal charcoal, which is found in nature as the product of burning organic material such as wood. For the white pigment, the FTIR spectra suggested the use of kaolin, either in the ceramic body or in the proper white pigment, due to the presence of the characteristic bands of the kaolinite. Complementary, the additives applied as anti-plastics were identified as charcoal and quartz, being the latter found in the rocks present in the archeological site. (C) 2010 Elsevier B.V. All rights reserved.

Efficient supervised optimum-path forest classification for large datasets

Fundação de Amparo à Pesquisa do Estado de São Paulo (FAPESP)

CENSUS HISTOGRAMS: A SIMPLE FEATURE EXTRACTION and MATCHING APPROACH FOR FACE RECOGNITION

Most face recognition approaches require a prior training where a given distribution of faces is assumed to further predict the identity of test faces. Such an approach may experience difficulty in identifying faces belonging to distributions different from the one provided during the training. A face recognition technique that performs well regardless of training is, therefore, interesting to consider as a basis of more sophisticated methods. In this work, the Census Transform is applied to describe the faces. Based on a scanning window which extracts local histograms of Census Features, we present a method that directly matches face samples. With this simple technique, 97.2% of the faces in the FERET fa/fb test were correctly recognized. Despite being an easy test set, we have found no other approaches in literature regarding straight comparisons of faces with such a performance. Also, a window for further improvement is presented. Among other techniques, we demonstrate how the use of SVMs over the Census Histogram representation can increase the recognition performance.

Evidence supporting the recognition of Cole latent virus as a distinct carlavirus

Some molecular properties are described of Cole latent virus (CoLV), hitherto designated a tentative species of the Carlavirus genus. CoLV genomic RNA (Ribonucleic acid) of 8.3 Kb is polyadenylated. Two unencapsidated polyadenylated subgenomic RNAs (2.6 and 1.3 Kb) and three double-stranded RNAs (dsRNAs) (8.3, 2.6 and 1.3 Kbp), which are twice the size of the genomic and subgenomics ssRNAs, are produced in CoLV-infected plants, two additional dsRNAs (7.2 and 6.3 Kbp) were also detected plant extracts. By using a Carlavirus specific primer and a CoLV cDNA, a-3'-terminus fragment of 116 bp was amplified; it had homology with the carlaviruses Potato virus M (62%)., Hop latent virus (37%) and Blueberry scorch virus (36%) but no significant homology with 11 other carlaviruses. These results support the classification of CoLV as a distinct species of the Carlavirus genus.

Artificial immune systems for classification of petroleum well drilling operations

This paper presents two approaches of Artificial Immune System for Pattern Recognition (CLONALG and Parallel AIRS2) to classify automatically the well drilling operation stages. The classification is carried out through the analysis of some mud-logging parameters. In order to validate the performance of AIS techniques, the results were compared with others classification methods: neural network, support vector machine and lazy learning.

Pattern recognition theory in nonlinear signal processing

A body of research has developed within the context of nonlinear signal and image processing that deals with the automatic, statistical design of digital window-based filters. Based on pairs of ideal and observed signals, a filter is designed in an effort to minimize the error between the ideal and filtered signals. The goodness of an optimal filter depends on the relation between the ideal and observed signals, but the goodness of a designed filter also depends on the amount of sample data from which it is designed. In order to lessen the design cost, a filter is often chosen from a given class of filters, thereby constraining the optimization and increasing the error of the optimal filter. To a great extent, the problem of filter design concerns striking the correct balance between the degree of constraint and the design cost. From a different perspective and in a different context, the problem of constraint versus sample size has been a major focus of study within the theory of pattern recognition. This paper discusses the design problem for nonlinear signal processing, shows how the issue naturally transitions into pattern recognition, and then provides a review of salient related pattern-recognition theory. In particular, it discusses classification rules, constrained classification, the Vapnik-Chervonenkis theory, and implications of that theory for morphological classifiers and neural networks. The paper closes by discussing some design approaches developed for nonlinear signal processing, and how the nature of these naturally lead to a decomposition of the error of a designed filter into a sum of the following components: the Bayes error of the unconstrained optimal filter, the cost of constraint, the cost of reducing complexity by compressing the original signal distribution, the design cost, and the contribution of prior knowledge to a decrease in the error. The main purpose of the paper is to present fundamental principles of pattern recognition theory within the framework of active research in nonlinear signal processing.

A Fast Large Scale Iris Database Classification with Optimum-Path Forest Technique: A Case Study

Majority of biometric researchers focus on the accuracy of matching using biometrics databases, including iris databases, while the scalability and speed issues have been neglected. In the applications such as identification in airports and borders, it is critical for the identification system to have low-time response. In this paper, a graph-based framework for pattern recognition, called Optimum-Path Forest (OPF), is utilized as a classifier in a pre-developed iris recognition system. The aim of this paper is to verify the effectiveness of OPF in the field of iris recognition, and its performance for various scale iris databases. This paper investigates several classifiers, which are widely used in iris recognition papers, and the response time along with accuracy. The existing Gauss-Laguerre Wavelet based iris coding scheme, which shows perfect discrimination with rotary Hamming distance classifier, is used for iris coding. The performance of classifiers is compared using small, medium, and large scale databases. Such comparison shows that OPF has faster response for large scale database, thus performing better than more accurate but slower Bayesian classifier.

Extended Hierarchical Censored Production Rules (EHCPRs) system: An approach toward generalized knowledge representation

One common problem in all basic techniques of knowledge representation is the handling of the trade-off between precision of inferences and resource constraints, such as time and memory. Michalski and Winston (1986) suggested the Censored Production Rule (CPR) as an underlying representation and computational mechanism to enable logic based systems to exhibit variable precision in which certainty varies while specificity stays constant. As an extension of CPR, the Hierarchical Censored Production Rules (HCPRs) system of knowledge representation, proposed by Bharadwaj & Jain (1992), exhibits both variable certainty as well as variable specificity and offers mechanisms for handling the trade-off between the two. An HCPR has the form: Decision If(preconditions) Unless(censor) Generality(general_information) Specificity(specific_information). As an attempt towards evolving a generalized knowledge representation, an Extended Hierarchical Censored Production Rules (EHCPRs) system is suggested in this paper. With the inclusion of new operators, an Extended Hierarchical Censored Production Rule (EHCPR) takes the general form: Concept If (Preconditions) Unless (Exceptions) Generality (General-Concept) Specificity (Specific Concepts) Has_part (default: structural-parts) Has_property (default:characteristic-properties) Has_instance (instances). How semantic networks and frames are represented in terms of an EHCPRs is shown. Multiple inheritance, inheritance with and without cancellation, recognition with partial match, and a few default logic problems are shown to be tackled efficiently in the proposed system.

Shape-based features for cat ganglion retinal cells classification

This article presents a quantitative and objective approach to cat ganglion cell characterization and classification. The combination of several biologically relevant features such as diameter, eccentricity, fractal dimension, influence histogram, influence area, convex hull area, and convex hull diameter are derived from geometrical transforms and then processed by three different clustering methods (Ward's hierarchical scheme, K-means and genetic algorithm), whose results are then combined by a voting strategy. These experiments indicate the superiority of some features and also suggest some possible biological implications.