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.

Face Detection and Facial Feature Localization for multi-pose faces and complex backgroundimages

The objective of this thesis work, is to propose an algorithm to detect the faces in a digital image with complex background. A lot of work has already been done in the area of face detection, but drawback of some face detection algorithms is the lack of ability to detect faces with closed eyes and open mouth. Thus facial features form an important basis for detection. The current thesis work focuses on detection of faces based on facial objects. The procedure is composed of three different phases: segmentation phase, filtering phase and localization phase. In segmentation phase, the algorithm utilizes color segmentation to isolate human skin color based on its chrominance properties. In filtering phase, Minkowski addition based object removal (Morphological operations) has been used to remove the non-skin regions. In the last phase, Image Processing and Computer Vision methods have been used to find the existence of facial components in the skin regions.This method is effective on detecting a face region with closed eyes, open mouth and a half profile face. The experiment’s results demonstrated that the detection accuracy is around 85.4% and the detection speed is faster when compared to neural network method and other techniques.

Identification of cause of impairment in spiral drawings, using non-stationary feature extraction approach

Parkinson’s disease is a clinical syndrome manifesting with slowness and instability. As it is a progressive disease with varying symptoms, repeated assessments are necessary to determine the outcome of treatment changes in the patient. In the recent past, a computer-based method was developed to rate impairment in spiral drawings. The downside of this method is that it cannot separate the bradykinetic and dyskinetic spiral drawings. This work intends to construct the computer method which can overcome this weakness by using the Hilbert-Huang Transform (HHT) of tangential velocity. The work is done under supervised learning, so a target class is used which is acquired from a neurologist using a web interface. After reducing the dimension of HHT features by using PCA, classification is performed. C4.5 classifier is used to perform the classification. Results of the classification are close to random guessing which shows that the computer method is unsuccessful in assessing the cause of drawing impairment in spirals when evaluated against human ratings. One promising reason is that there is no difference between the two classes of spiral drawings. Displaying patients self ratings along with the spirals in the web application is another possible reason for this, as the neurologist may have relied too much on this in his own ratings.

A Common-feature approach for testing present-value restrictions with financial data

It is well known that cointegration between the level of two variables (labeled Yt and yt in this paper) is a necessary condition to assess the empirical validity of a present-value model (PV and PVM, respectively, hereafter) linking them. The work on cointegration has been so prevalent that it is often overlooked that another necessary condition for the PVM to hold is that the forecast error entailed by the model is orthogonal to the past. The basis of this result is the use of rational expectations in forecasting future values of variables in the PVM. If this condition fails, the present-value equation will not be valid, since it will contain an additional term capturing the (non-zero) conditional expected value of future error terms. Our article has a few novel contributions, but two stand out. First, in testing for PVMs, we advise to split the restrictions implied by PV relationships into orthogonality conditions (or reduced rank restrictions) before additional tests on the value of parameters. We show that PV relationships entail a weak-form common feature relationship as in Hecq, Palm, and Urbain (2006) and in Athanasopoulos, Guillén, Issler and Vahid (2011) and also a polynomial serial-correlation common feature relationship as in Cubadda and Hecq (2001), which represent restrictions on dynamic models which allow several tests for the existence of PV relationships to be used. Because these relationships occur mostly with nancial data, we propose tests based on generalized method of moment (GMM) estimates, where it is straightforward to propose robust tests in the presence of heteroskedasticity. We also propose a robust Wald test developed to investigate the presence of reduced rank models. Their performance is evaluated in a Monte-Carlo exercise. Second, in the context of asset pricing, we propose applying a permanent-transitory (PT) decomposition based on Beveridge and Nelson (1981), which focus on extracting the long-run component of asset prices, a key concept in modern nancial theory as discussed in Alvarez and Jermann (2005), Hansen and Scheinkman (2009), and Nieuwerburgh, Lustig, Verdelhan (2010). Here again we can exploit the results developed in the common cycle literature to easily extract permament and transitory components under both long and also short-run restrictions. The techniques discussed herein are applied to long span annual data on long- and short-term interest rates and on price and dividend for the U.S. economy. In both applications we do not reject the existence of a common cyclical feature vector linking these two series. Extracting the long-run component shows the usefulness of our approach and highlights the presence of asset-pricing bubbles.

Evaluation of the Cartographic Communication Performance of a Route Guidance and Navigation System

This study evaluates the influence of different cartographic representations of in-car navigation systems on visual demand, subjective preference, and navigational error. It takes into account the type and complexity of the representation, maneuvering complexity, road layout, and driver gender. A group of 28 drivers (14 male and 14 female) participated in this experiment which was performed in a low-cost driving simulator. The tests were performed on a limited number of instances for each type of representation, and their purpose was to carry out a preliminary assessment and provide future avenues for further studies. Data collected for the visual demand study were analyzed using non-parametric statistical analyses. Results confirmed previous research that showed that different levels of design complexity significantly influence visual demand. Non-grid-like road networks, for example, influence significantly visual demand and navigational error. An analysis of simple maneuvers on a grid-like road network showed that static and blinking arrows did not present significant differences. From the set of representations analyzed to assess visual demand, both arrows were equally efficient. From a gender perspective, women seem to took at the display more than men, but this factor was not significant. With respect to subjective preferences, drivers prefer representations with mimetic landmarks when they perform straight-ahead tasks. For maneuvering tasks, landmarks in a perspective model created higher visual demands.

A novel algorithm for feature selection using Harmony Search and its application for non-technical losses detection

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

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.

New Insights on Nontechnical Losses Characterization Through Evolutionary-Based Feature Selection

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

Adaptive filter feature identification for structural health monitoring in an aeronautical panel

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Feature selection through gravitational search algorithm

In this paper we deal with the problem of feature selection by introducing a new approach based on Gravitational Search Algorithm (GSA). The proposed algorithm combines the optimization behavior of GSA together with the speed of Optimum-Path Forest (OPF) classifier in order to provide a fast and accurate framework for feature selection. Experiments on datasets obtained from a wide range of applications, such as vowel recognition, image classification and fraud detection in power distribution systems are conducted in order to asses the robustness of the proposed technique against Principal Component Analysis (PCA), Linear Discriminant Analysis (LDA) and a Particle Swarm Optimization (PSO)-based algorithm for feature selection.

Role of the surface state and structural feature in the thermoreversible sol-gel transition of a zirconyl aqueous precursor modified by sulfuric acid

The sols produced by admixture of ZrOCl2 acidified solutions to hot H2SO4 aqueous solutions were studied to clarify the effects of Cl- and SO42- ions on the kinetic stability of nanoparticles and to obtain some new evidence concerning the mechanism of a thermoreversible sol-gel transition observed in this system. The study of suspensions prepared with different molar ratios R-S = [Zr]/[SO42-] and R-Cl = [Zr]/[Cl-] revealed domains of composition of formation of thermoreversible gels, thermostable sols, and powder precipitation. The effects of R-S and R-Cl on the structural features of nanoparticles and on the particle solution interface were systematically analyzed for samples of thermoreversible and thermostable sol domains. Small-angle X-ray scattering measurements revealed the presence of small fractal aggregates in all samples of thermoreversible domains, while compact packing aggregates of primary particles are present in the thermostable sol. Extended X-ray absorption fine structure and elemental chemical analysis revealed that irrespective of the nominal value of R-S and R-Cl all studied samples of the thermoreversible domain are constituted by a well-defined compound possessing an inner core made of hydroxyl and oxo groups bridging together zirconium atoms surrounded on the surface by complexing sulfate ligands. zeta potentials of powders extracted by freeze-drying from the thermoreversible gel revealed a point of surface charge inversion attributed to the specific adsorption of SO42- ion. Thermoreversible gel formation is rationalized by considering the effect of the specific adsorption on the electrical double-layer repulsion together with the temperature dependency of the physical chemical properties of ions in solution.

Butanolides as a common feature of Iryanthera lancifolia and Virola surinamensis

A comparative phytochemical study between pericarps of Iryanthera lancifolia and Virola surinamensis showed that the first one contains a new pair of epimeric 2-alkenyl-gamma-lactones, besides an aryltetralinic lignan and one tocotrienol, while the second species contains the lignans, galgravin and veraguensin, seven juruenolides: juruenolides C, D, F, G and epi-juruenolides D, F, G, together with three pairs of epimeric aliphatic 2-alkenyl-gamma-lactones. Juruenolide F, epi-juruenolides D, F, G and the 2-alkenyl-gamma-lactones are new natural compounds. (C) 1998 Elsevier B.V. Ltd. All rights reserved.

SnO2, ZnO and related polycrystalline compound semiconductors: An overview and review on the voltage-dependent resistance (non-ohmic) feature

The present review describes mainly the history of SnO2-based voltage-dependent resistors, discusses the main characteristics of these polycrystalline semiconductor systems and includes a direct comparison with traditional ZnO-based voltage-dependent resistor systems to establish the differences and similarities, giving details of the basic physical principles involved with the non-ohmic properties in both polycrystalline systems. As an overview, the text also undertakes the main difficulties involved in processing SnO2- and ZnO-based non-ohmic systems, with an evaluation of the contribution of the dopants to the electronic properties and to the final microstructure and consequently to the system's non-ohmic behavior. However, since there are at least two review texts regarding ZnO-based systems [Levinson, L. M., and Philipp, H. R. Ceramic Bulletin 1985;64:639; Clarke, D. R. Journal of American Ceramic Society 1999;82:485], the main focus of the present text is dedicated to the SnO2-based varistor systems, although the basic physical principles described in the text are universally useful in the context of dense polycrystalline devices. However, the readers must be careful of how the microstructure heterogeneity and grain-boundary chemistry are capable to interfere in the global electrical response for particular systems. New perspectives for applications, commercialization and degradation studies involving SnO2-based polycrystalline non-ohmic systems are also outlined, including recent technological developments. Finally, at the end of this review a brief section is particularly dedicated to the presentation and discussions about others emerging non-ohmic polycrystalline ceramic devices (particularly based on perovskite ceramics) which must be deeply studied in the years to come, specially because some of these systems present combined high dielectric and non-ohmic properties. From both scientific and technological point of view these perovskite systems are quite interesting. (c) 2007 Elsevier Ltd. All rights reserved.