Classification of indian classical vocal styles from melodic contours

A prominent categorization of Indian classical music is the Hindustani and Carnatic traditions, the two styleshaving evolved under distinctly different historical andcultural influences. Both styles are grounded in the melodicand rhythmic framework of raga and tala. The styles differ along dimensions such as instrumentation,aesthetics and voice production. In particular, Carnatic music is perceived as being more ornamented. The hypothesisthat style distinctions are embedded in the melodic contour is validated via subjective classification tests. Melodic features representing the distinctive characteristicsare extracted from the audio. Previous work based on the extent of stable pitch regions is supported by measurements of musicians’ annotations of stable notes. Further, a new feature is introduced that captures thepresence of specific pitch modulations characteristic ofornamentation in Indian classical music. The combined features show high classification accuracy on a database of vocal music of prominent artistes. The misclassifications are seen to match actual listener confusions.

Determination of in situ uniaxial compressive strength of coal seams based on geophysical data

The central issue for pillar design in underground coal mining is the in situ uniaxial compressive strength (sigma (cm)). The paper proposes a new method for estimating in situ uniaxial compressive strength in coal seams based on laboratory strength and P wave propagation velocity. It describes the collection of samples in the Bonito coal seam, Fontanella Mine, southern Brazil, the techniques used for the structural mapping of the coal seam and determination of seismic wave propagation velocity as well as the laboratory procedures used to determine the strength and ultrasonic wave velocity. The results obtained using the new methodology are compared with those from seven other techniques for estimating in situ rock mass uniaxial compressive strength.

Drying soybean seed using air ambient temperature at low relative humidity

Under subtropical and tropical environments soybean seed (Glycine max (L.) Merrill) are harvested early to avoid deterioration from weathering. Careful after-harvest drying is required and is an important step in maintaining the physiological quality of the seed. Soybean seed should be harvested when the moisture content is in a range of 16-20%. Traditional drying utilizes a high temperature air stream passed through the seed mass without dehumidification. The drying time is long because the system is inefficient and the high temperature increases the risk of thermal damage to the seed. New technology identified as heat pipe technology (HPT) is available and has the unique feature of removing the moisture from the air stream before it is passed through the seed mass at the same environmental temperature. Two studies were conducted to evaluate the performance of HPT for dry soybean seed. In the first study the seeds were dried from 17.5 to 11.1% in 2 hours and 29 minutes and in the second sudy the seeds were dried from 22.6 to 11.9% in 16 hours and 32 minutes. This drying process caused no reduction in seed quality as measured by the standard germination, tetrazolium-viability, accelerated aging and seedling vigor classification tests. The only parameter that indicated a slight seed quality reduction was tetrazolium vigor in the second study. It was concluded that the HPT system is a promising technology for drying soybean seed when efficiency and maintenance of physiological quality are desired.

Whistle variability in South Atlantic spinner dolphins from the Fernando de Noronha Archipelago off Brazil

A series of quali- and quantitative analyses were conducted to evaluate the variability of spinner dolphin whistles from the Fernando de Noronha Archipelago off Brazil. Nine variables were extracted from each whistle contour, and the whistle contours shapes were classified into the seven categories described in Driscoll (1995). The analysis showed mean beginning and ending frequencies values of 10.78 and 12.74 kHz, respectively. on average, whistle duration was relatively short, with mean values around 0.495 s (N=702). Comparative analyses were also conducted to investigate the relationship between the obtained results and those presented in previous studies. When comparing averages, the results of the study of Oswald et al. (2003) in the Tropical Eastern Pacific (TEP) presented less significant differences in relation to this study; only whistle duration differed significantly between both works. The results of multivariate classification tests also pointed TEP population as the closest related to the population studied here. The similarities between such disjunct populations might be attributed to a more recent isolation event (the closing of the Panama Isthmus) than the divergence that has driven North and South Atlantic populations apart. (c) 2006 Acoustical Society of America.

Caracterização e biodegradação de lodo de estações de tratamento de água para descarte em aterro sanitário

Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES)

Cyclic behaviour of saturated sands subject to previous horizontal shear stresses

The dynamic behaviour of saturated sands has been studied from different perspectives. However, most experimental research on this field does not take into account the shear stress conditions existing prior to the application of dynamic loads; i.e., a null initial static shear stress (τo = 0) is assumed. The main objective of this work is to report on the influence that static shear stresses (τo) have on the behaviour of saturated sands under cyclic shear loads. This article presents the results and analysis of part of a wider experimental programme involving 30 monotonic and 26 cyclic simple shear tests for different combinations of static shear stress (τo) and cyclic shear stress (τc) (all undrained), besides identification and classification tests. The tested samples have been taken from the area of the North Entrance Mouth at the Port of Barcelona (Spain).

Whistle variability in South Atlantic spinner dolphins from the Fernando de Noronha Archipelago off Brazil

A series of quali- and quantitative analyses were conducted to evaluate the variability of spinner dolphin whistles from the Fernando de Noronha Archipelago off Brazil. Nine variables were extracted from each whistle contour, and the whistle contours shapes were classified into the seven categories described in Driscoll (1995). The analysis showed mean beginning and ending frequencies values of 10.78 and 12.74 kHz, respectively. on average, whistle duration was relatively short, with mean values around 0.495 s (N=702). Comparative analyses were also conducted to investigate the relationship between the obtained results and those presented in previous studies. When comparing averages, the results of the study of Oswald et al. (2003) in the Tropical Eastern Pacific (TEP) presented less significant differences in relation to this study; only whistle duration differed significantly between both works. The results of multivariate classification tests also pointed TEP population as the closest related to the population studied here. The similarities between such disjunct populations might be attributed to a more recent isolation event (the closing of the Panama Isthmus) than the divergence that has driven North and South Atlantic populations apart. (c) 2006 Acoustical Society of America.

Machine vision for the automatic classification of images acquired from Non-destructive tests

This project is based on Artificial Intelligence (A.I) and Digital Image processing (I.P) for automatic condition monitoring of sleepers in the railway track. Rail inspection is a very important task in railway maintenance for traffic safety issues and in preventing dangerous situations. Monitoring railway track infrastructure is an important aspect in which the periodical inspection of rail rolling plane is required.Up to the present days the inspection of the railroad is operated manually by trained personnel. A human operator walks along the railway track searching for sleeper anomalies. This monitoring way is not more acceptable for its slowness and subjectivity. Hence, it is desired to automate such intuitive human skills for the development of more robust and reliable testing methods. Images of wooden sleepers have been used as data for my project. The aim of this project is to present a vision based technique for inspecting railway sleepers (wooden planks under the railway track) by automatic interpretation of Non Destructive Test (NDT) data using A.I. techniques in determining the results of inspection.

Classification of lumber of Eucalyptus using non-destructive tests

Classification and standardization of the sawn wood is a usual activity, developed by countries that come as great consumers of this material. Brazil does not practice the classification of sawn wood. This work had the main objective of evaluating the sensibility of most common non-destructive tests in the classification of dimension lumber from fast grown Eucalyptus plantation. Wood was obtained from genetic material cultivated at Minas Gerais State, Brazil. 296 beams of structural dimensions (6 cm × 12 cm × 280 cm) from 10 different clones of Eucalyptus were sampled. Beams were non-destructively (stress wave, ultrasound and transverse vibration) and destructively (static bending and compression parallel to grain) tested. Non-destructive results showed sensibility in the classification of structural dimension lumber, being possible to establish wave velocity intervals that attend to the main strength classes reported by Wooden Structures Brazilian Code.

Classification of breast masses using a committee machine of artificial neural networks

This work proposes a new approach using a committee machine of artificial neural networks to classify masses found in mammograms as benign or malignant. Three shape factors, three edge-sharpness measures, and 14 texture measures are used for the classification of 20 regions of interest (ROIs) related to malignant tumors and 37 ROIs related to benign masses. A group of multilayer perceptrons (MLPs) is employed as a committee machine of neural network classifiers. The classification results are reached by combining the responses of the individual classifiers. Experiments involving changes in the learning algorithm of the committee machine are conducted. The classification accuracy is evaluated using the area A. under the receiver operating characteristics (ROC) curve. The A, result for the committee machine is compared with the A, results obtained using MLPs and single-layer perceptrons (SLPs), as well as a linear discriminant analysis (LDA) classifier Tests are carried out using the student's t-distribution. The committee machine classifier outperforms the MLP SLP, and LDA classifiers in the following cases: with the shape measure of spiculation index, the A, values of the four methods are, in order 0.93, 0.84, 0.75, and 0.76; and with the edge-sharpness measure of acutance, the values are 0.79, 0.70, 0.69, and 0.74. Although the features with which improvement is obtained with the committee machines are not the same as those that provided the maximal value of A(z) (A(z) = 0.99 with some shape features, with or without the committee machine), they correspond to features that are not critically dependent on the accuracy of the boundaries of the masses, which is an important result. (c) 2008 SPIE and IS&T.

Classification and staging of chronic liver disease from multimodal data

Chronic liver disease (CLD) is most of the time an asymptomatic, progressive, and ultimately potentially fatal disease. In this study, an automatic hierarchical procedure to stage CLD using ultrasound images, laboratory tests, and clinical records are described. The first stage of the proposed method, called clinical based classifier (CBC), discriminates healthy from pathologic conditions. When nonhealthy conditions are detected, the method refines the results in three exclusive pathologies in a hierarchical basis: 1) chronic hepatitis; 2) compensated cirrhosis; and 3) decompensated cirrhosis. The features used as well as the classifiers (Bayes, Parzen, support vector machine, and k-nearest neighbor) are optimally selected for each stage. A large multimodal feature database was specifically built for this study containing 30 chronic hepatitis cases, 34 compensated cirrhosis cases, and 36 decompensated cirrhosis cases, all validated after histopathologic analysis by liver biopsy. The CBC classification scheme outperformed the nonhierachical one against all scheme, achieving an overall accuracy of 98.67% for the normal detector, 87.45% for the chronic hepatitis detector, and 95.71% for the cirrhosis detector.

Classification Performance of Multilayer Perceptrons with Different Risk Functionals

In the present paper we assess the performance of information-theoretic inspired risks functionals in multilayer perceptrons with reference to the two most popular ones, Mean Square Error and Cross-Entropy. The information-theoretic inspired risks, recently proposed, are: HS and HR2 are, respectively, the Shannon and quadratic Rényi entropies of the error; ZED is a risk reflecting the error density at zero errors; EXP is a generalized exponential risk, able to mimic a wide variety of risk functionals, including the information-thoeretic ones. The experiments were carried out with multilayer perceptrons on 35 public real-world datasets. All experiments were performed according to the same protocol. The statistical tests applied to the experimental results showed that the ubiquitous mean square error was the less interesting risk functional to be used by multilayer perceptrons. Namely, mean square error never achieved a significantly better classification performance than competing risks. Cross-entropy and EXP were the risks found by several tests to be significantly better than their competitors. Counts of significantly better and worse risks have also shown the usefulness of HS and HR2 for some datasets.

A Survey of Active Learning Algorithms for Supervised Remote Sensing Image Classification

Defining an efficient training set is one of the most delicate phases for the success of remote sensing image classification routines. The complexity of the problem, the limited temporal and financial resources, as well as the high intraclass variance can make an algorithm fail if it is trained with a suboptimal dataset. Active learning aims at building efficient training sets by iteratively improving the model performance through sampling. A user-defined heuristic ranks the unlabeled pixels according to a function of the uncertainty of their class membership and then the user is asked to provide labels for the most uncertain pixels. This paper reviews and tests the main families of active learning algorithms: committee, large margin, and posterior probability-based. For each of them, the most recent advances in the remote sensing community are discussed and some heuristics are detailed and tested. Several challenging remote sensing scenarios are considered, including very high spatial resolution and hyperspectral image classification. Finally, guidelines for choosing the good architecture are provided for new and/or unexperienced user.

Binary classification of dyslipidemia from the waist-to-hip ratio and body mass index: a comparison of linear, logistic, and CART models.

BACKGROUND: We sought to improve upon previously published statistical modeling strategies for binary classification of dyslipidemia for general population screening purposes based on the waist-to-hip circumference ratio and body mass index anthropometric measurements. METHODS: Study subjects were participants in WHO-MONICA population-based surveys conducted in two Swiss regions. Outcome variables were based on the total serum cholesterol to high density lipoprotein cholesterol ratio. The other potential predictor variables were gender, age, current cigarette smoking, and hypertension. The models investigated were: (i) linear regression; (ii) logistic classification; (iii) regression trees; (iv) classification trees (iii and iv are collectively known as "CART"). Binary classification performance of the region-specific models was externally validated by classifying the subjects from the other region. RESULTS: Waist-to-hip circumference ratio and body mass index remained modest predictors of dyslipidemia. Correct classification rates for all models were 60-80%, with marked gender differences. Gender-specific models provided only small gains in classification. The external validations provided assurance about the stability of the models. CONCLUSIONS: There were no striking differences between either the algebraic (i, ii) vs. non-algebraic (iii, iv), or the regression (i, iii) vs. classification (ii, iv) modeling approaches. Anticipated advantages of the CART vs. simple additive linear and logistic models were less than expected in this particular application with a relatively small set of predictor variables. CART models may be more useful when considering main effects and interactions between larger sets of predictor variables.

Documentation of fracture severity with the AO classification of pediatric long-bone fractures.

BACKGROUND: The AO comprehensive pediatric longbone fracture classification system describes the localization and morphology of fractures, and considers severity in 3 categories: (1) simple, (2) wedge, and (3) complex. We evaluated the reliability and accuracy of surgeons in using this rating system. MATERIAL AND METHODS: In a first validation phase, 5 experienced pediatric (orthopedic) surgeons reviewed radiographs of 267 prospectively collected pediatric fractures (agreement study A). In a second study (B), 70 surgeons of various levels of experience in 15 clinics classified 275 fractures via internet. Simple fractures comprised about 90%, 99% and 100% of diaphyseal (D), metaphyseal (M), and epiphyseal (E) fractures, respectively. RESULTS: Kappa coefficients for severity coding in D fractures were 0.82 and 0.51 in studies A and B, respectively. The median accuracy of surgeons in classifying simple fractures was above 97% in both studies but was lower, 85% (46-100), for wedge or complex D fractures. INTERPRETATION: While reliability and accuracy estimates were satisfactory as a whole, the ratings of some individual surgeons were inadequate. Our findings suggest that the classification of fracture severity in children should be done in only two categories that distinguish between simple and wedge/complex fractures.