Fast automatic microstructural segmentation of ferrous alloy samples using optimum-path forest

In this work we propose a novel automatic cast iron segmentation approach based on the Optimum-Path Forest classifier (OPF). Microscopic images from nodular, gray and malleable cast irons are segmented using OPF, and Support Vector Machines (SVM) with Radial Basis Function and SVM without kernel mapping. Results show accurate and fast segmented images, in which OPF outperformed SVMs. Our work is the first into applying OPF for automatic cast iron segmentation. © 2010 Springer-Verlag.

Robust and fast vowel recognition using optimum-path forest

The applications of Automatic Vowel Recognition (AVR), which is a sub-part of fundamental importance in most of the speech processing systems, vary from automatic interpretation of spoken language to biometrics. State-of-the-art systems for AVR are based on traditional machine learning models such as Artificial Neural Networks (ANNs) and Support Vector Machines (SVMs), however, such classifiers can not deal with efficiency and effectiveness at the same time, existing a gap to be explored when real-time processing is required. In this work, we present an algorithm for AVR based on the Optimum-Path Forest (OPF), which is an emergent pattern recognition technique recently introduced in literature. Adopting a supervised training procedure and using speech tags from two public datasets, we observed that OPF has outperformed ANNs, SVMs, plus other classifiers, in terms of training time and accuracy. ©2010 IEEE.

Fast petroleum well drilling monitoring through optimum-path forest

Automatic inspection of petroleum well drilling has became paramount in the last years, mainly because of the crucial importance of saving time and operations during the drilling process in order to avoid some problems, such as the collapse of the well borehole walls. In this paper, we extended another work by proposing a fast petroleum well drilling monitoring through a modified version of the Optimum-Path Forest classifier. Given that the cutting's volume at the vibrating shale shaker can provide several information about drilling, we used computer vision techniques to extract texture informations from cutting images acquired by a digital camera. A collection of supervised classifiers were applied in order to allow comparisons about their accuracy and effciency. We used the Optimum-Path Forest (OPF), EOPF (Efficient OPF), Artificial Neural Network using Multilayer Perceptrons (ANN-MLP) Support Vector Machines (SVM), and a Bayesian Classifier (BC) to assess the robustness of our proposed schema for petroleum well drilling monitoring through cutting image analysis.

Morphological changes in the fast vs slow fiber profiles of the urethras of diabetic pregnant rats

Background: This study was undertaken to test the hypothesis that diabetes and pregnancy detrimentally affect the normal function of urethral striated muscles in rats, providing a model for additional studies related to urinary incontinence. The aim of this study was to evaluate morphological alterations in the urethral striated muscles of diabetic pregnant rats. Materials and Methods: Twenty female Wistar rats were distributed into four experimental groups of five rats as follows: virgin, pregnant, diabetic virgin, and diabetic pregnant. Diabetes was induced using streptozotocin administration (40 mg/kg i.v.). The rats were lethally anesthetized, and the urethra and vagina were extracted as a unit. Cryostat sections (6 μm thick) were cut and stained with hematoxylin-eosin, and immunohistochemical procedures were performed and subjected to morphological and semi quantitative analysis. Results: The urethral striated muscle from the diabetic pregnant rats presented with the following variations: thinning and atrophy, disorganization and disruption associated with the colocalization of fast and slow fibers and a steady decrease in the proportion of fast vs slow fibers. Conclusion: Diabetes and pregnancy impair the urethral striated muscle and alter its fiber type distribution. © Copyright G. Marini et al., 2011.

Fast identification of individuals based on iris characteristics for biometric systems

Nowadays, systems based on biométrie techniques have a wide acceptance in many different areas, due to their levels of safety and accuracy. A biometrie technique that is gaining prominence is the identification of individuals through iris recognition. However, to be proficiently used these systems must process their recognition task as fast as possible. The goal of this work has been the development of an iris recognition method to produce results rapidly, yet without losing the recognition accuracy. The experimental results show that the method is quite promising. © 2012 Taylor & Francis Group.

Fast robot voice interface through optimum-path forest

Voice-based user interfaces have been actively pursued aiming to help individuals with motor impairments, providing natural interfaces to communicate with machines. In this work, we have introduced a recent machine learning technique named Optimum-Path Forest (OPF) for voice-based robot interface, which has been demonstrated to be similar to the state-of-the-art pattern recognition techniques, but much faster. Experiments were conducted against Support Vector Machines, Neural Networks and a Bayesian classifier to show the OPF robustness. The proposed architecture provides high accuracy rates allied with low computational times. © 2012 IEEE.

Fast fault diagnosis in power transformers using optimum-path forest

In this paper we propose a fast and an accurate method for fault diagnosis in power transformers by means of Optimum-Path Forest (OPF) classifier. Since we applied Dissolved Gas Analysis (DGA), the samples have been labeled by IEEE/IEC standard, which was further analyzed by OPF and several other well known supervised pattern recognition techniques. The experiments have showed that OPF can achieve high recognition rates with low computational cost. © 2012 IEEE.

A fast cholinergic modulation of the primary acoustic startle circuit in rats

Cochlear root neurons (CRNs) are the first brainstem neurons which initiate and participate in the full expression of the acoustic startle reflex. Although it has been suggested that a cholinergic pathway from the ventral nucleus of the trapezoid body (VNTB) conveys auditory prepulses to the CRNs, the neuronal origin of the VNTB-CRNs projection and the role it may play in the cochlear root nucleus remain uncertain. To determine the VNTB neuronal type which projects to CRNs, we performed tract-tracing experiments combined with mechanical lesions, and morphometric analyses. Our results indicate that a subpopulation of non-olivocochlear neurons projects directly and bilaterally to CRNs via the trapezoid body. We also performed a gene expression analysis of muscarinic and nicotinic receptors which indicates that CRNs contain a cholinergic receptor profile sufficient to mediate the modulation of CRN responses. Consequently, we investigated the effects of auditory prepulses on the neuronal activity of CRNs using extracellular recordings in vivo. Our results show that CRN responses are strongly inhibited by auditory prepulses. Unlike other neurons of the cochlear nucleus, the CRNs exhibited inhibition that depended on parameters of the auditory prepulse such as intensity and interstimulus interval, showing their strongest inhibition at short interstimulus intervals. In sum, our study supports the idea that CRNs are involved in the auditory prepulse inhibition of the acoustic startle reflex, and confirms the existence of multiple cholinergic pathways that modulate the primary acoustic startle circuit. © 2013 Springer-Verlag Berlin Heidelberg.

Sensitive voltammetric sensor for fast detection of mycolic acids present in mycobacteria

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

Are early and late rate of force development differently influenced by fast-velocity resistance training?

This study examined the effect of fast-velocity concentric isokinetic resistance training (FV) on the rate of force development (RFD) at early (<100 ms) and late phases (>100 ms) of rising muscle force. Nine men participated in a 6-week resistance training intervention for the lower body, and nine matched subjects participated as controls (CON). During concentric isokinetic (180°s-1) knee extension training, subjects were instructed to do each contraction 'as fast and forcefully as possible'. Maximal muscle strength (MVC) and RFD (0-10, 0-20, ..., 0-250 ms from the onset of contraction) were measured during maximal voluntary isometric contraction of the knee extensors (KE). There were no significant changes in MVC of KE in both groups after intervention (FV = 314·2 ± 101·1 versus 338·7 ± 88·0 N{bullet operator}m, P>0·05; CON = 293·3 ± 94·8 versus 280·0 ± 72·2 N{bullet operator}m, P>0·05). The RFD increased 39-71% at time intervals up to 90 ms from the onset of the contraction (P<0·05), whereas no change occurred at later time intervals. Similarly, relative RFD (i.e.%MVC{bullet operator}s-1) (RFDr) increased 33-56% at time intervals up to 70 ms from the onset of the contraction (P<0·05). It can be concluded that a short period of resistance training performed with concentric fast-velocity isokinetic muscle contractions is able to enhance RFD and RFDr obtained at the early phase of rising muscle force. © 2013 The Authors Clinical Physiology and Functional Imaging © 2013 Scandinavian Society of Clinical Physiology and Nuclear Medicine.