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.

Optimizing optimum-path forest classification for huge datasets

Traditional pattern recognition techniques can not handle the classification of large datasets with both efficiency and effectiveness. In this context, the Optimum-Path Forest (OPF) classifier was recently introduced, trying to achieve high recognition rates and low computational cost. Although OPF was much faster than Support Vector Machines for training, it was slightly slower for classification. In this paper, we present the Efficient OPF (EOPF), which is an enhanced and faster version of the traditional OPF, and validate it for the automatic recognition of white matter and gray matter in magnetic resonance images of the human brain. © 2010 IEEE.

Parkinson's disease identification through Optimum-Path Forest

Artificial intelligence techniques have been extensively used for the identification of several disorders related with the voice signal analysis, such as Parkinson's disease (PD). However, some of these techniques flaw by assuming some separability in the original feature space or even so in the one induced by a kernel mapping. In this paper we propose the PD automatic recognition by means of Optimum-Path Forest (OPF), which is a new recently developed pattern recognition technique that does not assume any shape/separability of the classes/feature space. The experiments showed that OPF outperformed Support Vector Machines, Artificial Neural Networks and other commonly used supervised classification techniques for PD identification. © 2010 IEEE.

Environmental solutions of recovery of Amazonian forest mining operations

In order for the projects of recovery of degraded areas to be successful, it is necessary to have a perfect recovery of the soil where the revegetation will be implanted as an initial action in the recovery of the whole process. The use of native forest species fully adapted to these types of terrain is another aspect of great importance, once the non-selection of these species, even if abundant in the surrounding areas, as it is in our case, implies great mortality of individuals during the planting and their low fixation during the process. The establishment of a monitoring program that contemplates the advancements obtained in the soil, the vegetation and the return of wild animals also collaborate in the evaluation of the success of the process. And, finally, the effective participation of the mining company, accepting and applying the techniques tested and indicated by research, even if, initially, the return time is longer than expected, also guarantees the success of the process. The mining company not only implemented a partnership with important universities in Brazil to obtain solutions for the environmental problems but also applied the developed techniques and the monitoring program. In the present work, we have attempted to summarize important aspects to evaluate the advancements in the rehabilitation plan for those areas, being here presented some results of the monitoring of areas under different levels of recovery, in accordance with the techniques adopted. Biological parameters of the soil were used to verify the efficiency of these different techniques in the recovery process. This work is part of the monitoring program of areas in rehabilitation by the mining company, implemented as of 1999 and in partnership with universities. The microbial activity was determined through the quantification of the carbon and nitrogen microbial biomass (BMC and BMN) and the activity of the dehydrogenase evaluated in the mining floor and tailing areas in different levels of soil preparation and planting of native species. The analysis of the parameters studied revealed that the preparation of the soil, following the three years proposed by the methodology, was important for the success in establishing the rehabilitation process. Some of the areas analyzed already show some parameters with values close or superior to those found in the capoeira (secondary forest), the latter being the non-treated area. © 2010 WIT Press.