Bruno Rodrigues de Oliveira's Projects
A qualitative Decision Tree model for Common Beans and Cowpea classification
ANALYTIC HIERARCHY PROCESS (AHP) FOR TABULAR DATA
Automatically exported from code.google.com/p/ahpy
Alocação de recursos em investimentos utilizando um modelo da Análise Hierárquica de Processos (AHP)
Aproximação de séries temporais com polinômio de Chebyshev
Bitcoin price Prediction ( Time Series ) using LSTM Recurrent neural network
Obtenção de Bordas em Imagens utilizando Transformada Wavelet
Blind Source Separation
Classificação de Arritmias Cardíacas Utilizando Aprendizado de Máquina
This work presents a machine learning methodology to obtain classification models for nine forage cultivars, subject to moderate and severe water stress. The Naïve Bayes algorithm is used together with the Kernel Density Estimation method to obtain the densities used in the classification models.
Classification of soybean genotypes in drought and saline stress environment using Decision Tree algorithm
Comitê de Máquinas de Aprendizado (Ensemble Learning) - Voto Majoritário
Como exportar um DataFrame do Pandas para uma Tabela do MS Word
Selection of corn cultivars grown in agricultural areas with biological and mineral nitrogen management
We present a dataset obtained from forty soybean cultivars planted in subsequent seasons. The experiment used randomized blocks, arranged in a split-plot scheme, with four replications.
Decomposição em Valores Singulares e Análise de Componentes Principais
Decomposição em Valores Singulares em Multirresolução (MRSVD - Multiresolution Singular Value Decomposition)
Detecção/Remoção de Outliers com Python: Casos Univariado e Multivariado
Premature Ventricular Contraction (PVC) is an arrhythmia that can be associated with several cardiac disorders that affect from 40% to 75% of the general population. PVC occurrence is measure from Electrocardiogram (ECG). If in an ECG occur one (or two) PVC between two Normal heartbeats, then there is a Ventricular Bigeminy (or Trigeminy). The prevalence of Ventricular Bigeminy/Trigeminy rhythms was associated with angina, hypertension, congestive heart failure and myocardial infarction. For this, early detection of these rhythms is very important. In this work it is proposed a new approach for early diagnosis of these rhythms, which is based on Random Forest algorithm and information about previous heartbeat and heart rhythm. Thus, the proposed approach uses only the information before occurrence of Ventricular Bigeminy/Trigeminy. This simple approach was capable of predict the Bigeminy/Trigeminy occurrence with accuracy, sensitivity and specificity of 98.94%, 96.28% and 99.83, respectively. Furthermore, the results show that the Ventricular Bigeminy/Trigeminy is preceded for Normal, A-V junctional and Paced heart rhythms in most of the examples. Besides that, it is presented a simple algorithm for decision about the occurrence of Ventricular Bigeminy/Trigeminy rhythms.
Escalograma para análise de Séries Temporais
Growth and production models can help to simulate the growth of tree dimensions to predict forest productivity at different levels. In this context, the following questions arise: (i) is it possible to recognize the growth pattern of eucalyptus species based on spectral features using machine learning (ML) for data modeling? (ii) what spectral features provides better accuracy? and (iii) what ML algorithms are most accurate for performing this modeling? To answer these questions, the present study evaluated the use of ML techniques using breast height and total plant height to classify the growth of five species of eucalyptus and Corymbria citriodora in an unsupervised learning, and the obtained classes for induce ML algorithms to recognize the species with relation to their growth using vegetation indices (VIs) and spectral bands (SBs). It were evaluated five eucalyptus species (E. camaldulensis, E. uroplylla, E. saligna, E. grandis e E. urograndis) and C. citriodora in experimental design of randomized blocks with four replicates, with 20 plants inside each experimental plot. The diameter at breast height and total plant height at stand level were obtained by measuring five trees in each experimental unit in seven measurements. During this same period, a flight was carried out using a remotely piloted aircraft for the acquisition of spectral variables (SBs and VIs). For recognition of eucalyptus species in relation to their growth two machine learning approaches were employed: supervised and unsupervised. The average accuracy obtained from 10-fold cross-validation, employing Random Forest algorithm and 24 features, was 0.76. This result shows that the proposed approach is appropriate to recognize different eucalyptus species based on their growth.
Arquivos do livro Ciência de dados e aprendizado de máquina com aplicações em Python
Maximizing Cowpea Harvests Silicon Treatment Optimization through TOPSIS and Manhattan Distance Modeling
Osclass plugins
Seleção/Ponderação de Modelos de Classificação pela Análise Hierárquica de Processos
Introduction The analysis of electrocardiogram (ECG) signals allows the experts to diagnosis several cardiac disorders. However, the accuracy of such diagnostic depends on the signals quality. In this paper it is proposed a simple method for power-line interference (PLI) removal based on the wavelet decomposition, without the use of thresholding techniques.
Obter modelos de predição sobre a alta hospitalar e verificar se esses modelos são distintos considerando os gêneros masculino e feminino.
Premature Ventricular Contractions arrhythmias can be associated with sudden death and acute myocardial infarction and occurs in the 50% of the population for Holter monitoring. PVC patterns are very hard to recognizing as their waveforms can be confused with other heartbeats, such as Right and Left Bundle Branch Block. In this work it is proposed a new approach for PVC recognition, based on Gaussian Naive Bayes algorithm and AMUSE, which is a method for blind source separation problem. This approach provides a set of attributes which are combined by Linear Discriminant Analysis, allowing the training of an ensemble learning. Each learned model is weighted by the Analytic Hierarchy Process according to its importance, obtained from the performance metrics. This approach has some advantages over baseline methods as it does not use a pre-processing stage and employs a simple machine learning model, that is trained using only two parameters for each feature. Using a common dataset for training and test, the proposed approach achieves 98.75% of accuracy, 90.65% of sensitivity and 99.46% of specificity. For other datasets, the best performance was 99.57% of accuracy, 98.64% of sensitivity and 99.65% of specificity. In general, the proposed approach is better than most state-of-the-art methods for some performance metrics.