Multi-Dimensional Inference and Confidential Data Protection with Decision Tree Methods

A new automated approach for Electrocardiogram (ECG) arrhythmias characterization and classification with the combination of Wavelet transform and Decision tree classification is presented. The approach is based on two key steps. In the first step, the authors adopt the wavelet transform to extract the ECG signals wavelet coefficients as first features and utilize the combination of Principal Component Analysis (PCA) and Fast Independent Component Analysis (FastICA) to transform the first features into uncorrelated and mutually independent new features. In the second step, they utilize some decision tree methods currently in use: C4.5, Improved C4.5, CHAID (Chi - Square Automatic Interaction Detection) and Improved CHAID for the classification of ECG signals, which are taken, from the MIT-BIH database, including normal subjects and subjects affected by arrhythmia. The authors’ results suggest the high reliability and high classification accuracy of C4.5 algorithm with the bootstrap aggregation.

Download Full-text

Network traffic classification — A comparative study of two common decision tree methods: C4.5 and Random forest

2014 2nd International Conference on Electronic Design (ICED) ◽

10.1109/iced.2014.7015800 ◽

2014 ◽

Cited By ~ 6

Author(s):

Alhamza Munther ◽

Alabass Alalousi ◽

Shahrul Nizam ◽

Rozmie R. Othman ◽

Mohammed Anbar

Keyword(s):

Random Forest ◽

Decision Tree ◽

Comparative Study ◽

Network Traffic ◽

Traffic Classification ◽

Network Traffic Classification ◽

Tree Methods ◽

Decision Tree Methods

Download Full-text

Reduced Feature Set for Emotion Based Spoken Utterances of Normal and Special Children Using Multivariate Analysis and Decision Trees

Engineering, Technology & Applied Science Research ◽

10.48084/etasr.2177 ◽

2018 ◽

Vol 8 (4) ◽

pp. 3228-3233

Author(s):

M. A. Siddiqui ◽

S. A. Ali ◽

N. G. Haider

Keyword(s):

Factor Analysis ◽

Multivariate Analysis ◽

Decision Tree ◽

Multivariate Data Analysis ◽

Principal Component ◽

Feature Sets ◽

Tree Methods ◽

Special Children ◽

Children Speech ◽

Decision Tree Methods

The current paper deals with the use of multivariate data analysis and decision tree methods in order to reduce the feature set for the normal and special children speech in four different emotions: anger, happiness, neutral and sadness. Ten features were extracted, by an algorithm implemented in a previous study to classify the speech emotions of normal and special children. In the current study, the best features are selected using multivariate analysis: principal component analysis (PCA), factor analysis and decision tree. Step by step PCA is applied to reduce the feature set according to the variables that are collinear. The obtained reduced feature sets are applicable to both normal and special children samples. Experimental results revealed that PCA yields the feature set comprising pitch, intensity, formant, LPCC and rate of acceleration. Factor analysis provides three feature sets out of which the feature set comprising of Rasta PLP, MFCC, ZCR, and intensity provides the best result. Decision tree yields a feature set comprising energy, pitch and LPCC.

Download Full-text

An Assessment of Surface Water Detection Methods for Water Resource Management in the Nigerien Sahel

Sensors ◽

10.3390/s20020431 ◽

2020 ◽

Vol 20 (2) ◽

pp. 431 ◽

Cited By ~ 4

Author(s):

Kelsey Herndon ◽

Rebekke Muench ◽

Emil Cherrington ◽

Robert Griffin

Keyword(s):

Remote Sensing ◽

Surface Water ◽

Decision Tree ◽

Water Bodies ◽

Spectral Indices ◽

Dynamic Surface ◽

Tree Methods ◽

Global Surface ◽

Decision Tree Methods ◽

Semi Arid

Water is a scarce, but essential resource in the Sahel. Rainfed ephemeral ponds and lakes that dot the landscape are necessary to the livelihoods of smallholder farmers and pastoralists who rely on these resources to irrigate crops and hydrate cattle. The remote location and dispersed nature of these water bodies limits typical methods of monitoring, such as with gauges; fortunately, remote sensing offers a quick and cost-effective means of regularly measuring surface water extent in these isolated regions. Dozens of operational methods exist to use remote sensing to identify waterbodies, however, their performance when identifying surface water in the semi-arid Sahel has not been well-documented and the limitations of these methods for the region are not well understood. Here, we evaluate two global dynamic surface water datasets, fifteen spectral indices developed to classify surface water extent, and three simple decision tree methods created specifically to identify surface water in semi-arid environments. We find that the existing global surface water datasets effectively minimize false positives, but greatly underestimate the presence and extent of smaller, more turbid water bodies that are essential to local livelihoods, an important limitation in their use for monitoring water availability. Three of fifteen spectral indices exhibited both high accuracy and threshold stability when evaluated over different areas and seasons. The three simple decision tree methods had mixed performance, with only one having an overall accuracy that compared to the best performing spectral indices. We find that while global surface water datasets may be appropriate for analysis at the global scale, other methods calibrated to the local environment may provide improved performance for more localized water monitoring needs.

Download Full-text