Wyniki wyszukiwania - BazTech

Ograniczanie wyników

2 2022

Powiadomienia systemowe

Sesja wygasła!
Sesja wygasła!

Znaleziono wyników: 2

Liczba wyników na stronie

Wyniki wyszukiwania

Wyszukiwano:
w słowach kluczowych: algorytm drzewa decyzyjnego

Sortuj według:

Ogranicz wyniki do:

Enhanced decision tree induction using evolutionary techniques for Parkinson’s disease classification

Ghane Mostafa, Ang Mei Choo, Nilashi Mehrbakhsh, Sorooshian Shahryar

Biocybernetics and Biomedical Engineering

2022

Vol. 42, no. 3

902--920

The diagnosis of Parkinson’s disease (PD) is important in neurological pathology for appropriate medical therapy. Algorithms based on decision tree induction (DTI) have been widely used for diagnosing PD through biomedical voice disorders. However, DTI for PD diagnosis is based on a greedy search algorithm which causes overfitting and inferior solutions. This paper improved the performance of DTI using evolutionary-based genetic algorithms. The goal was to combine evolutionary techniques, namely, a genetic algorithm (GA) and genetic programming (GP), with a decision tree algorithm (J48) to improve the classification performance. The developed model was applied to a real biomedical dataset for the diagnosis of PD. The results showed that the accuracy of the J48, was improved from 80.51% to 89.23% and to 90.76% using the GA and GP, respectively.

An updated version of the ETAS model based on multiple change points detection

Benali Amel, Zhuang Jiancang, Talbi Abdelhak

Acta Geophysica

2022

Vol. 70, no 5

2013--2031

The stationary Epidemic-Type Aftershock Sequence (ETAS) model is applied to seismicity in Central Italy, in order to study the temporal changes of the corresponding earthquakes time series. However, the residual analysis reveals that some features of the observed seismicity cannot be captured by the stationary ETAS model in its standard formulation. In this case, a decision-tree algorithm is developed to deal with inference problems linked to the estimation of specific time points where stationarity may be potentially broken. Specifically, this algorithm considers the subdivision of the whole time period into two or more subintervals that join in specific time points called change points, where significant time variation in the ETAS parameters is observed. As a result, a three-stage ETAS model with two change points is selected as the best model describing seismicity of the Central Apennines region during the time period 2005–2017, compared to the standard ETAS model. The variation of the estimated ETAS parameters is statistically significant from one stage to another. In particular, the three-stage ETAS estimates of background seismicity rates are found to be increasing from one stage to another over time.