Wyniki wyszukiwania - BazTech

1

Automated segmentation and classification of brain stroke using expectation-maximization and random forest classifier

Subudhi Asit, Dash Manasa, Sabut Sukanta

Biocybernetics and Biomedical Engineering

|

2020

|

Vol. 40, no. 1

277--289

EN

Magnetic resonance imaging (MRI) is effectively used for accurate diagnosis of acute ischemic stroke. This paper presents an automated method based on computer aided decision system to detect the ischemic stroke using diffusion-weighted image (DWI) sequence of MR images. The system consists of segmentation and classification of brain stroke into three types according to The Oxfordshire Community Stroke Project (OCSP) scheme. The stroke is mainly classified into partial anterior circulation syndrome (PACS), lacunar syndrome (LACS) and total anterior circulation stroke (TACS). The affected part of the brain due to stroke was segmented using expectation-maximization (EM) algorithm and the segmented region was then processed further with fractional-order Darwinian particle swarm optimization (FODPSO) technique in order to improve the detection accuracy. A total of 192 scan of MRI were considered for the evaluation. Different morphological and statistical features were extracted from the segmented lesions to form a feature set which was then classified with support vector machine (SVM) and random forest (RF) classifiers. The proposed system efficiently detected the stroke lesions with an accuracy of 93.4% using RF classifier, which was better than the results of the SVM classifier. Hence the proposed method can be used in decision-making process in the treatment of ischemic stroke.

2

Comparison of methods for initializing EM algorithm for estimation of parameters of gaussian, multi-component, heteroscedastic mixture models

Sokół R., Polański A.

Studia Informatica

|

2013

|

Vol. 34, nr 1

49--73

EN

A basic approach to estimation of mixture model parameters is by using expectation maximization (EM) algorithm for maximizing the likelihood function. However, it is essential to provide the algorithm with proper initial conditions, as it is highly dependent on the first estimation (“guess”) of parameters of a mixture. This paper presents several different initial condition estimation methods, which may be used as a first step in the EM parameter estimation procedure. We present comparisons of different initialization methods for heteroscedastic, multi-component Gaussian mixtures.

PL

Algorytm EM (ang. expectation-maximization) jest szeroko stosowanym rozwiązaniem problemu estymacji parametrów mieszanin rozkładów prawdopodobieństwa poprzez maksymalizację wiarygodności. Istotne znaczenie dla działania algorytmu mają parametry początkowe, stanowiące pierwsze przybliżenie badanej mieszaniny. Publikacja przybliża kilka metod wyznaczania warunku początkowego dla iteracji algorytmu EM oraz porównuje ich skuteczność dla przypadku heteroscedastycznych, wieloskładnikowych mieszanin rozkładów normalnych.

3

Wykorzystanie filtru cząsteczkowego w problemie identyfikacji układów automatyki

Kozierski P.

Prace Instytutu Elektrotechniki

|

2012

|

Z. 260

157-169

PL

W artykule przedstawiono sposób identyfikacji parametrycznej obiektów nieliniowych zapisanych w przestrzeni stanu. Identyfikacja wykorzystuje metodę największej wiarygodności (ML), z zastosowaniem filtru cząsteczkowego i algorytmu oczekiwanie-maksymalizacja (EM).

EN

A way of parameter estimation of nonlinear dynamic systems in state-space form is presented. The identification uses Maximum Likelihood method (ML), Particle Filter approach and Expectation-Maximization algorithm (EM).

4

Two stage EMG onset detection method

Drapała J., Brzostowski K., Szpala A., Rutkowska-Kucharska A.

Archives of Control Sciences

|

2012

|

Vol. 22, no. 4

427-440

EN

Detection of the moment when a muscle begins to activate on the basis of EMG signal is important task for a number of biomechanical studies. In order to provide high accuracy of EMG onset detection, we developed novel method, that give results similar to that obtained by an expert. By means of this method, EMG is processed in two stages. The first stage gives rough estimation of EMG onset, whereas the second stage performs local, precise searching. The method was applied to support signal processing in biomechanical study concerning effect of body position on EMG activity and peak muscle torque stabilizing spinal column under static conditions.