Comparison of machine learning methods for classifying aphasic and non-aphasic speakers

Järvelin, Antti; Juhola, Martti

doi:10.1016/j.cmpb.2011.02.015

Cited by 13 publications

(1 citation statement)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Five attributes were then processed by Weka (a machine learning based software). [18][19][20][21][22][23][24] In the present study, to achieve the optimization of the results previously found we focused in an ECG analysis using wavelet transforms, statistical information and the original signal processed by LWL, J48, ADTree and RandomForest. These algorithms are inserted in Weka and have already been used in signal processing at different context/applications, as an open source software Weka has a high potential in many other applicantions.…”

Section: Figurementioning

confidence: 99%

Applying learning algorithms to extract anxiety levels using the heart rate variability measure

Magini

Mocaiber

Calembo

et al. 2015

JBGC

View full text Add to dashboard Cite

The classification problems in biological measures have been studied since mathematical methods and statistical tools were created to determine difference between two distinct samples. In this paper we present a mathematical methodology capable of differing 29 non-clinical volunteers with distinct degrees of trait anxiety (high or low) according to the State and Trait Anxiety Inventory (STAI-T) using an electrocardiogram (ECG) data as starting point. Specifically, the wavelet transforms and its statistical measures were used to extract simple patterns from the resting ECG and classify the group as low or high trait anxiety. The Daubechies, Haar and Symlet mother function were used to filter the original ECG data. Then, by means of the Weka Learning Algorithm and using only 5 attributes (Pearson Coefficient from Haar and Symlet, Median from Haar and Mode of Haar and Daubechies) we achieved a higher level of reliability, 96.90% (p < .05), with low training percentages. The results showed the efficiency of this methodology to classify volunteers according to their anxiety levels through an ECG data collection.

show abstract

Section: Figurementioning

confidence: 99%

Applying learning algorithms to extract anxiety levels using the heart rate variability measure

Magini

Mocaiber

Calembo

et al. 2015

JBGC

View full text Add to dashboard Cite

show abstract

Activity Recognition for Assisting People with Dementia

Fikry

Hamdhana

Lago

et al. 2021

Intelligent Systems Reference Library

View full text Add to dashboard Cite

A novel generalized belief structure comprising unprecisiated uncertainty applied to aphasia diagnosis

Sabahi

2016

Journal of Biomedical Informatics

View full text Add to dashboard Cite

Our basic understanding of evidential reasoning, in its vast and intricate complexity, has been guided by different methods including probabilistic and possibilistic models. However, restrictions surrounding evidence must be fully precisiated/validated before discussing their probability or possibility which is rarely achieved, especially in uncertain or imprecise environments. In this paper, a new generalization of the Dempster-Shafer Theory (DST) is presented that accounts for this issue. In the proposed generalization, we include information about the validity of a fuzzy body of evidence to represent its bearing on unprecisiated information, and then we distribute this knowledge over the belief structure. We provide an epistemic framework of evidence and study its behavior and its constraints in terms of validity, probability, and possibility to establish a foundation for evidential reasoning and unprecisiated uncertainty that exists in evidence. The suggested belief structure is crafted by min-max optimization method. Then, the proposed structure is used to estimate the probability density function (pdf) and is explored by the application diagnosis of aphasia, in which unprecisiated uncertainty is involved due to the subjectivity of the test items, inconsistency in the interpretation of aphasic syndromes, and the changeable precision of medical tests. Even in requiring more parameters, an accuracy improvement in the results is noticeably observed, especially when compared with the results of alternative approaches applied in the same database.

show abstract

Comparison of machine learning methods for classifying aphasic and non-aphasic speakers

Cited by 13 publications

References 11 publications

Applying learning algorithms to extract anxiety levels using the heart rate variability measure

Applying learning algorithms to extract anxiety levels using the heart rate variability measure

Activity Recognition for Assisting People with Dementia

A novel generalized belief structure comprising unprecisiated uncertainty applied to aphasia diagnosis

Contact Info

Product

Resources

About