國立虎尾科技大學 |

Diagnosis of Autism with EEG Analysis Using Discrete Wavelet Transform.

Record Type:	Language materials, manuscript : Monograph/item
Title/Author:	Diagnosis of Autism with EEG Analysis Using Discrete Wavelet Transform./
Author:	Kshirsagar, Prachi.
Description:	1 online resource (85 pages)
Notes:	Source: Masters Abstracts International, Volume: 56-05.
Contained By:	Masters Abstracts International56-05(E).
Subject:	Electrical engineering. -
Online resource:	click for full text (PQDT)
ISBN:	9780355101867

Diagnosis of Autism with EEG Analysis Using Discrete Wavelet Transform.
Kshirsagar, Prachi.

Diagnosis of Autism with EEG Analysis Using Discrete Wavelet Transform. - 1 online resource (85 pages)

Source: Masters Abstracts International, Volume: 56-05.

Thesis (M.S.)--Lamar University - Beaumont, 2017.

Includes bibliographical references

Autism Spectrum Disorder (ASD) is a group of increasingly recognized and extremely heterogeneous neurodevelopmental disorders defined by core impairments in social interaction, communication, restricted and repetitive behaviors. The term "spectrum" can be applied to the broad range of skills, levels of disability, and symptoms exhibited in Autistic populations.

Electronic reproduction.
Ann Arbor, Mich. :
ProQuest,
2018

Mode of access: World Wide Web

ISBN: 9780355101867Subjects--Topical Terms:

596380
Electrical engineering.
Index Terms--Genre/Form:

554714
Electronic books.

Diagnosis of Autism with EEG Analysis Using Discrete Wavelet Transform.
LDR:04140ntm a2200433Ki 4500 001 919576
005 20181129115238.5
006 m o u
007 cr mn||||a|a||
008 190606s2017 xx obm 000 0 eng d
020 $a 9780355101867
035 $a (MiAaPQ)AAI10281607
035 $a (MiAaPQ)lamar:11018
035 $a AAI10281607
040 $a MiAaPQ $b eng $c MiAaPQ $d NTU
100 1 $a Kshirsagar, Prachi. $3 1194187
245 1 0 $a Diagnosis of Autism with EEG Analysis Using Discrete Wavelet Transform.
264 0 $c 2017
300 $a 1 online resource (85 pages)
336 $a text $b txt $2 rdacontent
337 $a computer $b c $2 rdamedia
338 $a online resource $b cr $2 rdacarrier
500 $a Source: Masters Abstracts International, Volume: 56-05.
500 $a Adviser: Gleb V. Tcheslavski.
502 $a Thesis (M.S.)--Lamar University - Beaumont, 2017.
504 $a Includes bibliographical references
520 $a Autism Spectrum Disorder (ASD) is a group of increasingly recognized and extremely heterogeneous neurodevelopmental disorders defined by core impairments in social interaction, communication, restricted and repetitive behaviors. The term "spectrum" can be applied to the broad range of skills, levels of disability, and symptoms exhibited in Autistic populations.
520 $a Although no significant treatment exists for ASD, early detection can be extremely helpful for the therapeutic and behavioral interventions designed to remedy specific symptoms. Electroencephalography (EEG) is a well-established technique to seek the fundamental knowledge of brain and nervous system. Perhaps, this knowledge can be used to study and reduce the burden of neurological disorders. EEG provides irregular and complex signals containing information about neural activity of the brain that is related to its physiological states and can be analyzed with various techniques.
520 $a This thesis investigates an EEG analysis utilizing Discrete Wavelet Transform (DWT) targeted on extracting features that could be used for ASD detection. EEG is a non-stationary signal and DWT appears more suitable compared to the traditional Fourier-based analysis.
520 $a For this study, EEG was recorded from 2 autistics and 1 control subjects, while they were observing images of familiar and unfamiliar objects. Later, subjects were asked to recall and name the images.
520 $a EEG was analyzed using DWT and Permutation Entropy (PE) evaluated for the approximation and detail decomposition coefficients. Additionally, PEs were estimated for EEG elicited by the images of familiar and unfamiliar objects. In most cases, PE was higher for autistic participants than for the control.
520 $a The student's t-test was performed on the extracted approximation and detail coefficients that were later used as classification features. EEG-based features produced for most of the frontal electrodes resulted in p-values lower that the significance threshold (0.05). The latter indicates that the null hypothesis of equal population means should be rejected for these features. Therefore, EEG of autistic and control subjects may stem from different statistical distribution. Lastly, the extracted features were classified using the KNN classifier with the sensitivity exceeding 65%, specificity above 70%, and the average classification accuracy exceeding 70% for approximation and detail coefficients evaluated for frontal-channel EEG. This area of the human brain is linked to cognitive processing, short-term memory, and attention.
520 $a We conclude that the results obtained in the course of this study indicate that EEG is potentially valuable means in ASD research and that the EEG analysis techniques may contribute to a successful classification of autistic individuals.
533 $a Electronic reproduction. $b Ann Arbor, Mich. : $c ProQuest, $d 2018
538 $a Mode of access: World Wide Web
650 4 $a Electrical engineering. $3 596380
650 4 $a Biomedical engineering. $3 588770
650 4 $a Engineering. $3 561152
650 4 $a Neurosciences. $3 593561
655 7 $a Electronic books. $2 local $3 554714
690 $a 0544
690 $a 0541
690 $a 0537
690 $a 0317
710 2 $a ProQuest Information and Learning Co. $3 1178819
710 2 $a Lamar University - Beaumont. $b Electrical Engineering. $3 1194188
773 0 $t Masters Abstracts International $g 56-05(E).
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=10281607 $z click for full text (PQDT)