東華大學圖書館 |

Language: English

Help

回圖書館首頁

手機版館藏查詢

Back

Switch To: Labeled | MARC Mode | ISBD

Linked to FindBook

Google Book

Amazon

博客來

Noninvasive EEG-Based Prediction of Infantile Spasms Using Deep Learning Networks with Phase Amplitude Cross-Frequency Coupling.

Record Type:	Electronic resources : Monograph/item
Title/Author:	Noninvasive EEG-Based Prediction of Infantile Spasms Using Deep Learning Networks with Phase Amplitude Cross-Frequency Coupling./
Author:	Lucasius, Christopher.
Published:	Ann Arbor : ProQuest Dissertations & Theses, : 2020,
Description:	81 p.
Notes:	Source: Masters Abstracts International, Volume: 82-06.
Contained By:	Masters Abstracts International82-06.
Subject:	Artificial intelligence. -
Online resource:	http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28150087
ISBN:	9798698555018

Noninvasive EEG-Based Prediction of Infantile Spasms Using Deep Learning Networks with Phase Amplitude Cross-Frequency Coupling.
Lucasius, Christopher.

Noninvasive EEG-Based Prediction of Infantile Spasms Using Deep Learning Networks with Phase Amplitude Cross-Frequency Coupling. - Ann Arbor : ProQuest Dissertations & Theses, 2020 - 81 p.

Source: Masters Abstracts International, Volume: 82-06.

Thesis (M.A.S.)--University of Toronto (Canada), 2020.

This item must not be sold to any third party vendors.

Around one in 2,500 children develop West Syndrome where 90% develop infantile spasms within the first year of life. Being able to predict the onset of a spasm has the potential to greatly improve the lives of infants with epilepsy since treatment or care can be given by a caregiver prior to the event. In the literature, several seizure prediction algorithms have been developed, giving relatively mediocre sensitivities and specificities. This study improves on these metrics by applying several deep learning networks in combination with the phase amplitude cross-frequency coupling feature derived from scalp electroencephalography. All of the networks contain a convolutional neural network, where variants include the use of a multi-stage state classifier, biologically plausible filters for pre-processing, and a recurrent neural network for post-processing. Overall, the networks are able to produce high accuracies (99%) and significant latencies (10 min.). Explanation techniques are used to validate these models.

ISBN: 9798698555018Subjects--Topical Terms:

516317
Artificial intelligence.
Subjects--Index Terms:

Biologically inspired artificial intelligence

Noninvasive EEG-Based Prediction of Infantile Spasms Using Deep Learning Networks with Phase Amplitude Cross-Frequency Coupling.
LDR:02433nmm a2200445 4500 001 2344596
005 20220531064603.5
008 241004s2020 ||||||||||||||||| ||eng d
020 $a 9798698555018
035 $a (MiAaPQ)AAI28150087
035 $a AAI28150087
040 $a MiAaPQ $c MiAaPQ
100 1 $a Lucasius, Christopher. $3 3683382
245 1 0 $a Noninvasive EEG-Based Prediction of Infantile Spasms Using Deep Learning Networks with Phase Amplitude Cross-Frequency Coupling.
260 1 $a Ann Arbor : $b ProQuest Dissertations & Theses, $c 2020
300 $a 81 p.
500 $a Source: Masters Abstracts International, Volume: 82-06.
500 $a Advisor: Bardakjian, Berj L.
502 $a Thesis (M.A.S.)--University of Toronto (Canada), 2020.
506 $a This item must not be sold to any third party vendors.
520 $a Around one in 2,500 children develop West Syndrome where 90% develop infantile spasms within the first year of life. Being able to predict the onset of a spasm has the potential to greatly improve the lives of infants with epilepsy since treatment or care can be given by a caregiver prior to the event. In the literature, several seizure prediction algorithms have been developed, giving relatively mediocre sensitivities and specificities. This study improves on these metrics by applying several deep learning networks in combination with the phase amplitude cross-frequency coupling feature derived from scalp electroencephalography. All of the networks contain a convolutional neural network, where variants include the use of a multi-stage state classifier, biologically plausible filters for pre-processing, and a recurrent neural network for post-processing. Overall, the networks are able to produce high accuracies (99%) and significant latencies (10 min.). Explanation techniques are used to validate these models.
590 $a School code: 0779.
650 4 $a Artificial intelligence. $3 516317
650 4 $a Neurosciences. $3 588700
650 4 $a Information technology. $3 532993
650 4 $a Bioengineering. $3 657580
653 $a Biologically inspired artificial intelligence
653 $a Deep learning
653 $a Neural networks
653 $a Seizure prediction
653 $a Signal processing
653 $a West Syndrome
653 $a Spasms
653 $a Scalp electroencephalography
653 $a Infantile spasms
653 $a Caregiver
690 $a 0800
690 $a 0317
690 $a 0202
690 $a 0489
710 2 $a University of Toronto (Canada). $b Electrical and Computer Engineering. $3 2096349
773 0 $t Masters Abstracts International $g 82-06.
790 $a 0779
791 $a M.A.S.
792 $a 2020
793 $a English
856 4 0 $u http://pqdd.sinica.edu.tw/twdaoapp/servlet/advanced?query=28150087