VGU RESEARCH REPOSITORY
Please use this identifier to cite or link to this item:
https://epub.vgu.edu.vn/handle/dlibvgu/561
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Tu Duy Khang | en_US |
dc.date.accessioned | 2020-03-12T17:03:58Z | - |
dc.date.available | 2020-03-12T17:03:58Z | - |
dc.date.issued | 2018 | - |
dc.identifier.uri | http://epub.vgu.edu.vn/handle/dlibvgu/561 | - |
dc.description.abstract | Blind Source Separation (BSS) and Independent Component Analysis (ICA) are generally based on a wide class of unsupervised learning algorithms, and they have potential applications on practical problems from engineering to neuroscience. The recent trends in BSS are to consider the problems in speech processing, sound processing and notably image processing in medical field, conducting by a variety of research groups in different institutes and universities over the world. Blind Source Separation is the separation a set of mixed signals into different independently source signals, totally based on algorithms without aid of information about the source signals. The word “Blind” means that in this problem the algorithm processes do not have any information about the input excitation, from transmission channel to the transfer function of mixing process of original sources. In order to solve the BSS problem, there are a couple of algorithms, which can be utilized effectively; however, one of the most common algorithms is Independent Component Analysis (ICA), a conventional data-driven method. The goal of ICA is to recover independent sources given only the observation signals by receiver devices such as sensors and microphones. ICA algorithm not only decorrelates the signals, but also reduces the statistic dependencies, attempting to make the signals as independent as possible. In this work, a practical BSS case study on functional magnetic resonance imaging (fMRI) signal is represented with the chosen ICA algorithms for identifying functional connectivity networks. fMRI is used as one of the safest noninvasive techniques to understand how human brains operate while a subject is performing a task or in resting state or being affected by a neurological disorder. Specifically, fMRI signals, when applying ICA algorithm, are decomposed into morphological components which have sparse spatial overlap. The results of this implementation on fMRI signals show clearly and positively the functional components of human brain, identifying successfully the networks as assumption of neuroscience study | en_US |
dc.language.iso | en | en_US |
dc.publisher | Vietnamese-German University | en_US |
dc.rights | Attribution-NonCommercial 4.0 International | * |
dc.rights.uri | https://creativecommons.org/licenses/by-nc/4.0/ | * |
dc.subject | Cooling system | en_US |
dc.subject | Automation of lightning | en_US |
dc.title | Smart office - automation of lightning and cooling system | en_US |
dc.type | Thesis | en_US |
item.fulltext | With Fulltext | - |
item.languageiso639-1 | other | - |
item.grantfulltext | restricted | - |
Appears in Collections: | Electrical Engineering and Information Technology (EEIT) |
Files in This Item:
File | Description | Size | Format | Existing users please Login |
---|---|---|---|---|
Smart office - automation of lightning and cooling system.pdf | 1.61 MB | Adobe PDF |
Page view(s)
35
checked on Jul 12, 2024
Download(s)
14
checked on Jul 12, 2024
Google ScholarTM
Check
This item is licensed under a Creative Commons License