University of Jyväskylä | JYX Digital Repository

  • English  | Give feedback |
    • suomi
    • English
 
  • Login
JavaScript is disabled for your browser. Some features of this site may not work without it.
View Item 
  • JYX
  • Opinnäytteet
  • Väitöskirjat
  • View Item
JYX > Opinnäytteet > Väitöskirjat > View Item

Extracting Meaningful EEG Features Using Constrained Tensor Decomposition

Thumbnail
View/Open
10. Mb

Downloads:  
Show download detailsHide download details  
Published in
JYU dissertations
Authors
Wang, Deqing
Date
2019

 
Electroencephalography (EEG) is a powerful technique for the study of human brain and cognitive neuroscience. Nowadays, more and more EEG data are organized in high-dimension form, which is called tensor. Tensor decomposition is just the suitable tool to exploit the multiway data and extract EEG features that are linked to cognitive processes. Since the high-dimension EEG tensor often contains a large amount of data points, highly efficient tensor decomposition algorithm is desired. In addition, EEG tensor are sometimes nonnegative and the intrinsic features usually have some special properties, such as sparse. In order to extract meaningful feature components, it is necessary to incorporate constraint and regularization to tensor decomposition algorithm. In this dissertation, we study the CANDECOMP/PARAFAC (CP) tensor decomposition with both nonnegative constraint and sparse regularization, which is abbreviated as sparse NCP. An inexact block coordinate descent (BCD) framework is employed for the non-convex sparse NCP problem. Five optimization methods are employed to solve the sparse NCP, including multiplicative update (MU), alternating nonnegative least squares/quadratic programming (ANLS/ANQP), hierarchical altering least squares (HALS), alternating proximal gradient (APG) and alternating direction method of multipliers (ADMM), all of which are carefully tailored to the sparse regularization problem. In order to improve the stability, we also utilize proximal algorithm particularly for ANLS/ANQP and HALS. Applications on real-world EEG datasets are carried out. First, we use NCP to decompose a fifth-order event-related potential (ERP) tensor, which was collected by proprioceptive stimuli on human hands. Next, ongoing EEG tensors are analyzed using sparse NCP. The data were collected by naturalistic and continuous music stimulus. Finally, we analyze two modalities of ongoing EEG tensor and music signals simultaneously by N-way partial least square (N-PLS). In conclusion, our designed tensor decomposition methods with constraint and regularization are able to decompose high-order tensor data efficiently and extract meaningful EEG features linked to cognitive processes. Keywords: Tensor decomposition, nonnegative CANDECOMP/PARAFAC, sparse regularization, block coordinate descent, EEG data analysis ...
 
Elektroenkefalografia (EEG) on tehokas tapa tutkia ja mitata ihmisaivojen toimintaa ja edistää kognitiivista neurotiedettä. EEG-mittauksilla saatu data tallennetaan yhä yleisemmin moniuloitteisiin tietorakententeisiin eli tensoreihin. Hajottamalla tensori sen tekijöihin voidaan tutkia monikanavaista dataa ja irrottaa siitä ne EEGtekijät, jotka liittyvät kognitiivisiin prosesseihin. Koska EEG-tensoreissa on usein paljon data-alkioita monissa ulottuvuuksissa, oleellisten data-alkioiden irrottamiseen tarvitaan tehokas algoritmi tensorin tekijöiden hajottamiseen. Lisäksi EEGtensorit ovat joskus ei-negatiivisia ja erottamattomasti rakenteeltaan harvoja. Jotta tensorista voitaisiin irrottaa oleelliset piirteet, tensorin hajottamiseen soveltuvaan algoritmiin tulee liittää rajoitteita ja säännönmukaistamista. Tässä väitöskirjassa tutkitaan CANDECOMP/PARAFAC (CP) hajoittamismenetelmää, joka sisältää sekä ei-negatiivisen rajoituksen että harvan säännönmukaistamisen (sparse NCP). Epäkonveksin harvan säännönmukaistamisen ongelman ratkaisuun käytetään epäeksaktia koordinaattiakselien suuntaisen optimoinnin viitekehystä (block coordinate descent). Harvaan säännönmukaistamiseen käytetään viittä seuraavaa optimointimenetelmää: MU (multiplicative update), ANLS/ANQP (altering nonnegative least squares/quadratic programming), HALS (hierarchical altering least squares), APG (alternating proximal gradient) ja ADMM (alternating direction method of multipliers), joista jokainen on tarkoin suunniteltu harvan säännönmukaistamisen ongelmaan. Stabiliteetin parantamiseksi hyödynnetään ANLS/ANQP- ja HALS-menetelmissä myös nk. lähialgoritmia. Menetelmiä evaluoitiin todellisilla EEG-aineistoilla. Ensinnäkin NCP:tä käytettiin hajottamaan viidennen asteen herätevastetensori (event-related potential, ERP), joka oli koottu ihmiskäden asentoaistiärsykkeistä. Toisekseen harvaa NCP:tä käytettiin analysoimaan meneillään olevan EEG-mittauksen tuottamia tensoreita, jotka kuvasivat luonnollisia ja jatkuvia, musiikinkuuntelun aiheuttamia ärsykkeitä. Kolmanneksi analysoitiin kahden meneillään olevan EEG-mittauksen tuottamia tensoreita käyttämällä N-PLS-menetelmää. Suunniteltujen menetelmien avulla voidaan tehokkaasti hajottaa monimutkaista tensoridataa sen tekijöihin ja irrottaa kognitiivisiin prosesseihin liittyviä EEG-tekijöitä. Avainsanat: tensorin hajottaminen tekijöihin, ei-negativiinen CANDECOMP/ PARAFAC, harva säännönmukaistaminen, koordinaattiakselien suuntainen optimointi, EEG-data-analyysi ...
 
ISBN
978-951-39-7968-3
Contains publications
  • Artikkeli I: Deqing Wang, Xiulin Wang, Tapani Ristaniemi and Fengyu Cong. Sparse Nonnegative Tensor Decomposition in Inexact Block Coordinate Descent Framework. Submitted to a journal.
  • Artikkeli II: Wang, D., Cong, F., & Ristaniemi, T. (2019). Higher-order Nonnegative CANDECOMP/PARAFAC Tensor Decomposition Using Proximal Algorithm. In ICASSP 2019 : Proceedings of the 2019 IEEE International Conference on Acoustics, Speech and Signal Processing (pp. 3457-3461). IEEE. DOI: 10.1109/ICASSP.2019.8683217
  • Artikkeli III: Wang, D., Zhu, Y., Ristaniemi, T., & Cong, F. (2018). Extracting multi-mode ERP features using fifth-order nonnegative tensor decomposition. Journal of Neuroscience Methods, 308, 240-247. DOI: 10.1016/j.jneumeth.2018.07.020
  • Artikkeli IV: Wang, D., Wang, X., Zhu, Y., Toiviainen, P., Huotilainen, M., Ristaniemi, T., & Cong, F. (2018). Increasing Stability of EEG Components Extraction Using Sparsity Regularized Tensor Decomposition. In T. Huang, J. Lv, C. Sun, & A. V. Tuzikov (Eds.), ISNN 2018 : Advances in Neural Networks : 15th International Symposium on Neural Networks, Proceedings (pp. 789-799). Springer International Publishing. DOI: 10.1007/978-3-319-92537-0_89
  • Artikkeli V: Wang, D., Cong, F., Zhao, Q., Toiviainen, P., Nandi, A. K., Huotilainen, M., . . . , & Cichocki, A. (2016). Exploiting ongoing EEG with multilinear partial least squares during free-listening to music. In F. A. N. Palmieri, A. Uncini, K. Diamantaras, & J. Larsen (Eds.), Proceedings of MLSP 2016 : IEEE International Workshop on Machine Learning for Signal Processing. Institute of Electrical and Electronic Engineers. DOI: 10.1109/MLSP.2016.7738849
Keywords
EEG signaalinkäsittely signaalianalyysi algoritmit kognitiivinen neurotiede aivotutkimus tensor decomposition nonnegative CANDECOMP/PARAFAC sparse regularization block coordinate descent EEG data analysis
URI

http://urn.fi/URN:ISBN:978-951-39-7968-3

Metadata
Show full item record
Collections
  • JYU Dissertations [130]
  • Väitöskirjat [3177]

Related items

Showing items with similar title or keywords.

  • Shared and Unshared Feature Extraction in Major Depression During Music Listening Using Constrained Tensor Factorization 

    Wang, Xiulin; Liu, Wenya; Wang, Xiaoyu; Mu, Zhen; Xu, Jing; Chang, Yi; Zhang, Qing; Wu, Jianlin; Cong, Fengyu (Frontiers Media SA, 2021)
    Ongoing electroencephalography (EEG) signals are recorded as a mixture of stimulus-elicited EEG, spontaneous EEG and noises, which poses a huge challenge to current data analyzing techniques, especially when different ...
  • Sparse nonnegative tensor decomposition using proximal algorithm and inexact block coordinate descent scheme 

    Wang, Deqing; Chang, Zheng; Cong, Fengyu (Springer, 2021)
    Nonnegative tensor decomposition is a versatile tool for multiway data analysis, by which the extracted components are nonnegative and usually sparse. Nevertheless, the sparsity is only a side effect and cannot be explicitly ...
  • Extracting multi-mode ERP features using fifth-order nonnegative tensor decomposition 

    Wang, Deqing; Zhu, Yongjie; Ristaniemi, Tapani; Cong, Fengyu (Elsevier BV, 2018)
    Background Preprocessed Event-related potential (ERP) data are usually organized in multi-way tensor, in which tensor decomposition serves as a powerful tool for data processing. Due to the limitation of computation burden ...
  • Higher-order Nonnegative CANDECOMP/PARAFAC Tensor Decomposition Using Proximal Algorithm 

    Wang, Deqing; Cong, Fengyu; Ristaniemi, Tapani (IEEE, 2019)
    Tensor decomposition is a powerful tool for analyzing multiway data. Nowadays, with the fast development of multisensor technology, more and more data appear in higherorder (order > 4) and nonnegative form. However, the ...
  • Identifying Oscillatory Hyperconnectivity and Hypoconnectivity Networks in Major Depression Using Coupled Tensor Decomposition 

    Liu, Wenya; Wang, Xiulin; Xu, Jing; Chang, Yi.; Hämäläinen, Timo; Cong, Fengyu (Institute of Electrical and Electronics Engineers (IEEE), 2021)
    Previous researches demonstrate that major depression disorder (MDD) is associated with widespread network dysconnectivity, and the dynamics of functional connectivity networks are important to delineate the neural mechanisms ...
  • Browse materials
  • Browse materials
  • Articles
  • Conferences and seminars
  • Electronic books
  • Historical maps
  • Journals
  • Tunes and musical notes
  • Photographs
  • Presentations and posters
  • Publication series
  • Research reports
  • Research data
  • Study materials
  • Theses

Browse

All of JYXCollection listBy Issue DateAuthorsSubjectsPublished inDepartmentDiscipline

My Account

Login

Statistics

View Usage Statistics
  • How to publish in JYX?
  • Self-archiving
  • Publish Your Thesis Online
  • Publishing Your Dissertation
  • Publication services

Open Science at the JYU
 
Data Protection Description

Accessibility Statement

Unless otherwise specified, publicly available JYX metadata (excluding abstracts) may be freely reused under the CC0 waiver.
Open Science Centre