Go to the content. | Move to the navigation | Go to the site search | Go to the menu | Contacts | Accessibility

| Create Account

Kharati Koopaei, Ehsan (2018) Classification Approaches in Neuroscience: A Geometrical Point of View. [Ph.D. thesis]

Full text disponibile come:

[img]
Preview
PDF Document - Submitted Version
3139Kb

Abstract (english)

Functional magnetic resonance images (fMRI) are brain scan images by MRI machine which are taken functionally cross the time. Several studies have investigated methods analyzing such images (or actually the drawn data from them) and is interestingly growing up. For examples models can predict the behaviours and actions of people based on their brain pattern, which can be useful in many fields. We do the classification study and prediction of fMRI data and we develop some approaches and some modifications on them which have not been used in such classification problems. The proposed approaches were assessed by comparing the classification error rates in a real fMRI data study. In addition, many programming codes for reading from fMRI scans and codes for using classification approaches are provided to manipulate fMRI data in practice. The codes, can be gathered later as a package in R.
Also, there is a steadily growing interest in analyzing functional data which can often exploit Riemannian geometry. As a prototypical example of these kind of data, we will consider the functional data rising from an electroencephalography (EEG) signal in Brain-Computer interface (BCI) which translates the brain signals to the commands in the machine. It can be used for people with physical inability and movement problems or even in video games, which has had increased interest. To do that, a classification study on EEG signals has been proposed, while, the data in hand to be classified are matrices. A multiplicative algorithm (MPM), which is a fast and efficient algorithm, was developed to compute the power means for matrices which is the crucial step in our proposed approaches for classification. In addition, some simulation studies were used to examine the performance of MPM against existing algorithms. We will compare the behavior of different power means in terms of accuracy in our classifications, which had not been discovered previously. We will show that it is hard to have a guess to find the optimal power mean to have higher accuracy depending on the multivariate distribution of data available. Then, we also develop an approach, combination of power means, to have the benefit of all to improve the classification performance. All the codes related to the fast MPM algorithms and the codes for manipulating EEG signals in classification are written in MATLAB and can be developed later as a package.

Abstract (italian)

Le immagini da risonanza magnetica funzionale (functional magnetic resonance image - fMRI) sono immagini di scansioni cerebrali effettuate tramite la macchina MRI prese come funzione del tempo. Negli ultimi anni sta crescendo l'interesse sull'analisi di queste immagini, o meglio dei dati da loro estratti. L'obiettivo di questo tipo di analisi, applicabile in molti ambiti diversi, è quello di stimare e prevedere i comportamenti e le azioni delle persone a partire dai loro pattern cerebrali. Il nostro lavoro si basa sulla classificazione e previsione dei dati fMRI e sullo sviluppo di nuove tecniche che non sono mai state applicate a questi problemi di classificazione. La validazione delle tecniche proposte è stata effettuata tramite il confronto degli errori di misclassificazione su dati fMRI provenienti da studi reali. Inoltre, vengono forniti i codici di lettura dalle immagini fMRI ed quelli per applicare le tecniche di classificazione proposte per la manipolazione dei dati fMRI. In futuro i codici potranno essere organizzati per la creazione di un pacchetto R.
L'interesse nell'analisi di dati funzionali che utilizzano la geometria riemanniana è in costante crescita. Un prototipo di questi dati consiste nei dati funzionali generati dal segnale EEG nell'interfaccia Brain-Computer (BCI), la quale traduce i segnali cerebrali ai comandi nella macchina. Il BCI può essere utilizzato da persone con inabilità fisiche e problemi motori o persino, con crescente interesse, nell'ambito dei video giochi. A questo scopo, abbiamo proposto uno studio di classificazione dei segnali EEG i cui dati sono raccolti in matrici. Abbiamo sviluppato un algoritmo moltiplicativo (MPM) veloce ed efficiente nel calcolare le medie di potenza di matrici, punto cruciale dei metodi proposti per la classificazione. In alcuni studi di simulazione abbiamo esaminato le performance del MPM rispetto a quelle di algoritmi già esistenti. Abbiamo inoltre comparato il coportamento di diverse medie di potenza in termini di accuratezza delle classificazioni, cosa che non era stato mai fatta fino ad ora. Abbiamo verificato la difficoltà di scegliere la potenza associata con la migliore accuratezza del modello poichè questa dipende dalla distribuzione multivariata dei dati. Inoltre abbiamo sviluppato un approccio basato sulla combinazione di medie di potenza per poter beneficiare e per migliorare le performance di classificazione. Tutti i codici relativi all' algoritmo MPM veloce e quelli per la manipolazione dei segnali EEG nella classificazione sono scritti in MATLAB e possono essere sviluppati successivamente per la creazione di un pacchetto.

Statistiche Download
EPrint type:Ph.D. thesis
Tutor:Livio, Finos
Supervisor:Scarpa, Bruno
Ph.D. course:Ciclo 30 > Corsi 30 > SCIENZE STATISTICHE
Data di deposito della tesi:15 January 2018
Anno di Pubblicazione:15 January 2018
Key Words:Data mining, Machine learning, Classification, Riemannian geometry
Settori scientifico-disciplinari MIUR:Area 13 - Scienze economiche e statistiche > SECS-S/01 Statistica
Struttura di riferimento:Dipartimenti > Dipartimento di Scienze Statistiche
Codice ID:10566
Depositato il:26 Oct 2018 10:07
Simple Metadata
Full Metadata
EndNote Format

Bibliografia

I riferimenti della bibliografia possono essere cercati con Cerca la citazione di AIRE, copiando il titolo dell'articolo (o del libro) e la rivista (se presente) nei campi appositi di "Cerca la Citazione di AIRE".
Le url contenute in alcuni riferimenti sono raggiungibili cliccando sul link alla fine della citazione (Vai!) e tramite Google (Ricerca con Google). Il risultato dipende dalla formattazione della citazione.

Afsari, B., Tron, R. and Vidal, R. (2013) On the convergence of gradient descent for finding the riemannian center of mass. SIAM Journal on Control and Optimization 51(3), 2230–2260. Cerca con Google

Ando, T., Li, C.-K. and Mathias, R. (2004) Geometric means. Linear algebra and its applications 385, 305–334. Cerca con Google

Arnaudon, M., Barbaresco, F. and Yang, L. (2013) Riemannian medians and means with applications to radar signal processing. IEEE Journal of Selected Topics in Signal Processing 7(4), 595–604. Cerca con Google

Arsigny, V., Fillard, P., Pennec, X. and Ayache, N. (2007) Geometric means in a novel vector space structure on symmetric positive-definite matrices. SIAM journal on matrix analysis and applications 29(1), 328–347. Cerca con Google

Barachant, A., Bonnet, S., Congedo, M. and Jutten, C. (2010) Common spatial pattern revisited by riemannian geometry. In Multimedia Signal Processing (MMSP), 2010 IEEE International Workshop on, pp. 472–476. Cerca con Google

Barachant, A., Bonnet, S., Congedo, M. and Jutten, C. (2012) Multiclass brain–computer interface classification by riemannian geometry. IEEE Transactions on Biomedical Engineering 59(4), 920–928. Cerca con Google

Barachant, A., Bonnet, S., Congedo, M. and Jutten, C. (2013) Classification of covariance matrices using a riemannian-based kernel for bci applications. Neurocomputing 112, 172–178. Cerca con Google

Bhatia, R. (2009) Positive definite matrices. Princeton university press. Cerca con Google

Bhatia, R. and Holbrook, J. (2006) Riemannian geometry and matrix geometric means. Linear algebra and its applications 413(2-3), 594–618 Cerca con Google

Blankertz, B., Tomioka, R., Lemm, S., Kawanabe, M. and Muller, K.-R. (2008) Optimizing spatial filters for robust eeg single-trial analysis. IEEE Signal Processing Magazine 25(1), 41–56. Cerca con Google

Borg, I. and Groenen, P. J. (2005) Modern multidimensional scaling: Theory and applications. Springer Science & Business Media. Cerca con Google

Brants, M., Baeck, A., Wagemans, J. and de Beeck, H. P. O. (2011) Multiple scales of organization for object selectivity in ventral visual cortex. Neuroimage 56(3), 1372–1381. Cerca con Google

Chebbi, Z. and Moakher, M. (2012) Means of hermitian positive-definite matrices based on the log-determinant α-divergence function. Linear Algebra and its Applications 436(7), 1872–1889. Cerca con Google

Congedo, M. (2013) EEG source analysis. Ph.D. thesis, Citeseer. Cerca con Google

Congedo, M., Afsari, B., Barachant, A. and Moakher, M. (2015) Approximate joint diagonalization and geometric mean of symmetric positive definite matrices. PloS one 10(4), e0121423. Cerca con Google

Congedo, M., Barachant, A. and Andreev, A. (2013) A new generation of brain-computer interface based on riemannian geometry. arXiv preprint arXiv:1310.8115 . Cerca con Google

Congedo, M., Barachant, A. and Koopaei, E. K. (2017) Fixed point algorithms for estimating power means of positive definite matrices. IEEE Transactions on Signal Processing 65(9), 2211–2220. Cerca con Google

Congedo, M., Goyat, M., Tarrin, N., Ionescu, G., Varnet, L., Rivet, B., Phlypo, R., Jrad, N., Acquadro, M. and Jutten, C. (2011) ” brain invaders”: a prototype of an open-source p300-based video game working with the openvibe platform. In 5th Cerca con Google

International Brain-Computer Interface Conference 2011 (BCI 2011), pp. 280–283. Cerca con Google

Cox, D. D. and Savoy, R. L. (2003) Functional magnetic resonance imaging (fmri)brain reading: detecting and classifying distributed patterns of fmri activity in human visual cortex. Neuroimage 19(2), 261–270. Cerca con Google

Crosilla, F. and Beinat, A. (2002) Use of generalised procrustes analysis for the photogrammetric block adjustment by independent models. ISPRS Journal of Photogrammetry and Remote Sensing 56(3), 195–209 Cerca con Google

Devrim, M. (2003) Generalized procrustes analysis and its applications in photogrammetry. prepared for Praktikum in Photogrammetrie, Fernerkundung und GIS, ETH Zuerich. Cerca con Google

Dwyer, P. S. and MacPhail, M. (1948) Symbolic matrix derivatives. The annals of mathematical statistics pp. 517–534. Cerca con Google

Eckart, C. and Young, G. (1936) The approximation of one matrix by another of lower rank. Psychometrika 1(3), 211–218. Cerca con Google

Faraki, M., Harandi, M. T. and Porikli, F. (2015) More about vlad: A leap from euclidean to riemannian manifolds. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4951–4960. Cerca con Google

Fillard, P., Arsigny, V., Ayache, N. and Pennec, X. (2005) A riemannian framework for the processing of tensor-valued images. In DSSCV, pp. 112–123. Cerca con Google

Fletcher, P. T. (2013) Geodesic regression and the theory of least squares on riemannian manifolds. International journal of computer vision 105(2), 171–185. Cerca con Google

Georgiou, T. T. (2007) Distances and riemannian metrics for spectral density functions. IEEE Transactions on Signal Processing 55(8), 3995–4003. Cerca con Google

Goodall, C. (1991) Procrustes methods in the statistical analysis of shape. Journal of the Royal Statistical Society. Series B (Methodological) pp. 285–339. Cerca con Google

Gorgolewski, K. J., Storkey, A. J., Bastin, M. E., Whittle, I. and Pernet, C. (2013) Single subject fmri test–retest reliability metrics and confounding factors. Neuroimage 69, 231–243. Cerca con Google

Gower, J. C. (1975) Generalized procrustes analysis. Psychometrika 40(1), 33–51. Cerca con Google

Hastie, T., Tibshirani, R. and Friedman, J. (2008) The elements of statistical learning. Volume 2. Springer series in statistics Springer, USA. Cerca con Google

Haxby, J. V., Guntupalli, J. S., Connolly, A. C., Halchenko, Y. O., Conroy, B. R., Gobbini, M. I., Hanke, M. and Ramadge, P. J. (2011) A common, high-dimensional model of the representational space in human ventral temporal cortex. Neuron 72(2), 404–416. Cerca con Google

Higham, N. J. (1997) Stable iterations for the matrix square root. Numerical Algorithms 15(2), 227–242. Cerca con Google

Lawson, J. and Lim, Y. (2014) Karcher means and karcher equations of positive definite operators. Transactions of the American Mathematical Society, Series B 1(1), 1–22. Cerca con Google

Li, Y. and Wong, K. M. (2013) Riemannian distances for signal classification by power spectral density. IEEE Journal of Selected Topics in Signal Processing 7(4), 655–669. Cerca con Google

Li, Y., Wong, K. M. and de Bruin, H. (2012) Electroencephalogram signals classification for sleep-state decision–a riemannian geometry approach. IET signal processing 6(4), 288–299. Cerca con Google

Lim, Y. and P´alfia, M. (2012) Matrix power means and the karcher mean. Journal of Functional Analysis 262(4), 1498–1514. Cerca con Google

Logothetis, N. K., Pauls, J., Augath, M., Trinath, T. and Oeltermann, A. (2001) Neurophysiological investigation of the basis of the fmri signal. Nature 412(6843), 150–157. Cerca con Google

Moakher, M. (2005) A differential geometric approach to the arithmetic and geometric means of operators in some symmetric spaces. SIAM. J. Matrix Anal. Appl 26(3), 735–747. Cerca con Google

Moakher, M. (2006) On the averaging of symmetric positive-definite tensors. Journal of Elasticity 82(3), 273–296. Cerca con Google

Moakher, M. and Z´era¨ı, M. (2011) The riemannian geometry of the space of positivedefinite matrices and its application to the regularization of positive-definite matrixvalued data. Journal of Mathematical Imaging and Vision 40(2), 171–187. Cerca con Google

Nakamura, N. (2009) Geometric means of positive operators. Kyungpook mathematical journal 49(1), 167–181. Cerca con Google

P´alfia, M. (2016) Operator means of probability measures and generalized karcher equations. Advances in Mathematics 289, 951–1007. Cerca con Google

Pfurtscheller, G. and Da Silva, F. L. (1999) Event-related eeg/meg synchronization and desynchronization: basic principles. Clinical neurophysiology 110(11), 1842–1857. Cerca con Google

Sch¨onemann, P., Bock, R. and Tucker, L. (1965) Some notes on a theorem by eckart and young. Research Memorandum (25). Cerca con Google

Sch¨onemann, P. H. (1966) A generalized solution of the orthogonal procrustes problem. Psychometrika 31(1), 1–10. Cerca con Google

Skovgaard, L. T. (1984) A riemannian geometry of the multivariate normal model. Scandinavian Journal of Statistics 11(4), 211–223. Cerca con Google

Spiridon, M. and Kanwisher, N. (2002) How distributed is visual category information in human occipito-temporal cortex? an fmri study. Neuron 35(6), 1157–1165. Cerca con Google

Sra, S. (2016) Positive definite matrices and the s-divergence. Proceedings of the American Mathematical Society 144(7), 2787–2797. Cerca con Google

Ten Berge, J. M. (1977) Orthogonal procrustes rotation for two or more matrices. Psychometrika 42(2), 267–276. Cerca con Google

Tsao, D. Y., Freiwald, W. A., Tootell, R. B. and Livingstone, M. S. (2006) A cortical region consisting entirely of face-selective cells. Science 311(5761), 670–674. Cerca con Google

Zhang, T. (2014) A majorization-minimization algorithm for the karcher mean of positive definite matrices. arXiv, 1312.4654 . Cerca con Google

Zhang, X., Wang, Y., Gou, M., Sznaier, M. and Camps, O. (2016) Efficient temporal sequence comparison and classification using gram matrix embeddings on a riemannian manifold. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4498–4507. Cerca con Google

Zou, H. and Hastie, T. (2005) Regularization and variable selection via the elastic net. Cerca con Google

Journal of the Royal Statistical Society: Series B (Statistical Methodology) 67(2), 301–320. Cerca con Google

Download statistics

Solo per lo Staff dell Archivio: Modifica questo record