MARC보기
LDR02944nmm uu200481 4500
001000000332780
00520240805171555
008181129s2018 |||||||||||||||||c||eng d
020 ▼a 9780438423541
035 ▼a (MiAaPQ)AAI10810476
035 ▼a (MiAaPQ)upenngdas:13267
040 ▼a MiAaPQ ▼c MiAaPQ ▼d 248032
0820 ▼a 621.3
1001 ▼a Varol, Erdem.
24510 ▼a Advancing Statistical Inference for Population Studies in Neuroimaging Using Machine Learning.
260 ▼a [S.l.] : ▼b University of Pennsylvania., ▼c 2018
260 1 ▼a Ann Arbor : ▼b ProQuest Dissertations & Theses, ▼c 2018
300 ▼a 209 p.
500 ▼a Source: Dissertation Abstracts International, Volume: 80-01(E), Section: B.
500 ▼a Adviser: Christos Davatzikos.
5021 ▼a Thesis (Ph.D.)--University of Pennsylvania, 2018.
520 ▼a Modern neuroimaging techniques allow us to investigate the brain in vivo and in high resolution, providing us with high dimensional information regarding the structure and the function of the brain in health and disease. Statistical analysis tec
520 ▼a A prevalent area of research in neuroimaging is group comparison, i.e., the comparison of the imaging data of two groups (e.g. patients vs. healthy controls or people who respond to treatment vs. people who don't) to identify discriminative imag
520 ▼a However, existing statistical methods are limited by their reliance on ad-hoc assumptions regarding the homogeneity of disease effect, spatial properties of the underlying signal and the covariate structure of data, which imposes certain constra
520 ▼a The goal of this thesis is to address each of the aforementioned assumptions and limitations by introducing robust mathematical formulations, which are founded on multivariate machine learning techniques that integrate discriminative and generat
520 ▼a Specifically, 1. First, we introduce an algorithm termed HYDRA which stands for heterogeneity through discriminative analysis . This method parses the heterogeneity in neuroimaging studies by simultaneously performing clustering and classificat
520 ▼a We extensively validated the performance of the developed frameworks in the presence of diverse types of simulated scenarios. Furthermore, we applied our methods on a large number of clinical datasets that included structural and functional neur
590 ▼a School code: 0175.
650 4 ▼a Electrical engineering.
650 4 ▼a Neurosciences.
650 4 ▼a Statistics.
690 ▼a 0544
690 ▼a 0317
690 ▼a 0463
71020 ▼a University of Pennsylvania. ▼b Electrical and Systems Engineering.
7730 ▼t Dissertation Abstracts International ▼g 80-01B(E).
773 ▼t Dissertation Abstract International
790 ▼a 0175
791 ▼a Ph.D.
792 ▼a 2018
793 ▼a English
85640 ▼u http://www.riss.kr/pdu/ddodLink.do?id=T14997944 ▼n KERIS
980 ▼a 201812 ▼f 2019
990 ▼a 관리자