Multiple Manifold Clustering Using Curvature Constrained Path

Autor: Babaeian, Amir

Publikováno v: ICIP 2015

The problem of multiple surface clustering is a challenging task, particularly when the surfaces intersect. Available methods such as Isomap fail to capture the true shape of the surface nearby the intersection and result in incorrect clustering. The

Externí odkaz: http://arxiv.org/abs/1812.02327

Multiple Manifold Clustering Using Curvature Constrained Path.

Autor: Babaeian, Amir¹ ababaeian@ucsd.edu, Bayestehtashk, Alireza², Bandarabadi, Mojtaba³

Publikováno v: PLoS ONE. 9/16/2015, Vol. 10 Issue 9, p1-15. 15p.

Part I - Constrained Shortest-Path For Manifold Learning And Multiple Manifold Clustering Part II - Community Detection In Large Graphs; Analysis, Design And Implementation

Autor: Babaeian, Amir

Publikováno v: Babaeian, Amir. (2017). Part I-Constrained Shortest-Path For Manifold Learning And Multiple Manifold Clustering Part II-Community Detection In Large Graphs; Analysis, Design And Implementation. UC San Diego: Mathematics. Retrieved from: http://www.escholarship.org/uc/item/4w64w79x

In Part I of this thesis, we address the problem of manifold learning and clustering by introducing a novel constrained shortest-path algorithm. In the case of self-intersection, existing methods such as Isomap fail to capture the true shape of the s

Externí odkaz: https://explore.openaire.eu/search/publication?articleId=od_______325::b126b704a17a87c11128012bcd310b2d
http://www.escholarship.org/uc/item/4w64w79x

Robust speech recognition using multivariate copula models.

Autor: Bayestehtashk, Alireza, Shafran, Izhak, Babaeian, Amir

Publikováno v: 2016 IEEE International Conference on Acoustics, Speech & Signal Processing (ICASSP); 2016, p5890-5894, 5p