Please use this identifier to cite or link to this item:
|Title:||Ensemble learning for reliable feature detection in combinatorial mechanism induced angle closure glaucoma||Authors:||Kaushik, Rinsha||Keywords:||DRNTU::Engineering::Electrical and electronic engineering||Issue Date:||2015||Abstract:||Glaucoma refers to ocular disorders that are characterized by damage to the optic nerve or loss in the field of vision. It is often associated with an increased intraocular pressure of the eye. Continuous damage to the optic nerve may lead to permanent loss of vision. Angle closure glaucoma, one of the categories of glaucoma, can happen suddenly and leads to an emergency situation. It can occur due to different underlying mechanisms and sometimes due to a combination of two or more of them. Usually, Laser Peripheral Iridotomy (LPI) is used to treat angle closure glaucoma. However, it may not be effective because of its inability to address all the underlying mechanisms. Therefore, it becomes vital to identify the combinatorial mechanisms underlying angle closure glaucoma. In this project, a novel approach has been taken to obtain the optimal set of minimum features which aid in the accurate detection of angle closure glaucoma caused due to combinatorial mechanisms. Ensemble learning has been used to achieve our goal. This method has been compared with the ‘simplistic ranks fusion’ method proposed for identification of single mechanisms by Niwas and our results have been found to be superior.||URI:||http://hdl.handle.net/10356/65241||Rights:||Nanyang Technological University||Fulltext Permission:||restricted||Fulltext Availability:||With Fulltext|
|Appears in Collections:||SCSE Student Reports (FYP/IA/PA/PI)|
Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.