Evolutionary Learning of Classifiers for Disk Discrimination
Authors:
- 8 April 2015
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ASME Transactions on Mechatronics
- Vol. 20 (6) , 1-10
Abstract
A novel disk discrimination approach with two levels of classification is proposed. The optical pickup head is controlled to emit the digital versatile disk laser followed by the compact disk laser during the process of being pulled in from the neutral position toward the optical disk. Four features are measured and analyzed based on the reflected signals from the optical disk. Two levels of classifications are designed for the disk discrimination using these four features. A supervised learning approach based on the evolutionary ellipsoid classification algorithm is utilized to learn the classifiers and optimize the classifier parameterizations. Six different disk types have been successfully discriminated using the proposed approach.Keywords
This publication has 25 references indexed in Scilit:
- Nonlinear Controller With the Dead-Zone and Saturation for Optical Disk Drive Systems in the Presence of External ShocksIEEE/ASME Transactions on Mechatronics, 2013
- Switching control in blu-ray disk drivesMechatronics, 2010
- Auto-adjustment of the Objective Lens Neutral Position in Optical Disc DrivesIEEE Transactions on Consumer Electronics, 2007
- Detection of surface defects and servo signal restoration for a compact disc playerIEEE Transactions on Control Systems Technology, 2006
- Disc defect classification for optical disc drivesIEEE Transactions on Consumer Electronics, 2005
- Discrimination among different kinds of surface defects on compact discs2005
- A disk discrimination method for digital versatile disks using a fuzzy inference system2002
- A low power digital servo architecture for optical discIEEE Transactions on Consumer Electronics, 2001
- Dynamic cluster generation for a fuzzy classifier with ellipsoidal regionsIEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics), 1998
- Pattern Recognition with Fuzzy Objective Function Algorithms1981