التفاصيل البيبلوغرافية
| العنوان: |
Hybrid muddy electric fish and grasshopper optimization algorithm (MEF-GOA) based CNN for detection and severity differentiation of glaucoma in retinal fundus image. |
| المؤلفون: |
Sophia, Sundar Singh Sheeba Jeya, Diwakaran, S. |
| المصدر: |
Journal of Intelligent & Fuzzy Systems; 2023, Vol. 44 Issue 2, p2285-2303, 19p |
| مصطلحات موضوعية: |
ELECTRIC fishes, MATHEMATICAL optimization, RETINAL imaging, GLAUCOMA, GRASSHOPPERS |
| مستخلص: |
Glaucoma is an irreversible blindness that affects the people over the age of 40 years. Many approaches are proposed to detect glaucoma in image by dealing with its complex data. Redundancy is the major problem in medical image which could lead to increased false positive and false negative rates. This paper proposed a three-structure CNN optimized with Hybrid optimization approach for glaucoma detection and severity differentiation. The CNN structure is designed with three sub-groups to do attention prediction, segmentation and classification. The mathematical equation for Loss function is derived for the CNN structure with three hyper-parameters which is optimized with Hybrid approach. Hybrid optimization approach consist of Muddy Electric fish Optimization and Grass hopper optimization algorithm for exploration and exploitation processes. The proposed method is designed in a Matlab and validated with LAG and Rim-One database. The proposed method achieved accuracy greater than 95% and other metrics like F2 and AUC has reached 98%. [ABSTRACT FROM AUTHOR] |
|
Copyright of Journal of Intelligent & Fuzzy Systems is the property of IOS Press and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.) |
| قاعدة البيانات: |
Complementary Index |
