Pattern Recognition Using Hybrid Meta-Heuristic
Publication details: New Delhi STM Journals 2019Edition: Vol.6(2), May-AugDescription: 100-108pSubject(s): Online resources: In: Journal of artificial intelligence research and advances (JoAIRA)Summary: In this paper, two optimization algorithms i.e., Particle Swarm Optimization (PSO) and Gravitational Search Algorithm (GSA) are combined to produce a hybrid population-based algorithm PSOGSA. The approach of HPSOGSA is to use the assessment of PSO using the social thinking capability and the manipulation of GSA using the local search proficiency. To increase the performance of HPSOGSA, some benchmark functions are used. Two standard database ORL and YALE is used to assess the classification performance of the proposed method. Classification accuracy is compared for diverse number of training samples per class. Further lead of proposed method is confirmed by analyzing percentage improvement in classification accuracy. With limited accessibility of training sample, percentage enhancement is very successful for face recognition applications.| Item type | Current library | Status | Barcode | |
|---|---|---|---|---|
Articles Abstract Database
|
School of Engineering & Technology Archieval Section | Not for loan | 2020182 |
In this paper, two optimization algorithms i.e., Particle Swarm Optimization (PSO) and Gravitational Search Algorithm (GSA) are combined to produce a hybrid population-based algorithm PSOGSA. The approach of HPSOGSA is to use the assessment of PSO using the social thinking capability and the manipulation of GSA using the local search proficiency. To increase the performance of HPSOGSA, some benchmark functions are used. Two standard database ORL and YALE is used to assess the classification performance of the proposed method. Classification accuracy is compared for diverse number of training samples per class. Further lead of proposed method is confirmed by analyzing percentage improvement in classification accuracy. With limited accessibility of training sample, percentage enhancement is very successful for face recognition applications.
There are no comments on this title.
Click on an image to view it in the image viewer