Hybrid multiagent based adaptive genetic algorithm for limited view tomography using oppositional learning. (May 2022)

• Record Type: Journal Article
• Authors: Mishra, Raghavendra; Bajpai, Manish Kumar
• Is Part Of: Biomedical signal processing and control. Volume 75(2022)
• Publication Date: 2022-05
• Subjects: Multiagent GA -- Simulated annealing -- Fitness function -- Oppositional learning; Signal processing -- Periodicals; Biomedical engineering -- Periodicals; Signal Processing, Computer-Assisted -- Periodicals; Image Processing, Computer-Assisted -- Periodicals; Biomedical Engineering -- Periodicals; 610.28
• DOI: 10.1016/j.bspc.2022.103610
• Languages: English
• ISSNs: 1746-8094

Abstract

Highlights: This manuscript presents Hybrid Multiagent based Adaptive Genetic Algorithm (HMAGA) for limited view tomography. HMAGA is a combination of multiagent-based genetic algorithm (MAGA) and simulated annealing (SA) with adaptive crossover and mutation rate. The proposed algorithm uses two methods for reducing the loss of diversity and increases the convergence rate; these methods are oppositional learning and new random population. The proposed algorithm is suitable for limited view tomography. Abstract: Computed tomography (CT) plays a crucial role in the field of medical diagnosis. The prime objective of limited view tomography is to estimate the object's internal structure with limited view projection data. Limited view computed tomography (CT) has the ability to reduce the X-ray radiation dose imposed on the patient. This manuscript presents Hybrid Multiagent based Adaptive Genetic Algorithm (HMAGA) for limited view tomography. HMAGA is a combination of multiagent-based genetic algorithms and simulated annealing with adaptive crossover and mutation rate. The proposed algorithm uses two methods for reducing the loss of diversity and increases the convergence rate, and these methods are oppositional learning and a new random population. Experimental results reveal that the proposed algorithm provides satisfactory results with low computation overhead. The present manuscript also outperforms other states of the art reconstruction algorithms.