Blockchain-Based Optimization Model for Evaluating Psychological Mental Disease and Mental Fitness

• Published in: Computational intelligence and neuroscience 2022-07, Vol.2022, p.1-9
• Main Authors: Prasad, Jayashree Rajesh, Athawale, Shashikant V., Raut, Roshani, Patil, Sonali, Bhandari, Sheetal U., Shah, Mohd Asif
• Format: Article
• Language: English
• Subjects: Accuracy; Algorithms; Analysis; Artificial neural networks; Biogeography; Blockchain; Cognitive ability; Cognitive style; Cryptography; Fitness; Health care reform; Interactive learning; Learning strategies; Machine learning; Mathematical optimization; Mental disorders; Mental health; Mental illness; Mutation; Neural networks; Optimization algorithms; Optimization models; Optimization techniques; Psychology; Social psychology; Students; Teachers
• ISSN: 1687-5265; 1687-5273
• DOI: 10.1155/2022/8657313

The current work describes a blockchain-based optimization approach that mimics the psychological mental illness evaluation procedure and evaluates mental fitness. Combining lightweight models with blockchains can give a variety of benefits in the healthcare business. This study aims to offer an improved review and learning optimization technique (SPLBO) based on the social psychology theory to overcome the biogeography-based optimization (BBO) algorithm’s shortcomings of low optimization accuracy and instability. It also creates high-accuracy solutions in recognized domains quickly. To retain student individuality, students can be divided into two groups: Human psychological variables are incorporated in the algorithm’s improvement: in the “teaching” step of the original BBO algorithm; the “expectation effect” theory of social psychology is combined: “field-independent” and “field-dependent” cognitive styles. As a consequence, low-weight deep neural networks have been designed in such a manner that they require fewer resources for optimal design while also improving quality. A responsive student update component is also introduced to duplicate the effect of the environment on students’ learning efficiency, increase the method’s global search capabilities, and avoid the problem of falling into a local optimum in the first repetition.