An ensemble classification and binomial cumulative based PCA for diagnosis of parkinson’s disease and autism spectrum disorder

A. Syed Haroon () and T. Padma ()
Additional contact information
A. Syed Haroon: Bharathiar University
T. Padma: Sona College of Technology

International Journal of System Assurance Engineering and Management, 2024, vol. 15, issue 1, No 20, 216-231

Abstract: Abstract Parkinson's disease is the brain disorder that affects the nervous system. A large number of research works have been carried out on this topic for better diagnosis of Parkinson’s disease. This paper introduces the Score-based Artificial Fish Swarm Algorithm (SAFSA) and the Fuzzy-based Beetle Swarm Optimization Algorithm (FBSOA) for ensemble feature selection for the rapid and accurate detection of psychological disorders related to Parkinson Disease (PD) and Autism Spectrum Disorder (ASD). This method extracts the most key features from the dataset, resulting in a higher rate of disease identification. Initially, the Min–Max Normalization approach is used as the data pre-processing technique. The binomial cumulative distribution function-based Principal Component Analysis (BCDPCA) dimensionality algorithm is used for dimensionality reduction. Next, FBSOA-based feature selection is proposed for finding the best features in the dataset. The fuzzy membership function is used to compute the weight value in the proposed FBSOA method. The FBSOA method uses a unique phenomenon of modifying the weight value of BSOA throughout the optimization process to improve outcomes. Finally, the disease classification is carried out by ensemble learning classification approaches like hybrid classifier of Fuzzy K-Nearest Neighbor (FKNN), Kernel Support Vector Machines (KSVM), Fuzzy Convolution Neural Network (FCNN) and Random Forest (RF). These classifiers are trained using UCI ML data source data, and the results are verified using Leave-One-Person-Out Cross-Validation (LOPOCV). Metrics used to assess the classification algorithm efficiency include accuracy, FAR, F-measure, Matthews Correlation Coefficient, Specificity, Sensitivity. Furthermore, the proposed method is highly stable and reliable, particularly when ensemble classification algorithms, classification accuracy of PD can reach 97% and the classification accuracy of ASD can reach 95%.

Keywords: Min–max normalization; Binomial cumulative distribution function based principal component analysis (BCDPCA); Score based artificial fish swarm algorithm (SAFSA); Fuzzy based beetle swarm optimization algorithm (FBSOA); Classification methods (search for similar items in EconPapers)
Date: 2024
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://link.springer.com/10.1007/s13198-022-01699-x Abstract (text/html)
Access to the full text of the articles in this series is restricted.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:spr:ijsaem:v:15:y:2024:i:1:d:10.1007_s13198-022-01699-x

Ordering information: This journal article can be ordered from
http://www.springer.com/engineering/journal/13198

DOI: 10.1007/s13198-022-01699-x

Access Statistics for this article

International Journal of System Assurance Engineering and Management is currently edited by P.K. Kapur, A.K. Verma and U. Kumar

More articles in International Journal of System Assurance Engineering and Management from Springer, The Society for Reliability, Engineering Quality and Operations Management (SREQOM),India, and Division of Operation and Maintenance, Lulea University of Technology, Sweden
Bibliographic data for series maintained by Sonal Shukla () and Springer Nature Abstracting and Indexing ().