https://doi.org/10.1140/epjp/s13360-025-06396-9
Regular Article
Optimized convolutional neural network–multilayer perceptron for the detection of COVID-alike viruses using genome sequencing data
1
Department of Computer Application, Noorul Islam Centre for Higher Education, Kanyakumari, Tamil Nadu, India
2
Department of Computer Science and Engineering, V.S.B College of Engineering Technical Campus, Anna University, Coimbatore, Tamil Nadu, India
Received:
13
February
2025
Accepted:
3
May
2025
Published online:
28
May
2025
The COVID-19 pandemic caused by extremely serious respiratory syndrome SARS-Cov-2 has been spreading fatally at an exceptional pace. It has spread to millions of individuals and persists to significantly affect the health and well-being of the global population. Under this circumstance, researchers and medical experts may find it easier to comprehend the genetic variations of SARS-Cov-2 or COVID-19 with the use of advanced artificial intelligence algorithms and genome sequence analysis. Genome sequence evaluation of COVID-19 is important to comprehend the structure, origin, and behaviors of virus that may assist developing/producing antiviral drugs, vaccines, and proficient preventive schemes. This research develops a new optimization approach, called Trend Factor Smoothing Lyrebird Optimization Algorithm (TFSLOA) that is an integration of Trend Factor Smoothing (TFS) and Lyrebird Optimization Algorithm (LOA), to train learning rate of 1D CNN-MLP model for viruses, like COVID-19, SARS-Cov-2, MERS, and Orthomyxo analysis. Initially, the input genome sequence is fed to feature extraction that is performed by entropy, encoded genes, and n-gram features. Subsequently, genome sequencing data analysis is performed by employing 1D CNN-MLP which is adopted by a combination of 1D CNN and MLP techniques. Moreover, 1D CNN-MLP is trained by using TFSLOA. Finally, the experimentation analysis reveals that TFSLOA attains better accuracy of 0.947, precision of 0.951, recall of 0.953, and F-measure of 0.953.
Copyright comment Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
© The Author(s), under exclusive licence to Società Italiana di Fisica and Springer-Verlag GmbH Germany, part of Springer Nature 2025
Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.
