Перейти к основному содержанию
AkademIndex

Продукты

Для разработчиков

AkademBaseскороОткрытый API экосистемы
Латиница
Русский
Статья

DATA ANALYSIS OF FRACTAL-FRACTIONAL CO-INFECTION COVID-TB MODEL WITH THE USE OF ARTIFICIAL INTELLIGENCE

Hasib KhanDepartment of Mathematics and Sciences, Prince Sultan University, 11586 Riyadh, Saudi ArabiaJehad AlzabutCenter for Research and Innovation, Asia International University, Yangiobod MFY, G’ijduvon Street, House 74, Bukhara, UzbekistanD. K. AlmutairiDepartment of Mathematics, College of Science Al-Zulfi, Majmaah University, 11952 Al-Majmaah, Saudi ArabiaHaseena GulzarDepartment of Biotechnology, Shaheed Benazir Bhutto University, Sheringal, Dir Upper, 18000 Khyber Pakhtunkhwa, PakistanWafa AlqurashiDepartment of Mathematics, Faculty of Science, Umm Al-Qura University, Makkah, Saudi Arabia
Fractalsjournal2025en
ABI

Аннотация

With the objective to better understand the dynamics of co-infection concepts for COVID-19 and tuberculosis (TB), this study employs proficient computational approaches, stability analysis, and the search for solutions. First, we verify the theoretical verification of the co-infection model by determining the existence of solutions. Consistency of projections depends on the model’s resilience against disruptions, whose stability analysis is demonstrated. We used artificial intelligence to apply neural networks to the analysis of the model data, and the results show the usefulness of our technique with mean square error performance that varies from [Formula: see text] to [Formula: see text] and a regression of [Formula: see text]. Complex patterns in time series data are further captured by nonlinear autoregressive (NAR) models. Neural network clustering analysis uncovers complex data structures and improves model understanding. This all-encompassing method integrates data clustering, AI-driven analysis, stability, and solution existence to establish an effective framework for exploring co-infection dynamics.

Темы

Идентификаторы

Цитирования и источники

Показатели — AkademScholar · Скоро