Dublin Core The Dublin Core metadata element set is common to all Omeka records, including items, files, and collections. For more information see, http://dublincore.org/documents/dces/. Title A name given to the resource Faculty Publications Article Faculty Publications -Articles Dublin Core The Dublin Core metadata element set is common to all Omeka records, including items, files, and collections. For more information see, http://dublincore.org/documents/dces/. Creator An entity primarily responsible for making the resource Kumar, Pankaj; Thomas, Merin; Manur, Manohar; Pani, Alok Kumar Title A name given to the resource Convolutional Neural Network based Di-Strategy Cheetah Optimization Algorithm for Automatic Diabetes Prediction Date A point or period of time associated with an event in the lifecycle of the resource 01-01-2025 Source A related resource from which the described resource is derived International Journal of Computing;Volume;24;Issue;2;pp.328-335 Identifier An unambiguous reference to the resource within a given context <a href="https://doi.org/10.47839/ijc.24.2.4016" target="_blank" rel="noreferrer noopener">https://doi.org/10.47839/ijc.24.2.4016</a> <br /><br /><a href="https://www.scopus.com/pages/publications/105010074256?origin=resultslist" target="_blank" rel="noreferrer noopener">https://www.scopus.com/pages/publications/105010074256?origin=resultslist</a> Coverage The spatial or temporal topic of the resource, the spatial applicability of the resource, or the jurisdiction under which the resource is relevant Kumar P., Department of Computer Science and Engineering, Government Engineering College, Vaishali, India; Thomas M., School of Computer science, RV University, Bengaluru, India; Manur M., Department of Computer Science and Engineering, CHRIST (Deemed to be University), Bengaluru, India; Pani A.K., Birla School of Applied Sciences, Birla Global University, Bhubaneswar, India Description An account of the resource Diabetes is a chronic metabolic disease characterized by elevated blood sugar levels. Diabetes prediction leverages patient data to assess the risk of developing the condition, facilitating early diagnosis and intervention. However, existing models struggle to capture the complex interactions between risk factors due to limited feature representation, leading to inaccurate predictions. This research proposes a Convolutional Neural Network-based Di-Strategy Cheetah Optimization Algorithm (CNN-DS-COA) for automatic diabetes prediction using patient data. The COA is enhanced with tent chaotic mapping and an adaptive search agent, which improves population diversity distribution and convergence speed. Initially, the Pima Indians Diabetes Database (PIMA) and Germany datasets are employed to evaluate the performance of CNN-DS-COA. Min-max normalization is applied to scale the data within a uniform range while preserving relationships among values. The CNN is then used for automatic diabetes prediction, with DS-COA fine-tuning the CNNs parameter values effectively using two strategies. The proposed CNN-DS-COA achieves superior accuracy, with 99.90% and 99.72% on the PIMA and Frankfurt Hospital, Germany datasets, respectively, outperforming existing methods such as stacked ensemble approaches and statistical predictive models. 2025, Research Institute of Intelligent Computer Systems. All rights reserved. Subject The topic of the resource adaptive search agent; convolutional neural network; di-strategy cheetah optimization algorithm; min-max normalization; tent chaotic mapping Publisher An entity responsible for making the resource available Research Institute of Intelligent Computer Systems Relation A related resource ISSN: 17276209; Language A language of the resource English Type The nature or genre of the resource Article Rights Information about rights held in and over the resource All Open Access; Gold Open Access Format The file format, physical medium, or dimensions of the resource online