ABCGSA: A Novel Hybrid Artificial Bee Colony Gravitational Search Algorithm for Feature Selection of Fingerprint Intramodal Biometric System
Year: 2026
Type: article
Abstract: The feature selection (FS) algorithm extracts the most relevant and significant data from the large-dimensional feature space in the dataset, enhancing the biometric system’s classification accuracy. However, optimizing the feature diversity of high-dimensional feature space of the FS algorithm has been given little attention in existing FS algorithms. Therefore, a hybrid artificial bee colony (ABC)- based disruptive selection and Gravitational Search Algorithm (GSA) to form ABCGSA for enhanced FS prior to the classification phase of Fingerprint Intramodal Biometric System (FIBS) was developed. The developed ABCGSA was used to select optimal feature sets during FS to enhance the sensitivity, recognition accuracy (RA), false positive rate (FPR), false negative rate (FNR), and recognition time (RT) of FIBS. When compared with the existing algorithms used for FS, the results showed that ABCGSA’s sensitivity and RA increased by 3.21% and 4.73%, while FPR and FNR decreased by 8.96% and 3.21%, and RT improved by 20 s, thus enhancing the efficacy of FIBS. The developed algorithm could be used for FS of an intramodal biometric system to enhance access control in facilities. Received: 3 December 2025 | Revised: 24 February 2026 | Accepted: 1 April 2026 Conflicts of Interest The authors declare that they have no conflicts of interest to this work. Data Availability Statement The data that support the findings of this study are openly available in Kaggle at https://www.kaggle.com/datasets/ruizgara/socofing. Author Contribution Statement Janet O. Jooda: Conceptualization, Methodology, Software, Validation, Formal analysis, Investigation, Data curation, Writing – original draft, Visualization. Sunday A. Ajagbe: Conceptualization, Methodology, Software, Validation, Formal analysis, Investigation, Data curation, Writing – original draft, Visualization. Misan Paul Etchie: Software, Validation, Investigation, Data curation, Writing – original draft, Writing – review & editing, Visualization. Oluyinka T. Adedeji: Conceptualization, Methodology, Formal analysis, Resources, Writing – review & editing, Supervision, Project administration, Funding acquisition. Alice O. Oke: Conceptualization, Methodology, Formal analysis, Resources, Writing – review & editing, Supervision, Project administration, Funding acquisition. Pragasen Mudali: Resources, Writing – review & editing, Supervision, Project administration, Funding acquisition.
Authors: Janet O. Jooda(Conceptualization, Data curation, Formal analysis, Investigation, Methodology, Software, Validation, Visualization, Writing – original draft), Sunday Ajagbe(Conceptualization, Data curation, Formal analysis, Investigation, Methodology, Software, Validation, Visualization, Writing – original draft), Misan Paul Etchie(Data curation, Investigation, Software, Validation, Visualization, Writing – original draft, Writing – review & editing), Oluyinka T. Adedeji(Conceptualization, Formal analysis, Funding acquisition, Methodology, Project administration, Resources, Supervision, Writing – review & editing), Alice O. Oke(Conceptualization, Formal analysis, Funding acquisition, Methodology, Project administration, Resources, Supervision, Writing – review & editing), Pragasen Mudali(Funding acquisition, Project administration, Resources, Supervision, Writing – review & editing)
Language: English
Subfield: Signal Processing
Field: Computer Science
Domain: Physical Sciences
Keywords: feature selection, artificial bee colony algorithm, gravitational search algorithm, hybrid metaheuristic, fingerprint recognition, diversifying selection, high-dimensional feature space, recognition accuracy, access control, biometric classification, false positive and false negative rates, recognition time reduction, biometric template protection
Open Access status: diamond
Funder: University of Zululand
OpenAlex ID: W7204497898
