A HYBRID INTELLIGENCE FRAMEWORK FOR PERSONALIZED EYEWEAR RECOMMENDATION: INTEGRATING HAAR CASCADE LOCALIZATION WITH A GENETICALLY TUNED CNN CLASSIFIER
ZONAsi: Jurnal Sistem Informasi · 2026
DOI: 10.31849/3cy8ft64 ↗Kurz gefasst
Fachartikel in der Zeitschrift ZONAsi: Jurnal Sistem Informasi, 2026. Verfasst von Abimanyu Putra Aria und 1 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY-SA 4.0).
Abstract (Originalsprache)
A hybrid intelligence framework was presented to improve eyewear recommendations through robust face shape classification. A Haar Cascade Classifier was integrated for initial facial localization, alongside a Convolutional Neural Network (CNN) based on the InceptionV3 architecture for the primary classification task. A pseudo-labeling technique was utilized to refine the dataset, which elevated the initial model to 88.54% test accuracy. Furthermore, the CNN's hyperparameters were systematically tuned using a Genetic Algorithm (GA). This evolutionary tuning process yielded a significant performance boost, culminating in a final classification accuracy of 97.65%. It was concluded that the synergistic combination of advanced preprocessing, data refinement, and a genetically optimized deep learning model provided a highly accurate solution for personalized recommendation systems.
Zitieren
APA
Aria, A. P., & Widodo, T. (2026). A HYBRID INTELLIGENCE FRAMEWORK FOR PERSONALIZED EYEWEAR RECOMMENDATION: INTEGRATING HAAR CASCADE LOCALIZATION WITH A GENETICALLY TUNED CNN CLASSIFIER. ZONAsi: Jurnal Sistem Informasi. https://doi.org/10.31849/3cy8ft64
Vancouver
Aria AP, Widodo T. A HYBRID INTELLIGENCE FRAMEWORK FOR PERSONALIZED EYEWEAR RECOMMENDATION: INTEGRATING HAAR CASCADE LOCALIZATION WITH A GENETICALLY TUNED CNN CLASSIFIER. ZONAsi: Jurnal Sistem Informasi. 2026. doi:10.31849/3cy8ft64
BibTeX
@article{Aria2026,
author = {Aria, Abimanyu Putra and Widodo, Tri},
title = {A HYBRID INTELLIGENCE FRAMEWORK FOR PERSONALIZED EYEWEAR RECOMMENDATION: INTEGRATING HAAR CASCADE LOCALIZATION WITH A GENETICALLY TUNED CNN CLASSIFIER},
journal = {ZONAsi: Jurnal Sistem Informasi},
year = {2026},
doi = {10.31849/3cy8ft64}
}
EUVIMED