EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

Explainable AI (XAI) for feature selection optimization in deep neural networks using the Howells craniometric dataset

Surya Aditya GD, Robert Marco

Science, Technology, and Communication Journal · 29.10.2026 · 7 (1) · 13-24

DOI: 10.59190/stc.v7i1.411 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Science, Technology, and Communication Journal, online erschienen am 29.10.2026. Verfasst von Surya Aditya GD und 1 weiteren Autor:innen. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).

AbstractBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Biological profile identification through cranial metrics is a crucial procedure in forensic anthropology. The use of high-dimensional tabular craniometric data often triggers information redundancy problems that degrade the performance of computational models. Moreover, rejection in the medical and legal domains frequently occurs due to the black-box nature of Deep Learning algorithms, which fail to provide anatomical transparency. This research develops an advanced hybrid expert system framework for classification using craniometric data. In the pre-processing stage, feature selection is optimized using a hybrid approach of genetic algorithm (GA) and particle swarm optimization (PSO) to optimally extract 15 critical cranial parameters from the 82 raw features of the William W. Howells craniometric dataset. In the classification stage, a 1D convolutional neural network (1D-CNN) is constructed. To validate the effectiveness of the proposed method, the GA-PSO 1D-CNN model is compared against a baseline 1D-CNN model trained on all 82 raw features without feature selection. To overcome the transparency issue, the black-box nature of the model is dismantled using the explainable AI (XAI) method based on SHAP via GradientExplainer. The experimental results show that the GA-PSO optimization successfully reduces feature dimensionality deterministically, preventing the curse of dimensionality while maintaining classification precision. Furthermore, the visual SHAP analysis is able to present the hierarchy of the 15 most determining craniometric parameters, providing a rationalization of operational decisions that are cross-validated with the principles of human biological anatomy.

Zitieren

APA

GD, S. A., & Marco, R. (2026). Explainable AI (XAI) for feature selection optimization in deep neural networks using the Howells craniometric dataset. Science, Technology, and Communication Journal, 7(1), 13-24. https://doi.org/10.59190/stc.v7i1.411

Vancouver

GD SA, Marco R. Explainable AI (XAI) for feature selection optimization in deep neural networks using the Howells craniometric dataset. Science, Technology, and Communication Journal. 2026;7(1):13-24. doi:10.59190/stc.v7i1.411

BibTeX
@article{GD2026,
  author = {GD, Surya Aditya and Marco, Robert},
  title = {Explainable AI (XAI) for feature selection optimization in deep neural networks using the Howells craniometric dataset},
  journal = {Science, Technology, and Communication Journal},
  year = {2026},
  volume = {7},
  number = {1},
  pages = {13--24},
  doi = {10.59190/stc.v7i1.411}
}
Kostenlos starten →