DARTS Meets Ants: A Hybrid Search Strategy for Optimizing KAN-Based 3D CNNs for Violence Recognition in Video

Buribayev, Zholdas; Zhassuzak, Mukhtar; Aouani, Maria; Zhangabay, Zhansaya; Abdirazak, Zemfira; Yerkos, Ainur

doi:10.3390/app152011035

This is an early access version, the complete PDF, HTML, and XML versions will be available soon.

Open AccessArticle

DARTS Meets Ants: A Hybrid Search Strategy for Optimizing KAN-Based 3D CNNs for Violence Recognition in Video

by

Zholdas Buribayev

¹,

Mukhtar Zhassuzak

^1,*,

Maria Aouani

²

,

Zhansaya Zhangabay

²,

Zemfira Abdirazak

¹ and

Ainur Yerkos

¹

Institute of Information and Computational Technologies, Almaty 050010, Kazakhstan

²

Department of Computer Science, Al-Farabi Kazakh National University, Almaty 050040, Kazakhstan

^*

Author to whom correspondence should be addressed.

Appl. Sci. 2025, 15(20), 11035; https://doi.org/10.3390/app152011035

Submission received: 17 August 2025 / Revised: 10 October 2025 / Accepted: 13 October 2025 / Published: 14 October 2025

(This article belongs to the Section Computing and Artificial Intelligence)

Download Versions Notes

Abstract

The optimization capabilities of Kolmogorov–Arnold Networks (KANs) remain largely unexplored, which has limited their practical use in video anomaly recognition compared to conventional 3D-CNNs. To address this gap, we introduce a novel hybrid optimization framework that combines a Minimax Ant System (MMAS) for hyperparameter selection with a modified DARTS strategy for adaptive tuning of the 3D KAN architecture. Unlike existing approaches, our method simultaneously optimizes both learning dynamics and architectural configurations, enabling KANs to better exploit their expressive power in spatiotemporal feature extraction. Applied to a three-class video dataset, the proposed approach improved model accuracy to 87%, surpassing the performance of a standard 3D-CNN by 6%.

Keywords: 3D CNN; Kolmogorov–Arnold Network; neural architecture search; ant colony optimization; violence detection; spatiotemporal features

Share and Cite

MDPI and ACS Style

Buribayev, Z.; Zhassuzak, M.; Aouani, M.; Zhangabay, Z.; Abdirazak, Z.; Yerkos, A. DARTS Meets Ants: A Hybrid Search Strategy for Optimizing KAN-Based 3D CNNs for Violence Recognition in Video. Appl. Sci. 2025, 15, 11035. https://doi.org/10.3390/app152011035

AMA Style

Buribayev Z, Zhassuzak M, Aouani M, Zhangabay Z, Abdirazak Z, Yerkos A. DARTS Meets Ants: A Hybrid Search Strategy for Optimizing KAN-Based 3D CNNs for Violence Recognition in Video. Applied Sciences. 2025; 15(20):11035. https://doi.org/10.3390/app152011035

Chicago/Turabian Style

Buribayev, Zholdas, Mukhtar Zhassuzak, Maria Aouani, Zhansaya Zhangabay, Zemfira Abdirazak, and Ainur Yerkos. 2025. "DARTS Meets Ants: A Hybrid Search Strategy for Optimizing KAN-Based 3D CNNs for Violence Recognition in Video" Applied Sciences 15, no. 20: 11035. https://doi.org/10.3390/app152011035

APA Style

Buribayev, Z., Zhassuzak, M., Aouani, M., Zhangabay, Z., Abdirazak, Z., & Yerkos, A. (2025). DARTS Meets Ants: A Hybrid Search Strategy for Optimizing KAN-Based 3D CNNs for Violence Recognition in Video. Applied Sciences, 15(20), 11035. https://doi.org/10.3390/app152011035

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Menu

DARTS Meets Ants: A Hybrid Search Strategy for Optimizing KAN-Based 3D CNNs for Violence Recognition in Video

Abstract

Share and Cite

Article Metrics

Article Access Statistics

Further Information

Guidelines

MDPI Initiatives

Follow MDPI