Izvorni znanstveni članak

https://doi.org/10.17559/TV-20250923003008

Optimization-Enhanced Vector Quantization and Encryption Using Spotted Hyena Algorithm for Efficient IIoT Data Management

R. Rengaraj alias Muralidharan, ; Department of Information technology, Saranathan College of Engineering, Trichy, India
S. P. Santhoshkumar ; Department of Computer Science and Engineering, School of Computing, Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science & Technology, Chennai, Tamilnadu, India
Hanan Abdullah Mengash ; Department of Information Systems, College of Computer and Information Sciences, Princess Nourah bint Abdulrahman University, P. O. Box 84428, Riyadh 11671, Saudi Arabia
Shravan Kumar Adepu ; Department of Biomedical Engineering, Saveetha School of Engineering, Saveetha Institute of Medical and Technical Sciences, Saveetha University, Saveetha Nagar, Thandalam, Chennai, Tamil Nadu, India *

* Dopisni autor.

Sažetak

In the context of the Industrial Internet of Things (IIoT), efficient and lightweight data compression and secure transmission methods are essential due to limited bandwidth, constrained device computation capabilities, and increasing cybersecurity threats. This paper presents the Spotted Hyena Optimizer-Vector Quantization with Encryption Scheme (SHO-VQES), a unified workflow that integrates SHO-optimized Linde-Buzo-Gray (LBG) codebook generation, Lempel-Ziv-Welch (LZW) compression, and Block-Based Perceptual Encryption (BBPE). The proposed framework is designed to enhance compression efficiency while providing perceptual-level data confidentiality suitable for real-time IIoT environments. In the SHO-VQES model, the Spotted Hyena Optimizer ensures optimal codebook generation, thereby improving quantization accuracy and reducing reconstruction errors. LZW compression further minimizes data size without imposing heavy computational overhead, making it ideal for resource-limited IIoT nodes. BBPE provides lightweight encryption by obscuring sensitive visual features, enabling a balance between privacy preservation and low-latency transmission. Experiments conducted on industrial defect image datasets (512 × 512 grayscale) and simulated IIoT sensor logs demonstrate that SHO-VQES achieves notable improvements compared to existing VQ-based schemes. Specifically, the method increases Peak Signal-to-Noise Ratio (PSNR) by 3.5-5 dB, boosts Compression Ratio (CR) by 25-35%, and reduces Computation Time (CT) by nearly 20%. While BBPE offers only perceptual rather than cryptographically strong security, and the evaluation relies on simulated rather than large-scale industrial deployments, the findings indicate that SHO-VQES provides a promising and practical solution for resource-constrained IIoT devices. Future research will focus on integrating stronger encryption mechanisms and validating the system in real-world smart manufacturing testbeds.

Ključne riječi

BBPE; data compression; encryption; IIoT; LZW; spotted hyena optimizer; vector quantization

Hrčak ID:

348680

URI

https://hrcak.srce.hr/348680

Datum izdavanja:

30.6.2026.

Posjeta: 0 *