Claim Missing Document
Check
Articles

Optimation of image encryption using fractal Tromino and polynomial Chebyshev based on chaotic matrix Elkaf Rahmawan Pramudya; Moch. Arief Soeleman; Cahaya Jatmoko; Eko Hari Rachmawanto; Aris Marjuni; Pulung Nurtantio Andono; Folasade Olubusola Isinkaye
TELKOMNIKA (Telecommunication Computing Electronics and Control) Vol 22, No 6: December 2024
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/telkomnika.v22i6.26080

Abstract

Image encryption is a critical process aimed at securing digital images, safeguarding them from unauthorized access, tampering, or viewing to ensure the confidentiality and integrity of sensitive visual information. In this research, we integrate polynomial Chebyshev, fractal Tromino, and substitution S-box methods into a comprehensive image encryption approach. Our evaluation focuses on standardized 256×256-pixel images of Lena, Peppers, and Baboon, assessing key performance metrics like mean squared error (MSE), peak signal-to-noise ratio (PSNR), unified average changing intensity (UACI), number of pixel changes rate (NPCR), and entropy. The results reveal varying encryption quality across images, with Lena exhibiting the highest MSE (4702) and the lowest PSNR (12.89 dB). However, UACI, NPCR, and entropy values remain consistent across all images, indicating the proposed method’s stability concerning changing intensity, pixel alterations, and entropy levels. These findings contribute valuable insights into the effectiveness of the proposed encryption method, providing a foundation for further exploration and optimization in the field of cryptographic research. For future research direction, it is recommended to explore the impact of varying image sizes and types on the proposed method’s performance. Additionally, by focusing on the area of cryptographic threats, further analysis of the algorithm’s resistance against advanced attacks and its computational efficiency would be beneficial.
Video classification of Indonesian traditional dance using a hybrid CNN-LSTM model with pose estimation Candra Irawan; Heru Praomono Hadi; Cahaya Jatmoko; Mohamed Doheir
Bulletin of Electrical Engineering and Informatics Vol 15, No 1: February 2026
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/eei.v15i1.11093

Abstract

The preservation and recognition of traditional Indonesian dances face challenges due to limited digital documentation and declining intergenerational transmission. Manual annotation of dance videos is time-consuming and prone to subjectivity, creating urgency for automated solutions. This study proposes a deep learning-based approach combining convolutional neural networks (CNN) for spatial feature extraction and long short-term memory (LSTM) for temporal modeling to recognize traditional dance movements from video sequences. The system leverages OpenPose for keypoint detection and gesture estimation, enabling frame-wise pose representation prior to classification. A hyperparameter tuning process was applied to optimize the CNN-LSTM architecture using 80% of the dataset for training and 20% for testing. Experimental results show the proposed model achieved a macro accuracy of 98.4%, with perfect precision, recall, and F1-score. This research contributes to cultural heritage digitization and intelligent video analysis by enabling accurate, real-time classification of traditional dances, providing a foundation for future systems in education, archiving, and motion-driven applications.