Data security is becoming important as the amount of video data transmitted over the internet grows rapidly. This research article aims to maximize the security of transmitted video data by proposing a novel hybrid technique for video encryption and decryption. Elliptic Curve Cryptography (ECC) and the Modified Advanced Encryption Standard (MAES) are two encryption techniques that are included in the hybrid approach. By providing a more effective and safe method for video encryption and decryption, this research considerably advances the field of video data protection in Internet communication. In the proposed technique the video frames are extracted, and each frame is first encrypted using MAES technique and then again encrypted using ECC technique. After the encryption, the individual frames are merged to make an encrypted video. The same process is performed in reverse order to perform decryption of the video. The results of the experiments demonstrate the effectiveness of the suggested scheme: higher security, better accuracy, and shorter processing times when compared to well-known techniques such as Advanced Encryption Standard (AES), MAES, ECC, Simplified Data Encryption Standard (SDES), and Chaotic Map methods.
25 January 2025 in International Journal of Geometric Methods in Modern Physics
There are many difficulties in managing and detecting preterm pregnancies, especially in the early stages. Analyzing electrohysterogram data, which show the electrical activity of uterine muscles, is a promising non-invasive method for classifying term and preterm pregnancies. However, the effectiveness of machine learning classifiers is hampered by the inherent class imbalance in datasets. In order to overcome this constraint, this study uses a Generative Adversarial Network to produce high-quality synthetic EHG data while maintaining the statistical properties of actual signals. By successfully reducing class imbalance, the enhanced dataset makes it possible for machine learning models to be trained with resilience. Real and synthetic features did not differ significantly, according to statistical validation using a t-test (p > 0.05). With this method, the Random Forest classifier obtained a ROC-AUC of 0.99 and a 10-fold cross-validation accuracy of 98%. The suggested GAN-based method’s simplicity and efficacy demonstrate its promise for resolving class imbalance and developing reliable classification systems for diagnostic applications.