In this paper, we employ a deep learning technique for individual recognition based on the use of ear images as a biometric trait. This methodology relies on advanced deep learning techniques to optimize individual identification. to evaluate our approach, we have exploited the Mathematical analysis of images (AMI)” database, developed by esther gonzalez. This database contains images of students, teachers and staff from the computer science department of the university of las palmas de gran canaria (ulpgc) in Spain. The results obtained proved promising, attesting to the suitability of this method for ear-based biometric recognition.
The rise of social networks has increased user interactions but also led to a surge in fake accounts, threatening privacy and security. These fraudulent profiles undermine trust and facilitate misinformation, making their detection crucial. This study proposes an improved machine learning approach using the Negative Selection Algorithm (NSA) to enhance fake account identification. Inspired by the human immune system, NSA helps distinguish between genuine and fraudulent accounts. Additionally, K-Means clustering refines the training dataset by removing anomalies, improving classification accuracy. Experimental results show promising improvements, contributing to more effective fake account detection and a safer online environment.