No abstract

In recent years, age estimation and gender classification was one of the issues most frequently discussed in the field of pattern recognition and computer vision. This paper proposes automated predictions of age and gender based features extraction from human facials images. Contrary to the other conventional approaches on the unfiltered face image, in this study, we show that a substantial improvement be obtained for these tasks by learning representations with the use of deep convolutional neural networks (CNN). The feedforward neural network method used in this research enhances robustness for highly variable unconstrained recognition tasks to identify the gender and age group estimation. This research was analyzed and validated for the gender prediction and age estimation on both the Essex face dataset and the Adience benchmark. The results obtained show that the proposed approach offers a major performance gain, our model achieve very interesting efficiency and the state-of-the-art performance in both age and gender scoring.Povzetek: V prispevku je opisana študija s konvolucijskimi nevronskimi mrežami (CNN) za prepoznavanje starosti in spola iz obrazov na slikah.

No abstract

Every day, professionals generate and use massive healthcare data to save, treat and ameliorate the lives of patients. The healthcare industry has adopted cloud-based solutions to solve several problems in a cost-effective manner. Therefore, privacy and security mechanisms should be deployed to protect valuable medical information from unauthorized access. Much of the work in literature in recent years has focused on using artificial intelligence techniques such as deep learning and federated learning to solve various problems in the health field.Federated learning (FL) is a special technique for machine learning for privacy preservation. This study aims to compare the traditional centralized training approach and FL to show the advantages of using FL in the medical field and prove that FL can be adopted for security and data latency in e-health systems. The results obtained showed the feasibility of FL when compared to traditional methods used in the aspect of securing data and latency in the medical field .