An Effective Dictionary Learning Algorithm Based on fMRI Data for Mobile Medical Disease Analysis

With the continuous development and progress of the healthcare monitoring system, medical diagnosis for human health plays a, particularly, critical role, which can help doctors make correct choices and effective treatment plans. However, effective feature extraction is very important for the analysis of functional magnetic resonance imaging data; the traditional feature-based dictionary learning algorithm ignores the relationship between atoms and the input samples, and the small sample data is prone to over-fitting. In this paper, we propose a new weighting mechanism, which effectively considers the relationship between the atom and the input sample; meanwhile, the cross-validation method performed well on obtaining additional validation sets but proved to be over-fitting on small datasets in the traditional dictionary learning algorithm. Therefore,
$\mathrm {\ell 2}$
-norm and
$\mathfrak{F}$
-norm regularization constraint is adopted to avoid over-fitting, achieve the limitations of the model space, and improve the generalization ability of the model. In order to extract features better, this paper uses the cosine similarity method to select good feature subsets, which effectively improves further the generalization ability and enhances the feature extraction accuracy. The results show that the improved dictionary classification algorithm has better performance in terms of accuracy, sensitivity, and specificity, and it also demonstrates that the proposed algorithm has an effective classification about mobile multimedia medical diseases, which can provide a better guidance for the diagnosis of later diseases, so as to promote the rapid development of medical feature extraction.