Health-care app detection using optimized clustering

Medical health-care apps have become ubiquitous in today’s world, enhancing health-care quality at affordable costs. The continuous development of new apps underscores their high acceptance and popularity. Machine learning techniques offer effective app identification owing to their high prediction accuracy, particularly with a training dataset of known apps. Although machine learning techniques provide high detection accuracy for known apps, they exhibit abysmal accuracy in detecting unknown and novel apps. This research proposes a novel approach to optimizing the K-means clustering algorithm for detecting zero-day apps. The proposed technique integrates a perceptron feed-forward neural network to determine the coordinates of the centroids of the clusters in K-means clustering. Experimental evaluations demonstrate the efficacy of the proposed approach in enhancing the performance of K-means clustering, providing improved detection for both known and unknown medical health-care apps. A total of 30 health-care apps was utilized in this evaluation. This research enhances the detection accuracy of medical healthcare apps, particularly zero-day apps. The intercluster similarity of the benign class improved to 0.99, and that of the malicious class improved to 0.91, highlighting the improved classification of the apps. The major contribution of this work is achieving an intercluster similarity of 0.89 for detecting novel apps.