Search

The paper proposes a classification algorithm based on support tensor machines which finds the maximum margin between the tensor spaces. The proposed algorithm has been deployed to classify erythemato-squamous diseases (ESDs) with the help of its features. Features are derived from the skin lesion images of ESDs, and it has been represented as second-order tensors, i.e., $$ \varvec{X} \in \varvec{ }{\mathbb{R}}^{\varvec{n}} $$ X∈Rn can be transformed into $$ \varvec{X} \in \,\varvec{ }{\mathbf{\Re }}^{{\varvec{n}_{1} }} \,\varvec{ } \otimes \,{\mathbf{\Re }}^{{\varvec{n}_{2} }} $$ X∈ℜn1⊗ℜn2 where $$ n_{1} \times n_{2} \cong n $$ n1×n2≅n . After deriving the features from the skin lesion images, dominant features are extracted using Tucker tensor decomposition method. Most of the existing machine learning algorithms depend on the vector-based learning models, and these algorithms suffer from the data overfitting problem. To resolve this problem, in this paper, tensor-based learning is implemented for classification. Proposed algorithm is evaluated with the real-time dataset (Xie et al. in: He, Liu, Krupinski, Xu (eds) Health information science, Springer, Berlin, 2012), and higher classification accuracy of 99.93–100% is achieved. The acquired results are compared with the existing machine learning algorithms, and it drives home the point that the proposed algorithm provides higher classification accuracy.

With the increase of data and computation in the healthcare industry, officials are looking for reliable alternatives to compete globally. Cloud technology is a viable option that reduces data and computation overhead at the host side. Due to the fast growth of cloud vendors (CVs), the apt selection of a vendor becomes crucial. Extant CV selection models 1) have reduced scope for minimizing subjective randomness; 2) cannot offer agents with flexible preference window; and 3) have higher human intervention during the decision process. Driven by these lacunae and to counter the same, a novel scientific model is developed in this article. Generalized orthopair fuzzy information is adopted to express preferences. Later, the attitudinal-CRITIC approach is put forward to determine the significance of functional factors. Agents’ attitude values are calculated by extending the variance approach. Agent wise personalized prioritization algorithm is developed to rank CVs based on individual perceptions, query vectors, and cumulative rank factors. The scientific model's usefulness is verified by adopting a case study of CV selection in a private medical unit in Trichy. Finally, sensitivity analysis and comparison with extant models help understand the merits and limitations of the proposed work.