Shanookha Ali

Shanookha Ali, Nitha Niralda P C

Coronary heart disease (CHD) arises from complex interactions among uncontrollable factors, controllable lifestyle factors, and clinical indicators, where relationships are often uncertain. Fuzzy subgraph connectivity (FSC) provides a systematic tool to capture such imprecision by quantifying the strength of association between vertices and subgraphs in fuzzy graphs. In this work, a fuzzy CHD graph is constructed with vertices for uncontrollable, controllable, and indicator components, and edges weighted by fuzzy memberships. Using FSC, we evaluate connectivity to identify strongest diagnostic routes, dominant risk factors, and critical bridges. Results show that FSC highlights influential pathways, bounds connectivity between weakest and strongest correlations, and reveals critical edges whose removal reduces predictive strength. Thus, FSC offers an interpretable and robust framework for modeling uncertainty in CHD risk prediction and supporting clinical decision-making.

Shanookha Ali, Nitha Niralda, Sunil Mathew

The process of pooling vertices involves the creation of a new vertex, which becomes adjacent to all the vertices that were originally adjacent to the endpoints of the vertices being pooled. After this, the endpoints of these vertices and all edges connected to them are removed. In this document, we introduce a formal framework for the concept of fuzzy vertex pooling (FVP) and provide an overview of its key properties with its applications to neural networks. The pooling model demonstrates remarkable efficiency in minimizing loss rapidly while maintaining competitive accuracy, even with fewer hidden layer neurons. However, this advantage diminishes over extended training periods or with larger datasets, where the model's performance tends to degrade. This study highlights the limitations of pooling in later stages of deep learning training, rendering it less effective for prolonged or large-scale applications. Consequently, pooling is recommended as a strategy for early-stage training in advanced deep learning models to leverage its initial efficiency.