View full-text article in PMC Diagnostics (Basel). 2024 Sep 29;14(19):2181. doi: 10.3390/diagnostics14192181 Search in PMC Search in PubMed View in NLM Catalog Add to search Copyright and License information © 2024 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/). PMC Copyright notice Algorithm 1: Feature Similarity Calculation using GWT Input:Weighted graph G=V,E,Dis,where V=v0,v1,…vN−1,E=v0v1,v1v2,…vN−2vN−1Output:minimum and maximum similar feature data represented by Umin and Umax respectivelyFeature Similarity Calculation:1:For k=0,1,2,…N−12: For minimum similar featurre calculation, while, do3: Adding the vertex into Umin, Umin={vk}4: Continue untill all the data feature path calculation5: For vertex vk, neighbour calcualtion Nk=vj∈V−Umin vkvj∈E}6: Calculate vj=argmin dk,j=argmin vj−vk w. r. t. vj∈N(k)7: Adding the vertex value vj to the end of the Umin data8: Assign vk=vj9: Till V−Umin=∅10: For maximum similarity calculation, while, do11: Adding the vertex into Umax, Umax={vk}12: Continue untill all the data feature path calculation13: For vertex vk, neighbour calcualtion Nk=vj∈V−Umax vkvj∈E}14: Calculate vj=argmax dk,j=argmax vj−vk w. r. t. vj∈N(k)15: Adding the vertex value vjto the end of the Umax data16: Assign vk=vj17: Till V−Umax=∅18:End