Comparison of Modified Hierarchical Clustering Based on Density Peaks Using Kernel Function with Support Vector Machines in the Classification of Sinusitis

Zuherman Rustam, Sri Hartini, Nadisa Karina Putri, Jacob Pandelaki

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

There are two classes of sinusitis, acute and chronic. This research compares the modified hierarchical clustering based on density peaks (HCDP), using kernel function with support vector machines, utilizing dataset taken from Cipto Mangunkusumo Hospital, Indonesia. This collected detail consists of 102 acute and 98 chronic sinusitis samples. The results of this research therefore conclude that HCDP, using Gaussian radial basis kernel function, with the parameter $$ \sigma = 0.01 $$ possess an accuracy of 72.69% and has a better running time. However, the average accuracy of support vector machines is 98.53%.

Original languageEnglish
Title of host publicationAdvanced Intelligent Systems for Sustainable Development, AI2SD 2019 - Volume 4 - Advanced Intelligent Systems for Applied Computing Sciences
EditorsMostafa Ezziyyani
PublisherSpringer
Pages194-201
Number of pages8
ISBN (Print)9783030366735
DOIs
Publication statusPublished - 1 Jan 2020
Event2nd International Conference on Advanced Intelligent Systems for Sustainable Development, AI2SD 2019 - Marrakech, Morocco
Duration: 8 Jul 201911 Jul 2019

Publication series

NameAdvances in Intelligent Systems and Computing
Volume1105 AISC
ISSN (Print)2194-5357
ISSN (Electronic)2194-5365

Conference

Conference2nd International Conference on Advanced Intelligent Systems for Sustainable Development, AI2SD 2019
CountryMorocco
CityMarrakech
Period8/07/1911/07/19

Keywords

  • Classification
  • Density peaks
  • Hierarchical clustering
  • Kernel function
  • Sinusitis
  • Support vector machines

Fingerprint Dive into the research topics of 'Comparison of Modified Hierarchical Clustering Based on Density Peaks Using Kernel Function with Support Vector Machines in the Classification of Sinusitis'. Together they form a unique fingerprint.

  • Cite this

    Rustam, Z., Hartini, S., Putri, N. K., & Pandelaki, J. (2020). Comparison of Modified Hierarchical Clustering Based on Density Peaks Using Kernel Function with Support Vector Machines in the Classification of Sinusitis. In M. Ezziyyani (Ed.), Advanced Intelligent Systems for Sustainable Development, AI2SD 2019 - Volume 4 - Advanced Intelligent Systems for Applied Computing Sciences (pp. 194-201). (Advances in Intelligent Systems and Computing; Vol. 1105 AISC). Springer. https://doi.org/10.1007/978-3-030-36674-2_21