Search results

Filters

  • Journals
  • Authors
  • Keywords
  • Date
  • Type

Search results

Number of results: 1
items per page: 25 50 75
Sort by:
Download PDF Download RIS Download Bibtex

Abstract

The invasive method of medically checking hemoglobin level in human body by taking the blood sample of the patient requiring a long time and injuring the patient is seen impractical. A non-invasive method of measuring hemoglobin levels, therefore, is made by applying the K-Nearest Neighbor (KNN) algorithm and the Artificial Neural Network Back Propagation (ANN-BP) algorithm with the Internet of Thingsbased HTTP protocol to achieve the high accuracy and the low endto- end delay. Based on tests conducted on a Noninvasive Hemoglobin measuring device connected to Cloud Things Speak, the prediction process using algorithm by means of Python programming based on Android application could work well. The result of this study showed that the accuracy of the K-Nearest Neighbor algorithm was 94.01%; higher than that of the Artificial Neural Network Back Propagation algorithm by 92.45%. Meanwhile, the end-to-end delay was at 6.09 seconds when using the KNN algorithm and at 6.84 seconds when using Artificial Neural Network Back Propagation Algorithm.
Go to article

Authors and Affiliations

R. Munadi
1
S. Sussi
1
N. Fitriyanti
2
D.N. Ramadan
3

  1. Department Telecomunication Engineering, School of Electric Engineering, Telkom University, Indonesia
  2. Department Physics Engineering, School of Electric Engineering, Telkom University, Indonesia
  3. School of Applied Science, Telkom University, Indonesia

This page uses 'cookies'. Learn more