Respiration Classification Based on Logistic Regression Algorithm 


Vol. 46,  No. 1, pp. 162-169, Jan.  2021
10.7840/kics.2021.46.1.162


PDF Full-Text
  Abstract

In this paper, we propose the approach for classifying a breathing state of human using a learning-based algorithm. In particular, the experiments acquire respiratory signal in contactless manner. Most previous studies using bio-signals have used contact based methods that achieve accurate information about respiration. However, non-contact based methods show more robust performance in real environments that have external factors such as light, weather and motion artifacts than contact based methods do. In order to classify respiratory states, the previous work on signal processing techniques focused on the pre-processing of signals using filters to accomplish specific data types. In this paper, logistic regression and softmax function, unrestricted learning-based algorithm, are employed to achieve classification results. The experimental results show promising accuracy of the classification, and the results of classification accuracy increase according to the increase of the number of iterations of learning process.

  Statistics
Cumulative Counts from November, 2022
Multiple requests among the same browser session are counted as one view. If you mouse over a chart, the values of data points will be shown.


  Cite this article

[IEEE Style]

C. Park and D. Lee, "Respiration Classification Based on Logistic Regression Algorithm," The Journal of Korean Institute of Communications and Information Sciences, vol. 46, no. 1, pp. 162-169, 2021. DOI: 10.7840/kics.2021.46.1.162.

[ACM Style]

Cheolhyeong Park and Deokwoo Lee. 2021. Respiration Classification Based on Logistic Regression Algorithm. The Journal of Korean Institute of Communications and Information Sciences, 46, 1, (2021), 162-169. DOI: 10.7840/kics.2021.46.1.162.

[KICS Style]

Cheolhyeong Park and Deokwoo Lee, "Respiration Classification Based on Logistic Regression Algorithm," The Journal of Korean Institute of Communications and Information Sciences, vol. 46, no. 1, pp. 162-169, 1. 2021. (https://doi.org/10.7840/kics.2021.46.1.162)

Search
(IN TITLE, AUTHOR, ABSTRACT,KEYWORDS)

Advanced Search ▼

POPULAR KEYWORDS
(TOP 10 KEYWORDS)

Recent Publications
(LAST 3 YEARS)






pISSN : 1226 - 4717
eISSN : 2287 - 3880