Estimation of Heart Rate from Vocal Frequency Based on Support Vector Machine

Journal Title: International Journal of Advances in Scientific Research - Year 2016, Vol 2, Issue 1

Abstract

Heart rate (HR) is one of the vital signs used to assess our physical condition; it would be beneficial if HR could easily be obtained without special medical instruments. In this study, a feature of vocal frequency was used to estimate HR, because it can easily be recorded with a common device such as a smartphone. Previous studies proposed that a support vector machine (SVM) that adopted the inner product as the kernel function was efficient for estimating HR to a certain extent. However, these studies did not present the effectiveness of other kernel functions, such as the hyperbolic tangent function. Therefore, this study identified a combination of kernel functions of the kernel ridge regression (KRR). In addition, features of vocal frequency to effectively estimate HR were investigated. To evaluate the effectiveness, experiments were conducted with two subjects. In the experiment, 60 sets of HRs and voice data were measured per subject. To identify the most effective kernel function, four kernel functions (the inner function, Gaussian function, polynomial function, and hyperbolic tangent function) were compared. Moreover, effective features of vocal frequency were selected with the sequential feature selection (SFS) method. As a consequence, the hyperbolic tangent function worked best, and high-frequency components of voice were efficient. However, results of this research indicated that effective vocal spectrum components to estimate HR differ depending on prediction models.

Authors and Affiliations

Motoki Sakai

Keywords

Related Articles

Comparison and evaluation of ambient air quality at different nearby locations of LCL plant, 2014

The monitoring of ambient air quality is very important to evaluate the effect of running industry on environment. The Lahore compost Pvt. Ltd. has its own composting plant that utilizes tons of municipal solid waste to...

Contemporary Condition of Innovative Activity in the field of Health Care of the Republic of Kazakhstan

Context: Under these conditions innovative focus of the national health care system at all levels and new approaches to encourage innovation in medical organizations, taking into account the characteristics of their acti...

Structure and function of aconitase enzyme in TCA by estimating optical rotation of glucose and determining the relationship between cell density and absorbance

Enzyme aconitase have a great value in TCA path, this enzyme use to convert pyruvate and acetyl co A in to citrate and cis aconitase ( a six carbon molecule). This study was designed to find the tertiary structure of aco...

Model for Predicting and Analyzing the %Fe Removed as Deleterious Element from Al-Si alloys During Fe Removal Processing with Mn

Model equation for predicting and analysing %Fe removed from a eutectic Al-Si alloy during Fe removal processing with Mn under controlled conditions has been derived and validated. The model derived; % Fe removed = +1.30...

Analysis of Food Adulterants in Selected Food Items Purchased From Local Grocery Stores

Food is one among the basic needs for every living being. Food for human consumption should be in its possible purest form without adulterants and contaminants. The present study focuses on analyzing few selected food i...

Download PDF file
  • EP ID EP335259
  • DOI 10.7439/ijasr.v2i1.2849
  • Views 97
  • Downloads 0

How To Cite

Motoki Sakai (2016). Estimation of Heart Rate from Vocal Frequency Based on Support Vector Machine. International Journal of Advances in Scientific Research, 2(1), 16-22. https://europub.co.uk/articles/-A-335259