Applied Bionics and Biomechanics / 2017 / Article / Tab 4

Research Article

Comparison of Machine Learning Methods for the Arterial Hypertension Diagnostics

Table 4

Best classification scores.

Score, %Features

Linear discriminant analysis
91.33 ± 1.75HRVLFn(Fr)LF/HF(Fr)VLF(wt)
90.30 ± 1.37HRVLFn(Fr)VLF(wt)(LF/HF)int
90.04 ± 1.85HRLF/HF(Fr)VLF(wt)VLFn(wt)
90.44 ± 1.60HRVLFn(Fr)LF/HF(Fr)SDVLF
90.11 ± 1.80HRLF/HF(Fr)SDVLFVLFn(wt)
90.16 ± 1.61HRSDVLFVLFn(wt)(LF/HF)int

Quadratic discriminant analysis
90.31 ± 1.71HRVLFn(Fr)LF/HF(Fr)VLF(wt)

3-nearest neighbors
87.14 ± 2.12LF/HF(Fr)SDVLFVLFn(wt)W1/2VLF

4-nearest neighbors
85.56 ± 2.40SDVLFVLFn(wt)LF/HF(wt)W1/2VLF

5-nearest neighbors
86.63 ± 1.30HRHF(Fr)LFn(Fr)W1/2VLF

Support vector machine, radial base function
86.73 ± 2.24IASRFa2LFWVLF

Decision trees, max depth 5
87.10 ± 3.40IARPLF/HF(Fr)IASWLF

Decision trees, no max depth
87.34 ± 3.08IARPLF/HF(Fr)IASWLF

Naïve Bayes classifier
88.17 ± 1.07VLF(Fr)VLFn(Fr)LF/HF(Fr)W1/2LF

We are committed to sharing findings related to COVID-19 as quickly as possible. We will be providing unlimited waivers of publication charges for accepted research articles as well as case reports and case series related to COVID-19. Review articles are excluded from this waiver policy. Sign up here as a reviewer to help fast-track new submissions.