A Novel MOGA-SVM Multinomial Classification for Organ Inflammation Detection
Open Access
- 3 June 2019
- journal article
- research article
- Published by MDPI AG in Applied Sciences
- Vol. 9 (11) , 2284
Abstract
Wrist pulse signal (WPS) contains crucial information of humans’ health condition. It can serve as an alternative method for diagnosing of organ inflammation instead of traditional clinical measurement. In this paper, a novel multi-objective genetic algorithm based support vector machine (MOGA-SVM) has been proposed for the multinomial classification of the inflammations of appendix, pancreas, and duodenum. A customized similarity kernel (KCS) has been optimally designed. The performance of multinomial classification using KCS is compared with five types of kernels, linear, radial basis function (RBF), polynomial and sigmoid kernel, as well as mixtures of polynomial and RBF, to verify the effectiveness of KCS. The sensitivity, specificity and accuracy (Acc) of the proposed method are 92%, 91.2%, and 91.6% respectively. The results have demonstrated that KCS improves the accuracy of classification from 8.9% to 59.6%. When compared to related work, the proposed method increases the performance by more than 10%. It is believed that WPS can serve as alternative measures to diagnose organ inflammations.Keywords
This publication has 26 references indexed in Scilit:
- Body surface feature-based multi-modal Learning for Diabetes Mellitus detectionInformation Sciences, 2019
- Accuracy of Wrist-Worn Activity Monitors During Common Daily Physical Activities and Types of Structured Exercise: Evaluation StudyJMIR mHealth and uHealth, 2018
- Applied data science in patient-centric healthcare: Adaptive analytic systems for empowering physicians and patientsTelematics and Informatics, 2018
- Identification of motion outliers in wrist pulse signalComputers and Electrical Engineering, 2018
- A sensor-based wrist pulse signal processing and lung cancer recognitionJournal of Biomedical Informatics, 2018
- The Association of Radial Artery Pulse Wave Variables with the Pulse Wave Velocity and Echocardiographic Parameters in HypertensionEvidence-Based Complementary and Alternative Medicine, 2018
- Disease Diagnosis in Smart Healthcare: Innovation, Technologies and ApplicationsSustainability, 2017
- A new mathematical model of wrist pulse waveforms characterizes patients with cardiovascular disease – A pilot studyMedical Engineering & Physics, 2017
- Recognition of Pulse Wave Feature Points and Non-invasive Blood Pressure MeasurementJournal of Signal Processing Systems, 2016
- Computerized Wrist Pulse Signal Diagnosis Using Modified Auto-Regressive ModelsJournal of Medical Systems, 2009