APPLICATION OF INSTANCE-BASED LEARNERS FOR ARRHYTHMIA DETECTION IN ECG SIGNALS.

Journal Title: International Journal of Advanced Research (IJAR) - Year 2018, Vol 6, Issue 6

Abstract

Cardiac arrhythmia detection in heart activity related signals, like ECG, has been a center of attention for many researchers in medical field, and is as relevant, if not more, to this day. Aim of this paper is to investigate the accuracy of commonly used classifiers in classifying ECG signal segments of one heart beat into three classes ? normal, unrecognizable and arrhythmia ? and provide insight, which type of, or even specific classifier has a tendency to perform the best under given scenario. Results of the experiments showed that best performing classifiers are instance-based learning algorithms, top two performers being K* algorithm, based on entropic distance measure, with 99% correlation and 3,5% relative absolute error, while testing all input data as test data, 90% and 20% respectively, when testing with 75% of input data as training set, and the rest as testing set, along with IBk ? nearest neighbor based algorithm, which was only applicable with percentage split training method (75% / 25%), resulting in 84% correlation and 19% relative absolute error.

Authors and Affiliations

Andrius gudiskis.

Keywords

Related Articles

THE EFFECT OF TAURINE ON METHOTREXATE INDUCED HEPATORENAL TOXICITY IN RATS.

The aim of the work: Hepatorenal toxicity is a major side effect for methotrexate. Taurine is a natural compound with multiple pharmacological activities such as antioxidant, antiapoptotic and anti-inflammatory effects....

THE IMPACT OF PRODUCT, PROMOTION AND CONSUMER BEHAVIOR DIFFERENTIATION TOWARD T-CASH CUSTOMER SATISFACTION (CASE STUDY AT CELLULAR TELECOMMUNICATION COMPANY IN INDONESIA).

The objective of this research is toanalyze the Impact of Product, Promotion and Consumer Behavior Differentiation toward T-Cash Customer Satisfaction PT Telekomunikasi SelulerTbk inJakarta Based on the research objectiv...

POTENTIAL AREA MAPPING FOR SEAWEED AQUACULTURE BASED ON INTERVAL TYPE-2 FUZZY SETS AND MULTI-LAYER PERCEPTRON ALGORITHM.

This paper proposes a mapping model for seaweed aquaculture based on Interval Type-2 Fuzzy Sets (IT2FS) and Multi-Layer Perceptron (MLP) algorithm as a new framework to map potential area for seaweed cultivation to face...

MYOFIBROMATOSE INFANTILE: A PROPOS D UN CASINFANTILE MYO FIBROMATISIS : CASE REPORT.

Introduction: Infantile myofibromatosis (IM) is a rare benign mesenchymal tumor. It performs various clinical aspects. This is the most common fibromatosis of the child; it is characterized by a proliferation of fibrobla...

FREQUENCY OF CONSUMPTION AND PURCHASING BEHAVIOR FOR HEALTH BEVERAGES AMONGST THE URBAN POPULATION OF VADODARA, INDIA.

To estimate the frequency of consumption and factors affecting the purchase of health drinks including curd/buttermilk, fruit juices and probiotic beverages amongst the urban population of Vadodara. A total of 429 consum...

Download PDF file
  • EP ID EP343886
  • DOI 10.21474/IJAR01/7300
  • Views 52
  • Downloads 0

How To Cite

Andrius gudiskis. (2018). APPLICATION OF INSTANCE-BASED LEARNERS FOR ARRHYTHMIA DETECTION IN ECG SIGNALS.. International Journal of Advanced Research (IJAR), 6(6), 976-982. https://europub.co.uk/articles/-A-343886