c o m p u t e r m e t h o d s a n d p r o g r a m s i n b i o m e d i c i n e 1 1 0 ( 2 0 1 3 ) 447–454 jo ur nal ho me p ag e: www.intl.elsevierhealt h.com/journals/cmpb A heart disease recognition embedded system with fuzzy cluster algorithm Helton Hugo de Carvalho Junior a , Robson Luiz Moreno b , Tales Cleber Pimenta b,∗ , Paulo C. Crepaldi b , Evaldo Cintra b a IFSP, Campus Campos do Jordao, Rua Monsenhor José Vita – 280 – Abernessia, Campos do Jordao, SP, 12460-000, Brazil b Grupo de Microeletronica da UNIFEI, Avenida BPS – 1303 – Pinheirinho, Itajuba, MG, 37500-903, Brazil a r t i c l e i n f o Article history: Received 16 October 2011 Received in revised form 17 May 2012 Accepted 9 January 2013 Keywords: Real-time identification Heart disease Field programmable gate arrays Soft-core processors Fuzzy clustering Embedded system a b s t r a c t This article presents the viability analysis and the development of heart disease identi- fication embedded system. It offers a time reduction on electrocardiogram – ECG signal processing by reducing the amount of data samples, without any significant loss. The goal of the developed system is the analysis of heart signals. The ECG signals are applied into the system that performs an initial filtering, and then uses a Gustafson–Kessel fuzzy clustering algorithm for the signal classification and correlation. The classification indicated com- mon heart diseases such as angina, myocardial infarction and coronary artery diseases. The system uses the European electrocardiogram ST-T Database (EDB) as a reference for tests and evaluation. The results prove the system can perform the heart disease detection on a data set reduced from 213 to just 20 samples, thus providing a reduction to just 9.4% of the original set, while maintaining the same effectiveness. This system is validated in a Xilinx Spartan ® -3A FPGA. The field programmable gate array (FPGA) implemented a Xilinx Microblaze ® Soft-Core Processor running at a 50 MHz clock rate. © 2013 Elsevier Ireland Ltd. All rights reserved. 1. Introduction The analysis of an electrocardiogram is performed by physi- cians and other health professionals in order to diagnosis many heart diseases. The analysis consists of extracting information from the peaks and time intervals of the signal waveforms. Few advanced electronic equipments can even conduct the analysis at patient’s home, based on few extracted parameters [1]. Some heart diagnosis systems [2–7] are based on com- puter algorithms that use signal processing techniques for the interpretation of the electrocardiogram characteristics, thus allowing preliminary diagnosis of a cardiopathy. Ref. [2] pro- poses the multi-channel beat detection and segmentation, ∗ Corresponding author. Tel.: +55 35 3629 1193; fax: +55 35 3629 1187. E-mail address: tales@unifei.edu.br (T.C. Pimenta). waveform models and unsupervised patient adaptation method used to detect ischemia. It demonstrates the use of segmentation for the data analysis in the signal processing. It uses the same ECG data bank and the same sensitivity and positive predictivity as in our work. Heuristic rules provided by cardiologists are used as knowledge base. On the other hand, [3] introduces a cardiac arrhythmia classification system using fuzzy classifiers, that uses artifi- cial intelligence algorithms and a knowledge base to classify arrhythmias. Ref. [4] detects specific points of the elec- troencephalogram (segment ST) using network-based fuzzy interferences and a MIT-BIH [8] knowledge base to classify the segment forms and thus provide the diagnosis of few car- diac illnesses. Those works provide detection mechanism by comparison of the signal with a databank. 0169-2607/$ – see front matter © 2013 Elsevier Ireland Ltd. All rights reserved. http://dx.doi.org/10.1016/j.cmpb.2013.01.005