DESIGN OF A VLSI HAMMING NEURAL NETWORK FOR ARRHYTHMIA CLASSIFICATION

2009 ◽  
Vol 18 (04) ◽  
pp. 825-839 ◽  
Author(s):  
BEHZAD GHANAVTI ◽  
GHOLAMREZA SHOMALNASAB

The implantable cardioverter defibrillators (ICDs) detect and treat dangerous cardiac arrhythmia. This paper describes a VLSI neural network chip to be implemented using 0.35 μ CMOS technology which acts as an intercardia tachycardia classification system. The Hamming network used to classify non binary input pattern and also reduce impact of noise, drift and offset inherent in analog application. Simulation result using HSPICE and level 49 parameters (BSIM3V3) that verify the functionality of circuit are presented.

2009 ◽  
Vol 18 (3) ◽  
pp. 236-240 ◽  
Author(s):  
JUAN PABLO BECA ◽  
EDUARDO ROSSELOT ◽  
RENÉ ASENJO ◽  
VERÓNICA ANGUITA ◽  
RAFAEL QUEVEDO

A 68-year-old patient who suffered from gastric cancer diagnosed 8 months earlier presented with multiple peritoneal and hepatic metastasis, despite several rounds of chemo- and radiotherapy. After admission to hospital, his general condition quickly became severely compromised. He was nearly emaciated, despite being on partial parenteral feeding. Four years earlier, due to a cardiac arrhythmia that was refractory to medication, the patient had a cardiac pacemaker (CPM) implanted, regulated to go off at frequencies of below 70 beats per minute. Given the patient's terminal situation, the team started developing some doubts about the pacemaker's effects during his dying process. The patient had mentioned his intention to donate his pacemaker after his death, but had not asked for its deactivation. The specialists were not sure about the effect of the pacemaker in unnecessarily prolonging the patient's final hour. Nevertheless, they opposed deactivation, which they considered ethically uncertain. The family, who had been initially for the deactivation, decided against it. The patient's condition was progressively deteriorating, as he was falling into a state of sopor and, later, into a coma.


Sign in / Sign up

Export Citation Format

Share Document