Programs
- Amrita’s Fetal Cardiology learning ( AFCL) Module – Fetal Heart Hybrid - Fellowship
- B.Tech. in Artificial Intelligence (AI) and Data Science (Medical Engineering) - Undergraduate
Publication Type : Conference Paper
Publisher : Lyon-Villeurbanne
Source : Proceedings of Modelling and Simulation, MS'2004, Lyon-Villeurbanne, p.2.34-2.37 (2004)
Keywords : Blood, Cerebral blood flow (CBF), Computer hardware description languages, Computer simulation, Electroencephalography, Epilepsy risk level, Fuzzy sets, Integrated circuit layout, Mathematical models, Medical problems, Membership functions, Patient treatment, Risks, simulation, Single input rule modules (SIRM) fuzzy systems, VLSI circuits, VLSI design
Year : 2004
Abstract : This paper presents a novel approach to identify and design a simple robust fuzzy system with minimum number of fuzzy rules in order to classify the epilepsy risk level of diabetic patients from cerebral blood flow and EEG signals. Four different types of fuzzy models are developed and tested with 200 patients. The better fuzzy system is identified based on the performance and quality value. The tuned SIRM fuzzy system has 98.58% performance and quality value of 36.56. Therefore the tuned SIRM fuzzy system with five rules of fuzzy rule base is identified and modeled. VLSI design and simulation of the tuned SIRM fuzzy system is undertaken. VLSI system is tested for the same 200 cases of known diabetic patients. The average performance obtained for VLSI system is 98.28. This result shows that the VLSI simulation is closely fallows the original MATLAB derived fuzzy system.
Cite this Research Publication : Ka Paramasivam, Harikumar, Rb, and Mohanasundaram, S. Vc, “VLSI design and simulation of a sirm fuzzy system for classification of epilepsy risk level in diabetic patients”, in Proceedings of Modelling and Simulation, MS'2004, Lyon-Villeurbanne, 2004, pp. 2.34-2.37.