Jewajinda, Y. and Chongstitvatana, P., "A Parallel Genetic Algorithm for Adaptive Hardware and Its application to ECG Signal Classification," to be published in Neural Computing and Applications (ISSN: 0941-0643), 2012.


This paper presents a parallel genetic algorithm  and its implementation for adaptive hardware. An adaptive hardware based-on the parallel genetic algorithm is proposed to automate the real-time classification of ECG signals. The parallel genetic algorithm not only provides a strong search capability while maintaining genetic diversity using multiple genetic algorithms, but also has a cellular-like structure and is a straight forward algorithm suitable for hardware implementation. The hardware engine of the parallel genetic algorithm and an adaptive digital filter structure also perform an adaptive feature selection in real-time. In addition, the parallel genetic algorithm is applied to a block-based neural network for online learning in the hardware. Using an adaptive hardware approach based on the parallel genetic algorithm, an adaptive hardware for classifying ECG signal is feasible. The proposed adaptive hardware can be implemented in an FPGA or a small scale embedded system for portable medical devices applied to personalised ECG signal classifications for long- term patient monitoring.