Evolutionary Optimization of Neuromorphic Architecture for Low-power Cerebellum Prosthetic Instrumentation and Device in Biomedical Systems
Conference Publication ResearchOnline@JCUAbstract
Neuromorphic computing is a new generation of technique, which has been used in the neuroprosthetic implementation in biomedical applications. The spike-based computing mechanism enables it with low power consumption and real-time speed. However, there is a lack of optimization strategy for neuromorphic architecture of neuroprosthetic. In this paper, a novel optimization strategy for neuromorphic architecture of neuroprosthetic, named the Evolutionary Neuromorphic Optimization Framework (ENOF), is presented. A HEMA algorithm is proposed for the implementation of ENOF. It can continuously find the optimal mapping scheme and achieve better accuracy by jumping out of local optimization. Experimental results show that the proposed method can cut down the energy consumption and have better stability. Better optimization can be achieved along with the NoC scale increasing. The proposed work is meaningful for the low-power prosthetic instrumentation and device of biomedical systems, and can be applied in healthcare or clinical situations.
Journal
N/A
Publication Name
Conference Record - IEEE Instrumentation and Measurement Technology Conference
Volume
N/A
ISBN/ISSN
9781665453837
Edition
N/A
Issue
N/A
Pages Count
6
Location
Kuala Lumpur, Malaysia
Publisher
Institute of Electrical and Electronics Engineers
Publisher Url
N/A
Publisher Location
Piscataway, NJ, USA
Publish Date
N/A
Url
N/A
Date
N/A
EISSN
N/A
DOI
10.1109/I2MTC53148.2023.10176067