Result Details
ADEE-LID: Automated Design of Energy-Efficient Hardware Accelerators for Levodopa-Induced Dyskinesia Classifiers
Mrázek Vojtěch, Ing., Ph.D., DCSY (FIT)
Drahošová Michaela, Ing., Ph.D., DCSY (FIT)
Sekanina Lukáš, prof. Ing., Ph.D., DCSY (FIT)
Levodopa, a drug used to treat symptoms of Parkinson's disease, is connected to side effects known as Levodopa-induced dyskinesia (LID). LID is difficult to classify during a physician's visit. A wearable device allowing long-term and continuous classification would significantly help with dosage adjustments. This paper deals with an automated design of energy-efficient hardware accelerators for such LID classifiers. The proposed accelerator consists of a feature extractor and a classifier co-designed using genetic programming. Improvements are achieved by introducing a variable bit width for arithmetic operators, eliminating redundant registers, and using precise energy consumption estimation for Pareto front creation. Evolved solutions reduce energy consumption while maintaining classification accuracy comparable to the state of the art.
levodopa-induced dyskinesia, energy efficient,
hardware accelerator, genetic programming
@inproceedings{BUT184452,
author="Martin {Hurta} and Vojtěch {Mrázek} and Michaela {Drahošová} and Lukáš {Sekanina}",
title="ADEE-LID: Automated Design of Energy-Efficient Hardware Accelerators for Levodopa-Induced Dyskinesia Classifiers",
booktitle="2023 Design, Automation & Test in Europe Conference & Exhibition (DATE)",
year="2023",
pages="1--2",
publisher="Institute of Electrical and Electronics Engineers",
address="Antwerp",
doi="10.23919/DATE56975.2023.10137079",
isbn="978-3-9819263-7-8",
url="https://ieeexplore.ieee.org/document/10137079"
}Automated design of hardware accelerators for resource-aware machine learning, GACR, Standardní projekty, GA21-13001S, start: 2021-01-01, end: 2023-12-31, completed