Detail publikace

Multi-objective Design of Hardware Accelerators for Levodopa-Induced Dyskinesia Classifiers

HURTA, M. MRÁZEK, V. DRAHOŠOVÁ, M. SEKANINA, L.

Originální název

Multi-objective Design of Hardware Accelerators for Levodopa-Induced Dyskinesia Classifiers

Typ

abstrakt

Jazyk

angličtina

Originální abstrakt

Taking levodopa, a drug used to treat symptoms of Parkinson's disease, is often connected with severe side effects, known as Levodopa-induced dyskinesia (LID). It can fluctuate in severity throughout the day and thus is difficult to classify during a short period of a physician's visit. A low-power wearable classifier enabling long-term and continuous LID classification would thus significantly help with LID detection and dosage adjustment. This paper deals with a co-evolutionary design of energy-efficient hardware accelerators of LID classifiers that can be implemented in wearable devices. The accelerator consists of a feature extractor and a classifier co-evolved using cartesian genetic programming (CGP). We introduce and evaluate a fast and accurate energy consumption estimation method for the target architecture of considered classifiers. The proposed energy estimation method allows for a multi-objective design enabled by introducing energy constraints. With the introduction of variable data representation bit width, the proposed method achieves a good trade-off between accuracy (AUC) and energy consumption.

Klíčová slova

Cartesian genetic programming, Multi-objective design, Hardware accelerator, Energy-efficient, Levodopa-induced dyskinesia

Autoři

HURTA, M.; MRÁZEK, V.; DRAHOŠOVÁ, M.; SEKANINA, L.

Vydáno

12. 4. 2023

Místo

Brno

Strany počet

4

URL

https://www.fit.vut.cz/research/publication/12973/

BibTex

@misc{BUT185155,
  author="Martin {Hurta} and Vojtěch {Mrázek} and Michaela {Drahošová} and Lukáš {Sekanina}",
  title="Multi-objective Design of Hardware Accelerators for Levodopa-Induced Dyskinesia Classifiers",
  booktitle="Evo* 2023 -- Late-Breaking Abstracts Volume",
  year="2023",
  pages="4",
  address="Brno",
  url="https://www.fit.vut.cz/research/publication/12973/",
  note="abstract"
}