MODEE-LID: Multiobjective Design of Energy-Efficient Hardware Accelerators for Levodopa-Induced Dyskinesia Classifiers

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F23%3APU148869" target="_blank" >RIV/00216305:26230/23:PU148869 - isvavai.cz</a>

Výsledek na webu

<a href="https://ieeexplore.ieee.org/document/10139399" target="_blank" >https://ieeexplore.ieee.org/document/10139399</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1109/DDECS57882.2023.10139399" target="_blank" >10.1109/DDECS57882.2023.10139399</a>

Jazyk výsledku

angličtina

Název v původním jazyce

MODEE-LID: Multiobjective Design of Energy-Efficient Hardware Accelerators for Levodopa-Induced Dyskinesia Classifiers

Popis výsledku v původním jazyce

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 an automated 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 classification circuit co-designed using genetic programming (GP). We also introduce and evaluate a fast and accurate energy consumption estimation method for the target architecture of considered classifiers. In a multiobjective design scenario, GP evolves solutions showing the best trade-offs between accuracy and energy. Compared to the state-of-the-art solutions, the proposed method leads to classifiers showing a comparable accuracy while the energy consumption is reduced by 49 %.

Název v anglickém jazyce

MODEE-LID: Multiobjective Design of Energy-Efficient Hardware Accelerators for Levodopa-Induced Dyskinesia Classifiers

Popis výsledku anglicky

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 an automated 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 classification circuit co-designed using genetic programming (GP). We also introduce and evaluate a fast and accurate energy consumption estimation method for the target architecture of considered classifiers. In a multiobjective design scenario, GP evolves solutions showing the best trade-offs between accuracy and energy. Compared to the state-of-the-art solutions, the proposed method leads to classifiers showing a comparable accuracy while the energy consumption is reduced by 49 %.

Druh

D - Stať ve sborníku

CEP obor

—

OECD FORD obor

10201 - Computer sciences, information science, bioinformathics (hardware development to be 2.2, social aspect to be 5.8)

Projekt

<a href="/cs/project/GA21-13001S" target="_blank" >GA21-13001S: Automatizovaný návrh hardwarových akcelerátorů pro strojového učení zohledňující výpočetní zdroje</a><br>

Návaznosti

P - Projekt vyzkumu a vyvoje financovany z verejnych zdroju (s odkazem do CEP)

Rok uplatnění

2023

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název statě ve sborníku

2023 26th International Symposium on Design and Diagnostics of Electronic Circuits and Systems (DDECS)

ISBN

979-8-3503-3277-3

ISSN

—

e-ISSN

—

Počet stran výsledku

6

Strana od-do

155-160

Název nakladatele

Institute of Electrical and Electronics Engineers

Místo vydání

Tallinn

Místo konání akce

Tallinn

Datum konání akce

3. 5. 2023

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

001012062000030