Evolutionary Design of Reduced Precision Preprocessor for Levodopa-Induced Dyskinesia Classifier

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26230%2F22%3APU145297" target="_blank" >RIV/00216305:26230/22:PU145297 - isvavai.cz</a>

Výsledek na webu

<a href="https://link.springer.com/chapter/10.1007/978-3-031-14714-2_34" target="_blank" >https://link.springer.com/chapter/10.1007/978-3-031-14714-2_34</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/978-3-031-14714-2_34" target="_blank" >10.1007/978-3-031-14714-2_34</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Evolutionary Design of Reduced Precision Preprocessor for Levodopa-Induced Dyskinesia Classifier

Popis výsledku v původním jazyce

The aim of this work is to design a hardware-efficient implementation of data preprocessing in the task of levodopa-induced dyskinesia classification. In this task, there are three approaches implemented and compared: 1) evolution of magnitude approximation using Cartesian genetic programming, 2) design of preprocessing unit using two-population coevolution (2P-CoEA) of cartesian programs and fitness predictors, which are small subsets of training set, and 3) a design using three-population coevolution (3P-CoEA) combining compositional coevolution of preprocessor and classifier with coevolution of fitness predictors. Experimental results show that all of the three investigated approaches are capable of producing energy-saving solutions, suitable for implementation in hardware unit, with a quality comparable to baseline software implementation. Design of approximate magnitude leads to correctly working solutions, however, more energy-demanding than other investigated approaches. 3P-CoEA is capable of designing both preprocessor and classifier compositionally while achieving smaller solutions than the design of approximate magnitude. Presented 2P-CoEA results in the smallest and the most energy-efficient solutions along with producing a solution with significantly better classification quality for one part of test data in comparison with the software implementation.

Název v anglickém jazyce

Evolutionary Design of Reduced Precision Preprocessor for Levodopa-Induced Dyskinesia Classifier

Popis výsledku anglicky

The aim of this work is to design a hardware-efficient implementation of data preprocessing in the task of levodopa-induced dyskinesia classification. In this task, there are three approaches implemented and compared: 1) evolution of magnitude approximation using Cartesian genetic programming, 2) design of preprocessing unit using two-population coevolution (2P-CoEA) of cartesian programs and fitness predictors, which are small subsets of training set, and 3) a design using three-population coevolution (3P-CoEA) combining compositional coevolution of preprocessor and classifier with coevolution of fitness predictors. Experimental results show that all of the three investigated approaches are capable of producing energy-saving solutions, suitable for implementation in hardware unit, with a quality comparable to baseline software implementation. Design of approximate magnitude leads to correctly working solutions, however, more energy-demanding than other investigated approaches. 3P-CoEA is capable of designing both preprocessor and classifier compositionally while achieving smaller solutions than the design of approximate magnitude. Presented 2P-CoEA results in the smallest and the most energy-efficient solutions along with producing a solution with significantly better classification quality for one part of test data in comparison with the software implementation.

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

2022

Kód důvěrnosti údajů

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

Název statě ve sborníku

Parallel Problem Solving from Nature - PPSN XVII

ISBN

978-3-031-14713-5

ISSN

—

e-ISSN

—

Počet stran výsledku

14

Strana od-do

491-504

Název nakladatele

Springer Nature Switzerland AG

Místo vydání

Dortmund

Místo konání akce

Dortmund, Germany

Datum konání akce

10. 9. 2022

Typ akce podle státní příslušnosti

WRD - Celosvětová akce

Kód UT WoS článku

000871752100034