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

Created by W.Langdon from gp-bibliography.bib Revision:1.8656

@InProceedings{Hurta:2023:evostarLBA,

• author = "Martin Hurta and Vojtech Mrazek and Michaela Drahosova and Lukas Sekanina",
• title = "Multi-objective Design of Hardware Accelerators for Levodopa-Induced Dyskinesia Classifiers",
• booktitle = "Evostar 2023 Late breaking abstracts",
• year = "2023",
• editor = "Antonio M. Mora and Anna I. Esparcia-Alcazar",
• pages = "1--4",
• address = "Brno",
• month = "12-14 " # apr,
• organisation = "Species",
• keywords = "genetic algorithms, genetic programming, Cartesian genetic programming, Parkinson's disease, Multi-objective design, Hardware accelerator, Energy-efficient, Levodopa-induced dyskinesia",
• URL = "https://arxiv.org/abs/2403.13950",
• size = "4 pages",
• abstract = "Taking levodopa, a drug used to treat symptoms of Parkinsons 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 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.",

}

Genetic Programming entries for Martin Hurta Vojtech Mrazek Michaela Sikulova Lukas Sekanina

Citations