0558772 20250310155952.420220704235959.9 85134783820 000821082700001 10.14311/NNW.2022.32.005 20 s. cav_un_epca*02903211210-0552322 (2022)73-92Ústav informatiky AV ČR, v. v. i. hand detection ultrasound QRD RLS lattice algorithm parallel implementation hypothesis testing cav_un_auth*0330517 Likhonina Raissa UTIA-B Zpracování signálů Department of Signal Processing ZS ZS Department of Signal Processing CZ K Ústav teorie informace a automatizace AV ČR, v. v. i. cav_un_auth*0383037 Uglickich Evženie UTIA-B Zpracování signálů Department of Signal Processing ZS ZS Department of Signal Processing RU Ústav teorie informace a automatizace AV ČR, v. v. i. pdf http://library.utia.cas.cz/separaty/2022/ZS/uglickich-0558772.pdf http://nnw.cz/doi/2022/NNW.2022.32.005.pdf 8A21009 GA MŠk cav_un_auth*0432581 The present paper describes hand detection application implemented on Xilinx Zynq Ultrascale+ device, comprising multi-core processor ARM Cortex A53 and FPGA programmable logic. It uses ultrasound data and is based on adaptive QRD RLS lattice algorithm extended with hypothesis testing. The algorithm chooses between two use-cases: (1) “there is a hand in front of the device” vs (2) “there is no hand in front of the device”. For these purposes a new structure of the identification models was designed. The model presenting use-case (1) is a regression model, which has the order sufficient to cover all incoming data. The model responsible for use-case (2) is a regression model, which has a smaller order than the model (1) and a certain time delay, covering the maximal distance where the hand can possibly appear. The offered concept was successfully verified using real ultrasound data in MATLAB optimized for parallel processing and implemented in parallel on four cores of ARM Cortex A53 processor. It was proved that computational time of the algorithm is sufficient for applications requiring real-time processing. WOS IN 10000 10200 10201 2023 2 2 R hod 4 4rh 4 20250310154945.2 4 20250310155952.4 RVO:67985556 https://hdl.handle.net/11104/0332708 S 3+4 Article Computer Science Artificial Intelligence A COMPUTERSCIENCE.ARTIFICIALINTELLIGENCE 1.1 0 7.1 0.00019 0.165 389 0.247 0.800 19 Q4 5 Q4 Q4 0.17 Q4 4.5 2022 Soubory v repozitáři: uglickich-0558772.pdf 85134783820 SCOPUS PUBMED 000821082700001 WOS pdf cav_un_epca*0290321 Neural Network World 1210-0552 Roč. 32 č. 2 2022 73 92 Ústav informatiky AV ČR, v. v. i.