The Good, the Bad and the Unrecognized: Smart Textile Signal Clustering by Self-Organizing Map
Environment. Technology. Resources: Proceedings of the 11th International Scientific and Practical Conference. Vol.2 2017
Artyom Shootov, Jurijs Čižovs, Aleksandrs Okss, Aleksejs Kataševs

The present article is a series of publications dedicated to the research of smart fabric sensors integrated into socks and is also part of the project aimed at developing the measuring system based on smart fabric supplied with sensors and intellectual data processing. The aim of the article is to perform a practical study on the application of Self-Organizing Map to smart textile signal clustering. Within the framework of the research, different approaches to the organization of network training are explored. A method for encoding an input pattern is also proposed. It has been established that the network is able to recognize the signal as a good step, a bad step, and an unrecognized step. The primary classification allows further selecting specific algorithms for a detailed analysis of good steps and bad steps. The detailed analysis of bad steps is the key to solving the problem of revealing of an athlete’s special type of fatigue, leading to injuries.


Atslēgas vārdi
DAid® Pressure Sock System, self-organizing map, smart textile signal clustering.
DOI
10.17770/etr2017vol2.2567
Hipersaite
http://journals.ru.lv/index.php/ETR/article/view/2567/2569

Shootov, A., Čižovs, J., Okss, A., Kataševs, A. The Good, the Bad and the Unrecognized: Smart Textile Signal Clustering by Self-Organizing Map. No: Environment. Technology. Resources: Proceedings of the 11th International Scientific and Practical Conference. Vol.2, Latvija, Rezekne, 15.-17. jūnijs, 2017. Rezekne: Rezekne Academy of Technologies, 2017, 147.-153.lpp. ISSN 1691-5402. e-ISSN 2256-070X. Pieejams: doi:10.17770/etr2017vol2.2567

Publikācijas valoda
English (en)
RTU Zinātniskā bibliotēka.
E-pasts: uzzinas@rtu.lv; Tālr: +371 28399196