doktorska disertacija
Igor Pernek (Author), Peter Kokol (Mentor)

Abstract

Vseprisotno računalništvo je v preteklosti postalo popularno tudi v zdravstvu,predvsem na področju podpore rekreativnih fizičnih aktivnosti. Pri tem se je večina preteklih raziskav osredotočala na uporabo vseprisotnih senzorjev in naprav za prepoznavanje tipa ter količine izvedenih aktivnostih, manj pozornosti pa je bilo posvečeno zaznavanju kvalitativnih parametrov vadbe, kot sta pravilnost in intenzivnost vadbe. V doktorskem delu izvedemo analize in predlagamo algoritme za vrednotenje intenzivnosti in pravilnosti različnih tipov rekreativne fizične aktivnosti v realnem času na zmogljivostnoomejenih vseprisotnih napravah. Predlagamo algoritem, ki z 99 % natančnostjo prepoznava število ponovitev treninga moči in zaznava njihove mejne točke z napako 215 ms oz. 11 % dolžine posamezne ponovitev. Izvedemo analizo uporabnosti različnih značilk pospeška in metod numeričnega napovedovanja za ocenjevanje intenzivnosti aerobnih aktivnosti. Ugotovimo, da enostavne metode, kot je linearna regresija, z majhnim število natančno izbranih značilk omogočajo napovedovanje srčnega utripa vadbe z napako približno 15 utripov na minuto. Na koncu predlagamo še hierarhični algoritem, ki s podatki, pridobljenimi iz petih nosljivih pospeškometrov, omogoča prepoznavanje intenzivnosti treninga moči. Prepoznavanje intenzivnosti poteka v dveh fazah, pri čemer je v prvi fazi prepoznan tip aktivnosti, v drugi pa jezaznana intenzivnost z ozirom na prepoznano aktivnost. Predlagani algoritem dosega 86 % natančnost prepoznavanja tipa aktivnosti in 6 % napako zaznavanja intenzivnosti. Dodatno analiza različnih konfiguracij senzorjev pokaže, da uporaba podmnožice senzorjev dosega rezultate primerljive natančnosti.

Keywords

vseprisotno računalništvo;prepoznavanje aktivnosti;vrednotenje kvalitete;

Data

Language: Slovenian
Year of publishing:
Typology: 2.08 - Doctoral Dissertation
Organization: UM FERI - Faculty of Electrical Engineering and Computer Science
Publisher: I. Pernek]
UDC: 004.655.3:004.855(043.3)
COBISS: 270582528 Link will open in a new window
Views: 1448
Downloads: 148
Average score: 0 (0 votes)
Metadata: JSON JSON-RDF JSON-LD TURTLE N-TRIPLES XML RDFA MICRODATA DC-XML DC-RDF RDF

Other data

Secondary language: English
Secondary title: Recognizing quality parameters of physical activities based on ubiquitous computing
Secondary abstract: During the last years ubiquitous computing has become an interesting research topic in healthcare, particularly in the area of physical activity support. Most of the past research focused on recognizing different activites and theirduration, not taking into account qualitative activity parameters, such as activity intensity and execution correctness. This thesis describes algorithms for real-time recognizion of correctness and intensity for different types of physical activities using ubiquitous sensors. An algorithm is proposed being able to correctly recognize 99 % of strength training repetitions with an average temporal recognition error of 215 ms or 11 % of individual repetition duration. Further, different types of statistical features and supervised machine learning methods are evaluated for predicting the intensity of common aerobic activities. The results show that simple methods, such as linear regression, with a small set of carefully selected features, can be used to predict the intensity of aerobic activities with an average error of 15 heart beats per second. Finally, a hierarchical algorithm is proposed to recognize the intensity of strength training activities using aset of wearable sensors. The algorithm recognizes the type of the activity performed and its intensity in two successive steps. The accuracy of the algorithm is 86 % for recognizing the exercise types with a 6 % error in intensity recognition. Additionally, an in-depth analysis of different sensor configurations is performed, showing that using only a subset of sensors achieves promising results.
Secondary keywords: ubiquitos computing;activity recognition;machine learning;Računalništvo;Disertacije;Strojno učenje;
URN: URN:SI:UM:
Type (COBISS): Doctoral dissertation
Thesis comment: Univ. v Mariboru, Fak. za elektrotehniko, računalništvo in informatiko
Pages: XIX, 133 str.
ID: 8728030
Recommended works:
, diplomska naloga univerzitetnega študijskega programa
, diplomsko delo