prikaz prve stranice dokumenta Odabir pragova u algoritmima za detekciju pada
No public access
undergraduate thesis
Odabir pragova u algoritmima za detekciju pada
Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing, 2018. urn:nbn:hr:168:078580
Pavlaković, Lovro
University of Zagreb
Faculty of Electrical Engineering and Computing

Institutional repository: FER Repository

Cite this document

Pavlaković, L. (2018). Odabir pragova u algoritmima za detekciju pada (Undergraduate thesis). Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing. Retrieved from https://urn.nsk.hr/urn:nbn:hr:168:078580

Pavlaković, Lovro. "Odabir pragova u algoritmima za detekciju pada." Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2018. https://urn.nsk.hr/urn:nbn:hr:168:078580

Pavlaković, Lovro. "Odabir pragova u algoritmima za detekciju pada." Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, 2018. https://urn.nsk.hr/urn:nbn:hr:168:078580

Pavlaković, L. (2018). 'Odabir pragova u algoritmima za detekciju pada', Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, accessed 25 December 2024, https://urn.nsk.hr/urn:nbn:hr:168:078580

Pavlaković L. Odabir pragova u algoritmima za detekciju pada [Undergraduate thesis]. Zagreb: University of Zagreb, Faculty of Electrical Engineering and Computing; 2018 [cited 2024 December 25] Available at: https://urn.nsk.hr/urn:nbn:hr:168:078580

L. Pavlaković, "Odabir pragova u algoritmima za detekciju pada", Undergraduate thesis, University of Zagreb, Faculty of Electrical Engineering and Computing, Zagreb, 2018. Available at: https://urn.nsk.hr/urn:nbn:hr:168:078580

Metadata
TitleOdabir pragova u algoritmima za detekciju pada
Title (english)Threshold Selection in Fall Detection Algorithms
AuthorLovro Pavlaković
MentorRatko Magjarević (mentor)
Committee memberRatko Magjarević (predsjednik povjerenstva)
Committee memberGoran Šeketa (član povjerenstva)
Committee memberDominik Džaja (član povjerenstva)
GranterUniversity of Zagreb
Faculty of Electrical Engineering and Computing
Zagreb
Defense date and country2018-07-13, Croatia
Scientific / art field,
discipline and subdiscipline		TECHNICAL SCIENCES
Electrical Engineering
Abstract
Automatizirana detekcija pada se može provoditi obradom signala s troosnog akcelerometra pričvršćenog u područje kuka subjekta i provjerom postizanja graničnih vrijednosti. Za pravilan rad algoritma je potrebno optimizirati te granične vrijednosti. U radu se optimiziraju granične vrijednosti za dva algoritma predložena u prijašnjim radovima. Algoritmi su implementirani u Matlabu i testirani na 6 pronađenih skupova podataka koji sadrže velik broj simuliranih padova i aktivnosti svakodnevnog života. Karakteristične vrijednosti za sve padove su određene ručno i korištene u procesu optimizacije. Granične vrijednosti su odabrane odabirom percentila karakterističnih vrijednosti i postotnog odmaka za koji se ta granična vrijednost povećava. Ovim postupkom su u većini slučajeva dobivene osjetljivosti i točnosti iznad 90%.
Abstract (english)
Automated fall detection can be achieved using the signals from a triaxial accelerometer attached to the subject's waist and checking if the signals pass certain thresholds. The thresholds have to be optimized for the algorithm to work properly. The paper discusses the optimization of thresholds for two different algorithms proposed in other papers. The algorithms were implemented in Matlab and tested using 6 found datasets containing a large number of simulated falls and activities of daily life. Characteristic values for all the falls were determined manually and used in the optimization process. The thresholds were determined by choosing a percentile of the characteristic values and a percentage offset by which that value is increased. Using this method sensitivity and specificity of over 90% were achieved in most cases.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:168:078580
Study programmeTitle: Electrical Engineering and Information Technology
Study programme type: university
Study level: undergraduate
Academic / professional title: sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka elektrotehnike i informacijske tehnologije (sveučilišni/a prvostupnik/ prvostupnica (baccalaureus/baccalaurea) inženjer/inženjerka elektrotehnike i informacijske tehnologije)
Type of resourceText
File originBorn digital
Access conditionsClosed access
Terms of useLicence In copyright icon
Public note
Created on2019-03-13 23:41:47