prikaz prve stranice dokumenta Predviđanje pokreta čovjeka pomoću pametnih telefona
Access restricted to students and staff of home institution
master's thesis
Predviđanje pokreta čovjeka pomoću pametnih telefona
2017. urn:nbn:hr:145:484181
Đurašinović, Anita
Josip Juraj Strossmayer University of Osijek
Faculty of Economics and Business in Osijek
Chair of Quantitative Methods and Informatics

Cite this document

Đurašinović, A. (2017). Predviđanje pokreta čovjeka pomoću pametnih telefona (Master's thesis). Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Economics and Business in Osijek. Retrieved from https://urn.nsk.hr/urn:nbn:hr:145:484181

Đurašinović, Anita. "Predviđanje pokreta čovjeka pomoću pametnih telefona." Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Economics and Business in Osijek, 2017. https://urn.nsk.hr/urn:nbn:hr:145:484181

Đurašinović, Anita. "Predviđanje pokreta čovjeka pomoću pametnih telefona." Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Economics and Business in Osijek, 2017. https://urn.nsk.hr/urn:nbn:hr:145:484181

Đurašinović, A. (2017). 'Predviđanje pokreta čovjeka pomoću pametnih telefona', Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Economics and Business in Osijek, accessed 15 November 2024, https://urn.nsk.hr/urn:nbn:hr:145:484181

Đurašinović A. Predviđanje pokreta čovjeka pomoću pametnih telefona [Master's thesis]. Osijek: Josip Juraj Strossmayer University of Osijek, Faculty of Economics and Business in Osijek; 2017 [cited 2024 November 15] Available at: https://urn.nsk.hr/urn:nbn:hr:145:484181

A. Đurašinović, "Predviđanje pokreta čovjeka pomoću pametnih telefona", Master's thesis, Josip Juraj Strossmayer University of Osijek, Faculty of Economics and Business in Osijek, Osijek, 2017. Available at: https://urn.nsk.hr/urn:nbn:hr:145:484181

Please login to the repository to save this object to your list.
Metadata
TitlePredviđanje pokreta čovjeka pomoću pametnih telefona
Title (english)HUMAN ACTIVITY RECOGNITION WITH SMARTPHONES
AuthorAnita Đurašinović
MentorMarijana Zekić Sušac (mentor)
Committee memberMarijana Zekić Sušac (predsjednik povjerenstva)
Committee memberSanja Pfeifer (član povjerenstva)
Committee memberDomagoj Sajter (član povjerenstva)
GranterJosip Juraj Strossmayer University of Osijek
Faculty of Economics and Business in Osijek
(Chair of Quantitative Methods and Informatics)
Osijek
Defense date and country2017-09-11, Croatia
Scientific / art field,
discipline and subdiscipline		SOCIAL SCIENCES
Economics
Business Informatics
Abstract
Ovaj rad objašnjava tehnologije prepoznavanja pokreta čovjeka te pomoću softverskog alata Statistica se analiziraju podaci baze podataka „Human activity recognition with smartphones“ preuzete sa web-sjedišta Kaggle.com. Pametni telefoni su vrlo popularni danas te ih mnogo ljudi posjeduje što čini korištenje senzora u pametnim telefonima najpogodnijima i cjenovno napristupačnijim alatima za mjerenje pokreta čovjeka. Tehnologija prepoznavanja pokreta čovjeka može se upotrijebiti u zdravstvu (bilježeći podatke o starijim osobama te sprječavanju njihovih padova i sl.), bilježenju svakodnevnih aktivnosti čovjeka, bilježenju lokacije ljudi i dr. Svrha rada je objasniti prepoznavanje pokreta čovjeka kroz ciljeve: objasniti tehnologiju i vrste prepoznavanja pokreta čovjeka, objasniti pristupe u prepoznavanju pokreta čovjeka, navesti područja primjene ovakve tehnologije i njene izazove i objasniti rezultate baze podataka „Human activity recognition with smartphones“ obrađene u programskom alatu Statistica. U poglavlju 2. Teorijska podloga i prethodna istraživanja uvodi se u ovu temu objašnjavanjem pojmova kao što su senzori koji se upotrebljavaju u pametnim telefonima, primjena i izazovi tehnologije prepoznavanja pokreta čovjeka, a u poglavlju 4. Opis istraživanja i rezultati istraživanja obrađuje se baza podataka i objašnjavaju rezultati. Podaci za potrebe ovog rada su se analizirali u alatu Statistica gdje su se izradili modeli neuronskih mreža i stabla odlučivanja. Podatke se klasificiralo u 6 kategorija: ležanje, sjedenje, stajanje, hodanje, hodanje niz stepenice i hodanje uz stepenice. U modelu stabala odlučivanja moglo se podrobnije vidjeti koje varijable najviše utječu za kategoriziranje ljudi u 6 spomenutih aktivnosti. Model neuronskih mreža dao je točnije rezultate.
Abstract (english)
This paper explains technologies for human activity recognition and with the use of the software program Statistica, data from the dataset „Human activity recognition with smartphones“ downloaded from the web-site Kaggle.com is analysed. Today, smartphones are very popular and many people own them which makes the use of smartphone sensors most suitable and cost-effective tools for measurement of human activities. Human recognition technology can be used in health (recording data about elderly people and preventing their falls etc.), recording people's everyday activities, recording people's location etc. Purpose of this paper is to explain human activity recognition through goals: explain technology and types of human activity recognition, explain approaches in human activity recognition, mention applications of this type of technology and its challenges and explain results of the dataset „Human activity recognition with smartphones“ processed in a software Statistica. In chapter 2. Theoretical background and previous research this topic is introduced by explaining terms like sensors that are used in smartphones, applications and challenges of the human activity recognition technologies, and in chapter 4. Research description and research results the dataset is processed and results explained. For the purpose of this paper, the data was analysed in the software program Statistica where models of neural networks and decision trees were made. Data was classified in 6 categories: laying, sitting, standing, walking, walking downstairs and walking upstairs. In decision tree model, the variables that had most effect in categorizing people in these 6 activities was viewed.
Keywords
Keywords (english)
Languagecroatian
URN:NBNurn:nbn:hr:145:484181
Study programmeTitle: Business economy; specializations in: Business Informatics
Course: Business Informatics
Study programme type: university
Study level: graduate
Academic / professional title: Magistar/magistra ekonomije (Magistar/magistra ekonomije)
Type of resourceText
File originBorn digital
Access conditionsAccess restricted to students and staff of home institution
Terms of useLicence In copyright icon
Created on2017-10-11 11:21:53