| | SLO | ENG | Cookies and privacy

Bigger font | Smaller font

Show document Help

Title:Značilke pri razpoznavanju aktivnosti dnevnega življenja v pametnih domovih
Authors:ID Baketarić, Dražen (Author)
ID Donaj, Gregor (Author)
ID Sepesy Maučec, Mirjam (Author)
Files:.pdf Features_in_recognizing_activit-BaketariC-2024.pdf (4,66 MB)
MD5: 75A1244EC994EFE807EF06023D3254E0
 
URL https://journals.um.si/index.php/anali-pazu/article/view/4801
 
Language:Slovenian
Work type:Scientific work
Typology:1.01 - Original Scientific Article
Organization:UZUM - University of Maribor Press
FERI - Faculty of Electrical Engineering and Computer Science
Abstract:Slovenija se kot večina razvitih držav sooča s staranjem prebivalstva. Poraja se vprašanje, kako starostnikom zagotoviti varno bivanje v domačem okolju. Tehnološki razvoj na področju senzorskih tehnologij, strojnega učenja in umetne inteligence lahko prispeva k doseganju tega cilja. Sistemi za zaznavanje aktivnosti dnevnega življenja z visoko točnostjo razpoznavajo aktivnosti stanovalcev pametnih domov. Posledično lahko zaznajo motnje pri vsakodnevnem delovanju starostnika, kar lahko kaže na zdravstvene težave. Tovrstni sistemi temeljijo na senzorskih omrežjih in na podlagi aktivacije različnih senzorjev razpoznavajo aktivnosti stanovalcev. Točnost razpoznavanja aktivnosti je odvisna predvsem od kakovosti značilk, ki jih sestavimo iz senzorskih podatkov, in algoritma oz. modela za klasifikacijo, ki ga iz podatkov zgradimo v fazi učenja. V raziskavi se osredotočamo predvsem na izbiranje in izločanje značilk ter proučujemo kako le-to vpliva na končni rezultat razpoznavanja aktivnosti. Analiziramo, pri katerih aktivnostih je točnost razpoznavanja najboljša in pri katerih najslabša. Pri slednjih prikažemo tudi, s katerimi aktivnostmi le-te najpogosteje zamenjujemo.
Keywords:senzorji, aktivnosti, razpoznavanje aktivnosti, strojno učenje, klasifikacija
Publication status:Published
Publication version:Version of Record
Submitted for review:06.02.2024
Publication date:23.12.2024
Place of publishing:Maribor
Publisher:Univerza v Mariboru, Univerzitetna založba
Year of publishing:2024
Number of pages:21
Numbering:Letn.14, št.2
PID:20.500.12556/DKUM-97235 New window
UDC:004.5
ISSN on article:2820-364X
COBISS.SI-ID:223402755 New window
DOI:10.18690/analipazu.14.2.1-21.2024 New window
Publication date in DKUM:24.02.2026
Views:161
Downloads:9
Metadata:XML DC-XML DC-RDF
Categories:Misc.
:
Copy citation
  
Average score:(0 votes)
Your score:Voting is allowed only for logged in users.
Share:Bookmark and Share



Hover the mouse pointer over a document title to show the abstract or click on the title to get all document metadata.

Record is a part of a journal

Title:Anali PAZU
Publisher:Združenje Pomurska akademsko znanstvena unija, Združenje Pomurska akademsko znanstvena unija, Univerzitetna založba Univerze v Mariboru
ISSN:2232-416X
COBISS.SI-ID:257553152 New window

Document is financed by a project

Funder:ARIS - Slovenian Research and Innovation Agency
Project number:P2-0069
Name:Napredne metode interakcij v telekomunikacijah

Licences

License:CC BY-NC-ND 4.0, Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International
Link:http://creativecommons.org/licenses/by-nc-nd/4.0/
Description:The most restrictive Creative Commons license. This only allows people to download and share the work for no commercial gain and for no other purposes.

Secondary language

Language:English
Title:Features in Recognizing Activities of Daily Life in Smart Homes
Abstract:The question arises of how to ensure a safe stay for the elderly in their home environment. Development in sensor technology, machine learning, and artificial intelligence can contribute to achieving this goal. Activities of daily life recognition systems recognize the activities of residents in smart homes with high accuracy. They can consequently detect anomalies in the daily functioning of the elderly, which may indicate health problems. Systems of this type are based on sensor networks and recognize the activities of residents based on the activation of various sensors. The accuracy of activity recognition depends primarily on the quality of the features that are compiled from sensor data and the classification model, which is built from the collection of data in the learning phase. In the presented research, we mainly focus on selecting and extracting features and studying how different features affect the final result of activity recognition. We analyze which activities have the best and which have the worst recognition accuracy. In the latter's case, we also show which activities are most often misidentified.
Keywords:sensor, activity, activity recognition, machine learning, classification


Collection

This document is a part of these collections:
  1. Anali PAZU

Comments

Leave comment

You must log in to leave a comment.

Comments (0)
0 - 0 / 0
 
There are no comments!

Back
Logos of partners University of Maribor University of Ljubljana University of Primorska University of Nova Gorica