Találati lista | Tudóstér

001-es BibID:	BIBFORM070756
Első szerző:	Sütő József (programtervező informatikus)
Cím:	Recognition rate difference between real-time and offline human activity recognition / Jozsef Suto, Stefan Oniga, Claudiu Lung, Ioan Orha
Dátum:	2017
Megjegyzések:	Nowadays the trend toward sedentary lifestyle is one of the main causes of some dangerous health problems such as obesity, back pain and cardiovascular diseases [1]. Monitoring and recognizing daily activities of a people can help in the evaluation and prediction of his/her health status. Moreover, the rapidly growing rate of elderly population greatly influences the development of heath care services. Based on these new challenges, several approaches have been proposed by researchers for the recognition of human activities in different application areas such as health care, smart homes, and ambient-assisted living [2]. In the past few decades, researchers tried different information acquisition approaches for human activity recognition (HAR) including computer vision and wearable sensor based techniques. After the appearance of the Internet of Things topic, the usage of wearable sensors for different kinds of purposes has spread rapidly [3]. Due to the limitations and disadvantages of vision-based techniques (privacy issue, lighting conditions, special environment, etc.), acceleration-based wearable sensors have received higher attention. In addition, their advantages (small size, low cost, long term continuous data acquisition) further increased their popularity. It motivated companies and research groups to develop own data acquisition devices with different types of sensors and controllers for HAR purposes [4], [5]. Today's smartphones are well equipped with memory, fast processor(s), built in sensors and powerful battery thus they provide new opportunities in HAR research. Smartphones can be used as a complex HAR system without any additional hardware requirements. They have many advantages unlike special purpose data collector devices. For example, smartphones provide high level programming environment with different visualization, communication and data storage possibilities. Already several researchers used phones for HAR [6]. Most of them utilized the phone as data acquisition device and the evaluation happened offline by mathematical or data mining tools such as Matlab or Weka [7], [8].
ISBN:	978-1-5386-2064-9
Tárgyszavak:	Műszaki tudományok Informatikai tudományok tanulmány, értekezés Human activity recognition Feature extraction Machine learning Wearable sensors
Megjelenés:	Internet of Things for the Global Community : Proceedings : July 10-12, 2017, Madeira-Portugal / Fernando Morgado-Dias. - p. 13-18. -
További szerzők:	Oniga István László (1960-) (villamosmérnök) Lung, Claudiu (1977-) (villamosmérnök) Orha, Ioan
Pályázati támogatás:	ÚNKP-16-3 Egyéb
Internet cím:	Szerző által megadott URL DOI Intézményi repozitóriumban (DEA) tárolt változat
Borító:
Saját polcon: