| dc.contributor.author | Ozogur, Gokhan | |
| dc.contributor.author | Erturk, Mehmet Ali | |
| dc.contributor.author | Aydin, Muhammed Ali | |
| dc.date.accessioned | 2021-03-05T09:39:41Z | |
| dc.date.available | 2021-03-05T09:39:41Z | |
| dc.identifier.citation | Ozogur G., Erturk M. A. , Aydin M. A. , "Prediction of Physical Activity Times Using Deep Learning Method", 1st International Telecommunications Conference (ITelCon), İstanbul, Türkiye, 28 - 29 Aralık 2017, cilt.504, ss.299-307 | |
| dc.identifier.other | vv_1032021 | |
| dc.identifier.other | av_9ee9867a-9069-4a1e-b7ce-039893ac3bba | |
| dc.identifier.uri | http://hdl.handle.net/20.500.12627/106718 | |
| dc.identifier.uri | https://doi.org/10.1007/978-981-13-0408-8_26 | |
| dc.description.abstract | Sedentary life style causes some serious health problems. In order to minimize these problems, it is recommended to do physical activities regularly. Even though it is possible to track activity level, making physical activity a habit is not easy. In this study, we aimed to predict the times when people will be stationary in terms of physical activity such as sitting or sleeping. Historical physical activity data of each individual is used to generate a model in order to estimate the percentage of being stationary within the next period of time for each individual. In this way, it will be reasonable to suggest a more suitable time for physical activity. | |
| dc.language.iso | eng | |
| dc.subject | Bilgi Sistemleri, Haberleşme ve Kontrol Mühendisliği | |
| dc.subject | Mühendislik ve Teknoloji | |
| dc.subject | Mühendislik, Bilişim ve Teknoloji (ENG) | |
| dc.subject | Mühendislik | |
| dc.subject | TELEKOMÜNİKASYON | |
| dc.title | Prediction of Physical Activity Times Using Deep Learning Method | |
| dc.type | Bildiri | |
| dc.contributor.department | Arcelik AS , , | |
| dc.identifier.volume | 504 | |
| dc.contributor.firstauthorID | 155581 | |
