Human motion monitoring for falling detection using artificial intelligence
[ X ]
Tarih
2023
Yazarlar
Dergi Başlığı
Dergi ISSN
Cilt Başlığı
Yayıncı
Altınbaş Üniversitesi / Lisansüstü Eğitim Enstitüsü
Erişim Hakkı
info:eu-repo/semantics/closedAccess
Özet
Hospitals must continually monitor their patients' actions to lower the chance of accidents
such as patient falls and slides. Human behaviour is difficult to track due to the complexity
of human activities and the unpredictable nature of their conduct. As a result, creating a static
link that is used to influence human behaviour is challenging since it is hard to forecast how
individuals will think or act in response to a certain event. Deep learning and data mining
enable turbulence prediction models. Industry progressed greatly. This study anticipated four
motion turbulence types using auto encoding and two other methods. To improve accuracy.
The AEC's forecasts average 0.01 inaccuracy. Consequently, the 4SFNN method divides the
data into four areas for each classifier. The system now predicts 98.6025 percent. PSO
optimization boosts system performance, according to our research. Bayesian Regularization
training enhanced the recommended system's performance to 98.63 percent accuracy and
0.015 percent MAE.
Açıklama
Anahtar Kelimeler
4SFNN, PSO, AEC, Bayesian, Prediction, Accuracy, MAE, Falling, BSC, SDL, FOL, FKL
Kaynak
WoS Q Değeri
Scopus Q Değeri
Cilt
Sayı
Künye
Al-Hassani, R. T. A. (2023). Human motion monitoring for falling detection using artificial intelligence. (Yayınlanmamış doktora tezi). Altınbaş Üniversitesi, Lisansüstü Eğitim Enstitüsü, İstanbul.
