Düşme Tespit Sistemlerinde Aktivite Sınıfı Sayısının Etkisinin Araştırılması

Abstract

Bu çalışmada, yaşlı bireyler için geliştirilen düşme tespit sistemlerinde, makine öğrenmesi tabanlı sınıflandırıcılarda sınıf sayısının azaltılmasının doğruluk seviyesine katkısı araştırılmıştır. Çalışma kapsamında internette açık erişime sunulmuş bir veriseti kullanılmış, aktivite ve postür belirlemede sıkça kullanılan öznitelikler çıkarılmış ve MATLAB Machine Learning Framework’de bulunan sınıflandırıcıların tümü kullanılarak en başarılı sınıflandırıcının tahlili makine öğrenmesi metriklerine göre yapılmıştır. Sınıf sayısı kademeli olarak azaltılıp başarıya etkisi incelenmiştir. Başlangıç aşamasında sınıf sayısı azaltılmadan yapılan sınıflandırmada en başarılı sınıflandırıcı olarak Kübik Destek Vektör Makinesi (Cubic SVM)algoritması belirlenmiştir. Bu algoritmayı kullanarak gerçekleştirilen sınıflandırmada başarı % 96,4 olmuştur. Problemin doğasına da uygun olarak literatürdeki çalışmaların aksine sınıf sayısı 2’ye düşürüldüğünde k en yakın komşuluk (KNN) algoritması ile düşmeler %99,3 oranında doğru şekilde belirlenmiştir.

Keywords

• Düşme Tespit Sistemi
• Makine Öğrenmesi
• İvme Sensörü
• Sınıf Sayısı

Investigating the Impact of Activity Class Number in Fall Detection Systems

Abstract

In this study, the contribution of reducing the number of classes in the machine learning based classifiers to the accuracy level of the fall detection systems developed for older individuals is investigated. Within the scope of the study, a public dataset is used and the appropriate data source is determined, the features frequently used in determining the activity and posture are extracted and the analysis of the most successful classifier is made according to the machine learning metrics using all the classifiers in the MATLAB Machine Learning Framework. The number of classes is gradually decreased and its effect on success is examined. The classification carried out with the Cubic Support Vector Machine (Cubic SVM) algorithm, which is determined as the most successful classifier in the classification without reducing the number of classes at the initial stage, is 96.4%. In accordance with the nature of the problem, contrary to the studies in the literature, when the number of classes is reduced to two, the falls are correctly determined by 99.3% by using k nearest neighbor algorithm.

Keywords

• Fall Detection System
• Machine Learning
• Accelerometer
• Number of Classes

References

1. United Nations. (2019). World Population Prospects 2019. https://population.un.org/wpp/
2. Turkish Republic Ministry of Family and Social Policies. (2013). Dormitory and elderly aging national action plan implementation program in Turkey. https://www.tatd.org.tr/uploads/tbl_calisma_grubu_belgeleri/5bdc0c422b9e3_tbl_calisma_grubu_belgeleri2018113514.pdf
3. United Nations. (2019). World Population Ageing 2019. ttps://www.un.org/en/development/desa/population/publications/pdf/ageing/WorldPopulationAgeing2019-Report.pdf
4. World Health Organization. (2018). Falls. https://www.who.int/news-room/fact-sheets/detail/falls
5. Wild, D., Nayak, U.S.L., Isaacs B. (1981). How dangerous are falls in old people at home?. British Medical Journal (Clinical Research Edition), 282, 266–268.
6. World Health Organization. (2007). Global report on falls Prevention in older Age. https://www.who.int/ageing/publications/Falls_prevention7March.pdf
7. Williams, G., Doughty, K., Cameron, K., Bradley, D.A. (1998). A Smart Fall & Activity Monitor for Telecare Applications. Proceedings of the 20th Annual International Conference of the IEEE 3, 1151-1154.
8. Wu, G. (2000). Distinguishing fall activities from normal activities by velocity characteristics. Journal of Biomechanics. 33:1497–1500.

9. Prado, M., Reina-Tosina, J., Roa, L. (2002). Distributed intelligent architecture for falling detection and physical activity analysis in the elderly. Proceedings of 18th Annual International Conference of the IEEE Engineering in Medicine and Biology Society; 3, 1910–1911.
10. Noury, N. (2002). A smart sensor for the remote follow up of activity and fall detection of the elderly. Proceedings of 2nd Annual International IEEE-EMBS Special Topic Conference on Microtechnologies in Medicine and Biology.314–317.
11. Kang, J.M., Yoo, T., Kim, H. C. (2006). A wrist-worn integrated health monitoring instrument with a tele-reporting device for telemedicine and telecare. IEEE Transactions on Instrumentation and Measurement. 55:1655–1661.
12. Nyan, M. N., Tay, F. E. H., Tan, A.W.Y., Seah K. H. W. Distinguishing fall activities from normal activities by angular rate characteristics and high-speed camera characterization. Medical Engineering and Physics. 28, 842–849.
13. Lee, R. Y. W., Carlisle A. J. (2011). Detection of falls using accelerometers and mobile phone technology. Age Ageing. 40, 690–696.
14. Han, J., Shao, L., Xu, D., Shotton, J. (2013). Enhanced computer vision with Microsoft Kinect sensor: A review. IEEE Transactions on Cybernetics. 43, 1318–1334.
15. Kyriakopoulos, G., Ntanos, S., Anagnostopoulos, T., Tsotsolas, N., Salmon, I., Ntalianis, K. Internet of Things ( IoT ) -Enabled Elderly Fall Verification , Exploiting Temporal Inference Models in. Smart Homes. International Journal of Environmental Research and Public Health. 17, 1–14.
16. Sucerquia, A., López, J. D., Vargas-Bonilla, J. F. (2017). SisFall: A fall and movement dataset. Sensors (Switzerland).17, 1-14.