Predicting the level of knee osteoarthritis by using dimension reduction techniques on time series features of gait data

---

Tezin Türü: Yüksek Lisans

Tezin Yürütüldüğü Kurum: Orta Doğu Teknik Üniversitesi, Enformatik Enstitüsü, Sağlık Bilişimi Anabilim Dalı, Türkiye

Tezin Onay Tarihi: 2013

Öğrenci: SALİH CANER

Danışman: ÜNAL ERKAN MUMCUOĞLU

Özet:

Gait analysis is the systematic study of human walking. Gait analysis is also used on facilitating medical diagnosis decisions such as on a disease called knee osteoarthritis (OA) which is a disorder that affects joint cartilage. Gait data used in this study was collected from Ankara University Department of Physical Medicine and Rehabilitation Gait Laboratory for the study called “A Decision Support System for Grading Knee Osteoarthritis Using Gait Data” implemented by Şen. Some of the main obstacles of analyzing gait data which was captured by special video cameras are multidimensionality and correlation of data. Due to the complexity and high dimensionality of gait patterns, clinicians have limited understanding and difficulty interpreting raw data. The objective of this study is to implement some dimension reduction techniques on the waveforms of gait data to improve accuracy of classification methods in grading OA.