Wyniki wyszukiwania - BazTech

1

Knee joint osteoarthritis diagnosis based on selected acoustic signal discriminants using machine learning

Karpiński Robert

Applied Computer Science

|

2022

|

Vol. 18, no 2

71--85

EN

This paper presents the results of a preliminary study on simplified diagnosis of osteo-arthritis of the knee joint based on generated vibroacoustic processes. The analysis was based on acoustic signals recorded in a group of 50 people, half of whom were healthy, and the other half – people with previously confirmed degenerative changes. Selected discriminants of the signals were determined and statistical analysis was performed to allow selection of optimal discriminants used at a later stage as input to the classifier. The best results of classification using artificial neural networks (ANN) of RBF (Radial Basis Function) and MLP (Multilevel Perceptron) types are presented. For the problem involving the classification of cases into one of two groups HC (Healthy Control) and OA (Osteoarthritis) an accuracy of 0.9 was obtained, with a sensitivity of 0.885 and a specificity of 0.917. It is shown that vibroacoustic diagnostics has great potential in the non-invasive assessment of damage to joint structures of the knee.

2

Diagnostic factors for opened and closed kinematic chain of vibroarthrography signals

Machrowska Anna, Karpiński Robert, Krakowski Przemysław, Jonak Józef

Applied Computer Science

|

2019

|

Vol. 15, no 3

34--44

EN

The paper presents results of preliminary research of vibroarthrography signals recorded from one healthy volunteer. The tests were carried out for the open and closed kinematic chain in the range of motion 90° – 0° – 90°. Analysis included initial signal filtration using the EMD algorithm. The aim was to investigate the occurrence of differences in the values of selected energy and statistical parameters for the cases studied.

3

Application of acoustic signal processing methods in detecting differences between open and closed kinematic chain movement for the knee joint

Karpiński Robert, Machrowska Anna, Maciejewski Marcin

Applied Computer Science

|

2019

|

Vol. 15, no 1

36--48

EN

The paper presents results of preliminary research of analysis of signals recorded for open and closed kinematic chain in one volunteer with chondromalacia in both knees. The preliminary research was conducted in order to establish the accuracy of the proposed method and will be used for formulating further research areas. The aim of the paper is to show how FFT, recurrence plots and recurrence quantification analysis (RQA) can help in bioacoustic signals analysis.

4

Effects of performance level on lower limb kinematics during table tennis forehand loop

Qian J., Zhang Y., Baker J. S., Gu Y.

Acta of Bioengineering and Biomechanics

|

2016

|

Vol. 18, no. 3

149--155

EN

Understanding of biomechanics is important in performance development since each skill has a fundamental mechanical structure. The purpose of this study was to investigate differences in lower limb kinematics during table tennis forehand loop between superior players (SP) and intermediate players (IP). Thirteen male players as superior and thirteen as intermediate participated in this test. A VICON motion analysis system and a Novel Pedar insole plantar pressure measurement system were used to record kinematic and contact area data, respectively. Participants were asked to execute single forehand loop against topspin ball with maximal power. Key findings were that SP showed significantly larger hip flexion and knee external rotation at backward-end and larger hip internal rotation and extension at forward-end compared with IP. Contact areas at both events were larger for SP. In addition, SP showed significantly larger joints angular changing rate during forward swing at the ankle and hip. Results indicated that SP possessed better ability of using lower limb drive in forehand loop.