Wyniki wyszukiwania - BazTech

1

Determination of the relationship between EMG signals and hand grips using a commercial Myo armband

Błędowski Michał, Wołczowski Andrzej

Journal of Automation Mobile Robotics and Intelligent Systems

|

2019

|

Vol. 13, No. 2

40--47

EN

The work discusses the construction of a measurement system for determining the relationship between EMG signals and hand grip movements. The relationship is necessary for the synthesis of control of the hand bioprosthesis. The measurement system is based on commercial Myo armband with EMG signals sensors and sensory glove with bend and pressure sensors. There are presented possibilites, advantages and disadvantages of such approach.

2

Sterowanie bioprotezą dłoni - klasyfikacja miosygnałów za pomocą drzew decyzyjnych

Suchodolski T., Wołczowski A.

Prace Naukowe Politechniki Warszawskiej. Elektronika

|

2012

|

z. 182, t. 1

103--114

PL

Praca omawia problem sterowania decyzyjnego bioprotezą dłoni traktowany jako rozpatrywanie intencji ruchowych człowieka na drodze analizy sygnałów bioelektrycznych z kikuta protezowanej kończyny. Przedstawione podejście polega na połączeniu wybranych metod analizy danych (drzewa decyzyjne, sieci neuronowe, algorytmy genetyczne, kNN, jądrowy estymator gęstości) dla poprawy niezawodności klasyfikacji tych sygnałów.

EN

The paper discusses the problem of decision control of hand bioprosthesis. The problem is considered as human intention recognition by means if the electromyography (EMG) signals analysis. The signal characteristics and the large number of movement classis of a dexterous hand together with the high reliability of their recognition that is demanded make the decision control problem all the more difficult. The presented approach consist in combining such technics as Decision Tree, Neural Networks and Genetic Algorithms, to obtain the reliable recognition.

3

A continuous wavelet transform treatment of surface electromyographic (EMG) signals obtained from patients with low back pain before and after rehabilitation

Panagiotacopulos N., Amos M., Panayotakopoulos D.

Image Processing & Communications

|

2002

|

Vol. 8, no 2

113-120

EN

In this article we present the results of a study based on continuous wavelet transforms (CWT) of surface EMG signals. This analysis provides the distribution of the energy of the signal in the time-scale plane (scalogram). The data used in this study were signals obtained from patients with low back problems, and the analysis showed that there exist visual differences between the muscle responses before and after rehabilitation, as it can be seen in the associated scalograms.

4

Exploring the Human Handwriting Process

Bouslama F., Benrejeb M.

International Journal of Applied Mathematics and Computer Science

|

2000

|

Vol. 10, no 4

877-904

EN

The study of human handwriting movements is of great interest to researchers and biologists. It can lead to an understanding of the properties of the biological system that generates the human handwriting movements. With the identification of a dynamical system that exhibits characteristics similar to the biological one, it is possible to study handwriting movements, to identify their driving motor signals and to try to reproduce by machine the handwriting motion. In this paper, we give an analysis of modeling techniques for the handwriting process proposed in the literature. We show that either mathematical models based on the trajectories of handwritten objects or physical models obtained from the dynamic motion of the human hand can be used for modeling the handwriting process. We study the handwriting movements using these approaches and we give an analysis and synthesis of the driving motor signals. We apply the results to the generation of handwritten Arabic letters. We then propose a new synthesis technique where a more promising and realistic model can be obtained. We present the basic idea and expect that some improvement over the previous techniques can be obtained. The technique is based on Feedback Error Learning neural networks.

5

Time-frequency analysis of EMG signals

Moskalik M., Poręba T., Sokołowski M.

Automatyka / Akademia Górniczo-Hutnicza im. Stanisława Staszica w Krakowie

|

1999

|

T. 3, z. 2

403-411

EN

The results obtained by means of well known short-time Fourier transform is compared with the new approach, the wavelet transform. The influence of muscle fatiguing contractions on the myoelectric signal is examined. The results of experimental investigations are shown on figures.

PL

W artykule porównano wyniki uzyskane przy pomocy tradycyjnej krótkookresowej transformaty Fouriera z rezultatami analizy otrzymanymi dzięki transformacie falkowej. Badano wpływ zmęczenia mięśni w wyniku skurczów na elektromiogram (sygnał EMG). Otrzymane wyniki badań eksperymentalnych zamieszczono na rysunkach.