Wyniki wyszukiwania - BazTech

1

Classification of mild and severe adolescent idiopathic scoliosis (AIS) from healthy subjects via a supervised learning model based on electromyogram and ground reaction force data during gait

Sikidar Arnab, Vidyasagar Koyyana Eshwar Chandra, Gupta Manish, Garg Bhavuk, Kalyanasundaram Dinesh

Biocybernetics and Biomedical Engineering

|

2022

|

Vol. 42, no. 3

870--887

EN

At early stages, adolescent idiopathic scoliosis (AIS) is quite hard to be distinguished from healthy (HC) subjects by the naked eye. AIS demands multiple corrective surgeries when detected later, thereby causing significant physical and psychological trauma as no mathematical models exist for the classification of mild AIS (MS) (20° < Cobb’s angle < 40°) from HC, we propose a k-nearest neighbour (kNN) method based model. In this work, we collected both the EMG and GRF data from nine severe AIS (SS), three MS and four female HC during gait. Delayed muscle activation in Erector spinatus Iliocostalis, Gluteus Medius and Gastrocnemius lateralis was observed in SS compared to HC. However, no such distinction was noticed between MS and HC motivating for a mathematical model. Eighteen time-domain and nine frequency-domain features were computed from the EMG data of 14 lower extremity muscles, while five time-domain features were calculated from GRF data during gait. Out of all the features computed for each subject, the principal component analysis (PCA) yielded 15 principal components that coupled both time and frequency domains (TFD). Further, the kNN model classified SS, MS and HC from each other by these 15 TFD features. The model was trained and validated using 32 and 21 EMG and GRF data datasets during gait, respectively. The classification and validation accuracy of 90.6% and 85.7% were obtained among SS, MS and HC. The proposed model is capable of early detection of AIS and can be used by medical professionals to plan treatments and corrective measures.

2

Efficient compression of bio-signals by using Tchebichef moments and Artificial Bee Colony

Hosny K. M., Khalid A. M., Mohamed E. R.

Biocybernetics and Biomedical Engineering

|

2018

|

Vol. 38, no. 2

385--398

EN

In this paper, an algorithm is proposed for efficient compression of bio-signals based on discrete Tchebichef moments and Artificial Bee Colony (ABC). The Tchebichef moments are used to extract features of the bio-signals, then, the ABC algorithm is used to select of the optimum features which achieve the best bio-signal quality for a specific compression ratio (CR). The proposed algorithm has been tested by using different datasets of Electrocardio-gram (ECG), Electroencephalogram (EEG), and Electromyogram (EMG). The optimum feature selection using ABC significantly improve the quality of the reconstructed bio-signals. Different numerical experiments are performed to compress different records of ECG, EEG and EMG bio-signals by using the proposed algorithm and the most recent existing methods. The performance of the proposed algorithm and the other existing methods are evaluated using different metrics such as CR, PRD, and peak signal to noise ratio (PSNR). The comparison has shown that, at the same CR, the proposed compression algorithm yields the best quality of the reconstructed signals over the other existing methods.

3

Fourier analysis of motor unit action potentials

Dobrowolski A., Tomczykiewicz K., Komur P.

Electronics and Telecommunications Quarterly

|

2007

|

Vol. 53, No 2

127-141

EN

Electromyography (EMG) is a functional examination that plays a fundamental role in the diagnosis of neuromuscular disorders. The method allows for distinction between records of a healthy muscle and a changed muscle as well as for determination of whether pathological changes are of primary myopathic or neuropathic character. The statistical processing of electromyographic signal examination performed in the time domain ensures mostly correct classification of pathology; however, because of an ambiguity of most temporal parameter definitions, a diagnosis can include a significant error that strongly depends on the neurologist's experience. Then, selected temporat parameters are determined for each run, and their mean values are calculated. In the final stage, these mean values are compared with a standard and, including additional clinical information, a diagnosis is given. An inconvenience of this procedure is high time consumption that arises from, among other things, the necessity of determination of many parameters. Additionally, an ambiguity in determination of basic temporal parameters can cause doubts when parameters found by the physician are compared with standard parameters determined in other research centers. In this paper, we present a definition for single-point spectral discriminant that directly enables a unique diagnosis to be made. An essential advantage of the suggested discriminant is a precise and algorithmically realized definition that enables an objective comparison of examination results obtained by physicians with different experiences or working in different research centers. Therefore, the definition fulfills a fundamental criterion for the parameter used for preparation of a standard. A suggestion of the standard for selected muscle based on a population of 70 healthy cases is presented in the Results section.

4

Estimation method of the number of motor units by processing mass electromyogram

Yoshida M.

Biocybernetics and Biomedical Engineering

|

2000

|

Vol. 20, no. 3

65-75

EN

The new method of estimating the number and the size of active motor units by processing mass electromyogram (EMG) is devised. This method is based on a model of mass EMG generation, which is founded on the knowledge of the mode of motor units activities. This model is described as follows. (1) Mass EMG is the sum of all active motor units action potential trains. (2) An input of each motor unit is a statistically independent random pulse train. (3) Motor units are divided into groups by their threshold force for recruitment. (4) The firing rate is the function of force. By using the theory of the shot noise, the number and the size of motor units of each group are expressed as a function of the second and fourth moment of mass EMG and firing rate. This estimation starts from the lowest threshold force group. This method is applied to the human brachialis muscle and the human extensor digitorum communis muscle. The estimated results agree to the size principie and the physiological knowledge of the relation between the threshold force and the number of motor units. This agreement confirms the propriety of this estimation method.

PL

W pracy zaproponowano nową metodę oceny liczby i rozmiaru czynnych jednostek ruchowych mięśnia dzięki przetworzeniu zbiorczego sygnału elektromiograficznego (EMG). Metoda ta jest oparta na modelu generacji sygnału EMG, który został zbudowany na podstawie wiedzy o cechach czynności jednostek ruchowych. Przyjęto następujące założenia: (I) zbiorczy sygnał EMG jest sumą potencjałów czynnościowych aktywnych jednostek ruchowych, (II) sygnał wejściowy każdej jednostki ruchowej jest statystycznie niezależnym impulsowym ciągiem probabilistycznym, (III) jednostki ruchowe różnią się wartością siły, przy której są rekrutowane, (IV) częstość generowanych przez jednostki ruchowe potencjałów czynnościowych jest zależna od poziomu siły. Używając teorii procesów stochastycznych określono liczbę i rozmiar jednostek jako funkcje drugiego i czwartego momentu EMG i częstości generacji potencjałów czynnościowych. Metodę tę zastosowano do analizy czynności mięśni człowieka. Uzyskane rezultaty są zgodne z zasadą rozmiaru i wiedzą o relacjach pomiędzy siłą i liczbą rekrutowanych jednostek mięśnia. Zgodność ta potwierdza słuszność metody.