The week's pick
Reseach Article
Evaluation of Different Time and Frequency Domain Features of Motor Neuron and Musculoskeletal Diseases
| International Journal of Computer Applications |
| Foundation of Computer Science (FCS), NY, USA |
| Volume 43 - Number 23 |
| Year of Publication: 2012 |
| Authors: Shaikh Anowarul Fattah, A. B. M. Sayeed Ud Doulah, Marzuka Ahmed Jumana, Md. Asif Iqbal3 |
10.5120/6422-8922
|
Shaikh Anowarul Fattah, A. B. M. Sayeed Ud Doulah, Marzuka Ahmed Jumana, Md. Asif Iqbal3 . Evaluation of Different Time and Frequency Domain Features of Motor Neuron and Musculoskeletal Diseases. International Journal of Computer Applications. 43, 23 ( April 2012), 34-40. DOI=10.5120/6422-8922
Abstract
Motor neuron and musculoskeletal diseases are the most frequently inherited muscular disorders. Motor neuron diseases are mostly found among people within 35-70 years of age, which selectively affect the motor neurons. Amyotrophic lateral sclerosis (ALS) is the most common variant of motor neuron diseases that progressively degenerates the motor cells in the brain and spinal cord, so that the muscles no longer receive signals to move. As a result, the body becomes paralyzed, which means that the muscles no longer work. On the other hand, one of the most common musculoskeletal diseases is myopathy which causes the weakness of the muscles. Muscle cramps, tautness and spasm are also associated with myopathy. One of the possible ways to investigate the indispensable features of the ALS and myopathy diseases independently in individuals is to analyze the electromyography (EMG) signals that are basically electrical signals originated from the muscles. In this paper, a classification scheme is developed to distinguish the ALS or myopathy affected signals from the normal ones based on some time and frequency domain operations, such as autocorrelation, zero crossing rate and Fourier transform. It is found that the proposed time and frequency domain features extracted from the EMG signals exhibit distinguishable characteristics for the case of ALS and myopathic diseases. For the purpose of classification, K-nearest neighborhood classifier is employed in a leave-one out cross validation technique. In order to show the classification performance, an EMG database consisted of 6 normal subjects aged 21-37 years, 6 ALS patients aged 35-67 years, and 6 myopathic patients aged 19-63 years is considered. From the experimentation on this database, it is found that the proposed method is capable of distinctly separating the ALS and myopathic patients based on the respective EMG signals
References
- J. V. Basmajian and C. J. De Luca, Muscles Alive. Their Function Revealed by Electromyography. Baltimore: Williams & Wilkens, 1985.
- S. M. Rissanen, M. Kankaanpää, M. P. Tarvainen, J. Nuutinen, I. M. Tarkka, A. Meigal, O. Airaksinen, and P. A. Karjalainen, "Extraction of typical features from surface EMG signals in Paarkinson's disease," 11th International Congress of Parkinsons's Disease and Movement Disorders, Istanbul, Turkey, 2007.
- M. B. I. Reaz, and M. S. Hussain, and F. M. Yasin "Techniques of EMG signal analysis: detection, processing, classification and applications," Biological Procedures Online, vol. 8, no. 1, pp. 11-35, 2006.
- B. Neogi, S. Ghosal, A. Ghosh, R. Darbar, S. Ganguly, and B. Brahma, "Approach towards the characteristic interpretation of Electromyography (EMG) signal with clinical study," Recent Advances in Intelligent Computational Systems (RAICS), pp. 788-791, 2011.
- R. F. M. Kleissen, J. H. Buurke, J. Harlaar, and G. Zilvold, "Electromyography in the biomechanical analysis of human movement and its clinical application," Gait Posture, vol. 8, no. 2, pp. 143-158, 1998.
- National Institute of Neurological Disorders and Stroke (NINDS). "ALS (Amyotrophic Lateral Sclerosis) Fact Sheet," NIH Publication No. 10-916, 2010. Available: http://www. ninds. nih. gov/disorders/amyotrophiclateralsclerosis/detail_ALS. htm.
- P. K. Kasi, "Characterization of motor unit discharge rate in patients with Amytrophic Lateral Sclerosis (ALS)," Worcester Polytechnic Institute, May 2009.
- National Institute of Neurological Disorders and Stroke (NINDS). "NINDS Myopathy information page," NIH Publication, 2011. Available: http://www. ninds. nih. gov/ disorders/myopathy/myopathy. htm.
- H. D. Katzberg, D. F. Barros, B. Widrow, C. S. Cho, and Y. T. So, "Analysis of continuous diaphragm electromyographic signal: Results from a patient with amyotrophic lateral sclerosis," Muscle & Nerve. , vol. 43, no. 6, pp. 801–806, 2011.
- E. H. Lambert, "Electromyography in amyotrophic lateral sclerosis," pp. 135-153. In: F. H. Norris, L. T. Kurland (Eds. ) "Motor neuron diseases: research in amyotrophic lateral sclerosis and related disorders," New York, Grune and Stratton, 1969.
- L. Cohen, "Time-frequency analysis," Englewood Cliffs, Prentice-Hall; New Jersey, USA, 1995.
- A. Phinyomark, P. Phukpattaranont, and C. Limsakul, "Feature reduction and selection for EMG signal classification," Expert Systems with Applications, vol. 39, no. 8, pp. 7420-7431.
- A. F. Kohn, "Autocorrelation and Cross-correlation Methods," Wiley Encyclopedia of Biomedical Engineering, Ed. Metin Akay, New Jersey: John Wiley & Sons, 23 pp, 2006.
- M. Nikolic, "Detailed Analysis of Clinical Electromyography Signals EMG Decomposition, Findings and Firing Pattern Analysis in Controls and Patients with Myopathy and Amytrophic Lateral Sclerosis", PhD Thesis, Faculty of Health Science, University of Copenhagen, 2001.
Index Terms
Keywords