International Journal of Information Technology and Computer Science (IJITCS)
IJITCS Vol. 5, No. 11, 8 Oct. 2013
Cover page and Table of Contents: PDF (size: 569KB)
WEBspike: A New Proposition of Deterministic Finite Automata and Parallel Algorithm Based Web Application for EEG Spike Recognition
Full Text (PDF, 569KB), PP.93-102
Views: 0 Downloads: 0
Author(s)
Anup Kumar Keshri
1,*
Shamba Chatterjee
1
Barda Nand Das
2
Rakesh Kumar Sinha
3
Index Terms
Deterministic Finite Automata, Electroencephalogram, Epileptic Spike, Message Passing Interface, Parallel Computing, Scalability, World Wide Web
Abstract
The brain signal or Electroencephalogram (EEG) has been proved as one of the most important bio-signal that deals with a number of problems and disorders related to the human being. Epilepsy is one of the most commonly known disorders found in humans. The application of EEG in epilepsy related research and treatment is now a very common practice. Variety of smart tools and algorithms exist to assist the experts in taking decision related to the treatment to be provided to an epileptic patient. However, web based applications or tools are still needed that can assist those doctors and experts, who are not having such existing smart tools for EEG analysis with them. In the current work, a web based system named WEBspike has been proposed that breaks the geographical boundary in assisting doctors in taking proper and fast decision regarding the treatment of epileptic patient. The proposed system receives the EEG data from various users through internet and processes it for Epileptic Spike (ES) patterns present in it. It sends back a report to the user regarding the appearance of ES pattern present in the submitted EEG data. The average spike recognition rate obtained by the system with the test files, was 99.09% on an average.
Cite This Paper
Anup Kumar Keshri, Shamba Chatterjee, Barda Nand Das, Rakesh Kumar Sinha, "WEBspike: A New Proposition of Deterministic Finite Automata and Parallel Algorithm Based Web Application for EEG Spike Recognition", International Journal of Information Technology and Computer Science(IJITCS), vol.5, no.11, pp.93-102, 2013. DOI:10.5815/ijitcs.2013.11.10
Reference
[1]Sinha RK. Electroencephalogram disturbances in different sleep-wake states following exposure to high environmental heat. Med. Biol. Eng. Computing (IEE) 2004;42:282 – 87.
[2]Adeli H, Zhou Z, Dadmehr N. Analysis of EEG records in an epileptic patient using wavelet transform. J. Neurosci. Methods. 2003;123: 69 – 87.
[3]Khan YU, Gotman J. Wavelet based automatic seizure detection in intracerebral electroencephalogram. Clin. Neurophysiol. 2003;114: 898 – 908.
[4]Zarjam P, Mesbah M, Boashash B. Detection of newborns EEG seizure using optimal features based on discrete wavelet transform. Proceeding of the IEEE International Conference on Acoustics Speech and Signal Processing. 2003;2: 265 – 268.
[5]Subasi A. Epileptic seizure detection using dynamic wavelet network. Expert Syst. Appl. 2005;29: 343 – 55.
[6]Subasi A. EEG signal classification using wavelet feature extraction and a mixture of expert model. Expert Syst. Appl. 2007;32: 1084 – 93.
[7]Indiradevi KP, Elias E, Sathidevi PS, Nayak SD Radhakrishnan KA. multi-level wavelet approach for automatic detection of epileptic spikes in the electroencephalogram. Computers in Biology and Medicine. 2008;38: 805 – 16.
[8]Ocak H. Automatic detection of epileptic seizures in EEG using discrete wavelet transform and approximate entropy. Expert Systems with Applications. 2009; 36:2027–36.
[9]Kiymik MK, Akin M, Subasi A. Automatic recognition of alertness level by using wavelets transform and artificial neural network. J. Neurosci. Methods. 2004;139: 231 – 40.
[10]Sinha RK, Ray AK, Agrawal NK. An artificial neural network to detect EEG seizures. Neurology India. 2004;52: 399-400.
[11]Subasi A. Automatic detection of epileptic seizure using dynamic fuzzy neural networks. Expert Syst. Appl. 2006;31: 320 – 28.
[12]Inan ZH, Kuntalp M. A study on fuzzy C-means clustering-based systems in automatic spike detection. Computers in Biology and Medicine 37: 2007;1160 – 66.
[13]Keshri AK, Sinha RK, Hatwal R, Das BN. Epileptic Spike Recognition in Electroencephalogram using Deterministic Finite Automata. Journal of Medical Systems 2009;33: 173 – 79.
[14]Keshri AK, Sinha RK, Singh A, Das BN. DFASpike: A new computational proposition for efficient recognition of Epileptic spike in EEG. Comput Biol Med. 2011;41 : 559 – 64.
[15]Keshri AK, Sinha RK, Mallick DK, Das BN., Parallel Algorithm to Analyze the Brain Signals : Application on Epileptic Spikes. J. Med. Syst. 2011;35:93 – 104.
[16]Fritschy J, Horesh L, Holder D, Bayford R. Applications of GRID in clinical neurophysiology and Electrical Impedance Tomography of brain function. Stud Health Technol Inform. 2005;112:138-45.
[17]Butler R, Lusk E. Monitors, messages, and clusters: the p4 parallel programming system. Journal of Parallel Computing. 1994;20(4): 547 – 64.
[18]Bala V, Kipnis S, Rudolph L, Snir M. Designing efficient, scalable, and portable communication libraries. SIAM 1993 Conference on Parallel Processing for Scientific Computing. 1993;862 – 72.
[19]Ktonas PY, Smith JR. Quantification of abnormal EEG characteristics. Comput Biol Med. 1974;4: 157 – 63.
[20]Adeli H, Dastidar SG, Dadmehr N. A Wavelet-Chaos Methodology for Analysis of EEGs and EEG Subbands to Detect Seizure and Epilepsy. IEEE Trans. on BME. 2007;54: 205- 11.