=Paper=
{{Paper
|id=Vol-1755/234-236
|storemode=property
|title=Classification of Human Brain Signal for Diagnosis of Stroke Disease Using Artificial Neural Network
|pdfUrl=https://ceur-ws.org/Vol-1755/234-236.pdf
|volume=Vol-1755
|authors=Joseph Igwe,Hight Inyiama
|dblpUrl=https://dblp.org/rec/conf/cori/IgweI16
}}
==Classification of Human Brain Signal for Diagnosis of Stroke Disease Using Artificial Neural Network==
https://ceur-ws.org/Vol-1755/234-236.pdf
Classification of Human Brain Signal for Diagnosis of
Stroke Disease Using Artificial Neural Network
Joseph Sunday Igwe H. C. Inyiama
Brain Hub Research Team Nnamdi Azikiwe University,
Computer Science Department Awka, Nigeria
Ebonyi State University, Nigeria drhcinyiama@gmail.com
igwejoesun@yahoo.com
1. ABSTRACT neuroscience will find this research to be a fertile land
for further researches.
The ravaging effect of stroke diseases in Nigeria is growing at an iv. Nigeria as a country will find the use of EEG and the
alarming rate. The masses are paying less attention to diagnosis ability of ANN to classify its reports for correct
and treatment. Neurologists lack efficient state of the art tools that diagnosis of stroke as an eye opener.
will aid diagnosis of stroke. Electroencephalograph (EEG) signal
records could improve the understanding of the mechanisms of
stroke. Artificial neural network (ANN) model was used in 4. BACKGROUND AND RELATED
classifying Electroencephalograph (EEG) signal report generated WORKS
by the brain for the diagnosis of stroke. The result obtained The manner stroke patients are being handled by medical
agrees with expert’s view of the patient’s condition. practitioners most times is disturbing. Due to lack of state of the
art tools, they most often recommend expensive scans such as
CCS concepts CAT, MRI, and PET that are costly to the sufferers. Majority of
• Computing methodologies ➝ Machine learning ➝ Machine the patients cannot afford the cost of those scans. EEG signal
learning approaches ➝ Neural network records can help to improve the understanding of the stroke
mechanisms. Functional behavior of the brain based on the EEG
Keywords signal is an important component in the diagnosis of stroke. EEG
Artificial Neural Network; Brain - Computer Interface; Brain is electrical representation and measurement of the electrical
Signals; Diagnosis; Electroencephalogram; Signal Classification. activity of the brain [1]. The detectors are worn on the scalp to
observe signals; these signals portray the brain movement. The
aim of this paper is to use an Artificial Neural Network (ANN)
2. PROBLEM STATEMENT model in classifying Electroencephalograph (EEG) signal report
This research is motivated by the following problems. generated by the brain for the diagnosis of stroke. Objectives are
i. Increasing cases of stroke patients in Nigeria. to: (i) Survey the awareness and usage of EEG signals for
ii. Inadequate Equipment for effective diagnosis of stroke. diagnosis of stroke. (ii)Capture EEG signals (iii) Create ANN for
iii. Lack of good user interface platform for sole purpose of classifying the brain signals. (iv) Design software for
reporting outcome of EEG signal. interpretation of EEG outcome.
iv. Inadequacy of qualified neurologists to handle the Researchers predict stroke disease by comparing the performance
increasing number of stroke patients. of predictive data mining. Data was collected from patients’
v. Inability of most patients to speak to experts so as to dataset in hospital about stroke diseases symptoms. Three
ascertain the level of consciousness. classification algorithms Decision Tree, Naive Bayes and ANN
were used. Observation shows that ANN performance is having
3. RELEVANCE OF STUDY more accuracy than decision tree and naïve Bayes’ models [2].
The benefits of this work are: A work on ANN in diagnosing thyroid disease was carried out.
i. The analysis of the result gotten from mining the EEG The purpose is to identify computer technology with high
data will lead to sensitization of programmes for causes, accuracy for diagnosing thyroid disease. Multi-layer Perceptron
prevention and cure of stroke. (MLP) ANN algorithm was used for classification. Result
ii. It will aid decision making and is going to lessen indicated accuracy level of 98.6% performance optimization [3].
pressure on the medical experts. Research was also carried on classifying EEG signals for
iii. Postgraduate students in computer science and detecting Parkinson disease. Focus was on how to classify EEG
signals in normal and abnormal person. Dataset of 10 subjects
were used. Two classifiers, Support Vector Machine (SVM) and
MLP were used. The result was promising [4].
CoRI’16, Sept 7–9, 2016, Ibadan, Nigeria.
5. RESEARCH METHODOLOGY
Multilayer Perceptron (MLP) classifier algorithm was used. One
stroke patient and one control subject participated. EEG machine
captured signals at scalp sites Left Front Parietal (FP1), Right
Front Parietal (FP2), Left Front Lobe (F3), Right Front Lobe (F4),
234
Left Center Lobe (C3), Right Center Lobe (C4), Left Parietal waves can be delta, theta, alpha, beta and gamma [6]. Depending
Lobe (P3), Right Parietal Lobe (P4), Left Occipital Lobe (O1), on the dominant wave observed, the signals may be adjudge to
Right Occipital Lobe (O2), Left Frontal Lobe (F7), Right Frontal normal or abnormal. Alpha, Beta and Gamma waves in awaked
Lobe (F8), Left Temporal Lobe (T3), Right Temporal Lobe (T4), adult indicates normalcy. Observance of Delta and Theta under
Mid Left Temporal Lobe (T5), Mid Right Temporal (T6), Center the same condition implies abnormal case.
(C) and SPO2 based on international 10/20 system. See figure 2 for the algorithm deployed in the diagnosis of stroke
Procedure are (i) Set up the equipment: electrodes jack box disease anchored on EEG signals captured. The algorithm creates,
amplifier BCI machine computer system (ii)Radiographer train and generate MLP network structure [7].
mark scalp area to place electrodes (iii)Rub scalp area with
Methylated Spirit (iv) Electrodes fix or wear EEG cap (v) Subject
is laid on a bed/sat in comfortable chair [5].
Figure 16 below illustrates the major component stages of the
proposed system in detail.
Figure 2: Algorithm for Diagnosis of Stroke Diseases (case:
MLP)
6. RESULT
The outcomes of this research are itemized below:
(i)The survey conducted suggested need for creating more
awareness on the ravaging effect of stroke diseases and on the use
Figure 1. Human Brain Signal Classification for Diagnosis of of EEG in aiding diagnosis of stroke.
Stroke Diseases (ii)EEG signals were successfully captured from both stroke
patient and control subject.
The EEG signals captured from the stroke patient’s brain are first (iii) ANN was created and trained using MATLAB 2013a
passed through Analog to Digital Converter. The digitized signals (iv) Captured Signals were classified into distinct bands of delta,
are filtered to remove artefacts. Feature extraction is used to theta, alpha, beta and gamma. (v)EEG recordings were interpreted
obtain the needed signals for further analysis/classification. EEG using VB.NET IDE (see figure 3).
235
(ii) The software developed will support and further describes the
outcome of EEG experiment to those with little knowledge of
radiography.
(iii) This is the first time someone will be using ANN with EEG
signal as a data to aid diagnosis of stroke ailment to best of our
knowledge.
9. REFLECTIONS
There is a need to capture EEG signals from more patients to
collaborate our results. Also, an innovative EEG based technology
Figure 3: Interpretation of EEG Recording using VB.NET (hardware) should be developed with sole aim of diagnosing
IDE stroke diseases. This will help to raise the acceptance rate of the
EEG technology among the medical practitioners.
Also figure 4 demonstrates the classification of EEG result in 10. REFERENCES
MATLAB environment. [1] Al-Kadi, M., Reaz, M. B. & Ali, M. A. Evolution of
Electroencephalogram Signal Analysis Techniques during
Anesthesia. Retrieved March 11, 2014, from PubMed Central:
http://www.ncbi.nlm.nih.gov/.../PMC3690072, 2013.
[2] Sudha, A., Gayathri, P., and Jaisankar, N., Effective
Analysis and Predictive Model of Stroke Disease using
Classification Methods, International Journal of Computer
Applications, 2012.
[3] Gharehchopogh, F. S., Molany, M., and Mokri, F. D.
Using Artificial Neural Network in Diagnosis of Thyroid Disease
International Journal on Computational Sciences & Applications
(IJCSA), 49-61, 2013.
[4] Bhosale, P. G., and Patil, S. Classification of EEG
Signals Using Wavelet Transform and Hybrid Classifier for
Figure 4: Classification of EEG Signals into Five Distinct Parkinson’s Disease Detection International Journal of
Frequency Waves Engineering Research & Technology, 2013.
[5] American Clinical Neurophysiology Society. (2006).
7. EVALUATION PLAN Guideline 8: Guidelines for Recording Clinical EEG on Digital
Brain Hub Research Team was established in Ebonyi State Media. Retrieved March 4, 2015, from
University to nurture and evaluate the success of this project in http:/www.acns.org/pdf/.../Guideline-8.pdf
the future. It is team made up of the principal researcher [6] MACALESTER COLLEGE, What is Electro Enchephalo
(computer scientist), System analyst, Neurologist, Computer Graphy? Retrieved March 07, 2015, from Mac Incorporates
Engineer, and Radiographer. A publication in international www.macalester.edu/academics/psychology/UBNRP/Imaging/eeg
reputable journals at a rate of two per year is our expected goal. .html, 2014.
[7] Ali, B., Mehradad, F., and Rabab, W. (2007). A Survey of
Signal Processing Algorithms in Brain-Computer Interfaces Based
8. EXPECTED CONTRIBUTION TO on Electrical Brain Signals. Journal of Neural Engineering , 32-
KNOWLEDGE 57.
(i) Survey will aid stroke diagnosis and help to raise the
awareness level of the ravaging effect of stroke in Nigeria.
236