2. Related Work
For automatic detection of normal and Coronary Artery Disease
conditions, Giri et al. [14], have used heart signals rather than
cardiac signals to design a methodology. The heart signals, are
associated with several frequency sub bands using Discrete Wavelet
Transform (DWT). Hence, to retrieve the heart signal from DWT and also
to reduce the dimensions of data, three statistical methods are applied
to the set of DWT coefficients. Further, the normalized information is
passed through a set of four classifiers such as Support Vector Machine
(SVM), Probabilistic Neural Network (PNN), Gaussian Mixture Model (GMM),
and K-Nearest Neighbor (KNN) for decision making. The results indicate
that the GMM model coupled with ICA provides higher accuracy rate.
Further, to improve the classification performance of the Coronary
Artery Disease, Babaoglu et al., [15] have developed a BPSO, GA and
SVM based classification model based on stress testing data. In the
proposed model, BPSO and GA techniques are applied for obtaining the
relevant set of features to predict Coronary Artery Disease. Whereas,
SVM is adopted as a classifier system to classify patients with CAD. For
enhancing the diagnostic rate, 10 cross fold techniques are incorporated
in SVM classifier. Results indicate that the proposed classification
model achieves higher accuracy rate and having less complexity. To
investigate the characteristics of diabetic patients and also to predict
type-2 diabetic effectively, Patil et al., [16] have developed a
hybrid prediction model for diabetic disease. In the proposed prediction
model k-means clustering algorithm is applied to validate the class
labels of diabetic dataset and the classical C4.5 method is selected to
build the final classifier using k-cross fold validation method. From
results, it is stated that the proposed system attains higher
sensitivity and specificity rate than the other methods being compared.
An intelligent hepatitis diagnostic system for caring and treatment of
hepatitis patients is reported in [17]. Another application of SVM
technique is also reported for effective diagnosis of cancer affected
patients [18]. Ucar et al. [19], have proposed a new hybrid
machine learning method for identification of tuberculosis disease. The
proposed machine learning method is the combination of adaptive neuro
fuzzy inference system and Rough sets. The results indicate that the
proposed method provides more vibal results in comparison to other
algorithms being compared. To predict the heart valve disorder, Uguz has
developed an adaptive neuro fuzzy based system [20]. In the proposed
system, three layers are presented for feature extraction, feature
selection and classification. Feature extraction is done by DWT,
whereas, the Shannon entropy algorithm is adopted for feature selection.
Finally, all selected features are classified using ANFIS classifier.
The proposed system obtains 98.3 % classification accuracy. For the
effective diagnosis of coronary artery disease (CAD), Muthukaruppan et
al.[21], have presented particle swarm optimization (PSO)-based
fuzzy expert system. In the proposed system, the initial decision tree
is implemented to find the best features for better prediction of
coronary artery disease. Further, these features are converted into
fuzzy if then rules and make a database of fuzzy rules. Prior to convert
the crisp set into fuzzy set, a fuzzy membership function is applied in
fuzzy set theory and this function has significant impact on the fuzzy
output. Further, in this work, authors are adopted PSO algorithm to tune
the value of the fuzzy membership function. From results, it is noted
that the proposed fuzzy system is more capable of diagnosis of coronary
artery disease in comparison to other methods being compared. Seera and
Lim have described a fuzzy min-max neural network for medical data
classification task [22]. The proposed system comprises of Fuzzy
Min–Max neural network, Regression Tree, and the Random Forest
algorithms. The efficacy of the proposed system is tested for Breast
Cancer, Diabetes and Liver Disorders diseases and provides significant
results. To achieve better accuracy and diagnostic rate of breast cancer
affected patients, Ubeyli et al. [23], have proposed an adaptive
neuro-fuzzy based inference system (ANFIS) for breast cancer detection.
In this work, the first order Sugeno model is applied with two fuzzy
if-then rules and further, this model integrates with neural network
architecture for effective detection of breast cancer disease. It is
found that the ANFIS achieves 99.08% accuracy rate.Kumar et al., have
developed a rule based classification model to predict the different
types of liver diseases and claimed that decision tree based
classification model gives higher accuracy [24]. In continuation of
their work, five machine learning approaches are applied to evaluate
seminal quality and it is observed that PSO-SVM approach provides better
results than MLP, DT, NB and SVM approaches [25]. Yadav et al.
[26], have applied three popular machine learning approaches such as
tree, statistical and SVM classifiers to find Parkinson’s disease
affected patients. It is seen that the performance of logistic
regression classifier is better than other classifiers.