Xingxing Zhou

Detection of Pathological Brain in MRI Scanning Based on Wavelet-Entropy and Naive Bayes Classifier

An accurate diagnosis is important for the medical treatment of patients suffered from brain disease. Nuclear magnetic resonance images are commonly used by technicians to assist the pre-clinical diagnosis, rating them by visual evaluations. The classification of NMR images of normal and pathological brains poses a challenge from technological point of view, since NMR imaging generates a large information set that reflects the conditions of the brain. In this work, we present a computer assisted diagnosis method based on a wavelet-entropy (In this paper 2D-discrete wavelet transform has been used, in that it can extract more information) of the feature space approach and a Naive Bayes classifier classification method for improving the brain diagnosis accuracy by means of NMR images. The most relevant image feature is selected as the wavelet entropy, which is used to train a Naive Bayes classifier. The results over 64 images show that the sensitivity of the classifier is as high as 94.50%, the specificity 91.70%, the overall accuracy 92.60%. It is easily observed from the data that the proposed classifier can detect abnormal brains from normal controls within excellent performance, which is competitive with latest existing methods.

Comparison of machine learning methods for stationary wavelet entropy-based multiple sclerosis detection

In order to detect multiple sclerosis (MS) subjects from healthy controls (HCs) in magnetic resonance imaging, we developed a new system based on machine learning. The MS imaging data was downloaded from the eHealth laboratory at the University of Cyprus, and the HC imaging data was scanned in our local hospital with volunteers enrolled from community advertisement. Inter-scan normalization was employed to remove the gray-level difference. We adjust the misclassification costs to alleviate the effect of unbalanced class distribution to the classification performance. We utilized two-level stationary wavelet entropy (SWE) to extract features from brain images. Then, we compared three machine learning based classifiers: the decision tree, k-nearest neighbors (kNN), and support vector machine. The experimental results showed the kNN performed the best among all three classifiers. In addition, the proposed SWE+kNN approach is superior to four state-of-the-art approaches. Our proposed MS detection approach is effective.

Combination of stationary wavelet transform and kernel support vector machines for pathological brain detection

Finding an appropriate and accurate technology for early detection of disease is significantly important to research early treatments. We proposed some novel automatic classification systems based on the stationary wavelet transform (SWT) and the improved support vector machine (SVM). Magnetic Resonance Imaging (MRI) is commonly used for brain imaging as a non-invasive diagnostic tool to assist the pre-clinical diagnosis. However, MRI generates a large information set, which poses a challenge for classification. To deal with this problem we proposed a new approach, which combines SWT and Principal Component Analysis for feature extraction. In our experiments, three different datasets and four kinds of classifiers of the SVM were employed. The results over 5×6-fold stratified cross-validation (SCV) for Dataset-66, and 5×5-fold SCV for the other two datasets show that the average accuracy is almost 100.00%.

Cluster Analysis by Variance Ratio Criterion and Quantum-Behaved PSO

(Aim) A novel and efficient method based on the quantum-behaved particle swarm was proposed to solve the cluster analysis problem. (Methods) The QPSO was utilized to detect the optimal point of the VAriance RAtio Criterion (VARAC), which was created by us as fitness function in the optimization model. The experimental dataset had 4 groups (400 data in total) with three various degrees of overlapping: non-overlapping, partial overlapping, and intensely overlapping. The proposed QPSO was compared with traditional global optimization algorithms: genetic algorithm (GA), combinatorial particle swarm optimization (CPSO), and firefly algorithm (FA) via running 20 times. (Results) The results demonstrated that QPSO could locate the best VARAC values with the least time among the four algorithms. (Conclusions) We can find that QPSO performs effectively and fast for the problem of cluster analysis.

Tea Category Classification Based on Feed-Forward Neural Network and Two-Dimensional Wavelet Entropy

(Aim) Tea plays a significant role because of its high value throughout the world. Computer vision techniques were successfully employed for rapid identification of teas. (Method) In our work, we present a computer assisted discrimination system on the basis of two steps: (i) two-dimensional wavelet-entropy for feature extraction; (ii) the feedforward Neural Network (FNN) for classification. Specifically, the wavelet entropy features were fed into a FNN classifier. (Results) The 10 runs of 75 images of three categories showed that the average accuracy achieved 90.70 %. The sensitivities of green, Oolong, and black tea are 92.80 %, 84.60 %, and 96.30 %, respectively. (Conclusions) It was easily observed that the proposed classifier can distinguish tea categories with satisfying performances, which was competitive with recent existing systems.

A TS-PSO Based Artificial Neural Network for Short-Term Load Forecast

(Aim) A short-term load forecast is an arduous problem due to the nonlinear characteristics of the load series. (Method) The artificial neural network (ANN) was employed. To train the ANN, a novel hybridization of Tabu Search and Particle Swarm Optimization (TS-PSO) methods was introduced. TS-PSO is a novel and powerful global optimization method, which combined the merits of both TS and PSO, and removed the disadvantages of both. (Results) Experiments demonstrated that the proposed TS-PSO-ANN is superior to GA-ANN, PSO-ANN, and BFO-ANN with respect to a mean squared error (MSE). (Conclusion) The TS-PSO-ANN is effective in a short-term load forecast.