Cover -- Title Page -- Copyright Page -- Dedication -- Contents -- Acknowledgments -- Chapter One - Introduction -- 1.1 - Alzheimer disease -- 1.2 - Causes and symptoms of the disease -- 1.3 - Stages and clinical diagnosis of Alzheimer's disease -- 1.4 - Importance of diagnosis of Alzheimer's disease and its impact on society -- 1.5 - A brief review on different methods used for diagnosis of Alzheimer disease -- 1.5.1 - Role of neuroimaging based techniques in diagnosis of Alzheimer disease -- 1.5.2 - Role of electroencephalogram techniques in diagnosis of Alzheimer disease -- Summary -- References -- Chapter Two - Electroencephalogram and Its Use in Clinical Neuroscience -- 2.1 - EEG recording and measurement -- 2.2 - EEG rhythms -- 2.3 - Early diagnosis of Alzheimer's disease by means of EEG signals -- 2.3.1 - Slowing of EEG signals in AD patients -- 2.3.2 - Perturbations in EEG synchrony -- 2.3.3 - Reduced complexity in EEG signals -- Summary -- References -- Chapter Three - Role of Different Features in Diagnosis of Alzheimer Disease -- 3.1 - Introduction -- 3.1.1 - Phase 1: Preprocessing -- 3.1.2 - Phases 2 and 3: Segmentation and feature extraction -- 3.1.3 - Phase 4: Classification -- 3.2 - What is feature extraction? -- 3.3 - Need of feature extraction -- 3.4 - Linear features -- 3.4.1 - Spectral features -- 3.4.2 - Wavelet-based features -- 3.4.3 - Complexity based features/nonlinear features -- 3.5 - Conclusions -- References -- Chapter Four - Use of Complexity Features for Diagnosis of Alzheimer Disease -- 4.1 - Introduction -- 4.1.1 - Sample entropy -- 4.1.2 - Approximate entropy -- 4.1.3 - Multiscale multivariate sample entropy -- 4.1.4 - Permutation entropy -- 4.1.5 - Multiscale multivariate permutation entropy (MSMPE) -- 4.1.6 - Auto-mutual information -- 4.1.7 - Tsallis entropy -- 4.1.8 - Lempel-Ziv complexity
4.2 - Use of new complexity features in Alzheimer's disease diagnosis -- 4.2.1 - Spectral entropy -- 4.2.2 - Spectral centroid -- 4.2.3 - Spectral roll off -- 4.2.4 - Zero crossing rate -- 4.3 - Discussion and conclusion -- Summary -- References -- Further Reading -- Chapter Five - Classification Algorithms in Diagnosis of Alzheimer's Disease -- 5.1 - Introduction -- 5.1.1 - Support Vector Machine -- 5.1.1.1 - Linear separation -- 5.1.1.2 - Nonseparable classes -- 5.1.1.3 - Nonlinear transformation with kernels -- 5.1.1.4 - Advantages of Support Vector Machine in classification of EEG signal -- 5.1.2 - K-Nearest Neighbor classifier (K-NN classifier) -- 5.1.2.1 - Estimating K-Nearest Neighbor value -- Summary -- References -- Chapter Six - Results, Discussions, and Research Challenges -- 6.1 - Results -- 6.1.1 - Spectral-based features -- 6.1.2 - Wavelet-based features -- 6.1.3 - Complexity-based features -- 6.1.3.1 - Support Vector Machine (SVM) -- 6.1.3.1.1 - Zero Crossing Rate (ZCR) -- 6.1.3.1.2 - Spectral roll off (SR) -- 6.1.3.1.3 - Spectral entropy (SE) -- 6.1.3.1.4 - Spectral centroid (SC) -- 6.1.3.2 - K-Nearest neighbor classifier (K-NN) -- 6.1.3.2.1 - Zero crossing rate (ZCR) -- 6.1.3.2.2 - Spectral Roll-off (SR) -- 6.1.3.2.3 - Spectral entropy (SE) -- 6.1.3.2.4 - Spectral centroid (SC) -- 6.1.4 - Classification -- 6.1.5 - Calculation of diagnostic accuracy obtained in the research work -- 6.2 - Conclusions -- 6.3 - Contribution -- 6.4 - Limitations of the study -- 6.5 - Future scope -- References -- Index -- Back cover