Cover -- Title Page -- Copyright -- Contents -- List of Figures -- List of Tables -- Preface -- Acknowledgments -- Chapter 1 Survey -- 1.1 Introduction of Kernel Analysis -- 1.2 Kernel Offline Learning -- 1.2.1 Choose the Appropriate Kernels -- 1.2.2 Adopt KA into the Traditionally Developed Machine Learning Techniques -- 1.2.3 Structured Database with Kernel -- 1.3 Distributed Database with Kernel -- 1.3.1 Multiple Database Representation -- 1.3.2 Kernel Selections Among Heterogeneous Multiple Databases -- 1.3.3 Multiple Database Representation KA Applications to Distributed Databases -- 1.4 Kernel Online Learning -- 1.4.1 Kernel-Based Online Learning Algorithms -- 1.4.2 Adopt "Online" KA Framework into the Traditionally Developed Machine Learning Techniques -- 1.4.3 Relationship Between Online Learning and Prediction Techniques -- 1.5 Prediction with Kernels -- 1.5.1 Linear Prediction -- 1.5.2 Kalman Filter -- 1.5.3 Finite-State Model -- 1.5.4 Autoregressive Moving Average Model -- 1.5.5 Comparison of Four Models -- 1.6 Future Direction and Conclusion -- References -- Chapter 2 Offline Kernel Analysis -- 2.1 Introduction -- 2.2 Kernel Feature Analysis -- 2.2.1 Kernel Basics -- 2.2.2 Kernel Principal Component Analysis (KPCA) -- 2.2.3 Accelerated Kernel Feature Analysis (AKFA) -- 2.2.4 Comparison of the Relevant Kernel Methods -- 2.3 Principal Composite Kernel Feature Analysis (PC-KFA) -- 2.3.1 Kernel Selections -- 2.3.2 Kernel Combinatory Optimization -- 2.4 Experimental Analysis -- 2.4.1 Cancer Image Datasets -- 2.4.2 Kernel Selection -- 2.4.3 Kernel Combination and Reconstruction -- 2.4.4 Kernel Combination and Classification -- 2.4.5 Comparisons of Other Composite Kernel Learning Studies -- 2.4.6 Computation Time -- 2.5 Conclusion -- References -- Chapter 3 Group Kernel Feature Analysis -- 3.1 Introduction.

3.2 Kernel Principal Component Analysis (KPCA) -- 3.3 Kernel Feature Analysis (KFA) for Distributed Databases -- 3.3.1 Extract Data-Dependent Kernels Using KFA -- 3.3.2 Decomposition of Database Through Data Association via Recursively Updating Kernel Matrices -- 3.4 Group Kernel Feature Analysis (GKFA) -- 3.4.1 Composite Kernel: Kernel Combinatory Optimization -- 3.4.2 Multiple Databases Using Composite Kernel -- 3.5 Experimental Results -- 3.5.1 Cancer Databases -- 3.5.2 Optimal Selection of Data-Dependent Kernels -- 3.5.3 Kernel Combinatory Optimization -- 3.5.4 Composite Kernel for Multiple Databases -- 3.5.5 K-NN Classification Evaluation with ROC -- 3.5.6 Comparison of Results with Other Studies on Colonography -- 3.5.7 Computational Speed and Scalability Evaluation of GKFA -- 3.6 Conclusions -- References -- Chapter 4 Online Kernel Analysis -- 4.1 Introduction -- 4.2 Kernel Basics: A Brief Review -- 4.2.1 Kernel Principal Component Analysis -- 4.2.2 Kernel Selection -- 4.3 Kernel Adaptation Analysis of PC-KFA -- 4.4 Heterogeneous vs. Homogeneous Data for Online PC-KFA -- 4.4.1 Updating the Gram Matrix of the Online Data -- 4.4.2 Composite Kernel for Online Data -- 4.5 Long-Term Sequential Trajectories with Self-Monitoring -- 4.5.1 Reevaluation of Large Online Data -- 4.5.2 Validation of Decomposing Online Data into Small Chunks -- 4.6 Experimental Results -- 4.6.1 Cancer Datasets -- 4.6.2 Selection of Optimum Kernel and Composite Kernel for Offline Data -- 4.6.3 Selection of Optimum Kernel and Composite Kernel for the New Online Sequences -- 4.6.4 Classification of Heterogeneous Versus Homogeneous Data -- 4.6.5 Online Learning Evaluation of Long-term Sequence -- 4.6.6 Evaluation of Computational Time -- 4.7 Conclusions -- References -- Chapter 5 Cloud Kernel Analysis -- 5.1 Introduction -- 5.2 Cloud Environments.

5.2.1 Server Specifications of Cloud Platforms -- 5.2.2 Cloud Framework of KPCA for AMD -- 5.3 AMD for Cloud Colonography -- 5.3.1 AMD Concept -- 5.3.2 Data Configuration of AMD -- 5.3.3 Implementation of AMD for Two Cloud Cases -- 5.3.4 Parallelization of AMD -- 5.4 Classification Evaluation of Cloud Colonography -- 5.4.1 Databases with Classification Criteria -- 5.4.2 Classification Results -- 5.5 Cloud Computing Performance -- 5.5.1 Cloud Computing Setting with Cancer Databases -- 5.5.2 Computation Time -- 5.5.3 Memory Usage -- 5.5.4 Running Cost -- 5.5.5 Parallelization -- 5.6 Conclusions -- References -- Chapter 6 Predictive Kernel Analysis -- 6.1 Introduction -- 6.2 Kernel Basics -- 6.2.1 KPCA and AKFA -- 6.3 Stationary Data Training -- 6.3.1 Kernel Selection -- 6.3.2 Composite Kernel: Kernel Combinatory Optimization -- 6.4 Longitudinal Nonstationary Data with Anomaly/Normal Detection -- 6.4.1 Updating the Gram Matrix Based on Nonstationary Longitudinal Data -- 6.4.2 Composite Kernel for Nonstationary Data -- 6.5 Longitudinal Sequential Trajectories for Anomaly Detection and Prediction -- 6.5.1 Anomaly Detection of Nonstationary Small Chunks Datasets -- 6.5.2 Anomaly Prediction of Long-Time Sequential Trajectories -- 6.6 Classification Results -- 6.6.1 Cancer Datasets -- 6.6.2 Selection of Optimum Kernel and Composite Kernel for Stationary Data -- 6.6.3 Comparisons with Other Kernel Learning Methods -- 6.6.4 Anomaly Detection for the Nonstationary Data -- 6.7 Longitudinal Prediction Results -- 6.7.1 Large Nonstationary Sequential dataset for Anomaly Detection -- 6.7.2 Time Horizontal Prediction for Risk Factor Analysis of Anomaly Long-Time Sequential Trajectories -- 6.7.3 Computational Time for Complexity Evaluation -- 6.8 Conclusions -- References -- Chapter 7 Conclusion -- Appendix A.

Appendix B Representative Matlab codes -- B.1 Accelerated Kernel Feature Analysis -- B.2 Experimental Evaluations -- B.3 Group Kernel Analysis -- B.4 Online Composite Kernel Analysis -- B.5 Online Data Sequences Contol -- B.6 Alignment Factor -- B.7 Cloud Kernel Analysis -- B.8 Plot Computation Time -- B.9 Parallelization -- Index -- Wiley Series on Adaptive and Cognitive Dynamic Systems -- EULA.