Big data analytics for intelligent healthcare management

Big data analytics for intelligent healthcare management

Big Data Analytics for Intelligent Healthcare Management covers both the theory and application of hardware platforms and architectures, the development of software methods, techniques and tools, applications and governance, and adoption strategies for the use of big data in healthcare and clinical...

Full description

Bibliographic Details
Other Authors: Dey, Nilanjan, author (author), Dey, Nilanjan, editor (editor)
Format: eBook
Language:Inglés
Published: London, England : Academic Press [2019]
Edition:First edition
Series:Advances in ubiquitous sensing applications for healthcare ; Volume three.
Subjects:
Computer system failures.
Data mining.
Database management.
Image processing.
See on Biblioteca Universitat Ramon Llull:https://discovery.url.edu/permalink/34CSUC_URL/1im36ta/alma991009630494506719
Table of Contents:
  • Front Cover
  • Big Data Analytics for Intelligent Healthcare Management
  • Copyright
  • Contents
  • Contributors
  • Preface
  • Acknowledgments
  • Chapter 1: Bio-Inspired Algorithms for Big Data Analytics: A Survey, Taxonomy, and Open Challenges
  • 1.1. Introduction
  • 1.1.1. Dimensions of Data Management
  • 1.2. Big Data Analytical Model
  • 1.3. Bio-Inspired Algorithms for Big Data Analytics: A Taxonomy
  • 1.3.1. Evolutionary Algorithms
  • 1.3.2. Swarm-Based Algorithms
  • 1.3.3. Ecological Algorithms
  • 1.3.4. Discussions
  • 1.4. Future Research Directions and Open Challenges
  • 1.4.1. Resource Scheduling and Usability
  • 1.4.2. Data Processing and Elasticity
  • 1.4.3. Resilience and Heterogeneity in Interconnected Clouds
  • 1.4.4. Sustainability and Energy-Efficiency
  • 1.4.5. Data Security and Privacy Protection
  • 1.4.6. IoT-Based Edge Computing and Networking
  • 1.5. Emerging Research Areas in Bio-Inspired Algorithm-Based Big Data Analytics
  • 1.5.1. Container as a Service (CaaS)
  • 1.5.2. Serverless Computing as a Service (SCaaS)
  • 1.5.3. Blockchain as a Service (BaaS)
  • 1.5.4. Software-defined Cloud as a Service (SCaaS)
  • 1.5.5. Deep Learning as a Service (DLaaS)
  • 1.5.6. Bitcoin as a Service (BiaaS)
  • 1.5.7. Quantum Computing as a Service (QCaaS)
  • 1.6. Summary and Conclusions
  • Acknowledgments
  • References
  • Further Reading
  • Chapter 2: Big Data Analytics Challenges and Solutions
  • 2.1. Introduction
  • 2.1.1. Consumable Massive Facts Analytics
  • 2.1.2. Allotted Records Mining Algorithms
  • 2.1.3. Gadget Failure
  • 2.1.4. Facts Aggregation Challenges
  • 2.1.5. Statistics Preservation-Demanding Situations
  • 2.1.6. Information Integration Challenges
  • 2.2. Records Analysis Challenges
  • 2.2.1. Scale of the Statistics
  • 2.2.2. Pattern Interpretation Challenges
  • 2.3. Arrangements of Challenges.
  • 2.3.1. User Intervention Method
  • 2.3.2. Probabilistic Method
  • 2.3.3. Defining and Detecting Anomalies in Human Ecosystems
  • 2.4. Demanding Situations in Managing Huge Records
  • 2.5. Massive Facts Equal Large Possibilities
  • 2.5.1. Present Answers to Challenges for the Quantity Mission
  • 2.5.1.1. Hadoop
  • 2.5.1.2. Hadoop-distributed file system
  • 2.5.1.3. Hadoop MapReduce
  • 2.5.1.4. Apache spark
  • 2.5.1.5. Grid computing
  • 2.5.1.6. Spark structures
  • 2.5.1.7. Capacity solutions for records-variety trouble
  • 2.5.2. Image Mining and Processing With Big Data
  • 2.5.3. Potential Answers for Velocity Trouble
  • 2.5.3.1. Transactional databases
  • 2.5.3.2. Statistics representation
  • 2.5.3.3. Massive actualities calculations
  • 2.5.3.4. Ability solutions for privateers and safety undertaking
  • 2.5.4. Ability Solutions for Scalability Assignments
  • 2.5.4.1. Big data and cloud computing
  • 2.5.4.2. Cloud computing service models
  • 2.5.4.3. Answers
  • 2.5.4.4. Use record encryption
  • 2.5.4.5. Imposing access controls
  • 2.5.4.6. Logging
  • 2.6. Discussion
  • 2.7. Conclusion
  • Glossary
  • References
  • Further Reading
  • Chapter 3: Big Data Analytics in Healthcare: A Critical Analysis
  • 3.1. Introduction
  • 3.2. Big Data
  • 3.3. Healthcare Data
  • 3.3.1. Structured Data
  • 3.3.2. Unstructured Data
  • 3.3.3. Semistructured Data
  • 3.3.4. Genomic Data
  • 3.3.5. Patient Behavior and Sentiment Data
  • 3.3.6. Clinical Data and Clinical Notes
  • 3.3.7. Clinical Reference and Health Publication Data
  • 3.3.8. Administrative and External Data
  • 3.4. Medical Image Processing and its Role in Healthcare Data Analysis
  • 3.5. Recent Works in Big Data Analytics in Healthcare Data
  • 3.6. Architectural Framework and Different Tools for Big Data Analytics in Healthcare Big Data
  • 3.6.1. Architectural Framework.
  • 3.6.2. Different Tools Used in Big Data Analytics in Healthcare Data
  • 3.7. Challenges Faced During Big Data Analytics in Healthcare
  • 3.8. Conclusion and Future Research
  • References
  • Further Reading
  • Chapter 4: Transfer Learning and Supervised Classifier Based Prediction Model for Breast Cancer
  • 4.1. Introduction
  • 4.2. Related Work
  • 4.3. Dataset and Methodologies
  • 4.3.1. Convolution Neural Networks (CNNs/ConvNets)
  • 4.3.1.1. Transfer learning and convolution networks
  • 4.3.1.2. Convolution networks as fixed feature extractors
  • 4.3.1.3. Dimensionality reduction and principle component analysis (PCA)
  • 4.3.1.4. Supervised machine learning
  • 4.4. Proposed Model
  • 4.5. Implementation
  • 4.5.1. Feature Extraction
  • 4.5.2. Dimensionality Reduction
  • 4.5.3. Classification
  • 4.5.4. Tuning Hyperparameters of the Classifiers
  • 4.6. Result and Analysis
  • 4.6.1. 10-fold Cross Validation Result
  • 4.6.2. Magnification Factor Wise Analysis on Validation Accuracy
  • 4.6.2.1. Validation accuracy of 40x
  • 4.6.2.2. Validation accuracy of 100x
  • 4.6.2.3. Validation accuracy of 200x
  • 4.6.2.4. Validation accuracy of 400x
  • 4.6.2.5. Best validation accuracy
  • 4.6.2.6. Performance on the test set
  • 4.6.3. Result and Analysis of Test Performance
  • 4.6.3.1. Test performance on 40x
  • 4.6.3.2. Overall performance on 40x
  • 4.6.3.3. Test performance on 100x
  • 4.6.3.4. Overall performance on 100x
  • 4.6.3.5. Test performance on 200x
  • 4.6.3.6. Test performance on 400x
  • 4.6.3.7. Overall performance on 400x
  • 4.7. Discussion
  • 4.8. Conclusion
  • References
  • Further Reading
  • Chapter 5: Chronic TTH Analysis by EMG and GSR Biofeedback on Various Modes and Various Medical Symptoms Using IoT
  • 5.1. Introduction and Background
  • 5.1.1. Biofeedback
  • 5.1.2. Mental Health Introduction.
  • 5.1.3. Importance of Mental Health, Stress, and Emotional Needs and Significance of Study
  • 5.1.4. Meaning of Mental Health
  • 5.1.5. Definitions
  • 5.1.6. Factors Affecting Mental Health
  • 5.1.7. Models of Stress: Three Models in Practice
  • 5.1.7.1. Types of stress
  • 5.1.7.2. Causes of stress
  • 5.1.7.3. Symptoms of stress
  • 5.1.8. Big Data and IoT
  • 5.2. Previous Studies (Literature Review)
  • 5.2.1. Tension Type Headache and Stress
  • 5.3. Independent Variable: Emotional Need Fulfillment
  • 5.4. Meditation-Effective Spiritual Tool With Approach of Biofeedback EEG
  • 5.4.1. Mind-Body and Consciousness
  • 5.5. Sensor Modalities and Our Approach
  • 5.5.1. Biofeedback Based Sensor Modalities
  • 5.5.2. Electromyograph
  • 5.5.3. Electrodermograph
  • 5.5.4. Proposed Framework
  • 5.6. Experiments and Results-Study Plot
  • 5.6.1. Study Design and Source of Data
  • 5.6.2. Study Duration and Consent From Subjects
  • 5.6.3. Sampling Design and Allocation Process
  • 5.6.4. Sample Size
  • 5.6.5. Study Population
  • 5.6.5.1. Inclusion criteria
  • 5.6.5.2. Exclusion criteria
  • 5.6.6. Intervention
  • 5.6.7. Outcome Parameters
  • 5.6.7.1. Primary variables
  • 5.6.7.2. Secondary variables
  • 5.6.8. Analgesic Consumption
  • 5.6.9. Assessment of Outcome Variables
  • 5.6.10. Pain Diary
  • 5.6.11. Data Collection
  • 5.6.12. Statistical Analysis
  • 5.6.13. Hypothesis
  • 5.7. Data Collection Procedure-Guided Meditation as per Fig. 5.7G
  • 5.8. Results, Interpretation and Discussion
  • 5.8.1. The Trend of Average of Frequency
  • 5.8.2. The Trend of Average of Duration
  • 5.8.3. The Trend of Average of Intensity
  • 5.8.4. The Trend of Duration per Cycle With Time
  • 5.8.5. Trend on Correlation of TTH Duration and Intensity
  • 5.8.6. Trend on Correlation of TTH Duration With Occurrence
  • 5.8.7. The Trend of Average of Frequency.
  • 5.8.8. The Trend of Average of Duration
  • 5.8.9. The Trend of Average of Intensity
  • 5.8.10. The Trend of Duration per Cycle With Time
  • 5.8.11. Trend on Correlation of TTH Duration and Intensity
  • 5.8.12. Trend on Correlation of TTH Duration With Occurrence
  • 5.8.13. The Trend of Average of Frequency
  • 5.8.14. The Trend of Average Duration
  • 5.8.15. The Trend of Average Intensity
  • 5.8.16. The Trend of Duration per Cycle With Time
  • 5.8.17. Trend on Correlation of TTH Duration and Intensity
  • 5.8.18. Trend on Correlation of TTH Duration With Occurrence
  • 5.8.19. The Trend of Average of Frequency
  • 5.8.20. The Trend of Average of Duration
  • 5.8.21. The Trend of Average Intensity
  • 5.8.22. The Trend of Duration per Cycle With Time
  • 5.8.23. Trend on Correlation of TTH Duration and Intensity
  • 5.8.24. Trend on Correlation of TTH Duration With Occurrence
  • 5.9. Findings in This Chapter
  • 5.10. Future Scope, Limitations, and Possible Applications
  • 5.11. Conclusion
  • 5.11.1. Comprehensive Conclusion
  • Acknowledgment
  • References
  • Further Reading
  • Chapter 6: Multilevel Classification Framework of fMRI Data: A Big Data Approach
  • 6.1. Introduction
  • 6.2. Related Work
  • 6.3. Our Approach
  • 6.3.1. Dataset
  • 6.3.2. Methodology
  • 6.3.3. Result Evaluation
  • 6.3.4. Experimental Results
  • 6.3.5. Subject-Dependent Experiments on PS+SP
  • 6.3.5.1. All features
  • 6.3.5.2. ROI-based feature
  • 6.3.5.3. Average ROI-based feature
  • 6.3.5.4. N-most active-based feature
  • 6.3.5.5. N-most active ROI-based feature
  • 6.3.6. Subject-Dependent Experiment on PS/SP
  • 6.3.6.1. ROI-based feature
  • 6.3.6.2. Average ROI-based feature
  • 6.3.6.3. N-most active-based feature
  • 6.3.6.4. Most active ROI-based feature
  • 6.4. Result Analysis
  • 6.4.1. Summary of the Subject-Dependent Results
  • 6.4.2. Subject-Independent Experiment.
  • 6.5. Conclusion and Future Work.

Similar Items