Keywords:
Machine learning.
;
Medical informatics.
;
Artificial intelligence-Medical applications.
;
Electronic books.
Type of Medium:
Online Resource
Pages:
1 online resource (460 pages)
Edition:
1st ed.
ISBN:
9780128217818
Series Statement:
Intelligent Data-Centric Systems Series
URL:
https://ebookcentral.proquest.com/lib/geomar/detail.action?docID=6641473
DDC:
610.28563
Language:
English
Note:
Intro -- Machine Learning, Big Data, and IoT for Medical Informatics -- Copyright -- Contents -- Contributors -- Preface -- Outline of the book and chapter synopses -- Special acknowledgments -- Chapter 1: Predictive analytics and machine learning for medical informatics: A survey of tasks and techniques -- 1. Introduction: Predictive analytics for medical informatics -- 1.1. Overview: Goals of machine learning -- 1.2. Current state of practice -- 1.3. Key task definitions -- 1.3.1. Diagnosis -- 1.3.2. Predictive analytics -- 1.3.3. Therapy recommendation -- 1.3.4. Automation of treatment -- 1.3.5. Other tasks in integrative medicine -- 1.4. Open research problems -- 1.4.1. Learning for classification and regression -- 1.4.2. Learning to act: Control and planning -- 1.4.3. Toward greater autonomy: Active learning and self-supervision -- 2. Background -- 2.1. Diagnosis -- 2.1.1. Diagnostic classification and regression tasks -- 2.1.2. Diagnostic policy-learning tasks -- 2.1.3. Active, transfer, and self-supervised learning -- 2.2. Predictive analytics -- 2.2.1. Prediction by classification and regression -- 2.2.2. Learning to predict from reinforcements and by supervision -- 2.2.3. Transfer learning in prediction -- 2.3. Therapy recommendation -- 2.3.1. Supervised therapy recommender systems -- 2.4. Automation of treatment -- 2.4.1. Classification and regression-based tasks -- 2.4.2. RL for automation -- 2.4.3. Active learning in automation -- 2.5. Integrating medical informatics and health informatics -- 2.5.1. Classification and regression tasks in HMI -- 2.5.2. Reinforcement learning for HMI -- 2.5.3. Self-supervised, transfer, and active learning in HMI -- 3. Techniques for machine learning -- 3.1. Supervised, unsupervised, and semisupervised learning -- 3.1.1. Shallow -- 3.1.2. Deep -- 3.2. Reinforcement learning -- 3.2.1. Traditional.
,
3.2.2. Deep RL -- 3.3. Self-supervised, transfer, and active learning -- 3.3.1. Traditional -- 3.3.2. Deep -- 4. Applications -- 4.1. Test beds for diagnosis and prognosis -- 4.1.1. New test beds -- 4.2. Test beds for therapy recommendation and automation -- 4.2.1. Prescriptions -- 4.2.2. Surgery -- 5. Experimental results -- 5.1. Test bed -- 5.2. Results and discussion -- 6. Conclusion: Machine learning for computational medicine -- 6.1. Frontiers: Preclinical, translational, and clinical -- 6.2. Toward the future: Learning and medical automation -- References -- Chapter 2: Geolocation-aware IoT and cloud-fog-based solutions for healthcare -- 1. Introduction -- 2. Related work -- 2.1. Health monitoring system with cloud computing -- 2.2. Health monitoring system with fog computing -- 2.3. Health monitoring system with cloud-fog computing -- 3. Proposed framework -- 3.1. Health data analysis -- 3.2. Geospatial analysis for medical facility -- 3.2.1. Overlay analysis to obtain nearest medical facilities -- 3.2.2. Shortest path to reach nearest medical centers -- 3.3. Delay and power consumption calculation -- 4. Performance evaluation -- 5. Conclusion and future work -- References -- Chapter 3: Machine learning vulnerability in medical imaging -- 1. Introduction -- 2. Computer vision -- 3. Adversarial computer vision -- 4. Methods to produce adversarial examples -- 5. Adversarial attacks -- 6. Adversarial defensive methods -- 7. Adversarial computer vision in medical imaging -- 8. Adversarial examples: How to generate? -- 9. Conclusion -- Acknowledgment -- References -- Chapter 4: Skull stripping and tumor detection using 3D U-Net -- 1. Introduction -- 1.1. Previous work -- 2. Overview of U-net architecture -- 2.1. 3D U-net -- 2.1.1. Batch normalization -- 2.1.2. Activation function -- 2.1.3. Pooling -- 2.1.4. Padding -- 2.1.5. Optimizer.
,
3. Materials and methods -- 3.1. Dataset -- 3.2. Implementation -- 4. Results -- 4.1. Experimental result -- 4.1.1. Dice coefficient -- 4.1.2. Accuracy -- 4.1.3. Intersection over Union (IoU) -- 4.2. Quantitative result -- 4.3. Qualitative result -- 5. Conclusion -- References -- Chapter 5: Cross color dominant deep autoencoder for quality enhancement of laparoscopic video: A hybrid deep learning an -- 1. Introduction -- 2. Range-domain filtering -- 3. Cross color dominant deep autoencoder (C2D2A) leveraging color spareness and saliency -- 3.1. Evolution of DCM through C2D2A -- 3.2. Inclusion of DCM into principal flow of bilateral filtering -- 4. Experimental results -- 5. Conclusion -- Acknowledgments -- References -- Chapter 6: Estimating the respiratory rate from ECG and PPG using machine learning techniques -- 1. Introduction -- 1.1. Motivation -- 1.2. Background -- 2. Related work -- 3. Methods -- 3.1. Data -- 3.2. Steps -- 3.3. RR signal extraction -- 3.4. Machine learning -- 4. Experimental results -- 5. Discussion and conclusion -- Acknowledgments -- References -- Chapter 7: Machine learning-enabled Internet of Things for medical informatics -- 1. Introduction -- 1.1. Healthcare Internet of Things -- 1.1.1. H-IoT architecture -- 1.1.2. Three-tier H-IoT architecture -- 2. Applications and challenges of H-IoT -- 2.1. Applications of H-IoT -- 2.1.1. Fitness tracking -- 2.1.2. Neurological disorders -- 2.1.3. Cardio vascular disorders -- 2.1.4. Ambient-assisted living -- 2.2. Challenges of H-IoT system -- 2.2.1. QoS improvement -- 2.2.2. Scalability challenges -- 3. Machine learning -- 3.1. Machine learning advancements at the application level of H-IoT -- 3.2. Machine learning advancements at network level of H-IoT -- 4. Future research directions -- 4.1. Novel applications of ML in H-IoT -- 4.1.1. Real-time monitoring and treatment.
,
4.1.2. Training for professionals -- 4.1.3. Advanced prosthetics -- 4.2. Research opportunities in network management -- 4.2.1. Channel access -- 4.2.2. Dynamic data management -- 4.2.3. Fully autonomous operation -- 4.2.4. Security -- 5. Conclusion -- References -- Chapter 8: Edge detection-based segmentation for detecting skin lesions -- 1. Introduction -- 2. Previous works -- 3. Materials and methods -- 3.1. Elitist-Jaya algorithm -- 3.2. Otsus method -- 4. Proposed method -- 4.1. Image preprocessing -- 4.2. Edge detection -- 5. Experiment and results -- 5.1. Dataset -- 5.2. Evaluation metrics -- 5.3. Results and discussion -- 5.4. Statistical analysis -- 6. Conclusion -- References -- Chapter 9: A review of deep learning approaches in glove-based gesture classification -- 1. Introduction -- 2. Data gloves -- 2.1. Early and commercial data gloves -- 2.2. Sensing mechanism in data gloves -- 2.2.1. Fiber-optic sensors -- 2.2.2. Conductive strain sensors -- 2.2.3. Inertial sensors -- 3. Gesture taxonomies -- 4. Gesture classification -- 4.1. Classical machine learning algorithms -- 4.1.1. K-nearest neighbor -- 4.1.2. Support vector machine (SVM) -- 4.1.3. Decision tree -- 4.1.4. Artificial neural network (ANN) -- 4.1.5. Probabilistic neural network (PNN) -- 4.2. Glove-based gesture classification with classical machine learning algorithms -- 4.3. Deep learning -- 4.3.1. Convolutional neural network (CNN) -- 4.3.2. Recurrent neural network (RNN) -- 4.4. Glove-based gesture classification using deep learning -- 5. Discussion and future trends -- 6. Conclusion -- References -- Chapter 10: An ensemble approach for evaluating the cognitive performance of human population at high altitude -- 1. Introduction -- 2. Methodology -- 2.1. Data collection -- 2.2. Data processing and feature selection -- 2.3. Differential expression analyses.
,
2.4. Association rule mining -- 2.5. Experimental set-up -- 3. Results and discussion -- 3.1. Differential analyses-Cognitive and clinical features -- 3.2. Discovered associative rules -- 3.3. Discussion -- 4. Future opportunities -- 5. Conclusions -- Acknowledgment -- References -- Chapter 11: Machine learning in expert systems for disease diagnostics in human healthcare -- 1. Introduction -- 2. Types of expert systems -- 3. Components of an expert system -- 4. Techniques used in expert systems of medical diagnosis -- 5. Existing expert systems -- 6. Case studies -- 6.1. Cancer diagnosis using rule-based expert system -- 6.2. Alzheimers diagnosis using fuzzy-based expert systems -- 6.2.1. Algorithm of fuzzy inference system -- 7. Significance and novelty of expert systems -- 8. Limitations of expert systems -- 9. Conclusion -- Acknowledgment -- References -- Chapter 12: An entropy-based hybrid feature selection approach for medical datasets -- 1. Introduction -- 1.1. Deficiencies of the existing models -- 1.2. Chapter organization -- 2. Background of the present research -- 2.1. Feature selection (FS) -- 3. Methodology -- 3.1. The entropy based feature selection approach -- 3.1.1. Equi-class distribution of instances -- 3.1.2. Splitting the dataset D into subsets: D1, D2, and D3 -- 4. Experiment and experimental results -- 4.1. Experiment using suggested feature selection approach -- 5. Discussion -- 5.1. Performance analysis of the suggested feature selection approach -- 6. Conclusions and future works -- Conflict of interest -- Appendix A -- A.1. Explanation on entropy-based feature extraction approach -- References -- Chapter 13: Machine learning for optimizing healthcare resources -- 1. Introduction -- 2. The state of the art -- 2.1. Resource management -- 2.2. Impact on peoples health -- 2.3. Exit strategies.
,
3. Machine learning for health data analysis.
Permalink