Machine Learning and the Internet of Medical Things in Healthcare

Title-page_2021_Machine-Learning-and-the-Internet-of-Medical-Things-in-Healt
Machine Learning and the Internet of Medical Things in Healthcare
Copyright_2021_Machine-Learning-and-the-Internet-of-Medical-Things-in-Health
Copyright
Contents_2021_Machine-Learning-and-the-Internet-of-Medical-Things-in-Healthc
Contents
List-of-contribut_2021_Machine-Learning-and-the-Internet-of-Medical-Things-i
List of contributors
Chapter-1---Machine-learning-arch_2021_Machine-Learning-and-the-Internet-of-
1 Machine learning architecture and framework
1.1 Introduction
1.1.1 Machine learning classification
1.1.1.1 Supervised learning
1.1.1.2 Unsupervised learning
1.1.1.3 Reinforcement learning
1.2 Architecture of machine learning
1.2.1 Data acquisition
1.2.2 Data processing
1.2.2.1 Arrangement of data
1.2.2.2 Analysis of data
1.2.2.3 Preprocessing of data
1.2.2.4 Transformation of data
1.2.3 Data modeling
1.2.4 Execution (model evaluation)
1.2.5 Deployment
1.3 Machine learning framework
1.3.1 Features of ML framework
1.3.2 Types of ML framework
1.3.2.1 TensorFlow
1.3.2.2 Amazon machine learning
1.3.2.3 Scikit-learn
1.3.2.4 Apache mahout
1.3.2.5 Cognitive toolkit of microsoft
1.4 Significance of machine learning in the healthcare system
1.4.1 Machine-learning applications in the healthcare system
1.4.1.1 Identification and diagnosis of disease
1.4.1.2 Discovery and manufacturing of drugs
1.4.1.3 Diagnosis through medical imaging
1.5 Conclusion
References
Chapter-2---Machine-learning-in-healthc_2021_Machine-Learning-and-the-Intern
2 Machine learning in healthcare: review, opportunities and challenges
2.1 Introduction
2.1.1 Machine learning in a nutshell
2.1.2 Machine learning techniques and applications
2.1.2.1 Supervised learning
2.1.2.2 Unsupervised learning
2.1.2.3 Reinforcement learning
2.1.3 Desired features of machine learning
2.1.4 How machine learning works?
2.1.5 Why machine learning for healthcare?
2.2 Analysis of domain
2.2.1 Background and related works
2.2.2 Integration scenarios of ML and Healthcare
2.2.3 Existing machine learning applications for healthcare
2.3 Perspective of disease diagnosis using machine learning
2.3.1 Future perspective to enhance healthcare system using machine learning
2.3.1.1 Challenges and risks
2.4 Conclusions
References
Chapter-3---Machine-learning-for-b_2021_Machine-Learning-and-the-Internet-of
3 Machine learning for biomedical signal processing
3.1 Introduction
3.2 Reviews of ECG signal
3.3 Preprocessing of ECG signal using ML based techniques
3.3.1 Least mean square (LMS)
3.3.2 Normalized least mean square (NLMS)
3.3.3 Delayed error normalized LMS (DENLMS) algorithm
3.3.4 Sign data least mean square (SDLMS)
3.3.5 Log least mean square (LLMS)
3.4 Feature extraction and classification of ECG signal using ML-based techniques
3.4.1 Artificial neural network (ANN)
3.4.2 Fuzzy logic (FL)
3.4.3 Wavelet transforms
3.4.4 Hybrid approach
3.5 Discussions and conclusions
References
Chapter-4---Artificial-itellig_2021_Machine-Learning-and-the-Internet-of-Med
4 Artificial itelligence in medicine
4.1 Introduction
4.1.1 Disease
4.1.1.1 Autoimmune diseases
4.1.1.2 Classification of diseases
4.1.1.3 Concept of diagnosis and treatment
4.1.2 Medicine
4.1.2.1 Medicine working
4.1.2.2 Different types of medicines
4.1.2.3 Discovering new medicines
4.1.2.4 Role of intelligent algorithm
4.1.2.5 History of AI
4.1.3 History of AI in medicine
4.1.4 Drug discovery process
4.1.5 Machine-learning algorithms in medicine
4.1.5.1 Linear regression
4.1.5.2 Logistic regression
4.1.5.3 Support vector machine
4.1.5.4 Convolutional neural network
4.1.6 Expert systems
4.1.7 Fuzzy expert systems
4.1.8 Artificial neural networks
4.2 Conclusion
References
Chapter-5---Diagnosing-of-disease_2021_Machine-Learning-and-the-Internet-of-
5 Diagnosing of disease using machine learning
5.1 Introduction
5.2 Background and related work
5.2.1 Challenges in conventional healthcare system
5.2.2 Machine-learning tools for diagnosis and prediction
5.2.3 Python
5.2.4 MATLAB
5.3 Types of machine-learning algorithm
5.4 Diagnosis model for disease prediction
5.4.1 Data preprocessing
5.4.2 Training and testing data set
5.4.3 Classification technique
5.4.4 Performance metrics
5.5 Confusion matrix
5.6 Disease diagnosis by various machine-learning algorithms
5.6.1 Support vector machine (SVM)
5.6.2 K-nearest neighbors (KNN)
5.6.3 Decision tree (DT)
5.6.4 Naive bayes (NB)
5.7 ML algorithm in neurological, cardiovascular, and cancer disease diagnosis
5.7.1 Neurological disease diagnosis by machine learning
5.7.2 Cardiovascular disease diagnosis by machine learning
5.7.3 Breast cancer diagnosis and prediction: a case study
5.7.3.1 Performance evaluation of breast cancer data set
5.7.4 Impact of machine learning in the healthcare industry
5.8 Conclusion and future scope
References
Chapter-6---A-novel-approach-of-telemedicine-for-_2021_Machine-Learning-and-
6 A novel approach of telemedicine for managing fetal condition based on machine learning technology from IoT-based wearabl...
6.1 Introduction
6.2 Healthcare and big data
6.3 Big data analytics
6.4 Need of IOT in the healthcare industry
6.5 Healthcare uses machine learning
6.6 Need for machine learning
6.7 Cardiotocography
6.8 Literature review
6.8.1 Research on revolutionary effect of telemedicine and its history
6.8.2 Role of machine learning in telemedicine/healthcare
6.8.3 Role of big data analytics in healthcare
6.8.4 Challenges faced in handling big data in healthcare/telemedicine
6.8.5 Research done on tracing the fetal well-being using telemedicine and machine learning algorithms
6.9 Methodology
6.9.1 Preprocessing and splitting of data
6.10 Evaluation
6.11 Conclusion and future work
References
Chapter-7---IoT-based-healthcare-delivery-serv_2021_Machine-Learning-and-the
7 IoT-based healthcare delivery services to promote transparency and patient satisfaction in a corporate hospital
7.1 Introduction
7.2 Uses of IoT in healthcare
7.3 Main problem area of a corporate hospital
7.3.1 Location
7.3.2 Hassle on outpatient services
7.3.3 Diagnostic services
7.3.4 Inpatient services
7.3.5 Support and utility services
7.3.6 Coordination in medical section
7.3.7 Medical record keeping
7.3.8 Transparency
7.3.9 Cost leadership model in market
7.4 Implementation of IoT-based healthcare delivery services
7.4.1 The work of value chain
7.4.1.1 IoT and medical record
7.4.1.2 IoT and therapeutic facilities
7.4.1.3 IoT in supportive and utility services
7.4.1.4 IoT in patient delight
7.4.1.5 Cost leadership with quality of care
7.5 Conclusion
References
Chapter-8---Examining-diabetic-subjects-on-the_2021_Machine-Learning-and-the
8 Examining diabetic subjects on their correlation with TTH and CAD: a statistical approach on exploratory results
8.1 Introduction
8.1.1 General application procedure
8.1.2 Medicinal imaging
8.1.2.1 Therapeutic photography and connected imaging methods for positron emission tomography (PET)
8.1.2.2 How is medical imaging used in digital health?
8.1.2.3 Biomedical image and analysis
8.1.3 Big data and Internet of Things
8.1.4 Artificial intelligence (AI) and machine learning (ML)
8.1.4.1 Artificial intelligence
8.1.4.2 Machine learning
8.1.4.2.1 Utilization of machine intelligence in healthcare
8.1.5 Big data and IoT applications in healthcare
8.1.6 Diabetes and its types
8.1.6.1 After effects of diabetes
8.1.6.2 Diabetes and headache
8.1.6.3 Obesity and overweight
8.1.7 Coronary artery disease (CAD)
8.1.7.1 Treatment
8.1.7.2 Insulin
8.1.7.3 Hypertension
8.1.7.4 Counteractive action
8.2 Review of literature
8.3 Research methodology
8.3.1 Trial setup
8.4 Result analysis and discussion
8.4.1 TTH cannot be
8.5 Originality in the presented work
8.6 Future scope and limitations
8.7 Recommendations and considerations
8.8 Conclusion
References
Chapter-9---Cancer-prediction-and-diagn_2021_Machine-Learning-and-the-Intern
9 Cancer prediction and diagnosis hinged on HCML in IOMT environment
9.1 Introduction to machine learning (ML)
9.1.1 Some machine learning methods
9.1.2 Machine learning
9.2 Introduction to IOT
9.3 Application of IOT in healthcare
9.3.1 Redefining healthcare
9.4 Machine learning use in health care
9.4.1 Diagnose heart disease
9.4.2 Diabetes prediction
9.4.3 Liver disease prediction
9.4.4 Surgery on robots
9.4.5 Detection and prediction of cancer
9.4.6 Treatment tailored
9.4.7 Discovery of drugs
9.4.8 Recorder of intelligent digital wellbeing
9.4.9 Radiology machine learning
9.4.10 Study and clinical trial
9.5 Cancer in healthcare
9.5.1 Methods
9.5.2 Result
9.6 Breast cancer in IoHTML
9.6.1 Study of breast cancer using the adaptive voting algorithm
9.6.2 Software development life cycle (SDLC)
9.6.3 Parts of undertaking duty PDR and PER
9.6.4 Info structure
9.6.5 Input stage
9.6.6 Output design
9.6.7 Responsible developers overview
9.6.8 Data flow
9.6.9 Cancer prediction of data in different views
9.6.10 Cancer predication in use case view
9.6.11 Cancer predication in activity view
9.6.12 Cancer predication in class view
9.6.13 Cancer predication in state chart view
9.6.14 Symptoms of breast cancer
9.6.15 Breast cancer types
9.7 Case study in breast cancer
9.7.1 History and assessment of patients
9.7.2 Recommendations for diagnosis
9.7.3 Discourse
9.7.4 Outcomes of diagnosis
9.8 Breast cancer algorithm
9.9 Conclusion
References
Chapter-10---Parameterization-technique_2021_Machine-Learning-and-the-Intern
10 Parameterization techniques for automatic speech recognition system
10.1 Introduction
10.2 Motivation
10.3 Speech production
10.4 Data collection
10.4.1 Recording procedure
10.4.2 Noise reduction
10.5 Speech signal processing
10.5.1 Sampling and quantization
10.5.2 Representation of the signal in time and frequency domain
10.5.3 Frequency analysis
10.5.4 Short time analysis
10.5.5 Short-time fourier analysis
10.5.6 Cepstral analysis
10.5.7 Preprocessing: the noise reduction technique
10.5.7.1 Spectral subtraction method
10.5.7.2 Endpoint detection
10.5.8 Frame blocking
10.5.9 Windowing
10.6 Features for speech recognition
10.6.1 Types of speech features
10.6.1.1 Spectral speech features
10.6.1.2 Continuous speech features
10.6.1.3 Qualitative speech features
10.7 Speech parameterization
10.7.1 Feature extraction
10.7.2 Linear predicative coding (LPC)
10.7.2.1 Autocorrelation method
10.7.3 Linear predictive cepstral coefficients (LPCC)
10.7.4 Weighted linear predictive cepstral coefficients (WLPCC)
10.7.5 Mel-frequency cepstral coefficients
10.7.5.1 Preemphasis
10.7.5.2 Framing
10.7.5.3 Windowing
10.7.5.4 Fast fourier transform
10.7.5.5 Mel-filter banking
10.7.5.6 Discrete cosine transform
10.7.6 Delta coefficients
10.7.7 Delta–delta coefficients
10.7.8 Power spectrum density
10.8 Speech recognition
10.8.1 Types of speech pattern recognition
10.9 Speech classification
10.9.1 Artificial neural network (ANN)
10.9.2 Support vector machine (SVM)
10.9.3 Linear discriminant analysis (LDA)
10.9.4 Random forest
10.10 Summary and discussion
Reference
Chapter-11---Impact-of-big-data-in-healthca_2021_Machine-Learning-and-the-In
11 Impact of big data in healthcare system—a quick look into electronic health record systems
11.1 A leap into the healthcare domain
11.2 The real facts of health record collection
11.3 A proposal for the future
11.4 Discussions and concluding comments on health record collection
11.5 Background of electronic health record systems
11.5.1 The definition of an electronic health record (EHR)
11.5.2 A short history of electronic health records
11.6 Review of challenges and study methodologies
11.6.1 Analyzing EHR systems and burnout
11.6.2 Analyzing EHR systems and productivity
11.6.3 Analyzing EHR systems and data accuracy
11.7 Conclusion and discussion
References
Index_2021_Machine-Learning-and-the-Internet-of-Medical-Things-in-Healthcare
Index