Читать книгу Computational Intelligence and Healthcare Informatics - Группа авторов - Страница 3

1 Chapter 1Figure 1.1 Machine learning and big data analysis in healthcare.Figure 1.2 Application of ML in healthcare.Figure 1.3 The types of machine learning algorithm.Figure 1.4 Sources of big data in healthcare.Figure 1.5 Applications of big data in healthcare.

2 Chapter 2Figure 2.1 Broad view of existing research.Figure 2.2 Types of chest pathologies.

3 Chapter 3Figure 3.1 (a) This what the normal data looks like. (b) “Big p and small n” pro...Figure 3.2 Feature selection process.Figure 3.3 Taxonomy of feature selection.Figure 3.4 Taxonomy of deep learning models.

4 Chapter 4Figure 4.1 Overview of the processes involved in building ML models.Figure 4.2 Machine Learning vs. Deep Learning workflow process.Figure 4.3 Overview of an Artificial Neural Network.Figure 4.4 The description of the raw dataset showing the first five rows.Figure 4.5 The code snippet showing the data processing of the attributes such a...Figure 4.6 The description of the cleaned and processed dataset showing the firs...Figure 4.7 Boxplot showing number of disease occurrences.Figure 4.8 Ten highest reported diseases.Figure 4.9 Ten highest reported symptoms.Figure 4.10 The code snippet of the label encoding and one hot encoding process ...Figure 4.11 List of the implemented algorithms while building the model. MLP pro...Figure 4.12 Work architecture of the proposed solution.Figure 4.13 The web application to predict disease based on symptoms.Figure 4.14 The user can input multiple symptoms at a time and get accurate pred...

5 Chapter 5Figure 5.1 PCG signal in time-frequency representation before and after filtered...Figure 5.2 (a) Standard spectrogram for normal sample. (b) for standard spectrog...Figure 5.3 (a) Mel-spectrogram for normal sample. (b) Mel-spectrogram for abnorm...Figure 5.4 (a) IIR-CQT spectrogram for normal sample. (b) IIR-CQT spectrogram fo...Figure 5.5 Kirschmask in eight different directions [12].Figure 5.6 Algorithm for the proposed heart sound classification system.Figure 5.7 Confusion matrix for dense CLBP method.

6 Chapter 6Figure 6.1 Process of proposed model.Figure 6.2 Performance on the Yeast data set.Figure 6.3 Performance on the Scene data set.Figure 6.4 Performance of the Emotion data set.Figure 6.5 Performance if the Enron data set.Figure 6.6 Performance if the Medical data set.

7 Chapter 7Figure 7.1 An Intelligent Computational Framework for diabetes disease predictio...Figure 7.2 Performance of all eight classification hypotheses on PIDD using 5-fo...Figure 7.3 F1-score and MCC of all eight classification hypotheses on PIDD apply...Figure 7.4 Precision and AUC of all eight classification hypotheses on PIDD usin...Figure 7.5 ROC curves of all used classification hypotheses applying 5-fold CV.Figure 7.6 Performance of all eight classification hypotheses on PIDD using 7-fo...Figure 7.7 F1-score and MCC of all eight classification hypotheses on PIDD using...Figure 7.8 Precision and AUC of all eight classification hypotheses on PIDD usin...Figure 7.9 ROC curves of all used classification hypotheses using 7-fold CV.Figure 7.10 Performance of all eight classification hypotheses on PIDD using 10-...Figure 7.11 F1-score and MCC of all eight classification hypotheses on PIDD usin...Figure 7.12 Precision and AUC of all eight classification hypotheses on PIDD usi...Figure 7.13 ROC curves of all eight classification hypotheses on PIDD using 10-f...

8 Chapter 8Figure 8.1 General schematic diagram of the proposed method for predicting heart...Figure 8.2 Process of building heart disease prediction model.Figure 8.3 Proposed classifier workflow.Figure 8.4 Random forest classifier workflow.Figure 8.5 Comparison of three ensemble classifier accuracy before and after gri...

9 Chapter 9Figure 9.1 Distribution of post-surgical complications in the selected dataset.Figure 9.2 High-level ML model architecture.Figure 9.3 ROC-AUC curve of post-surgical complication outcomes for SGD classifi...Figure 9.4 ROC-AUC curve of post-surgical complication outcomes for SVM nu-SVC c...Figure 9.5 ROC-AUC Curve of post-surgical complication outcomes for RF classifie...Figure 9.6 Basic LSTM unit.Figure 9.7 Bidirectional LSTM model network architecture.Figure 9.8 Precision of surgical participant classes.

10 Chapter 10Figure 10.1 Block diagram of n-cell periodic boundary cellular automata with hyb...Figure 10.2 E-healthcare steps toward medical diagnosis or disease detection.Figure 10.3 A typical system architecture based on cellular automata used in hea...Figure 10.4 Basic block diagram of Cellular Automata for Symbolic Induction (CAS...Figure 10.5 Detection of heart disease with hybrid random forest with linear mod...Figure 10.6 Basic block diagram of HL-DL-CA used in health informatics.

11 Chapter 11Figure 11.1 Performance graph of LMBP algorithm Mean Square Error (MSE) vs. epoc...Figure 11.2 Rise-wise classification of countries.

12 Chapter 12Figure 12.1 Architecture diagram of COVID-19 emotional classification.Figure 12.2 Pseudocode for Independent Component Analysis pre-processing (Prasty...Figure 12.3 Pseudocode for WMAR features extraction (Satu, Md Shahriare, et al. ...Figure 12.4 Chicken swarm optimization for COVID-19 emotional features optimizat...Figure 12.5 Pseudocode for chicken swarm optimization (Yang, Liping, Alan M. Mac...Figure 12.6 Structure of SVM.Figure 12.7 Pair-wise comparison format.Figure 12.8 Relative scale to compare COVID-19 two tweets.Figure 12.9 Choosing COVID-19 emotional prediction.Figure 12.10 Comparisons of accuracy, sensitivity, and specificity for various m...Figure 12.11 Comparisons of precision, recall, and F-measure for various SA meth...Figure 12.12 Comparison of processing time vs. no of products.

13 Chapter 13Figure 13.1 Different steps in the block diagram of the proposed methodology.Figure 13.2 Kohonen SOM network model.Figure 13.3 Membership of features.Figure 13.4 ROC curve of proposed methodology.Figure 13.5 (a) SOM Hit map. (b) SOM weight for input vectors. (c) SOM weight po...

14 Chapter 14Figure 14.1 Block diagram for proposed work.Figure 14.2 Dataset distribution in training set.Figure 14.3 Dataset distribution in testing set.Figure 14.4 Proposed VGG19.Figure 14.5 VGG19 layered architecture.Figure 14.6 Experiment history for each epoch.Figure 14.7 Accuracy curve.Figure 14.8 Loss curve.Figure 14.9 Normalized confusion matrix.Figure 14.10 Confusion matrix without normalization.Figure 14.11 Model prediction for sample images extracted from video stream.

15 Chapter 15Figure 15.1 Actinic keratosis.Figure 15.2 Melanoma.Figure 15.3 Pigmented keratosis.Figure 15.4 Nevus.Figure 15.5 Vascular lesion.Figure 15.6 SVM block diagram.Figure 15.7 Recurrent neural network architecture.Figure 15.8 Decision tree architecture.Figure 15.9 CNN architecture.Figure 15.10 Random Forest.Figure 15.11 Random Forest architecture.Figure 15.12 Accuracy rate.

16 Chapter 16Figure 16.1 Block diagram.Figure 16.2 (a) LM-35 temperature sensor, (b) AD8232 heart rate sensor, (c) puls...Figure 16.3 Circuit diagram.Figure 16.4 Data flow diagram.Figure 16.5 A working prototype.Figure 16.6 Reading on website.Figure 16.7 Heart rate graph.Figure 16.8 Pulse rate graph.Figure 16.9 Temperature graph.Figure 16.10 Gyroscopic inclination graph.Figure 16.11 Database entries: value1, temperature; value2, heart rate; value3, ...

17 Chapter 17Figure 17.1 Structure of 1D CA.Figure 17.2 Structure of 2D CA [7].Figure 17.3 (a) Von Neumann neighborhood models, (b) Moore neighborhood models, ...Figure 17.4 CNN architecture.Figure 17.5 System flow diagram.Figure 17.6 Schema of convolutional neural network part.Figure 17.7 Schema of artificial neural network part.Figure 17.8 Normal chest X-ray [20].Figure 17.9 COVID-19 positive chest X-ray [19].Figure 17.10 Pneumonia chest X-ray [20].Figure 17.11 Sample images of hidden layer 1.

18 Chapter 18Figure 18.1 Data collection and cleaning mechanism.Figure 18.2 Proposed GSA model.Figure 18.3 Graph representation of healthcare data.Figure 18.4 RDF data representation.Figure 18.5 Knowledge representation of COVID, KaTrace dataset.Figure 18.6 RDF for KaTrace, initial data only.Figure 18.7 District-wise patient represented by age.Figure 18.8 Betweenness centrality for knowledge graph.Figure 18.9 PageRank centrality for knowledge graph.Figure 18.10 RDF query on the knowledge graph.Figure 18.11 PageRank centrality for knowledge graph.Figure 18.12 Overall inter-district graph.Figure 18.13 Reference graph for P566.Figure 18.14 P653 spread to 45 nodes.Figure 18.15 P653 infect details.Figure 18.16 P4184, six-level parent-child relationships, and P4184 nodes connec...Figure 18.17 Child nodes of Congregation and parent nodes of Congregation patien...Figure 18.18 Part of the decision tree based on the apriori algorithm.Figure 18.19 Association rule of data.Figure 18.20 Model comparison.Figure 18.21 ROC for decision tree classifier.Figure 18.22 Age-wise case distribution.Figure 18.23 Cases from Maharashtra.Figure 18.24 Indicating cluster and reason attribute.Figure 18.25 Primary contact tracing.Figure 18.26 New cases forecast and active cases forecast.Figure 18.27 New cases trend and weekly curve and active cases trend and weekly ...Figure 18.28 New, active, and sample test curve.Figure 18.29 Distribution of age.Figure 18.30 Distribution of days.Figure 18.31 PDF and CDF.Figure 18.32 Box plot for survival rate.Figure 18.33 Cases for 1 lakh population and ratio curve for total test and conf...Figure 18.34 Ratio curve of sample tests over new cases and ratio curve predicti...Figure 18.35 Parent-child spread curve and cases represented age-wise.Figure 18.36 Day-wise cure status.Figure 18.37 Gender-wise infection.Figure 18.38 Curve rate over at a time.Figure 18.39 Bangalore urban age-wise spread.Figure 18.40 Cases for one lakh population and primary contact spread of major d...Figure 18.41 Oversea patient’s district-wise count and patient from Maharashtra ...Figure 18.42 Parent-child of the patient from Maharashtra.Figure 18.43 Parent-child with a reason.Figure 18.44 Death trend with reason.

19 Chapter 19Figure 19.1 Our three-strata approach for building a strategic telemedicine plat...Figure 19.2 Depiction of the flowchart of the “Homecare” model for our suggested...Figure 19.3 Modus operandi post risk evaluation based on the Homecare model for ...Figure 19.4 Integration of important components of the information flow that hea...Figure 19.5 Workflow for the community model for the proposed design.Figure 19.6 Depiction of the objectives of a possible surveillance system of the...Figure 19.7 Illustration of a possible ‘contact tracing’ strategy for suspected ...Figure 19.8 Classification of sleep apnea according to the different causes of o...Figure 19.9 Illustration depicting how a person suffering from OSA different tha...Figure 19.10 Depiction of the proposed design to effectively work in detection o...

20 Chapter 20Figure 20.1 Systematic process of annotation (adapted from Behera, 2017).Figure 20.2 ILCI ANN App v. 2.0.Figure 20.3 Feature template of the SVM POS tagger model.Figure 20.4 Typological statistics of errors.Figure 20.5 A comparison of error rates between HMT and ABDT.

21 Chapter 21Figure 21.1 Layout of Natural Language Processing.Figure 21.2 Chronology of Natural Language Processing.Figure 21.3 Abbreviation and its expansion used in the above article.Figure 21.4 Levels of Natural Language Processing in healthcare.Figure 21.5 Use of Natural Language Processing in clinical research.Figure 21.6 Solution to the challenges in Natural Language Processing.