Applied Smart Health Care Informatics. Группа авторов

Чтение книги онлайн.

СКАЧАТЬ high throughput data can help solving them. Next, an in depth overview of machine learning techniques of computing and learning methods that can be used in a variety of sequencing data analyses is provided.

      Cancer is one of the most devastating diseases worldwide. It affects nearly every household, although cancer types are prevalent in different geographical regions. One example is breast cancer, which is the most common type of cancer in women worldwide. Therefore, prevention strategies are needed to address this issue. Identifying risk factors of breast cancer is crucial since it allows physicians to acquaint them with the risks. Accordingly, physicians can recommend precautionary actions. In the first part of Chapter 6, the authors detail the discovery of significant rules for breast cancer patients, focusing on different ethnic groups. Predicting the risk of the occurrence of breast cancer is an essential issue for clinical oncologists. A reliable prediction will help oncologists and other clinicians in their decision‐making process and allow clinicians to choose the most reliable and evidence‐based treatment. In the second part of the chapter, a super learner or stacked ensemble technique is employed to the breast cancer data set obtained from the Breast Cancer Surveillance Consortium (BCSC) database. A comparison of the performance of the super learner and the individual base learners is conducted. The results of the first part of this study (rule extraction from breast cancer patients in distinct ethnic groups) found well‐known ethnic disparities in cancer prevalence. The experimental results revealed that the produced rules hold the highest confidence level. The crucial rules, which can be easily understood, are also interpreted.

      Negative‐stain transmission electron microscopy (TEM) is considered a fundamental approach for virus detection and identification. In this context, Chapter 7 presents a new architecture, based on neuro‐rough hybridization, for the analysis of TEM images. It assumes that a specific local descriptor at a given scale may be relevant in classifying a particular pair of virus classes but may not be able to encapsulate the inherent characteristics of another pair of classes. Important features from class‐pair relevant descriptors are, therefore, first identified using the rough hypercuboid approach, and then discriminatory features are learned using the contrastive divergence algorithm of the restricted Boltzmann machine (RBM). Finally, a support vector machine (SVM) with a linear kernel is adopted to categorize the TEM images into one of the known virus classes. The proficiency of the proposed approach with respect to several state‐of‐the‐art methods was established on a publicly available, benchmark Virus data set.

Computer vision plays a substantial role in health care applications such as the diagnosis of diseases and planning for treatment. Brain tumors are severe conditions that may be deadly if not detected and treated early. In India, brain tumors occur in five to ten people per one lakh population (100 000 people). Deep learning is a category of artificial intelligence that does not require any human intervention to learn the features. Deep learning algorithms learn the features of images on their own and are capable of learning more complex features from the images. While characterizing the deep neural networks, the selection of optimizers plays a vital role. Optimizers are used to minimize the loss function by varying the weights and learning rate attributes of the neural network. Optimization algorithms are essential for producing more accurate results by reducing the loss function of the neural network. In Chapter 8, the authors have analyzed popular optimizers such as sgd, adam, rmsprop, adagrad, adadelta, adamax, and nadam used with artificial neural network systems in the proposed work. Two models, a simple artificial neural network (ANN) model and a convolutional neural network (CNN) model, have been considered. Each optimizer is executed with these two models to classify abnormal slices from magnetic resonance imaging (MRI) of human brain scans. The BraTS2013 and WBA data sets were used for training and testing the models. The accuracies of every model were recorded to analyse the optimizer's performance.

      In Chapter 9, a machine learning approach is proposed to predict whether the given brain MRI scans are normal or abnormal. This prediction is needed for treatment planning and diagnosis. The proposed method makes use of the bilateral symmetric nature of the human brain by splitting it into the left and right hemispheres (LHS and RHS) to extract the feature differences between the hemispheres. A feature set of 763 x 39 dimensions are created as the input for the classification model. Among these 39 features, 16 were selected by the Pearson's correlation coefficient to have correlation value greater than 0.3. To train the model, six tumor volumes from the BraTS2013 and two normal volumes from the IBSR‐18 data sets were used. For testing the model, 11 tumor volumes from the BraTS2013 and two normal volumes from the IBSR‐18 data sets were used. The k‐nearest neighbourhood (KNN) model was trained using the training data and the prediction done on the test data. A stratified k‐fold cross‐validation was used to validate the proposed model. The proposed model was analysed in terms of false alarm (FA), missed alarm (MA), and accuracy (ACC) for performance. The results showed that the proposed model yielded a 98 and 95.6% accuracy on the validation and testing data, respectively.

      Chapter 10 draws a line of conclusion on the future aspects of healthcare informatics while stressing the need for the effective management of healthcare resources.

      This volume will benefit several categories of students and researchers. At the student level, this volume can serve as a treatise/reference book for the special papers at the master's level aimed at inspiring future researchers. Newly inducted PhD aspirants would also find the contents of this volume useful as far as their compulsory coursework is concerned. At the researchers' level, those interested in interdisciplinary research would also benefit from the volume. After all, the enriched interdisciplinary contents of the volume will always be a subject of interest to the faculties, existing research communities, and new research aspirants from diverse disciplines of the concerned departments of premier institutes across the globe.

Cooch Behar, India	Sourav De
Ranchi, India	Rik Das
Bengaluru, India	Siddhartha Bhattacharyya
Kolkata, India	Ujjwal Maulik
December, 2021

About the Editors

      Dr. Sourav De completed his bachelor's in information technology at The University of Burdwan, Burdwan, India in 2002. He earned his master's in information technology from The West Bengal University of Technology, Kolkata, India in 2005. He completed his PhD in Computer Science and Technology at the Indian Institute of Engineering & Technology, Shibpur, Howrah, India in 2015. He is an Associate Professor in the Computer Science & Engineering Department at the Cooch Behar Government Engineering College, West Bengal. Before 2016, he was an Assistant Professor for more than ten years in the Department of Computer Science and Engineering and Information Technology of the University Institute of Technology, The University of Burdwan, Burdwan, India. He served as a Junior Programmer at the Apices Consultancy Private Limited, Kolkata, India in 2005. He is a co‐author of one book, the co‐editor of twelve books, and has more than 54 research publications in internationally reputed journals, international books, and international IEEE conference proceedings as well as five patents in his name. Dr. De has served as a reviewer for several international IEEE conferences and on several international editorial books. He has also served as a reviewer at reputed international journals such as Applied Soft Computing, Elsevier, BV, Knowledge‐Based Systems, Computer Methods in Biomechanics and Biomedical Engineering Imaging & Visualization, Inderscience Journals, etc. He has been a member of organizing and technical СКАЧАТЬ