KC Santosh

To better understand the dynamics of human reproduction, this book identifies various factors that influence fertility, including the male and female reproductive systems, lifestyle choices, career demands, societal pressures, environmental factors, and personal habits (e.g., millennials).

Employing off-the-shelf machine learning models is not an innovation. The journey through technicalities and innovation in the machine learning field is ongoing, and we hope this book serves as a compass, guiding the readers through the evolving landscape of artificial intelligence. It typically includes model selection, parameter tuning and optimization, use of pre-trained models and transfer learning, right use of limited data, model interpretability and explainability, feature engineering and autoML robustness and security, and computational cost – efficiency and scalability. Innovation in building machine learning models involves a continuous cycle of exploration, experimentation, and improvement, with a focus on pushing the boundaries of what is achievable while considering ethical implications and real-world applicability. The book is aimed at providing a clear guidance that one should not be limited to building pre-trained models to solve problems using the off-the-self basic building blocks. With primarily three different data types: numerical, textual, and image data, we offer practical applications such as predictive analysis for finance and housing, text mining from media/news, and abnormality screening for medical imaging informatics. To facilitate comprehension and reproducibility, authors offer GitHub source code encompassing fundamental components and advanced machine learning tools.

Employing off-the-shelf machine learning models is not an innovation. The journey through technicalities and innovation in the machine learning field is ongoing, and we hope this book serves as a compass, guiding the readers through the evolving landscape of artificial intelligence. It typically includes model selection, parameter tuning and optimization, use of pre-trained models and transfer learning, right use of limited data, model interpretability and explainability, feature engineering and autoML robustness and security, and computational cost – efficiency and scalability. Innovation in building machine learning models involves a continuous cycle of exploration, experimentation, and improvement, with a focus on pushing the boundaries of what is achievable while considering ethical implications and real-world applicability. The book is aimed at providing a clear guidance that one should not be limited to building pre-trained models to solve problems using the off-the-self basic building blocks. With primarily three different data types: numerical, textual, and image data, we offer practical applications such as predictive analysis for finance and housing, text mining from media/news, and abnormality screening for medical imaging informatics. To facilitate comprehension and reproducibility, authors offer GitHub source code encompassing fundamental components and advanced machine learning tools.

Future epidemics are inevitable, and it takes months and even years to collect fully annotated data. The sheer magnitude of data required for machine learning algorithms, spanning both shallow and deep structures, raises a fundamental question: how big data is big enough to effectively tackle future epidemics? In this context, active learning, often referred to as human or expert-in-the-loop learning, becomes imperative, enabling machines to commence learning from day one with minimal labeled data. In unsupervised learning, the focus shifts toward constructing advanced machine learning models like deep structured networks that autonomously learn over time, with human or expert intervention only when errors occur and for limited data—a process we term mentoring. In the context of Covid-19, this book explores the use of deep features to classify data into two clusters (0/1: Covid-19/non-Covid-19) across three distinct datasets: cough sound, Computed Tomography (CT) scan, and chest x-ray (CXR). Not to be confused, our primary objective is to provide a strong assertion on how active learning could potentially be used to predict disease from any upcoming epidemics. Upon request (education/training purpose), GitHub source codes are provided.

AI has contributed a lot and biometrics is no exception. To make AI solutions commercialized/fully functional, one requires trustworthy and explainable AI (XAI) solutions while respecting ethical issues. Within the scope of biometrics, the book aims at both revisiting ethical AI principles by taking into account state-of-the-art AI-guided tools and their responsibilities i.e., responsible AI. With this, the long-term goal is to connect with how we can enhance research communities that effectively integrate computational expertise (with both explainability and ethical issues). It helps combat complex and elusive global security challenges that address our national concern in understanding and disrupting the illicit economy.

This book discusses and evaluates AI and machine learning (ML) algorithms in dealing with challenges that are primarily related to public health. It also helps find ways in which we can measure possible consequences and societal impacts by taking the following factors into account: open public health issues and common AI solutions (with multiple case studies, such as TB and SARS: COVID-19), AI in sustainable health care, AI in precision medicine and data privacy issues. Public health requires special attention as it drives economy and education system. COVID-19 is an example—a truly infectious disease outbreak. The vision of WHO is to create public health services that can deal with abovementioned crucial challenges by focusing on the following elements: health protection, disease prevention and health promotion. For these issues, in the big data analytics era, AI and ML tools/techniques have potential to improve public health (e.g., existing healthcare solutions and wellness services). In other words, they have proved to be valuable tools not only to analyze/diagnose pathology but also to accelerate decision-making procedure especially when we consider resource-constrained regions.

Deep Learning Models for Medical Imaging explains the concepts of Deep Learning (DL) and its importance in medical imaging and/or healthcare using two different case studies: a) cytology image analysis and b) coronavirus (COVID-19) prediction, screening, and decision-making, using publicly available datasets in their respective experiments. Of many DL models, custom Convolutional Neural Network (CNN), ResNet, InceptionNet and DenseNet are used. The results follow ‘with’ and ‘without’ transfer learning (including different optimization solutions), in addition to the use of data augmentation and ensemble networks. DL models for medical imaging are suitable for a wide range of readers starting from early career research scholars, professors/scientists to industrialists.