Zhongming Zhao – författare

Biomedical engineering is a rapidly growing interdisciplinary area that is providing solutions to biological and medical problems and improving the healthcare system. It is connected to various applications like protein structure prediction, computer-aided drug design, and computerized medical diagnosis based on image and signal data, which accomplish low-cost, accurate, and reliable solutions for improving healthcare services. With the recent advancements, machine learning (ML) and deep learning (DL) techniques are widely used in biomedical engineering to develop intelligent decision-making healthcare systems in real-time. However, accuracy and reliability in model performance can be a concern in tackling data generated from medical images and signals, making it challenging for researchers and practitioners. Therefore, optimized models can produce quality healthcare services to handle the complexities involved in biomedical research.Various optimization techniques have been employed to optimize parameters, hyper-parameters, and architectural information of ML/DL models explicitly applied to biological, medical, and signal data. The swarm intelligence approach has the potential to solve complex non-linear optimization problems. It mimics the collective behavior of social swarms such as ant colonies, honey bees, and bird flocks. The cooperative nature of swarms can search global settings of ML/DL models, which efficiently provide the solution to biomedical engineering applications. Finally, the book aims to provide the utility of swarm optimization and similar optimization techniques to design ML/DL models to improve the solutions related to biomedical engineering.

Biomedical engineering is a rapidly growing interdisciplinary area that is providing solutions to biological and medical problems and improving the healthcare system. It is connected to various applications like protein structure prediction, computer-aided drug design, and computerized medical diagnosis based on image and signal data, which accomplish low-cost, accurate, and reliable solutions for improving healthcare services. With the recent advancements, machine learning (ML) and deep learning (DL) techniques are widely used in biomedical engineering to develop intelligent decision-making healthcare systems in real-time. However, accuracy and reliability in model performance can be a concern in tackling data generated from medical images and signals, making it challenging for researchers and practitioners. Therefore, optimized models can produce quality healthcare services to handle the complexities involved in biomedical research.Various optimization techniques have been employed to optimize parameters, hyper-parameters, and architectural information of ML/DL models explicitly applied to biological, medical, and signal data. The swarm intelligence approach has the potential to solve complex non-linear optimization problems. It mimics the collective behavior of social swarms such as ant colonies, honey bees, and bird flocks. The cooperative nature of swarms can search global settings of ML/DL models, which efficiently provide the solution to biomedical engineering applications. Finally, the book aims to provide the utility of swarm optimization and similar optimization techniques to design ML/DL models to improve the solutions related to biomedical engineering.

In today’s data-driven world, biology and medicine are being transformed by the power of big data. Making sense of large, complicated biological datasets is a crucial problem that underlies every medical advancement and gene discovery. Feature Selection and Feature Extraction on Omics Data provides insight into this innovative area where biological science and computational science collide. This book, which is written in an approachable manner, explains the methods researchers employ to sort through vast amounts of multi-omics data to find insights that may result in better treatments, early disease diagnosis, and a greater comprehension of life at the molecular level. This volume provides a unique look at the technologies influencing the future of biological discovery and customized medicine, making it the perfect choice for anyone interested in learning more about how AI and data science are transforming biology and health.This collection explores cutting-edge feature selection and extraction methods across a broad range of omics data formats, such as metagenomics, genomics, transcriptomics, epigenomics, and datasets. Readers will learn how these techniques can be used to improve disease classification, find promising biomarkers, uncover significant biological patterns, and aid in early diagnosis. The chapters discuss techniques designed to regulate sparsity, minimize dimensionality, and preserve biological interpretability while fusing fundamental ideas with practical applications. Case studies and real-world applications show how these methods enhance computational models’ performance in tasks like disease prediction and gene identification. This book is a great resource whether you’re new to omics data analysis or looking to improve your current workflows using sophisticated feature engineering techniques. It connects theory and application with contributions from subject matter experts to assist readers in converting unprocessed data into biologically significant insights, making it an essential resource in contemporary computational biology and precision medicine.This book offers a comprehensive exploration of cutting-edge methodologies designed to address the complexities of high-dimensional biological datasets. This book serves as a practical and theoretical guide for researchers, data scientists, and students working at the intersection of bioinformatics and machine learning.This book is a comprehensive and application-focused approach to one of the most pressing challenges in modern bioinformatics: making sense of high-dimensional omics data. While many resources touch on machine learning or biological datasets in isolation, this book bridges the two, offering a unified, practical guide that combines theoretical depth with real-world implementation across diverse omics domains—including genomics, metagenomics, transcriptomics, and epigenomics data.

This reference text analyzes the integrated model of artificial intelligence, deep learning, and cloud computing for various bioinformatic problems including gene signature discovery, rare cell detection, disease classification, and rare disease detection. It discusses biomedical image processing, and deep learning integrated tools for stage detection of critical diseases like cancer.This book:Presents a comparative study of gradient boosted classifier and deep learning classifier for disease classification of multi-omics sequencing data. Showcases biomarker discovery and differential expression analysis in Single-cell RNA sequencing data through the integrated model of data imputation, feature selection, and cell clustering. Explains artificial intelligence, machine learning, and integrated models for DNA methylation and gene expression data analysis, and disease classification. Covers the fundamentals of artificial intelligence, machine learning, deep learning, and cloud computing tools in bioinformatics.Explores the rare cell detection, and transcriptomic analysis in single-cell RNA sequencing. It is primarily written for senior undergraduates, graduate students, and academic researchers in electrical engineering, electronics and communications engineering, computer science and engineering, and biomedical engineering.