Numerous machine learning algorithms are based upon optimization. Unfortunately, optimization has not been fully exploited in machine learning. Each machine learning approach contains several hyper-parameters that may be tweaked to identify the optimization method through evolutionary computing and improvement. Multi-objective evolutionary optimization may assist in satisfying specific requirements for machine learning prototype enhancement. Machine learning algorithms use a dataset to construct a prediction and description framework that is both efficient and accurate. Multi-objective evolutionary optimization facilitates machine learning algorithms by optimizing their hyperparameters, which often compete with one another, and picking the optimal platform for a particular profession. Machine learning (ML) techniques seek to optimize the methods for extracting information from computer-processable forms. In particular, poor data quality may impair the effectiveness of a training method. However, data pre-processing is a critical operation inside the machine learning workflow, often accomplished by deleting superfluous items and characteristics. Relevant information evolutionary techniques have been developed to address four significant statistical and machine learning challenges, including data pre-processing, classification, clustering, and association rules.

Recent research has identified evolutionary computation also as a superior approach to tackling multi-objective optimization issues, yielding simultaneously optimum and diversified solutions to satisfy the capability of many other techniques. Besides, multi-objective optimization issues with entire solution domains, as encountered in real-world ML issues with many attributes. Furthermore, it could contribute to feature selection by minimizing and decreasing predictions' percentages. It enables the simultaneous imputation of raw data and the development of prediction and classification models while learning incomplete information. Moreover, it could recognize patterns that were not comparable in attributes and instructive about the labeling for semi-supervised clustering. It may choose the optimal training dataset with classification performance and percentage removal. Multi-objective evolutionary optimization may be used to construct adaptable machine learning models which handle many problems concurrently. Due to their statistical data analysis characteristics, machine learning methods have been extensively applied in healthcare systems during recent generations. Machine Learning is concerned with collecting information from various resources and media.

Despite its significant capacity for handling enormous amounts of information, data categorization remains a considerable challenge in healthcare. Nowadays, numerous individuals are confronted with these critical ailments that need rapid recognition to initiate treatment promptly. Several examples exist in which multiple dangerous illnesses may go undetected by professionals. Once a disease reaches a certain level, it may well be incurable. MOEO is feasible by using a variety of machine learning techniques. Numerous machine learning techniques are significantly more capable of accurately analyzing massive amounts of detailed medical information, hospital records, and medical imaging in a relatively short period. As is the case in several other sectors, machine learning techniques are commonly utilized to address similar circumstances in healthcare.

Topics include, but are not limited to:

• Deep Reinforcement Learning in MOEO using Machine Learning for Complex Healthcare Systems
• Performance analysis of MOEO in Machine Learning for Complex Healthcare Systems
• Advancement in Parallel MOEO approaches using Machine Learning for Complex Healthcare Systems
• Mathematical computational techniques for MOEO in Machine Learning for Complex Healthcare Systems
• Metaheuristics enabled MOEO algorithms using Machine Learning for Complex Healthcare Systems
• Decentralized edge intelligence for MOEO in Machine Learning for Complex Healthcare Systems
• An AI-based data-driven approach for MOEO in Machine Learning for Complex Healthcare Systems
• Data analytics for Multi-objective evolutionary optimization using Machine Learning for Complex Healthcare Systems
• Enhanced Predictive analysis in MOEO using Machine Learning for Complex Healthcare Systems
• Advanced manufacturing optimization for Evolutionary multi-objective optimization for Complex Healthcare Systems

IMPORTANT DATES

Submission Deadline: 20.11.2022
Authors Notification: 25.02.2023
Final notification: 26.07.2023

HOW TO SUBMIT

1) Before submission, authors should carefully read the Instructions for Authors www.degruyter.com/publication/journal_key/JISYS/downloadAsset/JISYS_Instruction%20for%20Authors.pdf
2) All submissions to the Special Issue must be made electronically via the online submission system https://mc.manuscriptcentral.com/jisys
3) All manuscripts will undergo the standard peer-review process (single-blind, at least two independent reviewers). When entering your submission via the online submission system, please choose the option "SI Multi-Objective Evolutionary Optimization".

Submission of a manuscript implies that the work described has not been published before and is not under consideration for publication anywhere else.

We are looking forward to your submission!

In case of any further questions, please contact:
Editorial Office (JISYS_Editorial@degruyter.com)