Emerging Topics in Evolutionary Machine Learning for Big Data Processing and Analytics

Dear Colleagues,

With the explosion of the Internet and social media technologies, a large amount of data is generated from various devices, systems and applications. Big data is being used to better understand consumer habits and target marketing campaigns, improve operational efficiency and lower costs, and reduce risk.

However, challenges, including both data processing and data analysis exist in large-scale practical applications with few solutions to handle processing large amounts of data. Specifically, in data fusion, multi-modal data with multi-source and heterogeneous characteristics, including text, image and video, and data features with high-dimensional redundancy in feature selection represent a challenge to the current processing and analysis capabilities. In most situations, a variety of techniques have been applied to multi-model data and data feature selection, such as classification algorithm, gradient descent algorithm, and heuristic search. However, most existing methods still require human expert knowledge and high computational cost.

Therefore, an efficient adaptive learning and parameter training technique is needed to better solve these problems in big data processing and analytics. Recently, a kind of automatic design technology, termed as the evolutionary machine learning (EML) method, is attracting more and more attention from global researchers. As an enhanced ML, EML integrates the advantages of both ML and evolutionary computation (EC) to have the powerful potential to show excellent automatic design for addressing the big data analytic problems. On the one hand, EML, as an excellent automatic fusion of heterogeneous data and processing of multimodal and multidimensional data methods, shows significant merits in automatic algorithm optimization and framework design. On the other hand, EML can not only help obtain the optimal network parameter setting as the input of different data features but makes exploring complicated search data more excellent than the traditional algorithm. More than that, the EML algorithm shows good scalability and an easy to parallelize nature when a dataset increases in size. Therefore, it is of great interest to investigate the role of the EML technique in solving different data features and structures in big data processing and analytic problems.

This Special Issue aims to bring together both experts and newcomers from either academia or industry to discuss new and existing issues concerning EML and big data, in particular, to the integration between academic research and industry applications, and to stimulate further engagement with the user community. Potential topics include, but are not limited to: 

• EML system modeling and optimization; 
• Scalable EML architecture for big data; 
• EML for multi-objective optimization; 
• EML for hyperparameters optimization; 
• EML for high-dimensional and large-scale big data analytics; 
• EML for expert systems optimization; 
• EML for big data management for different scenarios; 
• EML by big data-driven; 
• EML for feature engineering; 
• Evolutionary search-based neural network architecture search; 
• EML for big data visualization and visual data analytics.

Prof. Dr. Lianbo Ma
Dr. Shangce Gao
Dr. Chaomin Luo
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 250 words) can be sent to the Editorial Office for assessment.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Applied Sciences is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.