Prof. Xingsi Xue

Email: xue.xingsi@fjut.edu.cn

Affiliation: Fujian Provincial Key Laboratory of Big Data Mining and Applications, Fujian University of Technology, Fuzhou, China

Homepage: 

Research Interests: semantic web, knowledge engineering, ontology, matching intelligent computation

Prof. Jeng-Shyang Pan

Email: jengshyangpan@gmail.com

Affiliation: College of Artificial Intelligence, Nanjing University of Information Science and Technology, Nanjing, China

Homepage: 

Research Interests: information hiding, image signal processing, computational intelligence, wireless sensor networks

Assist. Prof. Jun Yu

Email: yujun@ie.niigata-u.ac.jp

Affiliation: Institute of Science and Technology, Niigata University, Niigata, Japan

Homepage: 

Research Interests: artificial intelligence, artificial neural network

Prof. Wellington P. Santos

Email: wellington.santos@ufpe.br

Affiliation: Departamento de Engenharia Biomédica, Universidade Federal de Pernambuco, Recife, Brazil

Homepage: 

Research Interests: biomedical engineering, artificial intelligence

Dr. Nan Li

Email: linan10@sxu.edu.cn

Affiliation: School of Computer and Information Technology, Institute of Big Data Science and Industry, Shanxi University, Taiyuan, China

Homepage: 

Research Interests: neural architecture search, performance predictor, feature selection, ordinal learning, evolutionary computation

---

Summary

Automated Machine Learning (AutoML) and Neural Architecture Search (NAS) are transforming the development of intelligent systems by enabling end-to-end automation of model design, optimization, and deployment. Instead of relying on manual trial-and-error, these techniques provide computable, scalable, and engineering-oriented solutions for building high-performance models under complex constraints. Such capabilities are particularly important for modern intelligent systems that must operate across heterogeneous environments, including cloud platforms, edge devices, cyber-physical systems, and real-world industrial applications.

This special issues focuses on end-to-end intelligent system design driven by AutoML and NAS, with an emphasis on engineering deployment, scalable algorithms, and practical implementation. We aim to bring together recent advances in automated architecture design, multi-objective optimization, system-level learning, resource-aware computing, and reliable AI deployment. Contributions addressing real-world applications, efficient computation, and reproducible system frameworks are especially encouraged. Topics of interest include, but are not limited to:
· AutoML algorithms for engineering applications;
· Neural architecture search for scalable systems;
· Multi-objective and resource-aware optimization;
· Automated model deployment;
· Edge and distributed learning;
· Trustworthy and robust AI systems;
· AutoML for industrial and software engineering applications;
· End-to-end intelligent system integration.

---

Keywords

AutoML, neural architecture search, end-to-end intelligent systems, scalable machine learning, engineering deployment