한국통신학회 KICS

In recent years, the theory and applications of artificial intelligence (AI) driven information and communication technology (ICT) have developed rapidly, which bring a great deal of achievements in the fields of commerce, industry, education, agriculture, etc. However, most current studies are heavily based on large scale of labeled dataset, with a high cost of data collection and annotation. As a necessary supplement, the few-shot learning aims to learn from limited labeled data to obtain the generalized model. Therefore, the data quality and security have been becoming attractive and important for both big data for deep learning and small data for few-shot learning. Instead of crudely using large amounts of redundant data, data information analysis and efficient learning with limited samples perhaps make more sense for specific real-world ICT tasks. The future ICT systems should mine high-quality data for the real-world applications and take data security into account seriously, in both deep learning and few-shot learning forms. The aim of this Special Issue is to collect research focusing on advanced few-shot learning and deep learning, committed to providing solutions for commercial, industrial, or educational problems, especially on aspects of data mining and information evaluation. It aims to call for the state-of-the art research results in the theories, algorithms, models, systems, and applications of data analysis. The original research and review articles are both welcomed.

Topics of interest for this special section include but are not limited to the following:

• ​ New blockchain backbone network and protocol for content protection

• ​Data security and privacy in the AI-driven information systems

• ​Data mining and information evaluation for AI-based applications

• ​Advanced framework of few-shot learning and deep learning

• ​New techniques and theory for few-shot learning systems

• ​Multi-source data fusion for deep learning-based systems

• ​​Cloud computing for deep learning or few-shot learning

• ​Information extraction and evaluation from images and videos

• ​Model acceleration and edge computing based on AI methods

• ​Special hardware deployments, such as FPGA, Mobile phone

• ​Software packages of advanced deep learning or few-shot learning

• ​Specific applications, e.g., recommendation systems, anomaly detection, autonomous driving, smart agriculture, game decision-making, industrial quality inspection, etc

Guest Editors:

Dr. Jiachen Yang, Tianjin University, China, yangjiachen@tju.edu.cn

Dr. Houbing Song, Embry-Riddle Aeronautical University, USA, songh4@erau.edu 

Dr. Yang Li, Shihezi University, China, liyang328@shzu.edu.cn

Prof. Jong-Hyouk Lee, Sejong University, Republic of Korea, jonghyouk@sejong.ac.kr

Prof. Ilsun You, Soonchunhyang University, Republic of Korea, isyou@sch.ac.kr

Schedule (Tentative):

February 28, 2022: Paper submission deadline (Extended). PDF format with MS word or Latex source to ICT Express website

April 30, 2022: Reviews returned to authors

May 31, 2022: Final revised manuscript due

June 30, 2022: Final decision due

September 30, 2022: Publication date

Submission Procedure:

Submissions should follow the author instruction available at http://www.journals.elsevier.com/ict-express. The journal invites short-length (up to 6 pages in double columns) high-quality, original research articles that explicitly address the unique technical challenges encountered in the convergence of information and communication technology. ICT Express accepts review papers without page limits. However, we strongly recommend keeping the page count under 12 pages in double columns for ease of readability. Papers published in the ICT Express are indexed in Directory of Open Access Journals (DOAJ), Science Direct, and SCIE (Science Citation Index Expanded). For any questions, please contact the lead guest editor Prof. Jiachen Yang.​