Call for Papers — Meta Learning for Internet of Multimedia Things
Special Issue on Meta Learning for Internet of Multimedia Things
International Journal of Machine Learning and Cybernetics
Open for submissions until October 15 2021
Artificial Intelligence is in transition as the fast convergence of digital technologies and data science holds the promise to liberate consumer data and provide a faster and more cost-effective way of improving human initiatives. Particularly, Artificial Intelligence (AI) is heavily influencing Internet of Multimedia Things (IoMTs) nowadays. The AI driven-based Internet of Multimedia Things have the potential to reshape the expectations of human’s actions, the way that companies’ stakeholders collaborate, and revamp business models in the various industries.
However, the use of AI driven-based Internet of Multimedia Things comes with its concerns that lead user with distrust and ethical concerns. With inappropriate use of AI widespread access to consumer-generated information has brought negative impacts to individuals, organizations, industries, and society. For example, the collection and utilization of training data by AI algorithms give rise to serious issues where consumers could suffer from privacy invasion, fraud, ineffective and offensive or lack of control over IoMTs applications. If such ethical dilemma and concerns are not being correctly addressed when implementing meta for Internet of Multimedia Things, not only it will generate negative impacts on the general public, but also may lead to the potential loss of credibility for products, brands and hamper the company’s reputation.
To tackle these challenges, the data protection regulations in many countries have come into force such as the Data Protection Act 2018, which is the UK’s implementation of the General Data Protection Regulation (GDPR) formulated by the European Union, and Act on the Protection of Personal Information (APPI) in Japan. These regulations have the potential to improve consumers’ confidence in sharing personal information with engineers in the development of autonomous vehicles. Nevertheless, it may become a possible solution to study general AI for IoMTs. Although there are many researches and advancements on meta-learning, less work is for IoMTs applications. The general AI solutions (e.g., meta-learning) for different devices-based IoMT applications are especially needed in the future cyber-physical-based world.
This special issue aims to explore recent advances and disseminate state-of-the-art research related to meta-learning on designing, building, and deploying novel meta learning-based multimedia processing methods. Meta-learning is an exhilarating research domain in the field of pattern recognition right now. The current work on meta-learning focuses around neural networks and deep learning. Neural networks are powerful, generic, and versatile tools to learn relationships between inputs and outputs. However, manually designing a neural network is difficult because the search space of all possible networks can be combinatorically large. Luckily, meta-learning can help to reduce the burden of finding the best configuration of a neural network for a specific problem using machine learning for this process itself. Therefore, meta-learning is perfectly solving the recent deep learning algorithms’ issues. With plenty of research papers and advancements, meta-learning is clearly making a major breakthrough in machine learning. In this special issue we will report the progress of the achievements in this field.
- Fundamental issues in Meta Learning
- Novel theoretical insights on responsible AI, such as Siamese networks, prototypical networks.
- Responsible data collection and augmentation
- Zero-shot/metric/few-shot/meta learning for object recognition
- Explainable AI and soft computing for IoMTs
- Responsible data-driven AI for IoMTs
- Meta learning in image/video segmentation
- Meta learning in classification/tracking
- Edge computing in Future networks (5G, 6G etc.)
Dr Huimin Lu, Kyushu Institute of Technology, Japan
Dr Yichuan Wang, University of Sheffield, UK
Dr Yujie Li, Yangzhou University, China
Manuscript submission: October 15 2021Notification to authors: December 15 2021
Revised manuscripts due: March 15 2022
Final editorial decision: April 15 2022
Final papers due: June 15 2022