Manuscript Topics

The continuous popularization of artificial intelligence technology has given rise to intelligent systems, which refer to computer systems that can produce intelligent human behaviors. The intelligent systems can not only run on traditional Neumann computers but also the new generation non-Neumann computers. Due to better adaptability and flexibility, intelligent systems are expected to be applied to many cross-fields. Using mathematical symbols and formulas to describe different complex system processes, the complex decision-making processes can be realized instead of manual experience. Nowadays, mathematical modeling has become the main driving principle of intelligent systems. Typical cases include intelligent control systems, intelligent sensing systems, intelligent detection systems, etc.

The current mainstream mathematical modeling methods are mainly based on the knowledge of which domain mechanism is used to build specific mathematical models. However, this kind of knowledge-driven mathematical modeling method is facing bottlenecks, and it is difficult further to improve the modeling efficiency by simple model optimization. Knowledge-driven mathematical models often have complex parameter systems, which brings great difficulties to the continuous optimization of models. For this reason, data-driven mathematical modeling methods have recently been well-investigated by academia. They discover abstract patterns and implicit rules from massive historical data and build decision-makers that can execute expert actions, thus reducing the dependence on mechanism knowledge. However, without the support of mechanism knowledge, such pure data-driven mathematical modeling methods are still difficult to completely replace the role of knowledge-driven mathematical modeling methods.

Hence, data and knowledge-jointly-driven mathematical modeling have begun to receive extensive attention from many researchers in recent years. It is believed that their joint actions can make up for each other's limitations. However, how to achieve such a common effect still remains an important issue to be solved. This is because such complementarity cannot be realized only by a simple superposition of the two sides. It is necessary to study the independent interactive feedback and optimization frameworks for specific problem scenarios so as to achieve the effect of "one plus one is greater than two."

This special section invites scholars and researchers from different engineering technology fields to jointly explore data and knowledge-jointly driven mathematical modeling methods to construct advanced intelligent systems. The research and discussion of this special section, it is expected to solve the frontier and difficult problems in different engineering fields. Thus, it is expected to facilitate future research development of intelligent systems to make engineering technologies run automatically. The topics include but are not limited to:

• Data and knowledge-jointly driven mathematical modeling methods
• Data and knowledge-jointly driven human-computer interaction systems
• Data and knowledge-jointly driven smart decision systems
• Data and knowledge-jointly driven smart operation of engineering technologies
• Data and knowledge-jointly driven robotic systems/platforms
• Data and knowledge-jointly driven social computing systems
• Data and knowledge-jointly driven computer intelligent perception systems
• Data and knowledge-jointly driven energy control systems
• Data and knowledge-jointly driven IoT sensing systems
• Data and knowledge-jointly driven digital twins systems
• Data and knowledge-jointly driven enterprise information systems
• Data and knowledge-jointly driven autonomous cognitive systems

Instructions for authors
https://www.aimspress.com/mbe/news/solo-detail/instructionsforauthors
Please submit your manuscript to online submission system
https://aimspress.jams.pub/