Advanced Pattern Recognition Systems for Multimedia Data
1Nanjing University of Aeronautics and Astronautics, Nanjing, China
2Chongqing University, Chongqing, China
Advanced Pattern Recognition Systems for Multimedia Data
Description
Due to the development of cloud computing and the Internet and Internet of Things (IoT), a huge amount of multimedia data is now being generated. Multimedia data includes the combination of diverse content forms such as text, audio, images, video, animation, and interactive data. Recently, pattern recognition (PR) systems based on multimedia data have revolutionized modern industry and are widely applied in the fields of text recognition, audio and video analysis, automatic medical diagnosis, system anomaly detection, etc.
Based on correct models and high-quality and data, traditional PR systems can achieve appropriate recognition results. However, advanced pattern recognition (APR) systems are greatly needed, aiming to assist enterprise personnel to recognize potential problems, anomalies, system failures, and other hidden dangers earlier and more easily. APR systems present more advanced performance and analytical capabilities, including better few-shot learning, earlier recognition and prediction, root cause analysis, etc. However, there remain numerous challenges particularly in the implementation of these technologies in modern industry at low cost while designing APR systems.
The purpose of this Special Issue is to gather original research articles from both academia and industry on APR systems for multimedia data. We welcome articles particularly focusing on few-shot learning, predictive analytics, root cause analysis, and low-cost system implementation. Review articles discussing the current state of the art are also welcome.
Potential topics include but are not limited to the following:
- Multimedia data analysis and application
- Adaptive computing for multimedia data
- Applicable neural networks for multimedia data
- Few-shot learning systems
- Predictive analytics systems
- Root cause analysis systems
- Low-cost system implementation research
- Self-learning systems, software, and simulations
- Supervised and unsupervised learning methods
- Deep learning and machine learning system
- Reinforcement learning research
- Cross-domain feature learning and fusion research
- Feature extraction and representation research