AIMS AND SCOPE
Recent development in ICT and sensor devices brings us a new form of intelligent systems called Cyber-Physical System (CPS). In CPS, physical entities (e.g. humans, robots, cars, factories, houses, etc.) interact and communicate with other entities in both physical- and cyber-worlds. The information processed in cyber-physical worlds are video images, sounds, texts (documents, tweets, e-mails, etc.), control signals, sensor data, etc. and such data are continuously generated as stream data. The data include not only explicit information of physical entities such as location and moving direction, but also implicit information such as health conditions, emotion, and behaviors, which should be extracted from original sensor data. For this purpose, autonomous machine learning methods that can learn from high-dimensional stream data is solicited for CPS.
The purpose of this special session is to share new ideas to develop autonomous learning methods from stream data in cyber-physical worlds. A wide range of learning methods and applications of cyber-physical systems is covered in this special session including but not limited to the followings:
[Methodology]
- Supervised / Unsupervised Learning
- - Online / Incremental Learning
- - Online Feature Selection / Extraction
- Online Feature Selection
- - Online Clustering
- - Active Learning
- - Data Mining
- - Text Mining
- - Time-Series Analysis
[Applications]
- - Human-Robot Interactions
- - Smart Grids, Smart City, Smart Home, Smart Agriculture, etc.
- - Social Network Analysis (e.g. sentimental analysis, user profiling, etc.)
- - Cybersecurity
- - Opinion Mining
- - - Emotion/Behavior Mining
- - - Person Attitude Mining
- - - Realty Mining