Aim and scope
Emerging Internet-of-Things (IoT) applications in various fields, including smart city, smart home, smart grid, e-health, smart transportation, etc., critically require trustworthy networking solutions that are resilient against high mobility, high density, disasters, infrastructure failures, cyberattacks, and other disruptions. The networking framework should be capable of providing more secure in addition to more reliable and efficient communications in various network environments. Especially for the performance-sensitive and mission-critical applications, such as remote surgery and autonomous driving, more trustworthy and intelligent networking solutions are in urgent need.
Two main challenges exist in enforcing trustworthy IoT. The first challenge comes from the spatial diversity of the entities involved in communications, such as the high mobility of nodes, the large amount of devices, and the limitations of propagation media and other resources. The second challenge is due to the varying temporal features of the environment. Due to the spatial challenges, the connectivity between network nodes could be unreliable, and therefore the information maintained at each node could be inaccurate, which requires trustworthy solutions that are able to handle the dynamic, imprecise and uncertain information. This can possibly be solved by using computational intelligence (CI) technologies such as fuzzy logic and evolutionary computation. On the other hand, big data-based approaches, including deep neural networks, could facilitate data-driven prediction and performance improvement by capturing time-dependent properties of network elements such as user traffics and behaviours. However, the IoT data can be highly dimensional, heterogeneous, complex, unstructured and unpredictable. The challenges in analysing “IoT big data” call for CI technologies which are expected to provide efficient and powerful tools that scale well with data volume for IoT big data analytics and process, while addressing the challenges brought by the massive amount of data.
This workshop will focus on the technical challenges and the synergistic effect of big data and CI for IoT. While computational intelligence technologies can achieve a flexible and self-evolving system design, big data can facilitate the use of deep neural networks which is possible to learn the best strategy from complex data. It is envisioned that the combination of big data with a large collection of CI algorithms will reach the level of true artificial intelligence in IoT.