ICMS 2019

 

 

Location: Fukuoka International Congress Center, Fukuoka, Japan

Conference Date:  July 19-22, 2019

Speaker:  Professor Mario Köppen

Professor Mario Köppen

Editor in Chief, Applied Soft Computing (ASOC)
Editor in Chief, International Journal of Soft Computing and Networking (IJSCN)
Associate Editor, The International Journal of Hybrid Intelligent Systems (IJHIS)

Professor
Department of Computer Science and Electronics
Graduate School of Creative Informatics
Kyushu Institute of Technology. Japan

Tentative Title : Human-Centered Computing: Paradigms, Applications and Products

Abstract

These days, complex food supply chains, characterized by the production, distribution, transport, processing, retail and consumption of food get more and more entitled to various risks: contamination, domino effects caused by the inherent push&pull two-sided causality, contamination propagation (incl. virus spread), resource depletion, origination and quality disputes. Here, farming is not only farm production of food at some location, but has to be seen by its effects on the whole chain. This is a challenge for any novel concept of smart farming. We discuss the various stages and the related technology challenges.


 The novel viewpoint here is to take on the documentation of the whole system. The documentation aspects in more detail refer to: new sensors data logs, incl. polarization, thermal, multi-spectral imaging and wearables integration, incl. hierarchical classification and prediction tasks; security, esp. the tracking of ingredients mixtures, or the special multi-factor and small scale modality of blockchain technology. Further on, we need to explore new computational intelligence solutions for the task of retrieval of data to give it into the hand of consumers, a broad avenue for fuzzy information processing. Novel optimization approaches are needed for the interplay of the various optimization modalities of the food system: farmers’ “look after things” as a correction-driven cognitive ability of humans, scheduling with respect to distribution and transport stage, efficiency and non-physical optimization for the processing and manufacturing stage, and the price-driven retail and consumption stage. All those tasks have been studied in perfect isolation so far, but to keep them in a global balance poses new requirements on optimization algorithms. We might take inspiration from the microbiome and how it achieves it’s task to keep an organism up and running. As a last step, how about moving the food system from a chain to a circle and base it on circular economy, to tackle the problem of incentives driving the system and avoid future harm caused by the classical domino effect?


 The whole story has just opened its first chapter. But we have already promising technology at hand, incl. Big Data and IoT, global communication, low cost sensors, and Computational Intelligence. Those can surely support to move away from the isolated efficiency race per food system stage to the safety-oriented, open, holistic and versatile documentation point of view towards the design and conception of a future smart farming system.

Professor Xiaoyi Jiang

Professor Xiaoyi Jiang

Department of Computer Science 

University of Münster, German

Editor-in-Chief, 

International Journal of Pattern Recognition and Artificial Intelligence 

Tentative Title

Consensus Learning

Abstract

Consensus problems in various forms have a long history in computer science. In pattern recognition, for instance, there are no context- or problem-independent reasons to favor one classification method over another. Therefore, combining multiple classification methods towards a consensus decision can help compensate the erroneous decisions of one classifier by other classifiers. Practically, ensemble methods turned out to be an effective means of improving the classification performance in many applications. In general, this principle corresponds to combining multiple models into one consensus model, which helps among others reduce the uncertainty in the initial models. Consensus learning can be formulated and studied in numerous problem domains; ensemble classification is just one special instance. This talk will present an introduction to consensus learning. In particular, the focus will be the formal framework of so-called generalized median computation, which is applicable to arbitrary domains. The concept of this framework, theoretical results, and computation algorithms will be discussed. A variety of applications in pattern recognition and other fields will be shown to demonstrate the usefulness of consensus learning.