Some Real-world Applications of Soft Artificial Intelligence: Scientogram Mining, Assembly Line Balancing, and Forensic Identification

摘要

Soft artificial intelligence methods keep on tackling classical artificial intelligence problems such as heuristic search, knowledge representation, and machine learning. In this lecture we will review three different real-world applications solved by means of modern heuristic search techniques (metaheuristics) as well as by the use of fuzzy sets to represent the inherent imprecission of the available knowledge. First, the analysis and comparison of visual science maps (scientograms) will be tackled as a single- and multiobjective graph mining task, both using the classical Subdue method based on a beam search and extended variants based on evolutionary multiobjective optimization.