Improving the Analysis of Context-Aware Information via Marker-Based Stigmergy and Differential Evolution

We use the marker-based stigmergy, a mechanism that mediates animal-animal interactions, to perform context-aware information aggregation. In contrast with conventional knowledge-based models of aggregation, our model is data-driven and based on self-organization of information. This means that a functional structure called track appears and stays spontaneous at runtime when local dynamism in data occurs. The track is then processed by using similarity between current and reference tracks. Subsequently, the similarity value is handled by domaindependent analytics, to discover meaningful events. Given the changeability of human-centered scenarios, the overall process is also adaptive, thanks to parametric optimization performed via differential evolution. The paper illustrates the proposed approach and discusses its characteristics through two real-world case studies.