Mining intricate temporal rules for recognizing complex activities of daily living under uncertainty

Daily living activity recognition can be exploited to benefit mobile and ubiquitous computing applications. Techniques so far are mature to recognize simple actions. Due to the characteristics of diversity and uncertainty in daily living applications, most existing complex activity recognition approaches have notable limitations. First, graphical model-based approaches still lack sufficient expressive power to model rich temporal relations among activities. Second, it would be rather difficult for graphical model-based approaches to build a unified model for achieving multiple types of tasks. Third, current semantic-based approaches often fail to capture uncertainties. Fourth, formulae in these semantic-based approaches are often manually encoded. Meanwhile, it is impractical to handcraft each formula accurately in daily living scenarios where temporal relations among activities are intricate. To address these issues, we present a probabilistic semantic-based framework that combines Markov logic network with 15 temporal and hierarchical relations to explicitly perform diverse inference tasks of daily living in a unified manner. Advanced pattern mining techniques are introduced to automatically learn the propositional logic rules of intricate relations as well as their weights. Experimental results show that by logical reasoning with the mined temporal dependencies under uncertainty, the proposed model leads to an improved performance, particularly when recognizing complex activities involving the incomplete or incorrect observations of atomic actions.