Deep neural network-based fusion model for emotion recognition using visual data

The Journal of Supercomputing - In this study, we present a fusion model for emotion recognition based on visual data. The proposed model uses video information as its input and generates emotion...     

Disparate attributes algorithm for semantic assembly design rule management

To expedite a semantic product design environment, the relevant minimal set of design rules could optimally be distilled from the given disparate design rules. However, in disparate design rules, some attributes are frequently unused in other design rules. Treating all the attributes in all the rules increases reasoning complexity. In the situation of incomplete information, treating the attributes, which may be relevant to some rules and not to others, as “missing” ones is found to cause reasoning problems. In this paper, we present a new algorithm, i.e. the disparate attributes algorithm, for managing semantic assembly design rules. The proposed disparate attributes algorithm by identifying “inapplicable” information extends a rough set approach for managing semantic assembly design rules with systematic selection of various minimal sets of rules. To validate the disparate attributes algorithm, the approach is tested with multiple realistic assembly design cases.