Action Recognition from Motion Capture Data using Meta-cognitive RBF Network Classifier

Action recognition plays an important role in various applications, including smart homes and personal assistive robotics. In this paper, we propose an algorithm for recognizing human actions using motion capture action data. Motion capture data provides accurate three dimensional positions of joints which constitute the human skeleton. We model the movement of the skeletal joints temporally in order to classify the action. The skeleton in each frame of an action sequence is represented as a 129 dimensional vector, of which each component is a 31) angle made by each joint with a fixed point on the skeleton. Finally, the video is represented as a histogram over a codebook obtained from all action sequences. Along with this, the temporal variance of the skeletal joints is used as additional feature. The actions are classified using Meta-Cognitive Radial Basis Function Network (McRBFN) and its Projection Based Learning (PBL) algorithm. We achieve over 97% recognition accuracy on the widely used Berkeley Multimodal Human Action Database (MHAD).

Effect of applied pressure on densification of monolithic ZrCx ceramic by reactive hot pressing

The effect of applied pressure on reactive hot pressing (RHP) of zirconium (Zr):graphite (C) in molar ratios of 1:0.5, 1:0.67, 1:0.8, and 1:1 was studied at 1200 degrees C for 60 min. The relative density achievable increased with increasing pressure and ranged from 99% at 4 MPa for ZrC0.5 to 93% for stoichiometric ZrC at 100 MPa. The diminishing influence of pressure on the final density with increasing stoichiometry is attributed to two causes: the decreasing initial volume fraction of the plastically deforming Zr metal which leads to the earlier formation of a contiguous, stress shielding carbide skeleton and the larger molar volume shrinkage during reaction which leads to pore formation in the final stages. A numerical model of the creep densification of a dynamically evolving microstructure predicts densities that are consistent with observations and confirm that the availability of a soft metal is primarily responsible for the achievement of such elevated densification during RHP. The ability to densify nonstoichiometric compositions like ZrC0.5 at pressures as low as 4 MPa offers an alternate route to fabricating dense nonstoichiometric carbides.