A hybrid architecture consisting of several adaptive controllers is effective to control a multi-degree-of-freedom robot acting in unknown/dynamic environment. For such controllers, it is important to find out whether they are redundant with respect to the subtasks given for the sub-controllers. In this paper, we propose an adaptive sub-controller which have an ability to finding out its redund...

IR remote sensing and reconnaissance applications require transmission and/or store of line-scan thermal (IRLS) images in real-time. IRLS images exhibit a high degree of spatial redundancy that a codec reduces optimizing trade-off between bitrate and image distortion. In this paper, we propose adaptive coding based on joint optimization of image segmentation scheme and operational codec paramet...

Due to the strong correlation between symmetric frames, video signals have a high degree of temporal redundancy. Motion estimation techniques are computationally expensive and time-consuming processes used in compression reduce The block-matching technique is, on other hand, most popular efficient different motion compensation techniques. based generally uses minimization either mean square err...

ACKNOWLEDGMENTS I am deeply indebted to my advisor Dr. John Tyler for his continuous support and encouragement throughout my graduate studies. His patience, enthusiasm, and generous contribution of time and resources have greatly helped me to achieve my goals. He has been more than my advisor, as he often made me feel part of his family. I am especially thankful for his trust in my ideas and ab...

Recent research on deep neural networks (DNNs) has primarily focused improving the model accuracy. Given a proper learning framework, it is generally possible to increase depth or layer width achieve higher level of However, huge number parameters imposes more computational and memory usage overhead leads parameter redundancy. In this paper, we address redundancy problem in DNNs by replacing co...