Abstract: State of the art track width adjustment mechanism fail to support track width adjustment while vehicle is in motion. They also require manual intervention, which causes inconvenience. The disclosure herein generally relates to wheel track adjustment, and, more particularly, to a changeable wheel track mechanism for track width adjustment (referred to as TWA mechanism). The TWA mechanism includes a steer and drive unit, a plurality of links, and a sliding unit. The TWA mechanism allows movement of a wheel in inward and outward directions, causing the track width adjustment. The track width is achieved by changing the wheel position to be at a wider position, or a narrower position, or any intermediate position. The TWA mechanism may be associated with any vehicle for which the track width adjustment is to be achieved.

Abstract: This disclosure relates generally to system and method for parameter compression of capsule networks using deep features. The conventional capsule networks have distinct capability of retaining spatial correlations between extracted features but that comes at a cost of intensive computational, cost, memory usage and bandwidth requirement. The embodiments herein disclose a system and method for employing a lightweight deep features based capsule network that is capable of compressing the parameters. In an embodiment, the system includes a deep feature based capsule network such that the capsule layer is preceded by feature blocks. Said feature blocks comprises convolutional operation with a kernel size 3, followed by convolutional operation with kernel of size 1, and a Batch Normalization layer, and hence are able to extract deep features.