Patents by Inventor Sandeep Gattani

Sandeep Gattani has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).

  • Patent number: 11962497
    Abstract: Techniques disclosed herein provide a method and systems for installing routes by a route reflect (RR) device when the tunnel RIB of the RR device does not include any tunnel labels definitions. The unicast routing information base (RIB) of route reflector (RR) device is configured to include a next hop associated with a first network device. When the RR device receives a route from the first network device that comprises a tunnel label for reaching the second network device, the RR device resolves the next hop of the received route using the unicast RIB of the RR device. In response to the resolving, the RR device forwards the route to a third network device (e.g., identified by an export route target of the RR device).
    Type: Grant
    Filed: April 24, 2023
    Date of Patent: April 16, 2024
    Assignee: ARISTA NETWORKS, INC.
    Inventors: Saurav Arora, Akshay Gattani, Sandeep Betha, Sharad Birmiwal
  • Patent number: 8700557
    Abstract: A computer-based system and method to improve the multimodal fusion output at the decision level is disclosed. The method proposes computation of a confidence weighted measure for the individual score values obtained for each modality and fuse these new updated scores to get the final decision. These confidence weights are the performance parameters (measured in terms of F-measure) during the offline training step. The process significantly increases the accuracy of the multimodal system.
    Type: Grant
    Filed: August 26, 2011
    Date of Patent: April 15, 2014
    Assignee: Tata Consultancy Services Limited
    Inventors: Rohit Kumar Gupta, Sandeep Gattani, Aniruddha Sinha, Ayan Chaki, Arpan Pal
  • Publication number: 20120290526
    Abstract: A computer-based system and method to improve the multimodal fusion output at the decision level is disclosed. The method proposes computation of a confidence weighted measure for the individual score values obtained for each modality and fuse these new updated scores to get the final decision. These confidence weights are the performance parameters (measured in terms of F-measure) during the offline training step. The process significantly increases the accuracy of the multimodal system.
    Type: Application
    Filed: August 26, 2011
    Publication date: November 15, 2012
    Applicant: TATA CONSULTANCY SERVICES LIMITED
    Inventors: Rohit Kumar Gupta, Sandeep Gattani, Aniruddha Sinha, Ayan Chaki, Arpan Pal