US 12,067,766 B2
Methods and systems of resilient mobile distributed computing
Qi Zhao, Germantown, MD (US); Huong Ngoc Dang, Germantown, MD (US); Yi Li, Germantown, MD (US); Xin Tian, Germantown, MD (US); Nichole Sullivan, Germantown, MD (US); Genshe Chen, Germantown, MD (US); and Khanh Pham, Kirtland AFB, NM (US)
Assigned to Intelligent Fusion Technology, Inc., Germantown, MD (US)
Filed by Intelligent Fusion Technology, Inc., Germantown, MD (US)
Filed on Dec. 15, 2021, as Appl. No. 17/551,436.
Prior Publication US 2023/0186620 A1, Jun. 15, 2023
Int. Cl. G06V 10/94 (2022.01); G06V 10/764 (2022.01); G06V 10/77 (2022.01); G06V 10/82 (2022.01); G06V 10/96 (2022.01)
CPC G06V 10/95 (2022.01) [G06V 10/764 (2022.01); G06V 10/7715 (2022.01); G06V 10/82 (2022.01); G06V 10/96 (2022.01)] 20 Claims
OG exemplary drawing
 
1. A resilient distributed computing system, comprising:
a named data networking (NDN) based Spark distributed computing network, comprising a Spark distributed computing network including a master computer node and a plurality of slave computer nodes, and a named data networking (NDN) protocol installed on the Spark distributed computing network, and a coded distributed computing (CDC) target recognition model deployed on the NDN-based Spark distributed computing network,
wherein the NDN-based Spark distributed computing network is configured to:
receive one or more batches of input images for classification;
generate a parity image from each batch of the input images by resizing and concatenating the batch of the input images;
predict a label for each input image of the batch of the input images using a deep neural network (DNN)-based inference base model of the CDC target recognition model;
process the generated parity image using a DNN-based inference parity model of the CDC target recognition model;
upon a label prediction of one input image of the batch of the input images being unavailable, reconstruct the unavailable label prediction; and
classify labels for each input image.