公开(公告)号：US11131692B1

公开(公告)日：2021-09-28

申请号：US16392089

申请日：2019-04-23

Applicant: Amazon Technologies, Inc.

Inventor： Jared Lee ,  Huyen Van Nguyen ,  Richard Arvel Stevens ,  David Leonard Robinson ,  Tong He ,  Hong Ghee Yow ,  Xulong Zhan ,  Xia Yang

IPC: G01R31/04 ,  G01R15/14 ,  G01R1/04 ,  H01R24/30

Abstract: A line isolating power connector can include a housing for connecting with a power cable and a power source, and wires positioned through the housing that include at least a line wire and a neutral wire. The housing is separated by an aperture into a line conduit and a neutral conduit, and the aperture is sized to receive a portion of a contactless power quality probe such that the power quality probe can be connected around the first line conduit or neutral conduit in order to measure power quality in either the line wire or the neutral wire.

公开(公告)号：US11860977B1

公开(公告)日：2024-01-02

申请号：US17307701

申请日：2021-05-04

Applicant: Amazon Technologies, Inc.

Inventor： Yifan Xing ,  Tianjun Xiao ,  Tong He ,  Yongxin Wang ,  Yuanjun Xiong ,  Wei Xia ,  David Paul Wipf ,  Zheng Zhang ,  Stefano Soatto

IPC: G06F18/2323 ,  G06N20/00 ,  G06F18/2415 ,  G06F18/23213 ,  G06F18/2413

CPC classification number: G06F18/2323 ,  G06F18/23213 ,  G06F18/2415 ,  G06F18/24147 ,  G06N20/00

Abstract: Techniques for performing visual clustering with a hierarchical graph neural network framework including a joint linkage prediction and density estimation graph model are described. Embodiments herein recurrently run the joint linkage prediction and density estimation graph model to generate intermediate clusters in multiple iterations (e.g., until convergence) to obtain a final clustering result. In certain embodiments, for each iteration, the input graph contains nodes that are merged from nodes assigned to intermediate clusters from the previous iteration. By using a small and fixed bandwidth k in each iteration, embodiments herein alleviate the sensitivity to the k selection for different clustering applications. Certain embodiments herein remove the tuning of a different k (e.g., k-bandwidth) for k-nearest neighbor graph construction over different clustering applications.