-
1.
公开(公告)号:US20240176654A1
公开(公告)日:2024-05-30
申请号:US18317004
申请日:2023-05-12
Inventor: Youngjoo LEE , Hyeokjun KWON , Young-Seok KIM
CPC classification number: G06F9/4881 , G06F5/01 , G06F7/50 , G06F7/523 , G06F7/5443 , G06F9/5027
Abstract: Provided is a method of optimizing calculation of a convolutional layer including a plurality of channels and a convolutional neural network (CNN) accelerator. The method includes a classification operation of classifying weights of the plurality of channels as outlier (OL) elements and non-outlier (NOL) elements, a combination operation of combining two or more NOL elements which are put into calculation with the same activation value and present at the same slot in the plurality of channels, and a scheduling operation of moving a scheduling candidate element in a fetch window after the combination operation to a slot which is assigned no value.
-
公开(公告)号:US20230029222A1
公开(公告)日:2023-01-26
申请号:US17481220
申请日:2021-09-21
Inventor: Yoonyoung CHUNG , Young-Seok KIM , Inyeol YUN
Abstract: According to an embodiment, a method of processing acceleration information by a wearable device is provided, the method including: acquiring the acceleration information indicating acceleration according to movement of the wearable device; acquiring a plurality of acceleration characteristics including a plurality of characteristics of a power spectrum of the acceleration and a range of the acceleration on the basis of the acceleration information; determining characteristic values according to two characteristics determined according to a type of a disease to be monitored among the plurality of acceleration characteristics; and providing an alarm signal in response to the characteristic value falling within an abnormality range.
-