US 11,755,945 B2
Time-series data uncertainty reduction
Edward Vitkin, Yoqneam Ilit (IL); Igor Kostirev-Kronos, Adamit (IL); Alex Melament, Kiriat Mozkin (IL); and Yardena Lia Peres, Haifa (IL)
Assigned to INTERNATIONAL BUSINESS MACHINES CORPORATION, Armonk, NY (US)
Filed by INTERNATIONAL BUSINESS MACHINES CORPORATION, Armonk, NY (US)
Filed on Aug. 7, 2019, as Appl. No. 16/534,582.
Prior Publication US 2021/0042587 A1, Feb. 11, 2021
This patent is subject to a terminal disclaimer.
Int. Cl. G06N 20/00 (2019.01); G06F 18/2415 (2023.01); G06F 18/21 (2023.01)
CPC G06N 20/00 (2019.01) [G06F 18/21 (2023.01); G06F 18/2415 (2023.01); G06F 2218/00 (2023.01)] 13 Claims
OG exemplary drawing
 
1. A system, comprising:
a computer having at least one processor programmed to initiate executable operations, the executable operations including:
generating an initial accumulated signal based on an event classifier prediction score, the event classifier prediction score generated by an event predicator based on time-series data and corresponding to a probability that a target event occurs;
imposing signal leakage on the initial accumulated signal; and
generating an alert in response to determining that the initial accumulated signal is greater than an alert threshold.