Research Article
Robust and Accurate Anomaly Detection in ECG Artifacts Using Time Series Motif Discovery
Algorithm 1
Proper length motif discovery algorithm for ECG.
Input: single-lead ECG , | : sampling rate | Output: motif: the 1st motif in single-lead ECG | (1) For = startingLength() to .length/2 | (2) := extractSubsequence() | (3) := Z-norm() | (4) := motifCandidateDiscovery() | (5) Group:= createGroup() | (6) if Group.bitsave < 0 then break | (7) while hasNextNeighbor() | (8) := NextNeighbor(, Group.center, ) | (9) bs:= BitsaveOfAdd(Group, ) | (10) if bs > Group.bitsave then | (11) Group.bitsave += bs | (12) Group:= AddToGroup(Group, ) | (13) else break | (14) end | (15) motif = updateWithMaxBitsave(motif, group) | (16) end for | (17) return motif |
|