Skip to main content

Table 3 Comparison of loss, accuracy, and time of OTS and characteristic subsequences on ResNet

From: Time series classification based on statistical features

ClassSub_accOri_accSub_lossOri_lossSub_time (ms)Ori_time (ms)MPCE
SubOri
Beef0.200000000.200000001.744965311.73106301515830860.02660.0266
_ECG_torso0.250000000.575000000.397113930.766369808006120080.01870.0106
FISH0.291428570.120000001.745087112.00773776502860340.00400.0050
Haptics0.219354840.116129031.591352291.631560848025590290.00500.0057
nlineSkate0.180000000.180000001.800858031.9935718713023130230.00820.0082
Lighting20.666666660.666666650.825551220.8048670410167111850.00550.0055
MALLAT0.818181810.254545450.451949660.6873092116007220090.00330.0135
CG_Thorax10.097777780.083888893.284997003.2940789518009230120.00050.0005
CG_Thorax20.130000000.022777783.315749413.4318707920010250130.00050.0005
OliveOil0.166666670.433333341.710290791.3171746718609206500.02780.0189
OSULeaf0.270000000.220000001.529140391.4555412021089220930.00360.0039
ightCurves0.966000000.841000000.118799470.24178773360045550070.00000.0001
Symbols0.879999990.400000000.431277030.5273389227027300300.00480.0240
yoga0.456666660.456666660.520880280.6469246732011360120.00180.0018
mean0.3994820.3264291.3905721.46694322171.6456299.360.00790.0089
  1. Data in italic means better experimental results