Skip to main content

Table 2 Comparison of loss, accuracy, and time of OTS and characteristic subsequences on FCN

From: Time series classification based on statistical features

Class

Sub_acc

Ori_acc

Sub_loss

Ori_loss

Sub_time (ms)

Ori_time (ms)

MPCE

Sub

Ori

Beef

0.20000000

0.20000000

1.74064850

1.78573286

3084

1027

0.0266

0.0266

_ECG_torso

0.25000000

0.12500000

0.75720222

0.95993692

2001

3002

0.0187

0.0219

FISH

0.12000000

0.16000000

1.89679190

2.04517563

1007

2009

0.0050

0.0048

Haptics

0.25161290

0.21935483

1.60219245

1.62430625

2007

2008

0.0048

0.0050

nlineSkate

0.14000000

0.21000000

1.87575633

1.92259577

2004

3006

0.0086

0.0079

Lighting2

0.66666665

0.58333333

0.7384292

0.66227742

2041

3046

0.0055

0.0069

MALLAT

0.30909091

0.12727272

1.18807646

1.60943770

4002

5002

0.0126

0.0159

CG_Thorax1

0.06666666

0.05833333

3.53328775

3.68092299

4002

5003

0.0005

0.0005

CG_Thorax2

0.08777777

0.04166666

3.56809761

3.69119312

4002

5003

0.0005

0.0005

OliveOil

0.16666667

0.26666668

1.39539515

1.85584843

4137

4149

0.0278

0.0244

OSULeaf

0.30000000

0.24500000

1.56651332

1.55764289

5020

55021

0.0035

0.0038

ightCurves

0.91000000

0.46100000

0.17210860

0.36349089

8942

11001

0.0001

0.0005

Symbols

0.92000001

0.36000001

0.75745789

1.02618091

6006

6006

0.0032

0.0256

yoga

0.45666666

0.49666666

0.58991410

0.67094716

7002

8003

0.0018

0.0017

mean

0.346082

0.253878

1.527277

1.675406

3946.929

8091.857

0.0085

0.0104

  1. Data in italic means better experimental results