Table 3 Comparison of different classifiers.

From: Cattle identification based on multiple feature decision layer fusion

Multiple classifiers

Accuracy

Precision

Recall

F1_Score

Validation

rate

FAR

DT-Decision Tree

0.88986

0.91173

0.83504

0.89208

0.86450

0.00079

LR-Logistic Regression

0.95244

0.95765

0.91202

0.95062

0.93584

0.00033

GS-Gaussian NB

0.81101

0.84502

0.73227

0.81257

0.78978

0.00124

RF-Random Forest

0.94117

0.94125

0.89441

0.93546

0.91556

0.00047

VotingClassifier:

DT, LR

0.94618

0.95405

0.88757

0.94434

0.93457

0.00039

VotingClassifier:

DT, GS

0.88360

0.90488

0.82857

0.88410

0.86030

0.00083

VotingClassifier:

DT,RF

0.90237

0.90940

0.83989

0.89939

0.87710

0.00069

VotingClassifier:

LR,GS

0.94868

0.95588

0.89372

0.94686

0.93147

0.00036

VotingClassifier:

LR,RF

0.95744

0.96679

0.92476

0.95644

0.94717

0.00032

VotingClassifier:

GS,RF

0.92615

0.93585

0.84863

0.92358

0.90318

0.00052

VotingClassifier:

DT, LR, GS

0.94743

0.95446

0.90163

0.94655

0.93258

0.00036

VotingClassifier:

DT, LR, RF

0.95118

0.96212

0.89813

0.95117

0.93324

0.00035

VotingClassifier:

LR, GS, RF

0.94117

0.94966

0.88222

0.93924

0.94518

0.00032

VotingClassifier:

DT, LR, GS, RF

0.95619

0.96193

0.92213

0.95420

0.94053

0.00033

Bagging: DT

0.91614

0.92938

0.84717

0.91552

0.89434

0.00055

Bagging: RF

0.93867

0.94408

0.89783

0.93470

0.91335

0.00041

Boosting:

Gradient Boosting Classifier

0.90863

0.92354

0.84346

0.90785

0.90229

0.00060

Boosting: LightGBM

0.88610

0.89453

0.77262

0.88177

0.84217

0.00075

Boosting: XGboost

0.92740

0.94001

0.85201

0.92730

0.90030

0.00039

Stacking: DT, LR

0.93992

0.95835

0.90234

0.94072

0.91909

0.00040

Stacking: DT, GS

0.88110

0.91620

0.84764

0.88495

0.85941

0.00075

Stacking: DT, RF

0.91739

0.94031

0.89668

0.91815

0.88704

0.00053

Stacking: LR, GS

0.94493

0.96190

0.90616

0.94437

0.91754

0.00038

Stacking: LR, RF

0.93867

0.95419

0.89365

0.93603

0.91998

0.00042

Stacking: GS, RF

0.89862

0.93196

0.86819

0.90262

0.88506

0.00049

Stacking: DT, LR, GS

0.94242

0.96162

0.89818

0.94263

0.91600

0.00036

Stacking: DT, LR, RF

0.94242

0.95825

0.90355

0.94176

0.91379

0.00043

Stacking: LR, GS, RF

0.93867

0.95749

0.89509

0.93895

0.91511

0.00039

Stacking: DT, LR, GS, RF

0.93742

0.95867

0.89801

0.93781

0.93302

0.00036

  1. The bold values indicate that this classifier performs better compared to the other classifiers.
Back to article page