Table 3 Result based on regression metrics for target variable Y1 (Heating_Load).

From: Active learning-based machine learning approach for enhancing environmental sustainability in green building energy consumption

Regression model

R2

MSE

MAE

RAE

RFR-AL # 1

0.9950

0.5445

0.3887

0.0171

RFR-AL #2

0.9947

0.5726

0.4011

0.0176

RFR-AL # 3

0.9951

0.5287

0.4045

0.0178

GBR-AL # 1

0.9907

1.0092

0.6424

0.0282

GBR-AL #2

0.9907

1.0092

0.6425

0.0282

GBR-AL # 3

0.9907

1.0092

0.6424

0.0282

KNR-AL # 1

0.9700

3.2378

1.1017

0.0484

KNR-AL #2

0.9700

3.2378

1.1017

0.0484

KNR-AL # 3

0.9700

3.2378

1.1017

0.0484

CBR-AL # 1

0.9975

0.2667

0.2984

0.0131

CBR-AL #2

0.9975

0.2667

0.2984

0.0131

CBR-AL # 3

0.9975

0.2667

0.2984

0.0131

XGBR-AL # 1

0.9941

0.6414

0.3774

0.0166

XGBR-AL #2

0.9941

0.6414

0.3774

0.0166

XGBR-AL # 3

0.9941

0.6414

0.3774

0.0166

LR-AL # 1

0.9666

3.6108

1.2413

0.0545

LR-AL #2

0.9666

3.6108

1.2413

0.0545

LR-AL # 3

0.9666

3.6108

1.2413

0.0545

LGBMR-AL # 1

0.9936

0.6904

0.5035

0.0221

LGBMR-AL #2

0.9936

0.6904

0.5035

0.0221

LGBMR-AL # 3

0.9936

0.6904

0.5035

0.0221

DTR-AL # 1

0.9948

0.5634

0.3569

0.0157

DTR-AL #2

0.9943

0.6149

0.3827

0.0168

DTR-AL # 3

0.9899

1.0896

0.4192

0.0184

  1. Key: R2, prediction accuracy; MSE, mean squared error; MAE, mean absolute error; RAE, relative absolute error.
Back to article page