Table 4 Result based on regression metrics for target variable Y2 (Cooling_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

0.9757

2.2447

0.8351

0.0336

RFR-AL #2

0.9758

2.2432

0.8293

0.0334

RFR-AL # 3

0.9765

2.1775

0.8087

0.0325

GBR-AL # 1

0.9774

2.0945

0.8743

0.0352

GBR-AL #2

0.9776

2.0761

0.8712

0.0351

GBR-AL # 3

0.9772

2.1077

0.8765

0.0353

KNR-AL # 1

0.9498

4.6474

1.3006

0.0524

KNR-AL #2

0.9498

4.6474

1.3006

0.0524

KNR-AL # 3

0.9498

4.6474

1.3006

0.0524

CBR-AL # 1

0.9883

1.0869

0.5869

0.0236

CBR-AL #2

0.9883

1.0869

0.5869

0.0236

CBR-AL # 3

0.9883

1.0869

0.5869

0.0236

XGBR-AL # 1

0.9798

1.8732

0.7444

0.0300

XGBR-AL #2

0.9798

1.8732

0.7444

0.0300

XGBR-AL # 3

0.9798

1.8732

0.7444

0.0300

LR-AL # 1

0.9584

3.8463

1.4451

0.0582

LR-AL #2

0.9584

3.8463

1.4451

0.0582

LR-AL # 3

0.9584

3.8463

1.4451

0.0582

LGBMR-AL # 1

0.9756

2.2564

0.9891

0.0398

LGBMR-AL #2

0.9756

2.2564

0.9891

0.0398

LGBMR-AL # 3

0.9756

2.2564

0.9891

0.0398

DTR-AL # 1

0.9617

3.5461

0.9135

0.0368

DTR-AL #2

0.9611

3.6014

0.9104

0.0366

DTR-AL # 3

0.9590

3.7957

0.9343

0.0376

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