Table 1 Performance comparison on Agra dataset.

From: A meta-learning ensemble framework for robust and interpretable prediction of emergency medical services demand

Metric

Variant

MLP

SVR

RF

XGB

AHELM

TBLSSVR

MHKLDMR

EM-LR

MAE

T

3.3920

5.0563

3.9058

3.7389

3.6023

5.8124

3.9088

3.0752

T+W

4.4666

4.8158

4.2538

3.8997

3.3605

7.9416

3.7198

3.1322

T+W+FS

3.3112

5.5833

3.8269

3.7389

3.6051

4.5064

3.5717

3.0757

RMSE

T

4.3928

6.2108

4.9953

4.8379

4.2627

6.9123

4.4165

3.9661

T+W

5.6049

5.9812

5.3699

4.9810

4.1316

9.0377

4.6631

4.0326

T+W+FS

4.2632

6.7767

4.9172

4.8379

4.2209

5.6678

4.2049

3.9544

MAPE

T

0.6614

4.7473

0.7117

0.6417

0.5221

0.7843

0.5697

0.4361

T+W

4.5873

6.3469

0.8702

0.7000

0.4486

0.7652

0.5359

0.4445

T+W+FS

0.5413

6.2817

0.6839

0.6417

0.4681

0.5134

0.4490

0.4274

MBE

T

– 2.0343

– 3.5715

– 2.9414

– 2.6799

– 2.1014

– 4.8027

– 2.3009

– 0.8676

T+W

– 3.9748

– 3.5624

– 3.5121

– 2.8449

– 0.4193

– 7.9280

0.2179

– 0.9173

T+W+FS

– 1.6496

– 4.5166

– 2.8188

– 2.6799

-0.3573

– 4.0181

– 0.8363

– 0.7192