Skip to main content

Table 5 Results of cluster analysis using DTW

From: Evaluating swine disease occurrence on farms using the state-space model based on meat inspection data: a time-series analysis

Disease

Optimal number of clusters

Classification

Optimal

1

2

3

PA

1

0.667

0.667

0.508

0.515

Diaphragmitis

2

0.777

0.467

0.777

0.735

Enteritis

3

0.558

0.600

0.513

0.542

IH

2

0.467

0.321

0.467

0.490

MPS

2

0.455

0.338

0.455

0.682

Mycobacteriosis

1

0.479

0.307

0.353

0.386

PH

1

0.528

0.600

0.528

0.481

Pericarditis

3

0.566

0.727

0.714

0.566

Perihepatitis

5

0.556

0.727

0.533

0.611

Peritonitis

4

0.581

0.783

0.550

0.661

Pleuritis

1

0.880

0.880

0.958

0.746

  1. Optimal number of clusters is the number of clusters based on gap statistics. Results from gap statistics show that the number of clusters is within three for many diseases. Classification is the results using the cluster.evaluation function (the Optimal column is the results using the cluster.evaluation function in the optimal number of clusters). This function also indicates that the larger the value, the better the fit
  2. PH, parasitic hepatitis; MPS, mycoplasmal pneumonia of swine; IH, interstitial hepatitis; PA, pulmonary abscess; DTW, dynamic time warping
Back to article page

Porcine Health Management

ISSN: 2055-5660

Contact us