Skip to main content
Advertisement
Browse Subject Areas
?

Click through the PLOS taxonomy to find articles in your field.

For more information about PLOS Subject Areas, click here.

< Back to Article

Table 1.

Canine posture recognition algorithms using IMUs reported in literature.

More »

Table 1 Expand

Fig 1.

IMUs sensor placement on the dogs’ neck, back, and chest.

More »

Fig 1 Expand

Table 2.

Behaviour Test Protocol for canine posture data monitoring and acquisition.

More »

Table 2 Expand

Table 3.

Categories of behaviour analysed.

More »

Table 3 Expand

Table 4.

Type, posture, and the number of observations in the IMU Posture dataset.

More »

Table 4 Expand

Fig 2.

Rolling window used for selecting data for feature extraction.

Hyper-parameters shown include re-sampling transition time (t_time) between postures, window size (w_size) used to calculate the statistical measures, and window offset (w_offset) to create separate observations.

More »

Fig 2 Expand

Table 5.

Number of observations after feature extraction per dataset per posture.

More »

Table 5 Expand

Table 6.

Grid search hyper-parameter set for the classifiers.

More »

Table 6 Expand

Fig 3.

Direct estimator used in Classifier 1.

More »

Fig 3 Expand

Fig 4.

Type, static and dynamic estimators used in Classifier 2.

More »

Fig 4 Expand

Fig 5.

Anomaly and normal estimators used in Classifier 3.

More »

Fig 5 Expand

Table 7.

Classifier 2 model’s hyper-parameter set selected by grid search, the time (in seconds) taken to train and validate the model using the development set, and f1-weighted performance on 10-fold validation sets (mean ± standard deviation) and test set.

More »

Table 7 Expand

Table 8.

Classifier 3 model’s hyper-parameter set selected by grid search, and f1-weighted performance on 10-fold validation sets (mean ± standard deviation) and test set.

More »

Table 8 Expand

Table 9.

Feature scores calculated by f-classification in Select K Best by IMU position and sensor.

More »

Table 9 Expand

Table 10.

Feature importance calculated by Random Forest classifier considering the 80 features previously selected by Select K Best.

More »

Table 10 Expand

Table 11.

Feature importance calculated by Random Forest classifier considering the 80 features selected by Select K Best by domain.

More »

Table 11 Expand

Table 12.

Classification metrics per posture achieved using the best models selected by grid search in Classifier 1 on the test set.

More »

Table 12 Expand

Table 13.

Classification metrics per posture achieved using the best models selected by grid search in Classifier 2 on the test set.

More »

Table 13 Expand

Table 14.

Classification metrics per posture achieved using the best models selected by grid search in Classifier 3 on the test set.

More »

Table 14 Expand

Fig 6.

Confusion matrix for Classifier 1 on the test set.

More »

Fig 6 Expand

Fig 7.

Confusion matrix for Classifier 2 on the test set.

More »

Fig 7 Expand

Fig 8.

Confusion matrix for Classifier 3 on the test set.

More »

Fig 8 Expand

Table 15.

Classification metrics per posture achieved using the best models selected by grid search in Classifier 1 on the golden set.

More »

Table 15 Expand

Table 16.

Classification metrics per posture achieved using the best models selected by grid search in Classifier 2 on the golden set.

More »

Table 16 Expand

Fig 9.

Confusion matrix for Classifier 1 on the golden set.

More »

Fig 9 Expand

Fig 10.

Confusion matrix for Classifier 2 on the golden set.

More »

Fig 10 Expand

Fig 11.

Confusion matrix for Classifier 3 on the golden set.

More »

Fig 11 Expand

Table 17.

Classification metrics per posture achieved using the best models selected by grid search in Classifier 3 on the golden set.

More »

Table 17 Expand

Table 18.

Classification metrics per posture achieved using the best models selected by grid search in Classifier 3 on the test and golden sets combined.

More »

Table 18 Expand

Fig 12.

Confusion matrix for Classifier 3 on the test and golden sets.

More »

Fig 12 Expand

Table 19.

Comparison between Classifier 3 performance and previous studies reporting inter-subject classification performance metrics per posture.

The best geometric means between TPR and TNR (g-mean) are in bold.

More »

Table 19 Expand