Learn R Programming

harbinger (version 1.2.767)

har_eval_soft: Evaluation of event detection (SoftED)

Description

Soft evaluation of event detection using SoftED doi:10.48550/arXiv.2304.00439.

Usage

har_eval_soft(sw_size = 15)

Value

har_eval_soft object

Arguments

sw_size

Integer. Tolerance window size for soft matching.

References

  • Salles, R., Lima, J., Reis, M., Coutinho, R., Pacitti, E., Masseglia, F., Akbarinia, R., Chen, C., Garibaldi, J., Porto, F., Ogasawara, E. SoftED: Metrics for soft evaluation of time series event detection. Computers and Industrial Engineering, 2024. doi:10.1016/j.cie.2024.110728

Examples

Run this code
library(daltoolbox)

# Load anomaly example data
data(examples_anomalies)

# Use the simple series
dataset <- examples_anomalies$simple
head(dataset)

# Configure a change-point detector (GARCH)
model <- hcp_garch()

# Fit the detector
model <- fit(model, dataset$serie)

# Run detection
detection <- detect(model, dataset$serie)

# Show detected events
print(detection[(detection$event),])

# Evaluate detections (SoftED)
evaluation <- evaluate(har_eval_soft(), detection$event, dataset$event)
print(evaluation$confMatrix)

# Plot the results
grf <- har_plot(model, dataset$serie, detection, dataset$event)
plot(grf)

Run the code above in your browser using DataLab