harbinger

Framework for integration and analysis of event detection methods - Research Project

https://github.com/cefet-rj-dal/harbinger

Repository

Framework for integration and analysis of event detection methods - Research Project

README.Rmd

---
output: github_document
---



```{r, include = FALSE}
knitr::opts_chunk$set(
  collapse = TRUE,
  comment = "#>",
  fig.path = "man/figures/README-",
  out.width = "100%",
  fig.alt = "Harbinger example figure"  
)
```

#  Harbinger


![GitHub Stars](https://img.shields.io/github/stars/cefet-rj-dal/harbinger?logo=Github)
![CRAN Downloads](https://cranlogs.r-pkg.org/badges/harbinger)


**Harbinger** is a framework for event detection in time series. It provides an integrated environment for anomaly detection, change point detection, and motif discovery. Harbinger offers a broad range of methods and functions for plotting and evaluating detected events.

For anomaly detection, methods are based on:
- Machine learning model deviation: Conv1D, ELM, MLP, LSTM, Random Regression Forest, and SVM
- Classification models: Decision Tree, KNN, MLP, Naive Bayes, Random Forest, and SVM
- Clustering: k-means and DTW
- Statistical techniques: ARIMA, FBIAD, GARCH

For change point detection, Harbinger includes:
- Linear regression, ARIMA, ETS, and GARCH-based approaches
- Classic methods such as AMOC, ChowTest, Binary Segmentation (BinSeg), GFT, and PELT

For motif discovery, it provides:
- Methods based on Hashing and Matrix Profile

Harbinger also supports **multivariate time series analysis** and **event evaluation** using both traditional and soft computing metrics.

The architecture of Harbinger is based on **Experiment Lines** and is built on top of the [DAL Toolbox](https://github.com/cefet-rj-dal/daltoolbox). This design makes it easy to extend and integrate new methods into the framework.

---

#  Examples

Examples of Harbinger are organized by application area:

- [General](https://github.com/cefet-rj-dal/harbinger/tree/master/general)
- [Anomalies](https://github.com/cefet-rj-dal/harbinger/tree/master/anomalies)
- [Change points](https://github.com/cefet-rj-dal/harbinger/tree/master/change_point)
- [Motifs](https://github.com/cefet-rj-dal/harbinger/tree/master/motifs)

```{r example}
library(harbinger)

#loading the example database
data(examples_anomalies)

#model
model <- harbinger()

#stub detector
detection <- detect(model, examples_anomalies$simple$serie)

# filtering detected events
library(dplyr)
print(detection |> dplyr::filter(event==TRUE))
```

---

#  Installation

The latest version of Harbinger is available on CRAN:

```r
install.packages("harbinger")
```

You can install the development version from GitHub:

```r
library(devtools)
devtools::install_github("cefet-rj-dal/harbinger", force = TRUE, upgrade = "never")
```

---

#  Bug reports and feature requests

If you find any bugs or would like to suggest new features, please submit an issue here:

Owner

GitHub Events

Packages