=======

CUBOID

Anomaly detection based on clustering representation

CUBOID is a time series anomaly detection Python program that comprises three modules:

1- a data representation module,

2- an anomaly modeling module,

3- an anomaly detection module.

In the data representation module, the program employs a clustering algorithm to represent time series. CUBOID was proposed in a research paper titled "Time Series Anomaly Detection via Clustering-based Representation," which was submitted to the Evolving System Journal.

Installation:

1- Create a python env

conda create -n envname python=3.8.12
conda activate envname

2- Install below packages:

pip install numpy

pip install pandas

pip install matplotlib

3- Clone the repository:

git clone https://github.com/ir1979/CUBOID.git

4- Navigate to the project directory and run the program:

cd CUBOID
python main_CUBOID.py

Note: Yahoo dataset is not included here due to license limitations.

In case of any issues, please feel free to contact us: ir1979@gmail.com OR r_mortazavi@du.ac.ir