This repository contains a program that detects anomalies using Long Short-Term Memory (LSTM) networks. LSTM is a type of recurrent neural network capable of learning order dependence in sequence prediction problems, making it a powerful tool for time series forecasting.
The program utilizes the LSTM and 1DCNN models for anomaly detection. These models are commonly used in time series analysis and have proven to be effective in detecting anomalies. The LSTM model captures long-term dependencies in sequential data, while the 1DCNN model applies convolutional operations to extract features from the input data.
The program uses the GE.csv dataset for anomaly detection using LSTM networks. This dataset represents a time series data that can be used to train and evaluate the LSTM model for anomaly detection purposes.
The following Python libraries are required to run the program:
- TensorFlow: An open-source machine learning framework that provides tools and resources for building and deploying machine learning models.
- Seaborn: A data visualization library built on top of Matplotlib, providing a high-level interface for creating attractive and informative statistical graphics.
- Pandas: A powerful data manipulation and analysis library for handling and analyzing structured data.
- NumPy: A fundamental library for scientific computing in Python, providing support for large, multi-dimensional arrays and mathematical functions.
- Matplotlib: A plotting library for creating static, animated, and interactive visualizations in Python.
- scikit-learn: A machine learning library that offers a wide range of algorithms and tools for data mining and analysis.
- sweetviz: A Python library for visualizing and analyzing datasets, generating detailed and informative visual and statistical reports.
To install the required dependencies, use the following commands:
TensorFlow: pip install tensorflow
Seaborn: pip install seaborn
Pandas: pip install pandas
NumPy: pip install numpy
Matplotlib: pip install matplotlib
scikit-learn: pip install scikit-learn
sweetviz: pip install sweetviz