The autoencoder model is implmented using modules of Long Short-Term Memory, LSTM, a form of recurrent neural network, RNN in PyTorch framework with Keras/TensorFlow implementation as a reference 1.

The reconstruction loss of the trained LSTM Autoencoder model is estimated for the up-to-date reliability streaming data, and the result is used to infer MEC services’ runtime reliability anomalies.

Data quality significantly impacts the results of data analytics. Researchers have proposed machine learning based anomaly detection techniques to identify incorrect data. Existing approaches fail to ...

This project implements an unsupervised multivariate Long Short-Term Memory (LSTM) Autoencoder model for detecting anomalies in time series data derived from Network Key Performance Indicators (KPIs).

Isolation Forest detects anomalies by isolating observations. It builds binary trees (called iTrees) by recursively ...

Article citations More>> Hajjouz, S. and Avksentieva, N. (2022) Autoencoder-Based Anomaly Detection for IoT DDoS Attack Identification. Journal of Network Security, 24, 512-525. has been cited by the ...