@mastersthesis {pub4171,
	title = {Real-World Anomaly Detection by using
Deep Learning algorithms and Digital
Twin systems},
	author = {Andrea Castellani},
	year = {2019},
	month = {October},
	abstract = {Nowadays, with the continuously growing amount of monitored data present in
Smart Company environment, the need for Anomaly Detection technique has become
more relevant in order to identify some anomalous behavior from time-series data
generated by sensors. With the Digital Twin, a detailed simulation of a complex
physical system, it is possible to provide more data to feed in a Machine Learning
algorithm and thus help in the anomaly detection task.
This thesis presents an approach to the Anomaly Detection on real-world multi-
variate sensor data, by the use of the Digital Twin to generate a synthetic dataset.
Those data are used to training some Artifi cial Neural Networks (Autoencoders) in
an unsupervised fashion, with the aim of detecting anomalies in a real-world dataset.
Then, a novel method based on Siamese Autoencoder is presented. It is aimed
to improve the performance of such unsupervised algorithms by only including a
rather small subset of labeled data in a weakly-supervised fashion. Furthermore,
an end-to-end Machine Learning model is presented, which is able to work with
raw data. De facto, it has the same structure of the Siamese Autoencoder but uses
Convolutional Neural Networks to extract automatically meaningful features from
the input data.
All the developed algorithms are compared with the state-of-the-art approach
for Anomaly Detection and the overall results are very promising. They show that
the presented methods, during testing, reach an ROC AUC measure and F2 score
noticeably higher the recent state-of-the-art Anomaly Detection techniques chosen
for comparison.},
	publisher = {unpublished},
	booktitle = {Universita Politechnica Delle Marche, Ancona, Italy}
}