Autocalibration of Outlier Threshold with Autoencoder Mean Probability Score

Anomaly detection is a widely studied field in computer science with applications ranging from intrusion and fraud detection, medical diagnosis and quality assurance in manufacturing. The underlying premise is that an anomaly is an observation that doesn't conform to what is considered to be no...

Full description

Saved in:
Bibliographic Details
Main Authors: Alampay, Raphael B, Abu, Patricia Angela R
Format: text
Published: Archīum Ateneo 2019
Subjects:
Online Access:https://archium.ateneo.edu/discs-faculty-pubs/190
https://dl.acm.org/doi/abs/10.1145/3375959.3375978
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Ateneo De Manila University
id ph-ateneo-arc.discs-faculty-pubs-1189
record_format eprints
spelling ph-ateneo-arc.discs-faculty-pubs-11892020-07-08T08:22:54Z Autocalibration of Outlier Threshold with Autoencoder Mean Probability Score Alampay, Raphael B Abu, Patricia Angela R Anomaly detection is a widely studied field in computer science with applications ranging from intrusion and fraud detection, medical diagnosis and quality assurance in manufacturing. The underlying premise is that an anomaly is an observation that doesn't conform to what is considered to be normal. A problem however is in defining the threshold that draws the line between what is normal and what is an anomaly which is largely dependent on a domain expert or from empirical testing that would yield the best result. Another problem is that the availability of data with regards to what is not normal is highly unavailable in real world scenarios making it difficult for traditional machine learning techniques to build a classification model. In this study, we propose a method that automatically determines the outlier threshold using a semi-supervised learning approach with autoencoders. To validate the performance of our proposed approach, we perform several experiments in comparison with traditional outlier detection approaches as well as an existing semi-supervised approach in one class classification, specifically OneClassSVM. The goal of this study is to eventually apply the method for autocalibration of anomaly detection of frames in video sequences. Initial results are also presented in a computer vision task. 2019-01-01T08:00:00Z text https://archium.ateneo.edu/discs-faculty-pubs/190 https://dl.acm.org/doi/abs/10.1145/3375959.3375978 Department of Information Systems & Computer Science Faculty Publications Archīum Ateneo Computing methodologies Machine learning Machine learning approaches Neural networks Computer Sciences
institution Ateneo De Manila University
building Ateneo De Manila University Library
continent Asia
country Philippines
Philippines
content_provider Ateneo De Manila University Library
collection archium.Ateneo Institutional Repository
topic Computing methodologies
Machine learning
Machine learning approaches
Neural networks
Computer Sciences
spellingShingle Computing methodologies
Machine learning
Machine learning approaches
Neural networks
Computer Sciences
Alampay, Raphael B
Abu, Patricia Angela R
Autocalibration of Outlier Threshold with Autoencoder Mean Probability Score
description Anomaly detection is a widely studied field in computer science with applications ranging from intrusion and fraud detection, medical diagnosis and quality assurance in manufacturing. The underlying premise is that an anomaly is an observation that doesn't conform to what is considered to be normal. A problem however is in defining the threshold that draws the line between what is normal and what is an anomaly which is largely dependent on a domain expert or from empirical testing that would yield the best result. Another problem is that the availability of data with regards to what is not normal is highly unavailable in real world scenarios making it difficult for traditional machine learning techniques to build a classification model. In this study, we propose a method that automatically determines the outlier threshold using a semi-supervised learning approach with autoencoders. To validate the performance of our proposed approach, we perform several experiments in comparison with traditional outlier detection approaches as well as an existing semi-supervised approach in one class classification, specifically OneClassSVM. The goal of this study is to eventually apply the method for autocalibration of anomaly detection of frames in video sequences. Initial results are also presented in a computer vision task.
format text
author Alampay, Raphael B
Abu, Patricia Angela R
author_facet Alampay, Raphael B
Abu, Patricia Angela R
author_sort Alampay, Raphael B
title Autocalibration of Outlier Threshold with Autoencoder Mean Probability Score
title_short Autocalibration of Outlier Threshold with Autoencoder Mean Probability Score
title_full Autocalibration of Outlier Threshold with Autoencoder Mean Probability Score
title_fullStr Autocalibration of Outlier Threshold with Autoencoder Mean Probability Score
title_full_unstemmed Autocalibration of Outlier Threshold with Autoencoder Mean Probability Score
title_sort autocalibration of outlier threshold with autoencoder mean probability score
publisher Archīum Ateneo
publishDate 2019
url https://archium.ateneo.edu/discs-faculty-pubs/190
https://dl.acm.org/doi/abs/10.1145/3375959.3375978
_version_ 1728621327414198272