From one-class to two-class classification by incorporating expert knowledge: Novelty detection in human behaviour

Abstract

One-class classification is the standard procedure for novelty detection. Novelty detection aims to identify observations that deviate from a determined normal behaviour. Only instances of one class are known, whereas so called novelties are unlabelled. Traditional novelty detection applies methods from the field of outlier detection. These standard one-class classification approaches have limited performance in many real business cases. The traditional techniques are mainly developed for industrial problems such as machine condition monitoring. When applying these to human behaviour, the performance drops significantly. This paper proposes a method that improves existing approaches by creating semi-synthetic novelties in order to have labelled data for the two classes. Expert knowledge is incorporated in the initial phase of this data generation process. The method was deployed on a real-life test case where the goal was to detect fraudulent subscriptions to a telecom family plan. This research demonstrates that the two-class expert model outperforms a one-class model on the semi-synthetic dataset. In a next step the model was validated on a real dataset. A fraud detection team of the company manually checked the top predicted novelties. The results show that incorporating expert knowledge to transform a one-class problem into a two-class problem is a valuable method.

Anomaly Detection in Electromechanical Systems by means of Deep-Autoencoder

“…And third, a probabilistic-based method: Gaussian mixture model. All the details regarding these techniques can be found in [9], [17].…”

“…The database provided by the Case Western Reserve University [17], is used to validate the proposed methodology and carry out the comparison with other methods. It was collected using accelerometers mounted at the drive end of motor which consists of normal data and faulty data.…”

Integrating Novelty Detection Capabilities with MSL Mastcam Operations to Enhance Data Analysis

“…This allows novelty detection systems to highlight abnormal data by evaluating how well (or how poorly) it can model the examples. These methods can be applied to various domains such as fraud detection based on card activity [16], human verification for websites from mouse and keyboard usage [17], fault detection for aerospace systems by analyzing ambient vibrations [3] and brain tumor identification using MRI images [4]. This work is based on previous work that developed novelty detection for multispectral images on Mars [5].…”

Performance Augmentation of Base Classifiers Using Adaptive Boosting Framework for Medical Datasets

“…Boosting in machine learning (ML) is achieved with the ability of the ML technique to boost the functionality of other classifers when combined [1]. Boosting is a very efective technique for solving bi-class classifcation problems [2]. Te boosting technique enhances the functioning and improves the correctness of any given learning algorithm by adding new modules.…”