Skip to Main content Skip to Navigation
New interface
Conference papers

Evaluating Sequence Discovery Systems in an Abstraction-Aware Manner

Abstract : Activity discovery is a challenging machine learning problem where we seek to uncover new or altered behavioural patterns in sensor data. In this paper we motivate and introduce a novel approach to evaluating activity discovery systems. Pre-annotated ground truths, often used to evaluate the performance of such systems on existing datasets, may exist at different levels of abstraction to the output of the output produced by the system. We propose a method for detecting and dealing with this situation, allowing for useful ground truth comparisons. This work has applications for activity discovery, and also for related fields. For example, it could be used to evaluate systems intended for anomaly detection, intrusion detection, automated music transcription and potentially other applications.
Document type :
Conference papers
Complete list of metadata

Cited literature [10 references]  Display  Hide  Download
Contributor : Hal Ifip Connect in order to contact the contributor
Submitted on : Friday, June 22, 2018 - 11:45:10 AM
Last modification on : Friday, June 22, 2018 - 12:00:51 PM
Long-term archiving on: : Monday, September 24, 2018 - 4:15:25 PM


Files produced by the author(s)


Distributed under a Creative Commons Attribution 4.0 International License



Eoin Rogers, Robert J. Ross, John D. Kelleher. Evaluating Sequence Discovery Systems in an Abstraction-Aware Manner. 14th IFIP International Conference on Artificial Intelligence Applications and Innovations (AIAI), May 2018, Rhodes, Greece. pp.261-272, ⟨10.1007/978-3-319-92007-8_23⟩. ⟨hal-01821052⟩



Record views


Files downloads