Activity Recognition and Abnormal Behaviour Detection with Recurrent Neural Networks
Authors: Arifoglu, D. and Bouchachia, A.
Journal: Procedia Computer Science
Volume: 110
Pages: 86-93
eISSN: 1877-0509
DOI: 10.1016/j.procs.2017.06.121
Abstract:In this paper, we study the problem of activity recognition and abnormal behaviour detection for elderly people with dementia. Very few studies have attempted to address this problem presumably because of the lack of experimental data in the context of dementia care. In particular, the paper investigates three variants of Recurrent Neural Networks (RNNs): Vanilla RNNs (VRNN), Long Short Term RNNs (LSTM) and Gated Recurrent Unit RNNs (GRU). Here activity recognition is considered as a sequence labelling problem, while abnormal behaviour is flagged based on the deviation from normal patterns. To provide an adequate discussion of the performance of RNNs in this context, we compare them against the state-of-art methods such as Support Vector Machines (SVMs), NäIve Bayes (NB), Hidden Markov Models (HMMs), Hidden Semi-Markov Models (HSMM) and Conditional Random Fields (CRFs). The results obtained indicate that RNNs are competitive with those state-of-art methods. Moreover, the paper presents a methodology for generating synthetic data reflecting on some behaviours of people with dementia given the difficulty of obtaining real-world data.
https://eprints.bournemouth.ac.uk/29720/
Source: Scopus
Activity Recognition and Abnormal Behaviour Detection with Recurrent Neural Networks
Authors: Arifoglu, D. and Bouchachia, A.
Journal: 14TH INTERNATIONAL CONFERENCE ON MOBILE SYSTEMS AND PERVASIVE COMPUTING (MOBISPC 2017) / 12TH INTERNATIONAL CONFERENCE ON FUTURE NETWORKS AND COMMUNICATIONS (FNC 2017) / AFFILIATED WORKSHOPS
Volume: 110
Pages: 86-93
ISSN: 1877-0509
DOI: 10.1016/j.procs.2017.06.121
https://eprints.bournemouth.ac.uk/29720/
Source: Web of Science (Lite)
Activity Recognition and Abnormal Behaviour Detection with Recurrent Neural Networks
Authors: Arifoglu, D. and Bouchachia, A.
Conference: MOBISPC 2017: 14th International Conference on Mobile Systems and Pervasive Computing:
Pages: 86-93
Abstract:© 2017 The Authors. Published by Elsevier B.V. In this paper, we study the problem of activity recognition and abnormal behaviour detection for elderly people with dementia. Very few studies have attempted to address this problem presumably because of the lack of experimental data in the context of dementia care. In particular, the paper investigates three variants of Recurrent Neural Networks (RNNs): Vanilla RNNs (VRNN), Long Short Term RNNs (LSTM) and Gated Recurrent Unit RNNs (GRU). Here activity recognition is considered as a sequence labelling problem, while abnormal behaviour is flagged based on the deviation from normal patterns. To provide an adequate discussion of the performance of RNNs in this context, we compare them against the state-of-art methods such as Support Vector Machines (SVMs), NäIve Bayes (NB), Hidden Markov Models (HMMs), Hidden Semi-Markov Models (HSMM) and Conditional Random Fields (CRFs). The results obtained indicate that RNNs are competitive with those state-of-art methods. Moreover, the paper presents a methodology for generating synthetic data reflecting on some behaviours of people with dementia given the difficulty of obtaining real-world data.
https://eprints.bournemouth.ac.uk/29720/
Source: BURO EPrints