Activity Recognition and Abnormal Behaviour Detection with Recurrent Neural Networks

Damla Arifoğlu, Abdelhamid Bouchachia

Procedia Computer Science · 2017 · 178 citations · 23 references

DOIFull text

Open access

Concepts

TL;DR

Very few studies have addressed activity recognition and abnormal behaviour detection in dementia care, largely due to a lack of experimental data. The study investigates activity recognition and abnormal behaviour detection in elderly dementia patients and proposes a synthetic data generation method to mitigate data scarcity. The authors evaluate Vanilla, LSTM, and GRU RNNs for sequence labeling of activity and abnormal behaviour, comparing their performance to SVM, NB, HMM, HSMM, and CRF baselines. RNNs perform competitively with state‑of‑the‑art classifiers such as SVM, NB, HMM, HSMM, and CRF.

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), Na¨ıve 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.

References

23