Towards the detection of unusual temporal events during activities using HMMs

Abstract

Most of the systems for recognition of activities aim to identify a set of normal human activities. Data is either recorded by computer vision or sensor based networks. These systems may not work properly if an unusual event or abnormal activity occurs, especially ones that have not been encountered in the past. By definition, unusual events are mostly rare and unexpected, and therefore very little or no data may be available for training. In this paper, we focus on the challenging problem of detecting unusual temporal events in a sensor network and present three Hidden Markov Models (HMM) based approaches to tackle this problem. The first approach models each normal activity separately as an HMM and the second approach models all the normal activities together as one common HMM. If the likelihood is lower than a threshold, an unusual event is identified. The third approach models all normal activities together in one HMM and approximates an HMM for the the unusual events. All the methods train HMM models on data of the usual events and do not require training data from the unusual events. We perform our experiments on a Locomotion Analysis dataset that contains gyroscope, force sensor, and accelerometer readings. To test the performance of our approaches, we generate five types of unusual events that represent random activity, extremely unusual events, unusual events similar to specific normal activities, no or little motion and normal activity followed by no or little motion. Our experiments suggest that for a moderately sized time frame window, these approaches can identify all the five types of unusual events with high confidence.

Review of fall detection techniques: A data availability perspective

“…In a realistic setting, due to the lack of availability of sufficient data for falls and the lack of knowledge and understanding of what those falls might be, approaches based on outlier/anomaly detection (see Taxonomy (II)d in Figure 1) and one-class classification (see Taxonomy (II)e in Figure 1) [62,63,64,65] show that falls can be identified without seeing them in the past or specific domain knowledge about them. Below, we review techniques that build classification models using only the normal activities data and treat fall as an anomaly.…”

Event Detection in Complex Environments: An Effective and Efficient Machine-Learning-Based Framework (S)

“…Moreover, even if the data of normal activities are not sufficient, then these techniques can produce excessive false positives. Recent research projects [4], [22], [16] show that falls can be identified without actually acquiring them. As evidenced by Klenk et al [11], simulated falls differ significantly from real-world falls.…”

“…Their results show high detection rates for falls on two activity recognition data sets, albeit with an increase in the number of false alarms. In [16], Khan et al experimentally show that this approach can give better results than supervised classification with limited fall data. When the number of fall data increases, the performance of supervised classifiers improves, but falling data collection can take a long time.…”

Detecting falls with X-Factor Hidden Markov Models

“…To detect falls using traditional HMM approaches (HM M 1 and HM M 2), typically, a threshold is set on the likelihood of the data given an HMM trained on this 'normal' data. This threshold is normally chosen as the maximum of negative log-likelihood [24], and can be interpreted as a slider between raising false alarms or risking missed alarms [15]. A major drawback of this approach is that it assumes that the data for each normal activity is correctly labelled and sensor readings are non-spurious.…”