Human behavioural analysis with self-organizing map for ambient assisted living

Abstract

Abstract-This paper presents a system for automatically classifying the resting location of a moving object in an indoor environment. The system uses an unsupervised neural network (Self Organising Feature Map) fully implemented on a low-cost, low-power automated home-based surveillance system, capable of monitoring activity level of elders living alone independently. The proposed system runs on an embedded platform with a specialised ceiling-mounted video sensor for intelligent activity monitoring. The system has the ability to learn resting locations, to measure overall activity levels and to detect specific events such as potential falls. First order motion information, including first order moving average smoothing, is generated from the 2D image coordinates (trajectories). A novel edge-based object detection algorithm capable of running at a reasonable speed on the embedded platform has been developed. The classification is dynamic and achieved in real-time. The dynamic classifier is achieved using a SOFM and a probabilistic model. Experimental results show less than 20% classification error, showing the robustness of our approach over others in literature with minimal power consumption. The head location of the subject is also estimated by a novel approach capable of running on any resource limited platform with power constraints.

Interoperable services based on activity monitoring in Ambient Assisted Living environments

“…In [8] a wide angle camera was used to monitor movement of a single room occupant. The systems uses visual information to build an edge map of the room which is then used to extract new edges representing the new or moving object.…”

“…This is to enable the system run for longer period when battery-powered. To satisfy these requirements, a novel edge-based differencing algorithm has been developed and implemented on the embedded ARM9 processor, rather than the standard background differencing algorithm [8], which requires the camera and the leopardboard to run continuously to update the background model. The system described in this article uses edge-based differencing, as edges are less sensitive to illumination changes.…”

“…Retraining of the system becomes necessary when the camera drifts slightly or when too many objects appear in the scene. Compared to [8], the proposed system is capable of identifying multiple objects and keeping track of the unique trajectory of those objects. This is then used for the personalised activity association.…”

IoT of active and healthy ageing: cases from indoor location analytics in the wild

“…1). More specifically, streamed Kinect-captured body trajectories are received and recorded by a client as a set of (x,y) locations of the body's center of mass [12]. The client then periodically applies a density based clustering algorithm [20] to the generated datasets, resulting in High Density Regions (HDR) of human activity.…”

“…Recently research has been done in indoor location classification techniques, intelligent monitoring approaches, and moving object tracking in real-life contexts [12]. Additionally machine learning methods have been utilized to estimate indoor location and movement speed [13], while time-series analysis has been used to identify abnormalities in continuous assessment of video trajectories [14].…”