Semantic Tagging and Support Vector Machines to Streamline the Analysis of Animal Accelerometry Data

Опубликовано 12 августа 2016, 2:52

Increasingly, animal biologists are taking advantage of low cost micro-sensor technology, by deploying accelerometers to monitor the behaviour and movement of a broad range of species. The result is an avalanche of complex tri-axial accelerometer data streams that capture observations and measurements of a wide range of animal body motion and posture parameters. We present a system which supports storing, visualizing, annotating and automatic recognition of activities in accelerometer data streams by integrating semantic annotation and visualization services with Support Vector Machine techniques.