Optimising sampling rates for accelerometer-based human activity recognition
| Autor: | Aftab Khan, Thomas Plötz, Sebastian Mellor, Nils Y. Hammerla |
|---|---|
| Rok vydání: | 2016 |
| Předmět: |
Computer science
010401 analytical chemistry Sampling (statistics) 020206 networking & telecommunications Sample (statistics) 02 engineering and technology computer.software_genre Accelerometer 01 natural sciences 0104 chemical sciences Activity recognition Sampling (signal processing) Artificial Intelligence Signal Processing 0202 electrical engineering electronic engineering information engineering Benchmark (computing) Computer Vision and Pattern Recognition Data mining computer Software Simulation Energy (signal processing) Statistical hypothesis testing |
| Zdroj: | Pattern Recognition Letters. 73:33-40 |
| ISSN: | 0167-8655 |
| Popis: | Activity recognition with wearable sensing typically uses non-optimal sampling rates.Sampling rates are up to 57% higher than necessary leading to waste of resources.We develop a method for automated, task specific optimisation of sampling rates.Using our method we can maintain recognition performance for the optimal rates.Experimental validation through recognition experiments using classification. Real-world deployments of accelerometer-based human activity recognition systems need to be carefully configured regarding the sampling rate used for measuring acceleration. Whilst a low sampling rate saves considerable energy, as well as transmission bandwidth and storage capacity, it is also prone to omitting relevant signal details that are of interest for contemporary analysis tasks. In this paper we present a pragmatic approach to optimising sampling rates of accelerometers that effectively tailors recognition systems to particular scenarios, thereby only relying on unlabelled sample data from the domain. Employing statistical tests we analyse the properties of accelerometer data and determine optimal sampling rates through similarity analysis. We demonstrate the effectiveness of our method in experiments on 5 benchmark datasets where we determine optimal sampling rates that are each substantially below those originally used whilst maintaining the accuracy of reference recognition systems. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect