Personal models for eHealth - improving user-dependent human activity recognition models using noise injection
- 13 February 2017
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-7
Abstract
In this paper, a noise injection method to improve personal recognition models is presented. The idea of the method is to build more general recognition models for eHealth using a small original data set and by expanding the area covered by training data using noise injection. This way, it is possible to train models that are less vulnerable to changing conditions, and thus more accurate, but still the data gathering phase can be non-burdensome. The proposed method was tested using two classifiers (linear discriminant analysis and quadratic discriminant analysis) and three human activity recognition data sets collected using inertial sensors of a smartphone. Two of these data sets are open data sets. The results show that noise injection improves the true positive recognition rates. With first data set the improvement varies from 1.3 to 2.0 percentage units, with second from 1.4 to 4.5 percentage units, and with third the highest improvement was 2.5 percentage units. Moreover, the results show that the method improves precision and reduces false positive rates. In addition, experiments were made using different training set sizes to show that the improvement in true positive rate is bigger if the original training data set is small. In this study, the method is experimented using human activity data sets but it is not limited to this application area and can be used with any time series data.Keywords
This publication has 17 references indexed in Scilit:
- Reducing Uncertainty in User-independent Activity Recognition - A Sensor Fusion-based Approach2016
- Learning from Life-Logging Data by Hybrid HMM: A Case Study on Active States Prediction2016
- Transition-Aware Human Activity Recognition Using SmartphonesNeurocomputing, 2016
- Fusion of Smartphone Motion Sensors for Physical Activity RecognitionSensors, 2014
- Synthetic pattern generation for imbalanced learning in image retrievalPattern Recognition Letters, 2012
- Performance metrics for activity recognitionACM Transactions on Intelligent Systems and Technology, 2011
- The Jigsaw continuous sensing engine for mobile phone applications2010
- Misleading worm signature generators using deliberate noise injection2006
- Exploiting Global and Local Decisions for Multimodal Biometrics VerificationIEEE Transactions on Signal Processing, 2004
- k-nearest neighbors directed noise injection in multilayer perceptron trainingIEEE Transactions on Neural Networks, 2000