Deep Activity Recognition Models with Triaxial Accelerometers
This work addresses the immature accuracy and data scarcity in activity recognition for mobile and wearable devices, offering a hybrid method that is incremental but with strong gains.
The paper tackles the problem of human activity recognition using triaxial accelerometers by proposing deep learning models and a hybrid DL-HMM approach, resulting in substantial recognition improvement over state-of-the-art methods on real-world datasets.
Despite the widespread installation of accelerometers in almost all mobile phones and wearable devices, activity recognition using accelerometers is still immature due to the poor recognition accuracy of existing recognition methods and the scarcity of labeled training data. We consider the problem of human activity recognition using triaxial accelerometers and deep learning paradigms. This paper shows that deep activity recognition models (a) provide better recognition accuracy of human activities, (b) avoid the expensive design of handcrafted features in existing systems, and (c) utilize the massive unlabeled acceleration samples for unsupervised feature extraction. Moreover, a hybrid approach of deep learning and hidden Markov models (DL-HMM) is presented for sequential activity recognition. This hybrid approach integrates the hierarchical representations of deep activity recognition models with the stochastic modeling of temporal sequences in the hidden Markov models. We show substantial recognition improvement on real world datasets over state-of-the-art methods of human activity recognition using triaxial accelerometers.