Deep Activity Recognition Models with Triaxial Accelerometers

Abstract

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.

Cited by in corpus (20)

• Deep Learning for Sensor-based Activity Recognition: A Survey
• Ensembles of Deep LSTM Learners for Activity Recognition using Wearables
• Human Activity Recognition using Inertial, Physiological and Environmental Sensors: a Comprehensive Survey
• Deep Learning for Sensor-based Human Activity Recognition: Overview, Challenges and Opportunities
• Layer-wise training convolutional neural networks with smaller filters for human activity recognition using wearable sensors
• Deep Learning-based Cattle Activity Classification Using Joint Time-frequency Data Representation
• A Novel Multi-Stage Training Approach for Human Activity Recognition from Multimodal Wearable Sensor Data Using Deep Neural Network
• DFTerNet: Towards 2-bit Dynamic Fusion Networks for Accurate Human Activity Recognition
• Self-supervised transfer learning of physiological representations from free-living wearable data
• Deep Learning-Based Gait Recognition Using Smartphones in the Wild
• Siamese Networks for Weakly Supervised Human Activity Recognition
• DanHAR: Dual Attention Network For Multimodal Human Activity Recognition Using Wearable Sensors
• Unsupervised Embedding Learning for Human Activity Recognition Using Wearable Sensor Data
• Learning behavioral context recognition with multi-stream temporal convolutional networks
• Guided-GAN: Adversarial Representation Learning for Activity Recognition with Wearables
• Attend And Discriminate: Beyond the State-of-the-Art for Human Activity Recognition using Wearable Sensors
• Co-Morbidity Exploration on Wearables Activity Data Using Unsupervised Pre-training and Multi-Task Learning
• Deep CHORES: Estimating Hallmark Measures of Physical Activity Using Deep Learning
• Understanding and Improving Recurrent Networks for Human Activity Recognition by Continuous Attention
• Landscape of Big Medical Data: A Pragmatic Survey on Prioritized Tasks