A Deep Learning Approach to on-Node Sensor Data Analytics for Mobile or Wearable Devices

By Daniele Ravì, Charence Wong, Benny P. L. Lo, Guang-Zhong Yang. 2017

395 citations recorded by the source corpus.

The increasing popularity of wearable devices in recent years means that a diverse range of physiological and functional data can now be captured continuously for applications in sports, wellbeing, and healthcare. This wealth of information requires efficient methods of classification and analysis where deep learning is a promising technique for large-scale data analytics. While deep learning has been successful in implementations that utilize high-performance computing platforms, its use on low-power wearable devices is limited by resource constraints. In this paper, we propose a deep learning methodology, which combines features learned from inertial sensor data together with complementary information from a set of shallow features to enable accurate and real-time activity classification. The design of this combined method aims to overcome some of the limitations present in a typical deep learning framework where on-node computation is required. To optimize the proposed method for real-time on-node computation, spectral domain preprocessing is used before the data are passed onto the deep learning framework. The classification accuracy of our proposed deep learning approach is evaluated against state-of-the-art methods using both laboratory and real world activity datasets. Our results show the validity of the approach on different human activity datasets, outperforming other methods, including the two methods used within our combined pipeline. We also demonstrate that the computation times for the proposed method are consistent with the constraints of real-time on-node processing on smartphones and a wearable sensor platform.

Subfields: Biomedical Engineering, Computer Vision and Pattern Recognition, Physiology

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Biomedical Engineering

In Computer Vision and Pattern Recognition

In Physiology

Athanasios V. Vasilakos

Citations in the corpus

Deep Learning for IoT Big Data and Streaming Analytics: A Survey (2017, methodology): “[202] have reported the development of a fitness app for mobile devices that uses DL for classifying human activities.”
The Future of Healthcare Internet of Things: A Survey of Emerging Technologies (2020, methodology): “To validate the importance of the on-node processing capabilities, authors in [121] have implemented a DL based proposal that adapts to the low resources by reducing the number of hidden layers in the neural network.”
A Survey of Deep Learning: Platforms, Applications and Emerging Research Trends (2018, background): “[110] applied deep learning to human activity recognition using inertial sensor data from wearable devices.”
Deep Learning in Mobile and Wireless Networking: A Survey (2018, background): “), or triggering alarms to remind users of taking medical actions [235].”
Deep learning for healthcare: review, opportunities and challenges (2018, background): “In fact, running an efficient and reliable deep architecture on a mobile device to process noisy and complex sensor data is still a challenging task that is likely to drain the device resources [101].”
Tackling Climate Change with Machine Learning (2019, background): “[339] Daniele Ravi, Charence Wong, Benny Lo, and Guang-Zhong Yang.”
Network Intrusion Detection for IoT Security Based on Learning Techniques (2019, background): “The same authors proposed in [159] a combination of shallow learned features from a deep learning approach to enable accurate and real-time activity classification.”
Deep Learning for Sensor-based Human Activity Recognition (2020, methodology): “atures and a neural network is a potential plan to achieve real-time activity recognition on a mobile device. In addition to the cascade structure of hand-crafted features and deep learning features, [118] proposed to arranged the deep learning features and hand-crafted features in parallel before f”
Comparison of Data Preprocessing Approaches for Applying Deep Learning to Human Activity Recognition in the Context of Industry 4.0 (2018, methodology): “Increasing the length of the segments can improve training required to obtain cause a delay in response for real-time applications [23] and restrict the application scenarios.”