AHAR: Adaptive CNN for Energy-efficient Human Activity Recognition in Low-power Edge Devices
Authors:
- Nafiul RashidNRNafiul Rashid
- Berken Utku DemirelBDBerken Utku Demirel
- Mohammad Abdullah Al FaruqueMFMohammad Abdullah Al Faruque
Preprint
Abstract
Human Activity Recognition (HAR) is one of the key applications of health monitoring that requires continuous use of wearable devices to track daily activities. This paper proposes an Adaptive CNN for energy-efficient HAR (AHAR) suitable for low-power edge devices. Unlike traditional early exit architecture that makes the exit decision based on classification confidence, AHAR proposes a novel adaptive architecture that uses an output block predictor to select a portion of the baseline architecture to use during the inference phase. Experimental results show that traditional early exit architectures suffer from performance loss whereas our adaptive architecture provides similar or better performance as the baseline one while being energy-efficient. We validate our methodology in classifying locomotion activities from two datasets- Opportunity and w-HAR. Compared to the fog/cloud computing approaches for the Opportunity dataset, our baseline and adaptive architecture shows a comparable weighted F1 score of 91.79%, and 91.57%, respectively. For the w-HAR dataset, our baseline and adaptive architecture outperforms the state-of-the-art works with a weighted F1 score of 97.55%, and 97.64%, respectively. Evaluation on real hardware shows that our baseline architecture is significantly energy-efficient (422.38x less) and memory-efficient (14.29x less) compared to the works on the Opportunity dataset. For the w-HAR dataset, our baseline architecture requires 2.04x less energy and 2.18x less memory compared to the state-of-the-art work. Moreover, experimental results show that our adaptive architecture is 12.32% (Opportunity) and 11.14% (w-HAR) energy-efficient than our baseline while providing similar (Opportunity) or better (w-HAR) performance with no significant memory overhead.Keywords
All Related Versions
This publication has 25 references indexed in Scilit:
- Wireless Qi-Powered, Multinodal and Multisensory Body Area Network for Mobile HealthIEEE Internet of Things Journal, 2020
- Deep Learning for Heterogeneous Human Activity Recognition in Complex IoT ApplicationsIEEE Internet of Things Journal, 2020
- HEAR: Fog-Enabled Energy-Aware Online Human Eating Activity RecognitionIEEE Internet of Things Journal, 2020
- Why Should We Add Early Exits to Neural Networks?Cognitive Computation, 2020
- Hierarchical Classification for Constrained IoT Devices: A Case Study on Human Activity RecognitionIEEE Internet of Things Journal, 2020
- Eyeriss v2: A Flexible Accelerator for Emerging Deep Neural Networks on Mobile DevicesIEEE Journal on Emerging and Selected Topics in Circuits and Systems, 2019
- Human activity recognition with smartphone sensors using deep learning neural networksExpert Systems with Applications, 2016
- A clinical view on the development of technology-based tools in managing Parkinson's diseaseMovement Disorders, 2016
- Measuring and Influencing Physical Activity with Smartphone Technology: A Systematic ReviewSports Medicine, 2014
- A threshold-based fall-detection algorithm using a bi-axial gyroscope sensorMedical Engineering & Physics, 2008