Feature-driven Approximate Computing for Wearable Health-Monitoring Systems
Authors: 
Nishanth Chennagouni, Mashrafi Kajol, Diliang Chen, Dongpeng Xu, Qiaoyan YuAuthors Info & Claims
Pages 712 - 717
Abstract
Real-time health monitoring systems generate a large volume of sensing data, requiring tremendous processing time and storage space. Orthogonal to existing approximate computing mechanisms, this work proposes a Feature-Driven Approximation (FDApx) method to address the pressing need for fast data processing and a limited storage budget in wearable health monitoring devices. The proposed FDApx method reverses the features interested in high-level applications to derive approximation thresholds to retain feature-critical information, rather than aimlessly storing and transmitting all raw data. Case studies in an insole sensing system for fall risk assessment show that FDApx can reduce the data size by up to 87% over raw data and up to 85% over 2-bit precision reduction-based approximation. The approximation from FDApx only results in up to a 2% deviation in swing time; in contrast, the approximation based on precision reduction causes a 30% deviation in the same gait feature1.
References
[1]
Bruce H Alexander, Frederick P Rivara, and Marsha E Wolf. 1992. The cost and frequency of hospitalization for fall-related injuries in older adults.American journal of public health 82, 7 (1992), 1020–1023.
[2]
Woongki Baek and Trishul M. Chilimbi. 2010. Green: A Framework for Supporting Energy-Conscious Programming using Controlled Approximation. In Proc. PLDI’2010. ACM SIGPLAN.
[3]
Toth Mate Banos Oresti and Amft Oliver. 2014. REALDISP Activity Recognition Dataset. UCI Machine Learning Repository.
[4]
Gwen Bergen, Mark R Stevens, and Elizabeth R Burns. 2016. Falls and fall injuries among adults aged 65 years—United States, 2014. Morbidity and Mortality Weekly Report 65, 37 (2016), 993–998.
[5]
I. Bhati, Z. Chishti, S. Lu, and B. Jacob. 2015. Flexible auto-refresh: Enabling scalable and energy-efficient DRAM refresh reductions. In Proc. ISCA. 235–246.
[6]
Diliang Chen, Yi Cai, and Ming-Chun Huang. 2018. Customizable pressure sensor array: Design and evaluation. IEEE Sensors Journal 18, 15 (2018), 6337–6344.
[7]
F. Frustaci, D. Blaauw, D. Sylvester, and M. Alioto. 2015. Better-than-voltage scaling energy reduction in approximate SRAMs via bit dropping and bit reuse. In Proc. PATMOS. 132–139.
[8]
Avrajit Ghosh, Arnab Raha, and Amitava Mukherjee. 2020. Energy-Efficient IoT-Health Monitoring System using Approximate Computing. Internet of Things 9 (2020), 100166. https://doi.org/10.1016/j.iot.2020.100166
[9]
E. Hadi, S. Adrian, C. Luis, and B. Doug. 2012. Architecture Support for Disciplined Approximate Programming. SIGARCH Comput. Archit. News 40, 1 (March 2012), 301–312.
[10]
Ping Jiang, Jonathan Winkley, Can Zhao, Robert Munnoch, Geyong Min, and Laurence T. Yang. 2016. An Intelligent Information Forwarder for Healthcare Big Data Systems With Distributed Wearable Sensors. IEEE Systems Journal 10, 3 (2016), 1147–1159. https://doi.org/10.1109/JSYST.2014.2308324
[11]
A. B. Kahng and S. Kang. 2012. Accuracy-configurable adder for approximate arithmetic designs. In DAC Design Automation Conference 2012. 820–825.
[12]
C. B. Kushwah and S. K. Vishvakarma. 2014. A sub-threshold eight transistor (8T) SRAM cell design for stability improvement. In Proc. ICICDT. 1–4.
[13]
Briana Moreland, Ramakrishna Kakara, and Ankita Henry. 2020. Trends in nonfatal falls and fall-related injuries among adults aged 65 years—United States, 2012–2018. Morbidity and Mortality Weekly Report 69, 27 (2020), 875.
[14]
Adrian Sampson, Werner Dietl, Emily Fortuna, Danushen Gnanapragasam, Luis Ceze, and Dan Grossman. 2011. EnerJ: Approximate Data Types for Safe and General Low-Power Computation. SIGPLAN Not. 46, 6 (June 2011), 164–174.
[15]
A. Sampson, J. Nelson, K. Strauss, and L. Ceze. 2013. Approximate storage in solid-state memories. In Proc. 2013 46th Annual IEEE/ACM International Symposium on Microarchitecture (MICRO). 25–36.
[16]
M. Sparsh. 2016. A Survey of Techniques for Approximate Computing. ACM Comput. Surv. 48, 4, Article 62 (March 2016), 33 pages.
[17]
Daniel A Sterling, Judith A O’connor, and John Bonadies. 2001. Geriatric falls: injury severity is high and disproportionate to mechanism. Journal of Trauma and Acute Care Surgery 50, 1 (2001), 116–119.
[18]
Pruthvy Yellu, Landon Buell, Miguel Mark, Michel A. Kinsy, Dongpeng Xu, and Qiaoyan Yu. 2021. Security Threat Analyses and Attack Models for Approximate Computing Systems: From Hardware and Micro-Architecture Perspectives. ACM Trans. Des. Autom. Electron. Syst. 26, 4, Article 32 (Apr 2021), 31 pages.
[19]
Pruthvy Yellu, Nishanth Chennagouni, and Qiaoyan Yu. 2022. Leveraging Intermediate Node Evaluation to Secure Approximate Computing for AI Applications. In 2022 IEEE International Symposium on Technologies for Homeland Security (HST). 1–8. https://doi.org/10.1109/HST56032.2022.10025430
[20]
Wiebren Zijlstra and At L Hof. 2003. Assessment of spatio-temporal gait parameters from trunk accelerations during human walking. Gait & posture 18, 2 (2003), 1–10.
Index Terms
- Feature-driven Approximate Computing for Wearable Health-Monitoring Systems
Recommendations
Garment-integrated wearable sensing for knee joint monitoring
ISWC '14 Adjunct: Proceedings of the 2014 ACM International Symposium on Wearable Computers: Adjunct ProgramBody monitoring is one of the most intuitive and direct applications for technologies that are wearable. Wearable devices are capable of detecting body movements using wearable sensors, and using signals to capture anomalies as well as good patterns in ...
A reliable fall detection system based on wearable sensor and signal magnitude area for elderly residents
ICOST'10: Proceedings of the Aging friendly technology for health and independence, and 8th international conference on Smart homes and health telematicsFalls are the primary cause of accidents for elderly people and often result in serious injury and health threats. It is also the main obstacle to independent living for frail and elderly people. A reliable fall detector can reduce the fear of falling ...
An approximate compressor for wearable biomedical healthcare monitoring systems
CODES '15: Proceedings of the 10th International Conference on Hardware/Software Codesign and System SynthesisTechnology advancements as well as the Internet-of-Things paradigm enable the design of wearable personal healthcare monitoring systems. Ultra-low-power design is a challenging area for these battery-operated wearable devices, where the energy supply is ...
Comments
Please enable JavaScript to view thecomments powered by Disqus.Information & Contributors
Information
Published In
June 2024
797 pages
ISBN:9798400706059
DOI:10.1145/3649476
Copyright © 2024 Owner/Author.
This work is licensed under a Creative Commons Attribution International 4.0 License.
Sponsors
Publisher
Association for Computing Machinery
New York, NY, United States
Publication History
Published: 12 June 2024
Check for updates
Author Tags
Qualifiers
- Research-article
- Research
- Refereed limited
Funding Sources
Conference
GLSVLSI '24
Sponsor:
Acceptance Rates
Overall Acceptance Rate 312 of 1,156 submissions, 27%
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 251Total Downloads
- Downloads (Last 12 months)251
- Downloads (Last 6 weeks)116
Reflects downloads up to 10 Dec 2024
Other Metrics
Citations
View Options
View options
View or Download as a PDF file.
PDFeReader
View online with eReader.
eReaderHTML Format
View this article in HTML Format.
HTML FormatLogin options
Check if you have access through your login credentials or your institution to get full access on this article.
Sign in