Abstract
Advances in integrated sensors and low-power electronics have led to an increase in the use of wearable devices for health and activity monitoring applications. These devices have severe limitations on weight, form-factor, and battery size since they have to be comfortable to wear. Therefore, they must minimize the total platform energy consumption while satisfying functionality (e.g., accuracy) and performance requirements. Optimizing the platform-level energy efficiency requires considering both the sensor and processing subsystems. To this end, this paper presents a sensor-classifier co-optimization technique with human activity recognition as a driver application. The proposed technique dynamically powers down the accelerometer sensors and controls their sampling rate as a function of the user activity. It leads to a 49% reduction in total platform energy consumption with less than 1% decrease in activity recognition accuracy.
| Original language | English (US) |
|---|---|
| Title of host publication | 2019 IEEE International Conference on Embedded Software and Systems, ICESS 2019 |
| Publisher | Institute of Electrical and Electronics Engineers Inc. |
| ISBN (Electronic) | 9781728124377 |
| DOIs | |
| State | Published - Jun 1 2019 |
| Event | 2019 IEEE International Conference on Embedded Software and Systems, ICESS 2019 - Las Vegas, United States Duration: Jun 2 2019 → Jun 3 2019 |
Publication series
| Name | 2019 IEEE International Conference on Embedded Software and Systems, ICESS 2019 |
|---|
Conference
| Conference | 2019 IEEE International Conference on Embedded Software and Systems, ICESS 2019 |
|---|---|
| Country | United States |
| City | Las Vegas |
| Period | 6/2/19 → 6/3/19 |
Fingerprint
Keywords
- Flexible hybrid electronics (FHE)
- Health monitoring
- Human activity recognition
- IoT
- Wearable computing
ASJC Scopus subject areas
- Software
- Instrumentation
- Computer Networks and Communications
- Hardware and Architecture
Cite this
Sensor-classifier co-optimization for wearable human activity recognition applications. / Nk, Anish; Bhat, Ganapati; Park, Jaehyun; Lee, Hyung Gyu; Ogras, Umit.
2019 IEEE International Conference on Embedded Software and Systems, ICESS 2019. Institute of Electrical and Electronics Engineers Inc., 2019. 8782506 (2019 IEEE International Conference on Embedded Software and Systems, ICESS 2019).Research output: Chapter in Book/Report/Conference proceeding › Conference contribution
}
TY - GEN
T1 - Sensor-classifier co-optimization for wearable human activity recognition applications
AU - Nk, Anish
AU - Bhat, Ganapati
AU - Park, Jaehyun
AU - Lee, Hyung Gyu
AU - Ogras, Umit
PY - 2019/6/1
Y1 - 2019/6/1
N2 - Advances in integrated sensors and low-power electronics have led to an increase in the use of wearable devices for health and activity monitoring applications. These devices have severe limitations on weight, form-factor, and battery size since they have to be comfortable to wear. Therefore, they must minimize the total platform energy consumption while satisfying functionality (e.g., accuracy) and performance requirements. Optimizing the platform-level energy efficiency requires considering both the sensor and processing subsystems. To this end, this paper presents a sensor-classifier co-optimization technique with human activity recognition as a driver application. The proposed technique dynamically powers down the accelerometer sensors and controls their sampling rate as a function of the user activity. It leads to a 49% reduction in total platform energy consumption with less than 1% decrease in activity recognition accuracy.
AB - Advances in integrated sensors and low-power electronics have led to an increase in the use of wearable devices for health and activity monitoring applications. These devices have severe limitations on weight, form-factor, and battery size since they have to be comfortable to wear. Therefore, they must minimize the total platform energy consumption while satisfying functionality (e.g., accuracy) and performance requirements. Optimizing the platform-level energy efficiency requires considering both the sensor and processing subsystems. To this end, this paper presents a sensor-classifier co-optimization technique with human activity recognition as a driver application. The proposed technique dynamically powers down the accelerometer sensors and controls their sampling rate as a function of the user activity. It leads to a 49% reduction in total platform energy consumption with less than 1% decrease in activity recognition accuracy.
KW - Flexible hybrid electronics (FHE)
KW - Health monitoring
KW - Human activity recognition
KW - IoT
KW - Wearable computing
UR - http://www.scopus.com/inward/record.url?scp=85070901127&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85070901127&partnerID=8YFLogxK
U2 - 10.1109/ICESS.2019.8782506
DO - 10.1109/ICESS.2019.8782506
M3 - Conference contribution
T3 - 2019 IEEE International Conference on Embedded Software and Systems, ICESS 2019
BT - 2019 IEEE International Conference on Embedded Software and Systems, ICESS 2019
PB - Institute of Electrical and Electronics Engineers Inc.
ER -