.png){kind=icon}
.png){kind=icon}
Return
IoT Based Longitudinal Monitoring of Activity and Posture Transitions in Smart Homes
.png){kind=icon}
PRE
AI
H
E
DOI：10.1109/southeastcon42311.2019.9020328.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
Substantial growth in the number of older adults around the globe, typically with multiple chronic conditions and insufficient number of geriatricians, created significant need for technological solutions that can support independence of older adults in their own homes, also known as aging in place. Continuous monitoring of activities of daily living provides opportunity for monitoring of behavior and the overall state of the users. Although many projects use commercially available wearable sensors based on low power/low range sensors, rapid development of IoT infrastructure provides new integration modalities. We present an implementation of a WiFi based IoT sensor for monitoring of user's activity and posture, using ESP8266 controller and BN0055 Inertial Measurement Unit (IMU). Sensor intelligence facilitates low duty cycle that extends battery life, which is necessary for prolonged and longitudinal monitoring. We developed a simple model to recognize likely posture transitions that can be run on limited resources of ESP8266, our primary focus is recognition of sitting-to-standing (Si2St) and standing-to-sitting (St2Si) transitions. All probable events are transmitted to a home server/gateway, in our case Raspberry Pi 3+, for final processing and storage in subject's record on a remote medical server. In this paper we present system implementation, signal processing, and results from the pilot test of the system.
AI Summary
Key information extracted from the uploaded paper, including a brief overview, abstract, background, key highlights, visual analysis, and future outlook.
Journal
I
IF:
0
Papers:
19
Citations:
0
Organization
Cited Papers