[论文笔记] Super Low Resolution RF Powered Accelerometers for Alerting on Hospitalized Patient Bed Exits

原文链接：Super Low Resolution RF Powered Accelerometers for Alerting on Hospitalized Patient Bed Exits | IEEE Conference Publication | IEEE Xplore

---

Motivation

1. Current approaches to recognize bed-exits using pressure sensors—for example, pressure mats —are shown to be ineffective in reducing falls in clinical trials.

2. Older people have expressed privacy concerns with the use of camera-based technologies. 

3.  It is observed that patient activity-related information in the frequency domain is found in very low frequencies of typically less than 4 Hz. => Therefore, we recognize the potential to use a low-resolution acceleration sensor (RF powered or passive sensing sensor with low-cost batteryless RFID) to gather human motion information 

---

Methodology (论文原图，侵删)

A bed-exit event is recognized as a transition from in-bed to out-of-bed.  The approach to recognize bed-exits is built around the observations that:

• human motion information can be extracted from the channel state measurements, RSSI and phase made by an RFID reader;
• low-frequency information associated with patient movements from the ID-Sensor where the data stream from the reader can also be used to extract low-resolution acceleration information. 

Classification Problem 

This paper treats the problem of determining whether a patient is in-bed or out- of-bed to be a binary classification problem. Subsequently, a bed-exit event is recognized as a change in classification from in-bed to out-of-bed.

• The data sequence collected is a time series and a single tag reading consists of the 4-tuple: i)reader antenna ID (aID); ii)RSSI; iii)Phase; and iv) tag ID (ID).
• For a given segment Si with respect to a given tag reading, i, we used the features summarized in Table I