Super Low Resolution RF Powered Accelerometers for Alerting on Hospitalized Patient Bed Exits

Abstract

Falls have serious consequences and are prevalent in acute hospitals and nursing homes caring for older people. Most falls occur in bedrooms and near the bed. Technological interventions to mitigate the risk of falling aim to automatically monitor bed-exit events and subsequently alert healthcare personnel to provide timely supervisions. We observe that frequency-domain information related to patient activities exist predominantly in very low frequencies. Therefore, we recognise the potential to employ a low resolution acceleration sensing modality in contrast to powering and sensing with a conventional MEMS (Micro Electro Mechanical System) accelerometer. Consequently, we investigate a batteryless sensing modality with low cost wirelessly powered Radio Frequency Identification (RFID) technology with the potential for convenient integration into clothing, such as hospital gowns. We design and build a passive accelerometerbased RFID sensor embodiment-ID-Sensor-for our study. The sensor design allows deriving ultra low resolution acceleration data from the rate of change of unique RFID tag identifiers in accordance with the movement of a patient's upper body. We investigate two convolutional neural network architectures for learning from raw RFID-only data streams and compare performance with a traditional shallow classifier with engineered features. We evaluate performance with 23 hospitalized older patients. We demonstrate, for the first time and to the best of knowledge, that: i) the low resolution acceleration data embedded in the RF powered ID-Sensor data stream can provide a practicable method for activity recognition; and ii) highly discriminative features can be efficiently learned from the raw RFID-only data stream using a fully convolutional network architecture.

Wearable Textile UHF-RFID Sensors: A Systematic Review

“…(o) Health-care-based textile UHF-RFID accelerometer sensor for alerting on hospitalized patient bed exits with a super low resolution (adapted from ref. [9]). (p) Textile UHF-RFID tag for exploring the impact from geometrical variations and deformations (adapted from ref.…”

“…[6]); (g) health-care-based textile UHF-RFID biosignal pressure sensors for infant heart monitoring, integrated with a modular software framework for interrogation, data storage and post-processing [7,8]); (h) health-care-based textile UHF-RFID accelerometer sensor for alerting on hospitalized patient bed exits with a superlow resolution (adapted from ref. [9]); (i) textile UHF-RFID concentration sensor for concentration detection using a sensing antenna (adapted from ref. [10]).…”

“…Machine learning technology for textile UHF-RFID sensors is also a novel research direction [82]. As mentioned in [9], a classical machine learning algorithm is used, which is capable of generating probabilistic models using feature vectors extracted from segments. As a part of machine learning, deep neural networks [83] are useful for feature extraction and classifier building when the textile UHF-RFID sensors are applied in some complex conditions for numerous data analysis.…”

“…Early efforts from textile UHF-RFID techniques were focused on feasibility, reliability and fundamental functions of tags, mainly including identification and tracking for garments in the fabrication process [4]. In recent years since 2012, the research targets of textile UHF-RFID techniques changed from the fundamental researches to tackle scenario-based applications such as exercise tracking [5,6], health-care monitoring [7][8][9], concentration detection of solutions [10], strain capacity [11] and associated applications. In order to achieve these aims, substantial efforts have been devoted to the development of textile sensors integrated into textile UHF-RFID tags.…”

<i>BAAS</i>: Backscatter as a Sensor for Ultra-Low-Power Context Recognition

“…Context recognition has attracted many researchers for various daily life applications. For example, in elderly care, the detection of leaving bed reduces the burden on caregivers [1]. The detection of opening and closing doors and windows is useful for adaptive control of air conditioning and intrusion detection [2].…”