Accelerometer-based bed occupancy detection for automatic, non-invasive long-term cough monitoring

نویسندگان

چکیده

We present a new machine learning based bed-occupancy detection system that uses the accelerometer signal captured by bed-attached consumer smartphone. Automatic is necessary for automatic long-term cough monitoring, since time which monitored patient occupies bed required to accurately calculate rate. Accelerometer measurements are more cost effective and less intrusive than alternatives such as video monitoring or pressure sensors. A 249-hour dataset of manually-labelled acceleration signals gathered from seven patients undergoing treatment tuberculosis (TB) was compiled experimentation. These characterised brief activity bursts interspersed with long periods little no activity, even when occupied. To process them effectively, we propose an architecture consisting three interconnected components. An occupancy-change detector locates instances at occupancy likely have changed, occupancy-interval classifies between detected changes occupancy-state corrects falsely-identified changes. Using short-term memory (LSTM) networks, this demonstrated achieve AUC 0.94. When integrated into complete system, daily rate TB determined over period 14 days. As colony forming unit (CFU) counts decreased positivity (TPP) increased, measured decreased, indicating treatment. This provides first indication on bed-mounted may non-invasive, non-intrusive cost-effective means recovery patients.

برای دانلود رایگان متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Reflectance-based detection for long term environmental monitoring

Here, the potential of colorimetric sensors utilizing porphyrin indicators for long term environmental monitoring is demonstrated. Prototype devices based on commercial color sensing chips (six per device) were combined with in-house developed algorithms for data analysis. The devices are intended to provide real-time sensing of threats. An initial outdoor data set was collected using prototype...

متن کامل

Sensor-based System for Automatic Cough Detection and Classification

Cough detection and classification present necessary tools for the evaluation of pathology severity in chronic illnesses. In literature, several approaches have been proposed for this aim. The latter presented a relative success since none of them allow a standardized exploitation and interpretation of sensors results in order to provide an efficient cough detection and classification. This pap...

متن کامل

Long-term recording and automatic analysis of cough using filtered acoustic signals and movements on static charge sensitive bed.

Reliable long-term assessment of cough is necessary in many clinical and scientific settings. A new method for long-term recording and automatic analysis of cough is presented. The method is based on simultaneous recording of two independent signals: high-pass filtered cough sounds and cough-induced fast movements of the body. The acoustic signals are recorded with a dynamic microphone in the a...

متن کامل

Diagnostic Tools of Waldenströms Macroglobulinemia - Best Possibilities for Non-invasive and Long-term Disease Monitoring.

Waldenströms macroglobulinemia (WM) is a B-cell malignancy characterized by high level of monoclonal immunoglobulin M (IgM) paraprotein in blood serum and associated with the bone marrow infiltration by malignant cells with lymphoplasmacytic differentiation. WM remains incurable advances in therapy. Most of WM cases are associated with a somatic point mutation L265P in MYD88. Significantly high...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

ژورنال

عنوان ژورنال: IEEE Access

سال: 2023

ISSN: ['2169-3536']

DOI: https://doi.org/10.1109/access.2023.3261557