Automatic Non-Invasive Cough Detection based on Accelerometer and Audio Signals

Abstract

We present an automatic non-invasive way of detecting cough events based on both accelerometer and audio signals. The acceleration signals are captured by a smartphone firmly attached to the patient’s bed, using its integrated accelerometer. The audio signals are captured simultaneously by the same smartphone using an external microphone. We have compiled a manually-annotated dataset containing such simultaneously-captured acceleration and audio signals for approximately 6000 cough and 68000 non-cough events from 14 adult male patients. Logistic regression (LR), support vector machine (SVM) and multilayer perceptron (MLP) classifiers provide a baseline and are compared with three deep architectures, convolutional neural network (CNN), long short-term memory (LSTM) network, and residual-based architecture (Resnet50) using a leave-one-out cross-validation scheme. We find that it is possible to use either acceleration or audio signals to distinguish between coughing and other activities including sneezing, throat-clearing, and movement on the bed with high accuracy. However, in all cases, the deep neural networks outperform the shallow classifiers by a clear margin and the Resnet50 offers the best performance, achieving an area under the ROC curve (AUC) exceeding 0.98 and 0.99 for acceleration and audio signals respectively. While audio-based classification consistently offers better performance than acceleration-based classification, we observe that the difference is very small for the best systems. Since the acceleration signal requires less processing power, and since the need to record audio is sidestepped and thus privacy is inherently secured, and since the recording device is attached to the bed and not worn, an accelerometer-based highly accurate non-invasive cough detector may represent a more convenient and readily accepted method in long-term cough monitoring.

Non-Contact Thermal and Acoustic Sensors with Embedded Artificial Intelligence for Point-of-Care Diagnostics

“…What It Is About Differences with Our Work [33] Cough detector based on audio and accelerometer signals.…”

Intelligent speech technologies for transcription, disease diagnosis, and medical equipment interactive control in smart hospitals: A review

“…Pahar et al also designed cough spotting and cougher identification methods for long-term personalized cough monitoring [ 225 ]. They also proposed an automatic non-invasive cough detection method based on audio and acceleration signals of a smartphone [ 225 , 226 ]. These non-contact cougher identification methods are helpful during the COVID-19 pandemic and promote the development of IST-based healthcare-monitoring technology.…”

Accelerometer-Based Bed Occupancy Detection for Automatic, Non-Invasive Long-Term Cough Monitoring

“…We calculate the frame skips by dividing the number of samples by the number of frames and taking the next positive integer. Extracted features include the power spectra, root mean square (RMS), moving average, kurtosis and crest factor; as they have shown promising results in our previous studies using accelerometer signals [4], [38]. The power spectra [39] are a common feature to extract from sensor magnitudes [40]- [43] as an input to the neural networks [44].…”