Efficient computation of image moments for robust cough detection using smartphones

Abstract

Health Monitoring apps for smartphones have the potential to improve quality of life and decrease the cost of health services. However, they have failed to live up to expectation in the context of respiratory disease. This is in part due to poor objective measurements of symptoms such as cough. Real-time cough detection using smartphones faces two main challenges namely, the necessity of dealing with noisy input signals, and the need of the algorithms to be computationally efficient, since a high battery consumption would prevent patients from using them. This paper proposes a robust and efficient smartphone-based cough detection system able to keep the phone battery consumption below 25% (16% if only the detector is considered) during 24 h use. The proposed system efficiently calculates local image moments over audio spectrograms to feed an optimized classifier for final cough detection. Our system achieves 88.94% sensitivity and 98.64% specificity in noisy environments with a 5500× speed-up and 4× battery saving compared to the baseline implementation. Power consumption is also reduced by a minimum factor of 6 compared to existing optimized systems in the literature.

Monitoring Health Parameters of Elders to Support Independent Living and Improve Their Quality of Life

“…Recently, mobile devices have also been used in the mHealth context towards detecting pathologies in patients' cough, a development mostly stemming from advancements in the quality of acoustic sensors and processing capacity of smartphones [20]. Two main challenges faced in smartphone-based cough detection are noisy input signals, as well as the highly demanding algorithms-in terms of battery consumption-that need to run on the device [21]. Nevertheless, current research efforts report positive results in terms of accuracy [22][23][24], but also in terms of sensitivity and in noisy environments and battery consumption [21].…”

“…Two main challenges faced in smartphone-based cough detection are noisy input signals, as well as the highly demanding algorithms-in terms of battery consumption-that need to run on the device [21]. Nevertheless, current research efforts report positive results in terms of accuracy [22][23][24], but also in terms of sensitivity and in noisy environments and battery consumption [21]. However, an important remark is that all the cough detection systems mentioned so far are trained and tested on specific acoustic sensing equipment while in many cases, a specific placement of the sensing device with respect to the patient is required [25][26][27].…”

Development and technical validation of a smartphone‐based pediatric cough detection algorithm

“…Furthermore, the semi‐automated counting method used by both devices remains laborious and requires training, which means that widespread use in large‐scale clinical trials or in general care is not feasible. Other algorithms that count coughs automatically have reported sensitivities of 78%–99% and specificities of 92%–99%, 7,18–23 but only a few have been applied on a smartphone 21,22,24 . The one that most resembles the current study is a smartphone‐based algorithm developed by Barata et al, 21 who use a convolutional neural network to classify nocturnal sounds in adult asthmatics and obtained a sensitivity of 99.9% with a specificity of 91.5% 21 .…”

“…Other algorithms that count coughs automatically have reported sensitivities of 78%-99% and specificities of 92%-99%, 7,18-23 but only a few have been applied on a smartphone. 21,22,24 The one that most resembles the current study is a smartphone-based algorithm developed by Barata et al, 21 who use a convolutional neural network to classify nocturnal sounds in adult asthmatics and obtained a sensitivity of 99.9% with a specificity of 91.5%. 21 In addition, other projects are often based on data obtained in tightly controlled environments and lack validation in independent or clinical datasets, 18,[22][23][24] and may show a similar drop in accuracy during validation as was observed for the algorithm developed here.…”

Diagnosis of Pneumonia by Cough Sounds Analyzed with Statistical Features and AI

“…where R represent the newly defined energy ratio. Here, a single value for loudness and the energy ratio was derived from the frame at 0.05 s (starting point of cough and calculation), which was carried out while moving the frame to overlap 75% to derive characteristics according to cough duration [27,28]. H rms is the root mean-square (RMS) value of the high-frequency component and L rms is the RMS value of the low-frequency component.…”