Efficient computation of image moments for robust cough detection using smartphones

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.

[2]  Pablo Casaseca-de-la-Higuera,et al.  Effect of importance sampling on robust segmentation of audio-cough events in noisy environments , 2016, 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[3]  E. Vizel,et al.  Validation of an ambulatory cough detection and counting application using voluntary cough under different conditions , 2010, Cough.

[4]  Xiao Sun,et al.  SymDetector: detecting sound-related respiratory symptoms using smartphones , 2015, UbiComp.

[5]  J. Flusser,et al.  2D and 3D Image Analysis by Moments , 2016 .

[6]  Vinayak Swarnkar,et al.  Cough Sound Analysis Can Rapidly Diagnose Childhood Pneumonia , 2013, Annals of Biomedical Engineering.

[7]  Vinayak Swarnkar,et al.  Automatic cough segmentation from non-contact sound recordings in pediatric wards , 2015, Biomed. Signal Process. Control..

[8]  Sung-Hwan Shin,et al.  Automatic Detection System for Cough Sounds as a Symptom of Abnormal Health Condition , 2009, IEEE Transactions on Information Technology in Biomedicine.

[9]  Mark Bocko,et al.  Automated Cough Assessment on a Mobile Platform , 2014, Journal of medical engineering.

[10]  Pablo Casaseca-de-la-Higuera,et al.  Efficient k-NN Implementation for Real-Time Detection of Cough Events in Smartphones , 2018, IEEE Journal of Biomedical and Health Informatics.

[11]  Vinayak Swarnkar,et al.  Automatic Identification of Wet and Dry Cough in Pediatric Patients with Respiratory Diseases , 2013, Annals of Biomedical Engineering.

[12]  D H Evans,et al.  The Leicester Cough Monitor: preliminary validation of an automated cough detection system in chronic cough , 2008, European Respiratory Journal.

[13]  Paul Jones,et al.  COPD uncovered: an international survey on the impact of chronic obstructive pulmonary disease [COPD] on a working age population , 2011, BMC public health.

[14]  Atsuo Shibuya,et al.  New non-invasive automatic cough counting program based on 6 types of classified cough sounds. , 2006, Internal medicine.

[15]  Paul Boersma,et al.  Speak and unSpeak with P RAATRAAT , 2002 .

[16]  Barry Allen Blesser Perception of spectrally rotated speech. , 1969 .

[17]  Pablo Casaseca-de-la-Higuera,et al.  Effect of downsampling and compressive sensing on audio-based continuous cough monitoring , 2015, 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC).

[18]  Pablo Casaseca-de-la-Higuera,et al.  Audio-cough event detection based on moment theory , 2018, Applied Acoustics.

[19]  Koji Yatani,et al.  BodyScope: a wearable acoustic sensor for activity recognition , 2012, UbiComp.

[20]  Keiichi Tokuda,et al.  Mel-generalized cepstral analysis - a unified approach to speech spectral estimation , 1994, ICSLP.

[21]  Eric C. Larson,et al.  Accurate and privacy preserving cough sensing using a low-cost microphone , 2011, UbiComp '11.

[22]  Thierry Dutoit,et al.  Objective Study of Sensor Relevance for Automatic Cough Detection , 2013, IEEE Journal of Biomedical and Health Informatics.

[23]  P. K. Chaturvedi,et al.  Communication Systems , 2002, IFIP — The International Federation for Information Processing.

[24]  E. Jassem,et al.  A portable automatic cough analyser in the ambulatory assessment of cough , 2010, Biomedical engineering online.

[25]  A. Sheikh,et al.  Effectiveness of telemonitoring integrated into existing clinical services on hospital admission for exacerbation of chronic obstructive pulmonary disease: researcher blind, multicentre, randomised controlled trial , 2013, BMJ.

[26]  Ming-Kuei Hu,et al.  Visual pattern recognition by moment invariants , 1962, IRE Trans. Inf. Theory.

[27]  Pablo Casaseca-de-la-Higuera,et al.  Robust Detection of Audio-Cough Events Using Local Hu Moments , 2019, IEEE Journal of Biomedical and Health Informatics.

[28]  Guihua Wen,et al.  Weighted spectral features based on local Hu moments for speech emotion recognition , 2015, Biomed. Signal Process. Control..

[29]  Th. M. Hupkens,et al.  Noise and intensity invariant moments , 1995, Pattern Recognit. Lett..

[30]  Sasan Adibi,et al.  Mobile Health: A Technology Road Map , 2015 .

[31]  E. Ecer,et al.  Numerical Linear Algebra and Applications , 1995, IEEE Computational Science and Engineering.

[32]  J. Smith,et al.  New Developments in the Objective Assessment of Cough , 2007, Lung.

[33]  Zheng Wang,et al.  Cough signal recognition with Gammatone Cepstral Coefficients , 2013, 2013 IEEE China Summit and International Conference on Signal and Information Processing.

[34]  Vinayak Swarnkar,et al.  Wavelet Augmented Cough Analysis for Rapid Childhood Pneumonia Diagnosis , 2015, IEEE Transactions on Biomedical Engineering.