A low power respiratory sound diagnosis processing unit based on LSTM for wearable health monitoring
-
Weixin Zhou
,
Lina Yu
,
Ming Zhang
Abstract
Early prevention and detection of respiratory disease have attracted extensive attention due to the significant increase in people with respiratory issues. Restraining the spread and relieving the symptom of this disease is essential. However, the traditional auscultation technique demands a high-level medical skill, and computational respiratory sound analysis approaches have limits in constrained locations. A wearable auscultation device is required to real-time monitor respiratory system health and provides consumers with ease. In this work, we developed a Respiratory Sound Diagnosis Processor Unit (RSDPU) based on Long Short-Term Memory (LSTM). The experiments and analyses were conducted on feature extraction and abnormality diagnosis algorithm of respiratory sound, and Dynamic Normalization Mapping (DNM) was proposed to better utilize quantization bits and lessen overfitting. Furthermore, we developed the hardware implementation of RSDPU including a corrector to filter diagnosis noise. We presented the FPGA prototyping verification and layout of the RSDPU for power and area evaluation. Experimental results demonstrated that RSDPU achieved an abnormality diagnosis accuracy of 81.4 %, an area of 1.57 × 1.76 mm under the SMIC 130 nm process, and power consumption of 381.8 μW, which met the requirements of high accuracy, low power consumption, and small area.
Funding source: Key Research Program of the Chinese Academy of Sciences
Award Identifier / Grant number: NO. XDPB22
Funding source: Chinese Academy of Sciences
Award Identifier / Grant number: Unassigned
-
Research funding: This work was funded Supported by the Key Research Program of the Chinese Academy of Sciences, Grant NO. XDPB22.
-
Author contribution: All authors have accepted responsibility for the entire content of this manuscript and approved its submission.
-
Competing interests: Authors state no conflict of interest.
-
Informed consent: Informed consent is not applicable.
-
Ethical approval: The conducted research is not related to either human or animal use.
References
1. Zar, HJ, Ferkol, TW. The global burden of respiratory disease. Pediatr Pulmonol 2014;49:430–4. https://doi.org/10.1002/ppul.23030.Search in Google Scholar PubMed
2. Cukic, V, Lovre, V, Dragisic, D, Aida, U. Asthma and chronic obstructive pulmonary disease (COPD) – differences and similarities. Mater Soc Med 2012;24:100–5. https://doi.org/10.5455/msm.2012.24.100-105.Search in Google Scholar PubMed PubMed Central
3. dhi, AP, Stuart, B, Esther, RV. Automatic adventitious respiratory sound analysis: a systematic review. PLoS One 2017;12:e0177926. https://doi.org/10.1371/journal.pone.0177926.Search in Google Scholar PubMed PubMed Central
4. Sarkar, M. Auscultation of the respiratory system. Ann Thorac Med 2015;10:158–68. https://doi.org/10.4103/1817-1737.160831.Search in Google Scholar PubMed PubMed Central
5. Chizner, MA. Cardiac auscultation: rediscovering the lost art. Curr Probl Cardiol 2008;33:326–408. https://doi.org/10.1016/j.cpcardiol.2008.03.003.Search in Google Scholar PubMed
6. Aykanat, M, Kılıç, Ö, Kurt, B, Sevgi, S. Classification of lung sounds using convolutional neural networks. EURASIP J Image Video Process 2017;65:1–9. https://doi.org/10.1186/s13640-017-0213-2.Search in Google Scholar
7. Berouti, M, Schwartz, R, Makhoul, J. Enhancement of speech corrupted by acoustic noise. In: IEEE international conference on acoustics, speech, and signal processing (ICASSP). Washington, America; 1979.Search in Google Scholar
8. Sengupta, N, Sahidullah, M, Saha, G. Lung sound classification using local binary pattern; 2017. Available from: https://arxiv.org/abs/1710.01703.Search in Google Scholar
9. Haider, NS, Singh, BK, Periyasamy, R, Behera, AK. Respiratory sound based classification of chronic obstructive pulmonary disease: a risk stratification approach in machine learning paradigm. J Med Syst 2019;43:255. https://doi.org/10.1007/s10916-019-1388-0.Search in Google Scholar PubMed
10. Nguyen, T, Pernkopf, F. Lung sound classification using snapshot ensemble of convolutional neural networks. In: Annual international conference of the IEEE engineering in medicine & biology society. Montreal, Canada; 2020.10.1109/EMBC44109.2020.9176076Search in Google Scholar PubMed
11. Shi, L, Du, K, Zhang, C, Ma, H, Yan, W. Lung sound recognition algorithm based on vggish-bigru. IEEE Access 2019;7:139438–49. https://doi.org/10.1109/access.2019.2943492.Search in Google Scholar
12. Jun, SY, Liao, CH, Wu, YS, Yuan, SM, Sun, CT. Efficiently classifying lung sounds through depthwise separable CNN models with fused STFT and MFCC features. Diagnostics 2021;11:732. https://doi.org/10.3390/diagnostics11040732.Search in Google Scholar PubMed PubMed Central
13. Gupta, S, Agrawal, M, Deepak, D. Gammatonegram based triple classification of lung sounds using deep convolutional neural network with transfer learning. Biomed Signal Process Control 2021;70:102947. https://doi.org/10.1016/j.bspc.2021.102947.Search in Google Scholar
14. Vaityshyn, V, Porieva, H, Makarenkova, A. Pre-trained convolutional neural networks for the lung sounds classification. In: 2019 IEEE 39th international conference on electronics and nanotechnology (ELNANO). Kyiv, Ukraine; 2019.10.1109/ELNANO.2019.8783850Search in Google Scholar
15. Acharya, J, Basu, A. Deep neural network for respiratory sound classification in wearable devices enabled by patient specific model tuning. IEEE Trans Biomed Circuits Syst 2020;14:535–44. https://doi.org/10.1109/tbcas.2020.2981172.Search in Google Scholar PubMed
16. Jayalakshmy, S, Priya, L, Sudha, GF. Synthesis of respiratory signals using conditional generative adversarial networks from scalogram representation. In: Generative adversarial networks for image-to-image translation. Academic Press; 2021:161–83 pp.10.1016/B978-0-12-823519-5.00024-5Search in Google Scholar
17. Kochetov, K, Putin, E, Balashov, M, Filchenkov, A, Shalyto, A. Noise masking recurrent neural network for respiratory sound classification. In: International conference on artificial neural networks. Rhodes, Greece; 2018.10.1007/978-3-030-01424-7_21Search in Google Scholar
18. Fraiwan, M, Fraiwan, L, Khassawneh, B, Ibnian, A. A dataset of lung sounds recorded from the chest wall using an electronic stethoscope. Data Brief 2021;35:106913. https://doi.org/10.1016/j.dib.2021.106913.Search in Google Scholar PubMed PubMed Central
19. Perna, D, Tagarelli, A. Deep auscultation: predicting respiratory anomalies and diseases via recurrent neural networks. In: 2019 IEEE 32nd international symposium on computer-based medical systems (CBMS). Reina Sofia, Spain; 2019.10.1109/CBMS.2019.00020Search in Google Scholar
20. Mamun, K, Mcfarlane, N. Integrated real time bowel sound detector for artificial pancreas systems. Sens Bio-Sens Res 2016;7:84–9. https://doi.org/10.1016/j.sbsr.2016.01.004.Search in Google Scholar
21. Baghel, N, Nangia, V, Dutta, MK. ALSD-Net: automatic lung sounds diagnosis network from pulmonary signals. Neural Comput Appl 2021;33:17103–18. https://doi.org/10.1007/s00521-021-06302-1.Search in Google Scholar
22. Zhao, K, Jiang, H, Wang, Z, Chen, P, Zhu, B, Duan, X. Long-term bowel sound monitoring and segmentation by wearable devices and convolutional neural networks. IEEE Trans Biomed Circuits Syst 2020;14:985–96. https://doi.org/10.1109/tbcas.2020.3018711.Search in Google Scholar
23. Lin, BS, Yen, TS. An FPGA-based rapid wheezing detection system. Int J Environ Res Publ Health 2014;11:1573–93. https://doi.org/10.3390/ijerph110201573.Search in Google Scholar PubMed PubMed Central
24. Meghanani, A, Anoop, CS, Ramakrishnan, AG. An exploration of log-mel spectrogram and MFCC features for Alzheimer’s dementia recognition from spontaneous speech. In: IEEE spoken language technology workshop (SLT); 2021. Online Conference.10.1109/SLT48900.2021.9383491Search in Google Scholar
25. Montavon, G, Orr, GB, Müller, K. Neural networks: tricks of the trade In: Lecture notes in computer science, 2nd ed.; 2012, vol 10:978–3 pp.10.1007/978-3-642-35289-8Search in Google Scholar
26. Sak, H, Senior, A, Beaufays, F. Long short-term memory based recurrent neural network architectures for large vocabulary speech recognition; 2014. Available from: https://arxiv.org/abs/1402.1128.10.21437/Interspeech.2014-80Search in Google Scholar
27. Chen, T, Du, Z, Sun, N, Wang, J, Wu, C, Chen, Y, et al.. DianNao: a small-footprint high-throughput accelerator for ubiquitous machine-learning. Comput Architect News 2014;42:269–84. https://doi.org/10.1145/2654822.2541967.Search in Google Scholar
28. Courbariaux, M, Hubara, I, Soudry, D, El-Yaniv, R, Bengio, Y. Binarized neural networks: training deep neural networks with weights and activations constrained to +1 or −1; 2016. Available from: https://arxiv.org/abs/1602.02830.Search in Google Scholar
29. Rocha, BM, Filos, D, Mendes, L, Vogiatzis, I, Perantoni, E, Kaimakamis, E, et al.. Α respiratory sound database for the development of automated classification. In: International conference on biomedical and health informatics. Thessaloniki, Greece; 2017.10.1007/978-981-10-7419-6_6Search in Google Scholar
30. Pham, L, McLoughlin, I, Phan, H, Tran, M, Nguyen, T, Palaniappan, R. Robust deep learning framework for predicting respiratory anomalies and diseases. In: 2020 42nd annual international conference of the IEEE engineering in medicine & biology society (EMBC). Montreal, Canada; 2020.10.1109/EMBC44109.2020.9175704Search in Google Scholar PubMed
31. Bardou, D, Zhang, K, Ahmad, SM. Lung sounds classification using convolutional neural networks. Artif Intell Med 2018;88:58–69. https://doi.org/10.1016/j.artmed.2018.04.008.Search in Google Scholar PubMed
32. Hassan Naqvi, S, Choudhry, M. Embedded system design for classification of COPD and pneumonia patients by lung sound analysis. Biomed Eng/Biomed Tech 2022;67:201–18. https://doi.org/10.1515/bmt-2022-0011.Search in Google Scholar PubMed
33. Ons, B, Mohammed, B. Efficient FPGA-based architecture of an automatic wheeze detector using a combination of MFCC and SVM algorithms. J Syst Architect 2018;88:54–64. https://doi.org/10.1016/j.sysarc.2018.05.010.Search in Google Scholar
34. Chen, C, Ding, H, Peng, H, Zhu, H, Ma, R, Zhang, P, et al.. OCEAN: an on-chip incremental-learning enhanced processor with gated recurrent neural network accelerators. In: ESSCIRC 2017-43rd IEEE European solid state circuits conference. Belgium; 2017.10.1109/ESSCIRC.2017.8094575Search in Google Scholar
35. Bang, S, Wang, J, Li, Z, Gao, C, Kim, Y, Dong, Q, et al.. 14.7 a 288µw programmable deep-learning processor with 270kb on-chip weight storage using non-uniform memory hierarchy for mobile intelligence. In: 2017 IEEE international solid-state circuits conference (ISSCC). Shanghai, China; 2017.10.1109/ISSCC.2017.7870355Search in Google Scholar
36. Kao, CY, Kuo, HC, Chen, JW, Lin, CL, Chen, PH, Lin, YL. RNNAccel: a fusion recurrent neural network accelerator for edge intelligence; 2020. Available from: https://arxiv.org/abs/2010.13311.Search in Google Scholar
37. Etchells, E, Chaim, B, Kenneth, R. Does this patient have an abnormal systolic murmur? J Am Med Assoc 1997;277:564–71. https://doi.org/10.1001/jama.1997.03540310062036.Search in Google Scholar
38. Strunic, SL, Rios-Gutiérrez, F, Alba-Flores, R, Nordehn, G, Burns, S. Detection and classification of cardiac murmurs using segmentation techniques and artificial neural networks. In: 2007 IEEE symposium on computational intelligence and data mining. Hawaii State, America; 2007.10.1109/CIDM.2007.368902Search in Google Scholar
© 2023 Walter de Gruyter GmbH, Berlin/Boston
Articles in the same Issue
- Frontmatter
- Review
- Research frontiers of electroporation-based applications in cancer treatment: a bibliometric analysis
- Research Articles
- Deep neural network to differentiate internet gaming disorder from healthy controls during stop-signal task: a multichannel near-infrared spectroscopy study
- A low power respiratory sound diagnosis processing unit based on LSTM for wearable health monitoring
- Effective deep learning classification for kidney stone using axial computed tomography (CT) images
- De- and recellularized urethral reconstruction with autologous buccal mucosal cells implanted in an ovine animal model
- The impact of right ventricular hemodynamics on the performance of a left ventricular assist device in a numerical simulation model
- Optimal assist strategy exploration for a direct assist device under stress‒strain dynamics
- Revisiting SFA stent technology: an updated overview on mechanical stent performance
- Parameter-based patient-specific restoration of physiological knee morphology for optimized implant design and matching
- Influences of smart glasses on postural control under single- and dual-task conditions for ergonomic risk assessment
Articles in the same Issue
- Frontmatter
- Review
- Research frontiers of electroporation-based applications in cancer treatment: a bibliometric analysis
- Research Articles
- Deep neural network to differentiate internet gaming disorder from healthy controls during stop-signal task: a multichannel near-infrared spectroscopy study
- A low power respiratory sound diagnosis processing unit based on LSTM for wearable health monitoring
- Effective deep learning classification for kidney stone using axial computed tomography (CT) images
- De- and recellularized urethral reconstruction with autologous buccal mucosal cells implanted in an ovine animal model
- The impact of right ventricular hemodynamics on the performance of a left ventricular assist device in a numerical simulation model
- Optimal assist strategy exploration for a direct assist device under stress‒strain dynamics
- Revisiting SFA stent technology: an updated overview on mechanical stent performance
- Parameter-based patient-specific restoration of physiological knee morphology for optimized implant design and matching
- Influences of smart glasses on postural control under single- and dual-task conditions for ergonomic risk assessment
