Deep Neural Network for Respiratory Sound Classification in Wearable Devices Enabled by Patient Specific Model Tuning

Acharya, Jyotibdha; Basu, Arindam

doi:10.1109/tbcas.2020.2981172

Cited by 136 publications

(116 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Here, we have shown results on one of the biggest and most popular datasets in visual classification, IMAGENET, our results are quite generally applicable for visual tasks which is already covering a very big application space. Second, it has been shown that networks pre-trained on IMAGENET can be used as feature extractors for spectrograms for audio analysis (Acharya and Basu, 2020); our method can thus potentially generalize to other types of datasets as well. We have also proposed an optimized mapping technique by considering a square shaped selection of neurons.…”

Section: Discussionmentioning

confidence: 99%

HFNet: A CNN Architecture Co-designed for Neuromorphic Hardware With a Crossbar Array of Synapses

et al. 2020

Self Cite

View full text Add to dashboard Cite

The hardware-software co-optimization of neural network architectures is a field of research that emerged with the advent of commercial neuromorphic chips, such as the IBM TrueNorth and Intel Loihi. Development of simulation and automated mapping software tools in tandem with the design of neuromorphic hardware, whilst taking into consideration the hardware constraints, will play an increasingly significant role in deployment of system-level applications. This paper illustrates the importance and benefits of co-design of convolutional neural networks (CNN) that are to be mapped onto neuromorphic hardware with a crossbar array of synapses. Toward this end, we first study which convolution techniques are more hardware friendly and propose different mapping techniques for different convolutions. We show that, for a seven-layered CNN, our proposed mapping technique can reduce the number of cores used by 4.9-13.8 times for crossbar sizes ranging from 128 × 256 to 1,024 × 1,024, and this can be compared to the toeplitz method of mapping. We next develop an iterative co-design process for the systematic design of more hardware-friendly CNNs whilst considering hardware constraints, such as core sizes. A python wrapper, developed for the mapping process, is also useful for validating hardware design and studies on traffic volume and energy consumption. Finally, a new neural network dubbed HFNet is proposed using the above co-design process; it achieves a classification accuracy of 71.3% on the IMAGENET dataset (comparable to the VGG-16) but uses 11 times less cores for neuromorphic hardware with core size of 1,024 × 1,024. We also modified the HFNet to fit onto different core sizes and report on the corresponding classification accuracies. Various aspects of the paper are patent pending.

show abstract

Section: Discussionmentioning

confidence: 99%

HFNet: A CNN Architecture Co-designed for Neuromorphic Hardware With a Crossbar Array of Synapses

et al. 2020

Self Cite

View full text Add to dashboard Cite

show abstract

“…Thoracic impedance measurement is a technique that can indirectly measure the change of lung volume caused by respiration through measuring the impedance changes between electrodes on the skin [ 64 ]. As a technology that has been used in the respiratory monitoring of severe patients or infants, thoracic impedance measurement is also widely used in wearable devices [ 65 ] thanks to their non-invasive and comfortable characteristics. The direct relationship between thoracic impedance and respiratory rate can be obtained by use of the lung model in relation to the electrode belt.…”

Section: Wearable Techniquesmentioning

confidence: 99%

“…A trained physician can easily recognize pathological breathing from respiratory sounds, while wearable techniques have enabled real-time ambulatory detection of abnormal breathing events. Respiratory sounds collected by wearable sensors have been used for wheeze and crackle analysis by applying a hybrid CNN-RNN framework on the Mel spectrogram [ 65 ]. Apnea events, another common abnormal respiratory event, can be detected using the sound-level sensor on a smartphone [ 151 ].…”

Section: Early Warning and Dysfunction Detectionmentioning

confidence: 99%

A review of wearable and unobtrusive sensing technologies for chronic disease management

Guo

Liu

Peng

et al. 2021

Computers in Biology and Medicine

View full text Add to dashboard Cite

“…They reported a AUC value of 0.8919 with MFCC-based features. Acharya et al [ 1 ] presented a deep learning-based approach for lung sound classification. They reported an accuracy of 71.81% on the ICBHI17 dataset of size 6800+ clips.…”

Section: Introductionmentioning

confidence: 99%

Automatic Lung Health Screening Using Respiratory Sounds

et al. 2021

View full text Add to dashboard Cite

Significant changes have been made on audio-based technologies over years in several different fields. Healthcare is no exception. One of such avenues is health screening based on respiratory sounds. In this paper, we developed a tool to detect respiratory sounds that come from respiratory infection carrying patients. Linear Predictive Cepstral Coefficient (LPCC)-based features were used to characterize such audio clips. With Multilayer Perceptron (MLP)-based classifier, in our experiment, we achieved the highest possible accuracy of 99.22% that was tested on a publicly available respiratory sounds dataset (ICBHI17) (Rocha et al. Physiol. Meas. 40(3):035,001 2019) of size 6800+ clips. In addition to other popular machine learning classifiers, our results outperformed common works that exist in the literature.

show abstract

Deep Neural Network for Respiratory Sound Classification in Wearable Devices Enabled by Patient Specific Model Tuning

Cited by 136 publications

References 47 publications

HFNet: A CNN Architecture Co-designed for Neuromorphic Hardware With a Crossbar Array of Synapses

HFNet: A CNN Architecture Co-designed for Neuromorphic Hardware With a Crossbar Array of Synapses

A review of wearable and unobtrusive sensing technologies for chronic disease management

Automatic Lung Health Screening Using Respiratory Sounds

Contact Info

Product

Resources

About