Breathing Sound Segmentation and Detection Using Transfer Learning Techniques on an Attention-Based Encoder-Decoder Architecture.

This paper focuses on the use of an attention-based encoder-decoder model for the task of breathing sound segmentation and detection. This study aims to accurately segment the inspiration and expiration of patients with pulmonary diseases using the proposed model. Spectrograms of the lung sound signals and labels for every time segment were used to train the model. The model would first encode the spectrogram and then detect inspiratory or expiratory sounds using the encoded image on an attention-based decoder. Physicians would be able to make a more precise diagnosis based on the more interpretable outputs with the assistance of the attention mechanism.The respiratory sounds used for training and testing were recorded from 22 participants using digital stethoscopes or anti-noising microphone sets. Experimental results showed a high 92.006% accuracy when applied 0.5 second time segments and ResNet101 as encoder. Consistent performance of the proposed method can be observed from ten-fold cross-validation experiments.

A novel home appliance control system for people with disabilities.

PURPOSE: This research proposed an eyeglass-type infrared-based home appliance control system for spinal cord injured (SCI) with tetraplegia. METHOD: This system is composed of four major components: A headset, an infrared transmitting module, an infrared receiving/signal-processing module, and a main controller, the Intel-8951 microprocessor. This design concept was based on the use of an infrared remote module fastened to the eyeglasses that could allow the convenient control of the input motion on the keys of a remote controller of a home appliance which are all modified with infrared receiving/signal-processing modules. For system evaluation, 12 subjects (4 male, 8 female, 26- 47-years-old were recruited. Six persons without disabilities were in the control group and 6 with SCI with tetraplegia formed the experimental group. RESULTS: The average accuracy of the control group and the experimental group are 88.8 +/- 10.6% and 85.9 +/- 14.3%, respectively. The average time cost of the control group and the experimental group are 57.2 +/- 8.1 sec and 66.6 +/- 12.3 sec, respectively. An independent t-test revealed that the differences in the average accuracy and the average time cost of the control group and the experimental group are not significant (p > 0.05). CONCLUSIONS: Using the novel home appliance control system not only provided the advantages of convenience, accuracy and sanitation for people with disabilities but it also helped them to live more independently.