Heart sounds play an important role in the initial screening of heart diseases. However, the accurate diagnosis with heart sound signals requires doctors to have many years of clinical experience and relevant professional knowledge. In this study, we proposed an end-to-end lightweight neural network model that does not require heart sound segmentation and has very few parameters. We segmented the original heart sound signal and performed a short-time Fourier transform (STFT) to obtain the frequency domain features. These features were sent to the improved two-dimensional convolutional neural network (CNN) model for features learning and classification. Considering the imbalance of positive and negative samples, we introduced FocalLoss as the loss function, verified our network model with multiple random verifications, and, hence, obtained a better classification result. Our main purpose is to design a lightweight network structure that is easy for hardware implementation. Compared with the results of the latest literature, our model only uses 4.29 K parameters, which is 1/10 of the size of the state-of-the-art work.

Flexible sensing devices provide a convenient and effective solution for real-time human motion monitoring, but achieving efficient and low-cost assembly of pressure sensors with high performance remains a considerable challenge. Herein, a highly compressible and sensitive flexible foam-shaped piezoresistive pressure sensor was prepared by sequential fixing multiwalled carbon nanotubes and ${\mathrm{Ti}}_3{\mathrm{C}}_2{\mathrm{T}}_{\mathrm{x}}$ MXene on the skeleton of melamine foam. Due to the porous skeleton of the melamine foam and the extraordinary electrical properties of the conductive fillers, the obtained MWCNTs/${\mathrm{Ti}}_3{\mathrm{C}}_2{\mathrm{T}}_{\mathrm{x}}$ MXene @ melamine foam device features high sensitivity of 0.339 kPa${}^{-1}$, a wide working range up to 180 kPa, a desirable response time and excellent cyclic stability. The sensing mechanism of the composite foam device is attributed to the change in the conductive pathways between adjacent porous skeletons. The proposed sensor can be used successfully to monitor human gestures in real-time, such as finger bending and tilting, scrolling the mouse and stretching fingers. By combining with the decision tree algorithm, the sensor can unambiguously classify different Arabic numeral gestures with an average recognition accuracy of 98.9%. Therefore, our fabricated foam-shaped sensor may have great potential as next-generation wearable electronics to accurately acquire and recognize human gesture signals in various practical applications.

Flexible pressure sensors have been studied as wearable voice-recognition devices to be utilized in human-machine interaction. However, the development of highly sensitive, skin-attachable, and comfortable sensing devices to achieve clear voice detection remains a considerable challenge. Herein, we present a wearable and flexible pressure and temperature sensor with a sensitive response to vibration, which can accurately recognize the human voice by combing with the artificial neural network. The device consists of a polyethylene terephthalate (PET) printed with a silver electrode, a filament-microstructured polydimethylsiloxane (PDMS) film embedded with single-walled carbon nanotubes and a polyimide (PI) film sputtered with a patterned Ti/Pt thermistor strip. The developed pressure sensor exhibited a pressure sensitivity of 0.398 kPa${}^{-1}$ in the low-pressure regime, and the fabricated temperature sensor shows a desirable temperature coefficient of resistance of 0.13% ${}^{\circ }$C in the range of 25 ${}^{\circ }$C to 105 ${}^{\circ }$C. Through training and testing the neural network model with the waveform data of the sensor obtained from human pronunciation, the vocal fold vibrations of different words can be successfully recognized, and the total recognition accuracy rate can reach 93.4%. Our results suggest that the fabricated sensor has substantial potential for application in the human-computer interface fields, such as voice control, vocal healthcare monitoring, and voice authentication.

Wearable and flexible pressure sensors have sparked great interest due to their unique capacity to conformally attach to the surface of the skin and quantify human activities into recordable electric signals. As a result, more and more research efforts are being devoted to developing high-sensitivity and cost-effective flexible sensors for monitoring an individual’s state of activity. Herein, a high-performance flexible piezoresistive sensor was designed and fabricated by combing 2D transition metal carbides, nitrides, and carbonitrides (MXene) with a honeycomb-like structure formed by femtosecond filamentating pulses. The sensing mechanism is attributed to the change of the connecting conductive paths between the top interdigital electrodes and the bottom microstructured films coated with MXene. The obtained sensing device demonstrates high sensitivity of 0.61 kPa⁻¹, relatively short response time, and excellent reliability and stability. Benefiting from the aforementioned extraordinary sensing performance, the sensor can be used with success to monitor tiny physiological signals, detect large deformations during human movement, and distinguish finger gestures, thus demonstrating its broad prospects in physiological analysis systems, health monitoring systems, and human–machine interaction.

Heart sound segmentation (HSS) is a critical step in heart sound processing, where it improves the interpretability of heart sound disease classification algorithms. In this study, we aimed to develop a real-time algorithm for HSS by combining the temporal convolutional network (TCN) and the hidden semi-Markov model (HSMM), and improve the performance of HSMM for heart sounds with arrhythmias. We experimented with TCN and determined the best parameters based on spectral features, envelopes, and one-dimensional CNN. However, the TCN results could contradict the natural fixed order of S1-systolic-S2-diastolic of heart sound, and thereby the Viterbi algorithm based on HSMM was connected to correct the order errors. On this basis, we improved the performance of the Viterbi algorithm when detecting heart sounds with cardiac arrhythmias by changing the distribution and weights of the state duration probabilities. The public PhysioNet Computing in Cardiology Challenge 2016 data set was employed to evaluate the performance of the proposed algorithm. The proposed algorithm achieved an F1 score of 97.02%, and this result was comparable with the current state-of-the-art segmentation algorithms. In addition, the proposed enhanced Viterbi algorithm for HSMM corrected 30 out of 30 arrhythmia errors after checking one by one in the dataset.

Flexible pressure sensors with excellent sensing properties have caused widespread concern due to their various potential applications in personalized healthcare monitoring, disease diagnosis and human-machine interaction. However, the challenge remains to simultaneously achieve high sensitivity and low fabrication cost. Herein, a compressible, reliable and flexible piezoresistive pressure sensor of Ti₃C₂T_x MXene/carbonized melamine foam (MXene@CMF) was fabricated by coating two-dimensional (2D) Ti₃C₂T_x MXene on the skeleton of carbonized melamine foam. Owing to the synergic effect of carbonized melamine foam and Ti₃C₂T_x MXene, the as-prepared MXene@CMF shows excellent performance in terms of high sensitivity (similar to 0.166 kPa⁻¹), fast response time (similar to 120 ms), subtle pressure detection limit of 9.6 Pa, and excellent cyclic stability. Benefiting from these excellent sensing capabilities, the applications of the sensor for artery pulse detection and bending joint monitoring are demonstrated. Moreover, with the assistance of the convolutional neural network, the proposed sensor can realize the exquisite identification of letter strokes with an average recognition accuracy of 96.3%. Based on the merit of high sensing performance and versatile application prospects, our proposed sensor may have great potential in medical and healthcare, human motion detection, handwriting verification, and anticounterfeiting applications.