RESUMEN
Surface electromyogram (sEMG)-based gesture recognition has emerged as a promising avenue for developing intelligent prostheses for upper limb amputees. However, the temporal variations in sEMG have rendered recognition models less efficient than anticipated. By using cross-session calibration and increasing the amount of training data, it is possible to reduce these variations. The impact of varying the amount of calibration and training data on gesture recognition performance for amputees is still unknown. To assess these effects, we present four datasets for the evaluation of calibration data and examine the impact of the amount of training data on benchmark performance. Two amputees who had undergone amputations years prior were recruited, and seven sessions of data were collected for analysis from each of them. Ninapro DB6, a publicly available database containing data from ten healthy subjects across ten sessions, was also included in this study. The experimental results show that the calibration data improved the average accuracy by 3.03%, 6.16%, and 9.73% for the two subjects and Ninapro DB6, respectively, compared to the baseline results. Moreover, it was discovered that increasing the number of training sessions was more effective in improving accuracy than increasing the number of trials. Three potential strategies are proposed in light of these findings to enhance cross-session models further. We consider these findings to be of the utmost importance for the commercialization of intelligent prostheses, as they demonstrate the criticality of gathering calibration and cross-session training data, while also offering effective strategies to maximize the utilization of the entire dataset.
Asunto(s)
Amputados , Miembros Artificiales , Humanos , Electromiografía/métodos , Calibración , Reconocimiento de Normas Patrones Automatizadas/métodos , Extremidad Superior , AlgoritmosRESUMEN
Deep learning (DL) has been used for electromyographic (EMG) signal recognition and achieved high accuracy for multiple classification tasks. However, implementation in resource-constrained prostheses and human-computer interaction devices remains challenging. To overcome these problems, this paper implemented a low-power system for EMG gesture and force level recognition using Zynq architecture. Firstly, a lightweight network model structure was proposed by Ultra-lightweight depth separable convolution (UL-DSC) and channel attention-global average pooling (CA-GAP) to reduce the computational complexity while maintaining accuracy. A wearable EMG acquisition device for real-time data acquisition was subsequently developed with size of 36mm×28mm×4mm. Finally, a highly parallelized dedicated hardware accelerator architecture was designed for inference computation. 18 gestures were tested, including force levels from 22 healthy subjects. The results indicate that the average accuracy rate was 94.92% for a model with 5.0k parameters and a size of 0.026MB. Specifically, the average recognition accuracy for static and force-level gestures was 98.47% and 89.92%, respectively. The proposed hardware accelerator architecture was deployed with 8-bit precision, a single-frame signal inference time of 41.9µs, a power consumption of 0.317W, and a data throughput of 78.6 GOP/s.
RESUMEN
Pressure sensors with high sensitivity, a wide linear range, and a quick response time are critical for building an intelligent disease diagnosis system that directly detects and recognizes pulse signals for medical and health applications. However, conventional pressure sensors have limited sensitivity and nonideal response ranges. We proposed a multichannel flexible pulse perception array based on polyimide/multiwalled carbon nanotube-polydimethylsiloxane nanocomposite/polyimide (PI/MPN/PI) sandwich-structure pressure sensor that can be applied for remote disease diagnosis. Furthermore, we established a mechanical model at the molecular level and guided the preparation of MPN. At the structural level, we achieved high sensitivity (35.02 kPa-1) and a broad response range (0-18 kPa) based on a pyramid-like bilayer microstructure with different upper and lower surfaces. A 27-channel (3 × 9) high-density sensor array was integrated at the device level, which can extract the spatial and temporal distribution information on a pulse. Furthermore, two intelligent algorithms were developed for extracting six-dimensional pulse information and automatic pulse recognition (the recognition rate reaches 97.8%). The results indicate that intelligent disease diagnosis systems have great potential applications in wearable healthcare devices.
Asunto(s)
Nanocompuestos , Nanotubos de Carbono , Dispositivos Electrónicos Vestibles , PercepciónRESUMEN
The cuff-less blood pressure (BP) monitoring method based on photoplethysmo- gram (PPG) makes it possible for long-term BP monitoring to prevent and treat cardiovascular and cerebrovascular events. In this paper, a portable BP prediction system based on feature combination and artificial neural network (ANN) is implemented. The robustness of the model is improved from three aspects. Firstly, an adaptive peak extraction algorithm was used to improve the accuracy of peaks and troughs detection. Secondly, multi-dimensional features were extracted and fused, including three groups of PPG-based features and one group of demographics-based features. Finally, a two-layer feedforward artificial neural networks algorithm was used for regression. Thirty-three subjects distributed in the three BP groups were recruited. The proposed method passed the European Society of Hypertension International Protocol revision 2010 (ESP-IP2). Experimental results show that the proposed method exhibits good accuracy for a diverse population with an estimation error of -0.07 ± 4.47 mmHg for SBP and 0.00 ± 3.61 mmHg for DBP. Moreover, the model tracked the BP of two subjects for half a month, laying the foundation work for daily BP monitoring. This work will contribute to the long-term wellness management and rehabilitation process, enabling timely detection and improvement of the user's physical health.