While most wearable gesture recognition approaches focus on the forearm or fingers, the wrist may a more suitable location for practical use. We present the design and validation of a real-time gesture recognition wristband based on surface electromyography (sEMG) and inertial measurement unit (IMU) sensing fusion, which can recognize 8 air gestures and 4 surface gestures with 2 distinct force levels. Ten healthy subjects performed an initial gesture recognition experiment, followed by a second experiment 1 hour later and a third experiment 1 day later. Classification accuracies for the initial experiment were 92.6% and 88.8% for air and surface gestures, respectively, and there were no changes in accuracy results during testing 1 hour and 1 day later (p>0.05). These results demonstrate the feasibility of wrist-based gesture recognition paving the way for potential future integration in to a smart watch or other wrist-worn wearable for intuitive human computer interaction.

Surface electromyography (EMG) signals are inevitably contaminated by various noise components, including powerline interference (PLI), baseline wandering (BW), and white Gaussian noise (WGN). These noises directly degrade the efficiency of EMG processing and affect the accuracy and robustness of further applications. Currently, most of the EMG filters only target one category of noise. Here, we propose a novel filter to remove all three types of noise. The noisy EMG signal is first decomposed into an ensemble of band-limited modes using variational mode decomposition (VMD). Each category of noise is located within specific modes and is separately removed in sub-bands. In particular, WGN is suppressed by soft thresholding with a noise level-dependent threshold. The denoising performance was assessed from simulated and experimental signals using three performance metrics: the root mean square error (RMSE), the improvement in signal-to-noise ratio (SNR_imp), and the percentage reduction in the correlation coefficient (). Other methods, including traditional infinite impulse response (IIR) filters, empirical mode decomposition (EMD) method, and ensemble empirical mode decomposition (EEMD) method, were examined for comparison. The proposed method achieved the best performance to remove BW or WGN. It also effectively reduced PLI noise when the signal-to-noise ratio (SNR) was low. The SNR was improved by 18.6, 19.2, and 8.0 dB for EMG signals corrupted with PLI, BW, and WGN at -6 dB SNR, respectively. The experimental results illustrated that noise was completely removed from resting states, and obvious spikes were distinguished from action states. For two of the ten subjects, the improved SNR reached 20 dB. This study explores the special characteristics of VMD and demonstrates the feasibility of using the VMD-based filter to denoise EMG signals. The proposed filter is efficient at removing three categories of noise and can be used for any application that requires EMG signal filtering at the preprocessing stage, such as gesture recognition and EMG decomposition.

Proper training is essential to achieve reliable pattern recognition (PR) based myoelectric control. The amount of training is commonly determined by experience. The purpose of this study is to provide an offline validation method that makes the offline performance transferable to online control and find the proper amount of training that achieves good online performance. In the offline experiment, eight able-bodied subjects and three amputees participated in a ten-day training. Repeatability index (RI) and classification error (CE) were used to evaluate user learning and machine learning, respectively. The performance of cross-validation (CV) and time serial related validation (TSV) was compared. Learning curves were established with different training trials by TSV. In the online experiment, sixteen able-bodied subjects were randomly divided into two groups with one- or five-trial training, respectively, followed by participating in the test with and without classifier-output feedback. The correlation between offline and online tests was analyzed. Results indicated that five-trial training was proper to train the user and the classifier. The long-term retention of skills could not shorten the learning process. The correlation between CEs of TSV and the online test was strong ( r=0.87) with five-trial training, while the correlation between CEs of CV and the online test was weak ( r=0.30). Outcomes demonstrate that offline performance evaluated by TSV is transferable to online performance and the learning process can guide the user to achieve good online myoelectric control with minimum training.

Security inspection is an important measure to ensure public safety. At present, X-ray security inspection equipment is widely used in security checkpoints. However, it is not efficient to recognize prohibited items in X-ray images manually. Automated security inspection system has become the development trend of security field. In this paper, the Yolov4 detector was used to detect prohibited items in X-ray images. In order to improve the detection performance, we added CBAM attention modules to different parts of Yolov4. A public dataset is used for simulation experiments, which shows that the addition of CBAM can effectively improve the detection performance of the detector.

The integration of in vitro biological neural networks (BNNs) with robotic systems to explore their information processing and adaptive learning in practical tasks has gained significant attention in the fields of neuroscience and robotics. However, existing BNN-based robotic systems cannot perceive the visual environment due to the inefficiency of sensory information encoding methods. In this study, we propose a biomimetic visual information spatiotemporal encoding method based on improved delayed phase encoding. This method transforms high-dimensional images into a series of pulse sequences through convolution, temporal delay, alignment, and compression for BNN stimuli. We conduct three stages of unsupervised training on in vitro BNNs using high-density microelectrode arrays (HD-MEAs) to validate the potential of the proposed encoding method for image recognition tasks. The neural activity is decoded via a logistic regression model. The experimental results show that the firing patterns of BNNs with different spatiotemporal stimuli are highly separable in the feature space. After the third training stage, the image recognition accuracy reaches 80.33% ± 7.94%, which is 13.64% higher than that of the first training stage. Meanwhile, the BNNs exhibit significant increases in the connection number, connection strength, and inter-module participation coefficient after unsupervised training. These results demonstrate that the proposed method significantly enhances the functional connectivity and cross-module information exchange in BNNs.