We propose a novel dual-channel electromyography (EMG) spatio-temporal differential (DESTD) method that can estimate volitional electromyography (vEMG) signals during time-varying functional electrical stimulation (FES). The proposed method uses two pairs of EMG signals from the same stimulated muscle to calculate the spatio-temporal difference between the signals. We performed an experimental study with five healthy participants to evaluate the vEMG signal estimation performance of the DESTD method and compare it with that of the conventional comb filter and Gram–Schmidt methods. The normalized root mean square error (NRMSE) values between the semi-simulated raw vEMG signal and vEMG signals which were estimated using the DESTD method and conventional methods, and the two-tailed $\mathit{t}$-test and analysis of variance were conducted. The results showed that under the stimulation of the gastrocnemius muscle with rapid and dynamically modulated stimulation intensity, the DESTD method had a lower NRMSE compared to the conventional methods (p < 0.01) for all stimulation intensities (maximum 5, 10, 15, and 20 mA). We demonstrated that the DESTD method could be applied to wearable EMG-controlled FES systems because it estimated vEMG signals more effectively compared to the conventional methods under dynamic FES conditions and removed unnecessary FES-induced EMG signals.

In this paper, we proposed a novel light-driven polymer actuator that could produce remotely controllable tensile stroke in response to near infrared (NIR) light. The light-driven polymer actuator was composed of a twisted and coiled nylon-6 fiber (TCN) and a thin poly(3,4-ethylenedioxythiophene) doped with p-toluenesulfonate (PEDOT-Tos) layer. By adopting dip-coating methodology with thermal polymerization process, we constructed a thin and uniform PEDOT-Tos layer on the surface of the three-dimensional TCN structure. Thanks to the PEDOT-Tos layer with excellent NIR light absorption characteristic, the NIR light illumination via a small LEDs array allowed the multiple PEDOT-Tos coated TCN actuators to be photo-thermally heated to a fairly consistent temperature and to simultaneously produce a contractile strain that could be modulated as high as 8.7% with light power. The actuation performance was reversible without any significant hysteresis and highly durable during 3000 cyclic operations via repetitive control of the LEDs. Together with its simple structure and facile fabrication, the light-driven actuator can lead to technical advances in artificial muscles due to its attractive benefits from remote controllability without complex coupled instruments and electromagnetic interference.

In this study, we collected data on human falls, occurring in four directions while walking or standing, and developed a fall recognition system based on the center of mass (COM). Fall data were collected from a lower-body motion data acquisition device comprising five inertial measurement unit sensors driven at 100 Hz and labeled based on the COM-norm. The data were learned to classify which stage of the fall a particular instance belongs to. It was confirmed that both the representative convolutional neural network learning model and the long short-term memory learning model were performed within a time of 10 ms on the embedded platform (Jetson TX2) and the recognition rate exceeded 94%. Accordingly, it is possible to verify the progress of the fall during the unbalanced and falling steps, which are classified by subdividing the critical step in which the real-time fall proceeds with the output of the fall recognition model every 10 ms. In addition, it was confirmed that a real-time fall can be judged by specifying the point of no return (PONR) near the point of entry of the falling down stage.