Stroke has been ranked as the second leading cause of death and disability-adjusted life-years worldwide. It has a high incidence, disability rate, recurrence rate, mortality rate, and financial burden.1 Motor, language, and swallowing dysfunctions are commonly observed in stroke survivors. The most common function deficit after a stroke is motor dysfunction, which can leave patients disabled and have a negative impact on their quality of life. Rehabilitation can assist in restoring some of the lost limb functions.2,3 At present, various clinical rating scales are usually used to evaluate the motor function of stroke patients, such as the Fugl-Meyer Assessment (FMA), Berg Balance Scale, and Brunnstrom. Although these methods are well validated and acknowledged, they are still limited by physician subjectivity, large time consumption, and low resolution.4
Exoskeleton robots serve as crucial tools for active rehabilitation training among patients with lower limb motor dysfunction. Accurately recognizing human motion intention poses a significant challenge for exoskeleton robots, which can be addressed by continuously estimating human joint angles. Nevertheless, most existing studies primarily focus on healthy subjects, neglecting the target audience of lower limb exoskeletons, namely, patients with lower limb hemiplegia. This paper proposed a general model utilizing a transfer learning (TL) strategy to predict the gait trajectory of hemiplegic patients. Firstly, a gait dataset is established featuring hemiplegic patients walking on level ground. The original sEMG signal sequence is then decomposed using the empirical mode decomposition (EMD) algorithm to mitigate noise and non-stationarity inherent in the data signals. Secondly, kernel principal component analysis (KPCA) is employed to extract key features from the sEMG signal sequence, eliminating redundant information from the original sequence. Thirdly, considering the impact of spatio-temporal correlation in gait data on prediction accuracy, a prediction model based on CNN-BiLSTM is devised. Finally, TL technology is applied between the healthy and affected sides of the subject to transfer knowledge learned from the source domain data to the target domain. This method enhanced the accuracy of gait trajectory prediction for hemiplegic patients, alleviated the training burden, and bolstered the model’s generalization. The findings indicated that this TL strategy holds significant application value for advancing the development of lower limb exoskeleton control systems.
1 December 2017 in Journal of Traditional Chinese Medicine
To investigate the effect of electroacupuncture (EA) of acupoints Neiguan (PC 6) and Tianquan (PC 2) on the skin temperature, blood perfusion, and alpha1- and beta2-adrenoreceptor (α1-AR and β2-AR) protein and mRNA level in rats with acute myocardial ischemia. Thirty male adult Wistar rats [(230 ± 20) g] were randomly assigned into five groups (n = 6 each): a control group, sham operation group, model group, model group treated with EA at low frequency (L-EA, 2 Hz, 1 mA) and model group treated with EA at high frequency (H-EA, 100 Hz, 1 mA). The rat model was prepared by ligating the left anterior descending coronary artery. Electroacupuncture was performed at the left Neiguan (PC 6) for 20min daily for 3 d. After the 3rd time of the treatment, measurements of skin blood perfusion and temperature in Neiguan (PC 6) and Tianquan (PC 2) in all groups were made by laser speckle contrast imaging and infrared thermal image instrument. Real-time PCR and ELISA were used to measure mRNA level and protein level of α1-AR and β2-AR in the skin tissues of Neiguan (PC 6) and Tianquan (PC 2), respectively. Serum levels of cTnT and electrocardiogram were used to identify the state of myocardium. In the group receiving electroacupunture at Neiguan (PC 6), compared with control group, the skin temperature, blood perfusion, and β2-AR mRNA and protein level of model group significantly decreased (P < 0.05), α1-AR mRNA and protein level of model group significantly increased (P < 0.05); compared with model group, the skin temperature, blood perfusion, and β2-AR mRNA and protein level of L-EA significantly increased (P < 0.05), α1-AR mRNA and protein level of L-EA and H-EA significantly decreased (P < 0.05). The same trend has taken place in the former four groups of the Tianquan (PC 2). Low-or high-frequency electroacupuncture can improve the skin temperature and blood perfusion which may be induced by decreasing the level of α1-AR and increasing the level of β2-AR of the Neiguan (PC 6) and Tianquan (PC 2) in the rat with acute myocaidial ischemia.