ABSTRACT
Aiming at the problems of individual differences in the asynchrony process of human lower limbs and random changes in stride during walking, this paper proposes a method for gait recognition and prediction using motion posture signals. The research adopts an optimized gated recurrent unit (GRU) network algorithm based on immune particle swarm optimization (IPSO) to establish a network model that takes human body posture change data as the input, and the posture change data and accuracy of the next stage as the output, to realize the prediction of human body posture changes. This paper first clearly outlines the process of IPSO's optimization of the GRU algorithm. It collects human body posture change data of multiple subjects performing flat-land walking, squatting, and sitting leg flexion and extension movements. Then, through comparative analysis of IPSO optimized recurrent neural network (RNN), long short-term memory (LSTM) network, GRU network classification and prediction, the effectiveness of the built model is verified. The test results show that the optimized algorithm can better predict the changes in human posture. Among them, the root mean square error (RMSE) of flat-land walking and squatting can reach the accuracy of 10 -3, and the RMSE of sitting leg flexion and extension can reach the accuracy of 10 -2. The R 2 value of various actions can reach above 0.966. The above research results show that the optimized algorithm can be applied to realize human gait movement evaluation and gait trend prediction in rehabilitation treatment, as well as in the design of artificial limbs and lower limb rehabilitation equipment, which provide a reference for future research to improve patients' limb function, activity level, and life independence ability.
Subject(s)
Humans , Algorithms , Gait , Machine Learning , Neural Networks, Computer , WalkingABSTRACT
Objective: Analyze the clinical application rule of Chinese patent medicine in cervical radiculopathy (CR) .Method: The clinical real-world data of CR were extracted by using information sharing system of traditional Chinese medicine and clinical research. Six hundred and twenty-eight inpatients and out patients with CR were enrolled from December 2012 to July 2014 in the information system database of Wangjing Hospital. The correlation analyses and mutual information value were recorded for Chinese patent medicine therapy application of all patients by using liquorice software. Complex network diagrams were generated. Result: Yuxuebi capsule and Jingshu granule is the highest frequency in application of Chinese patent medicine. Jingshu granule and Cobamamide for injection were the highest frequency in combined application of Chinese patent medicine and western medicine. Association frequency was 822, mutual information value was 268.07. Biqi capsule and Daiwenjiu cream were the highest frequency in combined application of Chinese patent medicine and topical drugs. Association frequency was 384, mutual information value was1754.76. Conclusion: The basic treating principle for CR was promoting blood circulation and removing blood stasis. The efficacy and safety of combined Chinese patent medicine with other medicine need further research
ABSTRACT
Objective To investigate the changes of expression of N-methyl-D-aspartate receptor(NMDAR)and mitogen activated protein kinase(MAPK)in Alzheimer disease(AD)rat model. Methods AD rat model was established by injection of amyloid-beta protein 1-40 1?l(10 g/L)into hippocampus of rat.NMDAR-mRNA and MAPK protein were immunostained by in situ hybradization histochemistry and immunohistochemistry respectively.Learning and memory ability,LTP were determined by Morris water maze and electrophysiological methods respectively. Results The escape latent was prolongated in Alzheimer rats two weeks after injection of A? than in control rats and in rats before the injection of A?(P