Objective To observe the influence of Bugan Jianyao Fang (Liver-tonifying Lumbarinvigorating Decoction) on expressions of intervertebral disc matrix metalloproteinase-3 (MMP-3) and tissue inhibitor of metalloproteinase-1 (TIMP-1) in rats with lumbar disc degeneration.Methods SD rats (n =75) were randomly divided into sham-operation group,model group,Yaobitong (Waist Impediment-Freeing Capsules) group,doxycycline (DOX) group and Bugan Jianyao Fang group (each n =15).Mter establishing successfully the model of lumbar disc degeneration in rats,all groups were,respectively,given orally Yaobitong,DOX and Bugan Jianyao Fang.The expressions of intervertebral disc MMP-3 and TIMP-1 were detected in all group after and 20 d and 4 d after intervention.Results After intervention for 20 d and 40 d,the expressions of intervertebral disc MMP-3 and TIMP-1 decreased in Yaobitong group,DOX group and Bugan Jianyao Fang group compared with model group (P ＜0.05).The difference in expressions of intervertebral disc MMP-3 and TIMP-1 had statistical significance in Yaobitong group,DOX group and Bugan Jianyao Fang group after intervention compared with those in the same groups before intervention (P ＜ 0.05).The comparison among Bugan Jianyao Fang group,Yaobitong group and DOX group showed that the difference had no statistical significance (P ＞ 0.05) at all time points.Conclusion Bugan Jianyao Fang can reduce the expressions of intervertebral disc MMP-3 and TIMP-1 in rats with lumbar disc degeneration,which may be one of mechanisms of Bugan Jianyao Fang preventing and curing lumbar disc degeneration.

We proposed a new deep learning model by analyzing electroencephalogram signals to reduce the complexity of feature extraction and improve the accuracy of recognition of fatigue status of pilots. For one thing, we applied wavelet packet transform to decompose electroencephalogram signals of pilots to extract the δ wave (0.4-3 Hz), θ wave (4-7 Hz), α wave (8-13 Hz) and β wave (14-30 Hz), and the combination of them was used as de-nosing electroencephalogram signals. For another, we proposed a deep contractive auto-encoding network-Softmax model for identifying pilots' fatigue status. Its recognition results were also compared with other models. The experimental results showed that the proposed deep learning model had a nice recognition, and the accuracy of recognition was up to 91.67%. Therefore, recognition of fatigue status of pilots based on deep contractive auto-encoding network is of great significance.