Background: Alzheimer’s disease (AD) is mainly manifested as a continuous and progressive decline in cognitive ability. Neurofibrillary tangles (NFTs) are pathological hallmarks of AD and due to accumulated phosphorylated Tau. Glycogen synthase kinase-3β (GSK3β), as a major Tau kinase and a downstream target of the serine protein kinase B (AKT) signaling pathway, can regulate Tau phosphorylation in AD. Importantly, the AKT/GSK3β signaling pathway is involved in glucose metabolism, and abnormal glucose metabolism is found in the AD brain. Numerous studies have shown that electroacupuncture (EA), which is thought to be a potential complementary therapeutic approach for AD, can protect cognitive ability to a certain extent.Objective: The purpose of this experiment was to investigate whether the protective and beneficial mechanism of EA on cognition was mediated by the AKT/GSK3β signaling pathway, thereby improving glucose metabolism and Tau phosphorylation in the brain.Methods: EA was applied to the Baihui (GV20) and Yintang (GV29) acupoints of 6-month-old amyloid precursor protein (APP)/presenilin-1 (PS1) mice for 20 min, and then quickly prick Shuigou (GV26) acupoint. The intervention was performed once every other day for 28 days. The Morris water maze (MWM) test was performed on C57BL/6N (Non-Tg) mice, APP/PS1 (Tg) mice and EA-treated Tg (Tg + EA) mice to evaluate the effect of EA therapy on cognitive function. 18F-FDG positron emission tomography (PET), immunohistochemistry, and western blotting (WB) were used to investigate the possible mechanism underlying the effect of EA on AD.Results: EA treatment significantly improved the cognition of APP/PS1 mice and the glucose uptake rate in the hippocampus. Furthermore, EA inhibited the phosphorylation of Tau (Ser199 and Ser202) proteins by inducing AKT (Ser473) and GSK3β (Ser9) phosphorylation.Conclusion: These results demonstrate that EA intervention protects cognition by enhancing glucose metabolism and inhibiting abnormal phosphorylation of Tau protein in the AD model mice, and the AKT/GSK3β pathway might play an irreplaceable role in the regulation process.
1 February 2021 in Journal of Physics: Conference Series
Reasonable sales forecast is very important for enterprises. The short-term and long-term sales changes of a product are helpful for enterprises to make marketing strategies and sales decisions. On the basis of in-depth analysis of the characteristics of a certain algorithm model and long and short memory neural network, and according to the data set provided by a supermarket chain in kaggle competition, a XGBoost-LSTM neural network combination model for sales forecasting and a classical time series prediction model are constructed to compare the experimental results. The experimental results show that the XGBoost-LSTM neural network prediction model has higher accuracy than the time series prediction model, which can provide an important scientific basis for the supermarket chain to make sales forecast.
1 February 2021 in Journal of Physics: Conference Series
Faced with massive amounts of data, people may not be able to choose the items they like. The recommendation system came into being, and it has achieved a breakthrough for a long time. Using deep learning can mine the hidden attributes of users' items and integrate them well, bringing new changes to the recommendation system. This article describes the deep learning-based recommendation system and the traditional recommendation system, and analyzes their advantages and disadvantages.
1 February 2021 in Journal of Physics: Conference Series
In order to solve the problem of information overload caused by the rapid expansion of information, it is particularly difficult for users to select the information they are interested in when faced with massive amounts of information. Traditional search has some drawbacks and cannot solve the problem of information overload. The recommendation algorithm provided by the recommendation system is a good strategy to deal with. This article mainly introduces two recommendation algorithms and their principles, content-based recommendation algorithms and collaborative filtering-based recommendation algorithms. And their advantages and disadvantages are compared.