Self-driving cars have gained a lot of research interest in both academia and industry. However, the current solutions mainly rely on either human pre-defined rules or a precise high-resolution map, which are not feasible for the unknown environments, especially when there are some extreme situations not described in the driving rules. In this paper, a new reinforcement learning based method is proposed to address these issues. First, a pre-trained VAE (Variational AutoEncoder) is used to extract representative features from road images, then PPO (Proximal Policy Optimization) algorithm is implemented to learn target-driven navigation for the self-driving car to eliminate the dependence on the map and predefined rules. Second, to improve the learning efficiency, human driving experiences are introduced and how to effectively incorporate human driving experiences into reinforcement learning is also investigated. To evaluate the performance, this algorithm is implemented and deployed in CARLA simulation environments and extensive experiments have been conducted to select the effective strategy of reusing driving experiences. The results prove that our algorithm can successfully navigate in the urban environment without a map or any predefined rules. And by integrating human driving experiences, the learning efficiency has been dramatically improved, especially when using Ratio strategy.
To reveal the distribution characteristics and demographic factors of traditional Chinese medicine (TCM) constitution among elderly individuals in China. Elderly individuals from seven regions in China were selected as samples in this study using a multistage cluster random sampling method. The basic information questionnaire and Constitution in Chinese Medicine Questionnaire (Elderly Edition) were used. Descriptive statistical analysis, chi-squared tests, and binary logistic regression analysis were used. The single balanced constitution (BC) accounted for 23.9%. The results of the major TCM constitution types showed that BC (43.2%) accounted for the largest proportion and unbalanced constitutions ranged from 0.9% to 15.7%. East China region (odds ratio [OR] = 2.097; 95% confidence interval [CI], 1.912 to 2.301), married status (OR = 1.341; 95% CI, 1.235 to 1.457), and managers (OR = 1.254; 95% CI, 1.044 to 1.505) were significantly associated with BC. Age > 70 years was associated with qi-deficiency constitution and blood stasis constitution (BSC). Female sex was significantly associated with yang-deficiency constitution (OR = 1.646; 95% CI, 1.52 to 1.782). Southwest region was significantly associated with phlegm-dampness constitution (OR = 1.809; 95% CI, 1.569 to 2.086). North China region was significantly associated with inherited special constitution (OR = 2.521; 95% CI, 1.569 to 4.05). South China region (OR = 2.741; 95% CI, 1.997 to 1.3.763), Central China region (OR = 8.889; 95% CI, 6.676 to 11.835), senior middle school education (OR = 2.442; 95% CI, 1.932 to 3.088), and managers (OR = 1.804; 95% CI, 1.21 to 2.69) were significantly associated with BSC. This study defined the distribution characteristics and demographic factors of TCM constitution in the elderly population. Adjusting and improving unbalanced constitutions, which are correlated with diseases, can help promote healthy aging through the scientific management of these demographic factors.
Peptic ulcer disease (PUD) is a common disease and frequently encountered in the clinic. Accumulating evidence suggests that PUD is associated with the gastrointestinal microbiota. Electroacupuncture (EA) is an improved version of acupuncture, which can improve the clinical effect by increasing the stimulation and delivering appropriate electrical pulses to needles. This method has been widely used in the treatment of peptic ulcer disease. However, its effect on gastrointestinal microbiota remains unclear. Therefore, in the present study, the ameliorative effect of EA was evaluated on the gastroduodenal mucosa, and the regulatory effect of the gastroduodenal microbiota was assessed in PUD mice. A total of 48 male Kun Ming mice were randomly divided into the following groups: normal control group (NC), PUD model group (PUD), Shousanli group (LI10), and Zusanli group (ST36) (n=12). The mice in groups LI10 and ST36 were treated with EA at LI10 and ST36, respectively. This intervention was continued for 7 days. Subsequently, we evaluated the morphological changes in the gastric and duodenal mucosa, and specific indices were measured, including the contents of serum dopamine (DA), the trefoil factor (TFF), and the vasoactive intestinal peptide (VIP). In addition, the gastric and duodenal microbiota were assessed via 16S ribosomal DNA sequencing. The results indicated that EA at LI10 or ST36 significantly reduced the injury of the gastroduodenal mucosa in PUD mice. The gastric microbial community structure of the groups LI10 and ST36 was similar to that of the NC group following comparison with the microbial community structure of the PUD model group. Moreover, the abundance of Firmicutes in the stomach was decreased, whereas that of Bacteroidetes was increased, and the abundance of Firmicutes in the duodenum was decreased. Furthermore, the microbial diversity and richness of the gastric microbiota in group LI10 were also significantly increased, and the serum dopamine and trefoil factor levels in group ST36 were significantly increased. Therefore, it is suggested that EA ameliorating PUD is in association with improving the levels of DA and TFF and regulating the relative abundances of Firmicutes and Bacteroidetes in the gastric microbiota.
To convert Na2SO4 into other high-value products (NaOH, H2SO4, and (NH4)2SO4), three types of cell configurations of electrodialysis were applied (three compartments bipolar membrane electrodialysis (BMED), four compartments electrodialysis metathesis (EDM) and five compartments bipolar membrane electrodialysis metathesis (BMED-5)) and parameters such as the average voltage variation, desalination rate, product concentration, conversion rate, ion flux and energy consumption were calculated and compared. The experimental results and calculations indicated that the overall performance of BMED-5 was inferior to that of BMED and EDM. An industrial model was established, indicating that the net profit of converting Na2SO4 using BMED-5 was always higher than that of BMED and EDM. Based on the advantages of low investment cost (132 $) and low energy cost (152 $/t Na2SO4), EDM was applicable to factories with a low output of Na2SO4 (production capacity < 45%), while BMED (157.3 $/t Na2SO4) and BMED-5 (227.6 $/t Na2SO4) were applicable to those with a high output of Na2SO4 (production capacity > 45%) based on high net profits.
Dissolved gas analysis (DGA) of insulation oil is widely used in potential fault analysis for transformers. In order to improve the accuracy of fault diagnosis, a hybrid model which combines the FRVM with the depth belief network (DBN) is proposed to establish the mapping relationship between gas and fault types. Considering that DBN needs to extract a huge amount of feature information, this paper uses FRVM to separate the discharge and overheating faults, and then uses DBN to realize further fault diagnosis. The diagnosis accuracy is studied when IEC ratio, Rogers ratio, Dornenburg ratio and non-cod ratios are used as input parameters, and the results show that the correct rate of diagnosis is highest when the non-cod ratios are used as characteristic parameter. In addition, the method has better performance compared with single DBN, support vector machine and artificial neural network, and it has the ability to diagnose multiple faults.
'/%3e%3cuse xlink:href='%23a' transform='rotate(23.036 .093 25.536)'/%3e%3cuse xlink:href='%23a' transform='rotate(45.87 1.273 16.18)'/%3e%3cuse xlink:href='%23a' transform='rotate(69.945 .996 12.078)'/%3e%3cuse xlink:href='%23a' transform='rotate(20.66 -19.689 31.932)'/%3e%3c/svg%3e)
'/%3e%3cuse xlink:href='%23a' transform='translate(288.889 -214.211)'/%3e%3cuse xlink:href='%23a' transform='translate(108 342.749)'/%3e%3cuse xlink:href='%23a' transform='translate(469.189 342.749)'/%3e%3c/svg%3e)