Explore the vast range of titles available.

This paper proposes a personalized learning resource recommendation method based on dynamic collaborative filtering algorithm. Pearson correlation coefficient is used to calculate the data similarity between learning users or project resources in the network, and the unscored value is obtained. In order to solve the problems of sparse data and poor scalability in collaborative filtering algorithm, dynamic k-nearest-neighbor and Slope One algorithm are used to optimize it, and the sparsity of learning resource data in the network is analyzed according to the result of neighbor selection. The bidirectional self-equalization of stage evolution is used to improve the personalized recommendation of resource push, and the fuzzy adaptive binary particle swarm optimization algorithm based on the evolution state judgment is used to solve the problem of the optimal sequence recommendation, so as to realize the personalized learning resource recommendation. The experimental results show that the proposed method has higher matching degree and faster recommendation speed.

In social network big data scheduling, it is easy for target data to conflict in the same data node. Of the different kinds of entropy measures, this paper focuses on the optimization of target entropy. Therefore, this paper presents an optimized method for the scheduling of big data in social networks and also takes into account each task’s amount of data communication during target data transmission to construct a big data scheduling model. Firstly, the task scheduling model is constructed to solve the problem of conflicting target data in the same data node. Next, the necessary conditions for the scheduling of tasks are analyzed. Then, the a periodic task distribution function is calculated. Finally, tasks are scheduled based on the minimum product of the corresponding resource level and the minimum execution time of each task is calculated. Experimental results show that our optimized scheduling model quickly optimizes the scheduling of social network data and solves the problem of strong data collision.

Red blood cell distribution width/albumin ratio (RAR) has been reported as an independent risk factor for diabetic retinopathy (DR), while its association and predictive value in the prognosis of DR patients has not been reported. This study aims to explore the association and predictive value of RAR in the prognosis of DR patients. This was a retrospective cohort study based on the National Health and Nutrition Examination Survey (NHANES). The independent variable was RAR, and dependent variables were all-cause mortality and cardiovascular diseases (CVD) mortality. The association between RAR and the risk of all-cause mortality and CVD mortality was assessed using univariate and multivariate cox regression models. The results were shown as HR (hazard ratio) with 95% confidence intervals (CIs). Subgroup analysis based on age or hyperlipidemia was performed. The discrimination of the prediction model was assessed using concordance index (C-index). A total of 725 eligible patients were finally included in this study. The increase of RAR was associated with increased risk of all-cause mortality (HR: 1.15, 95%CI: 1.01-1.31) and CVD mortality (HR: 1.35, 95%CI: 1.12-1.63) after adjusting the covariates. We also found the significant association between higher RAR and higher risk of CVD mortality in DR patients with age < 65 years (HR: 1.35, 95%CI: 1.09-1.67) and with hyperlipidemia (HR: 1.34, 95%CI: 1.10-1.64). C-index of RAR for all-cause mortality and CVD mortality was 0.63 (95%CI: 0.59-0.67) and 0.65 (95%CI: 0.59-0.71), respectively. Higher RAR was associated with the higher risk of all-cause mortality and CVD mortality in DR patients, and RAR may be a useful predictor for the prognosis of DR patients.

Enhancement method for edge texture details of the filmic and visual three-dimensional animation has the vital significance to the dynamic analysis and evaluation of the following images. The traditional enhancement method for edge texture detail mainly uses fuzzy contrast to improve the quality of animation. The contrast and clarity are poor. In order to reduce the noise, this paper proposes the enhancement method of filmic and visual three-dimensional animation edge texture detail based on statistical shape priors. Firstly, this method carries out the segmentation, de-noising, edge detection processing on animation, then uses statistical shape prior method to enhance the edge texture detail. Experimental results show that the proposed method can obtain more ideal edge detail information.

Cognitive computing is one kind of affective social computing, and becomes a research hotspot now. The traditional feature fusion method has the disadvantages to process big cognitive data, such as high redundancy, less efficient operation, increased energy consumption during data fusion, and reduced survival cycle of the data analysis. Therefore, a data feature fusion method based on BP neural network is proposed in this paper. First, the cognitive data features of big data analysis are extracted. Secondly, the data feature fusion method based on BP neural network is used to fuse the cognitive data features of big data analysis. It overcomes the shortcomings of the traditional method, such as reducing the redundancy of data transmission, improving the efficiency of operation, reducing the energy consumption in fusion process, and prolonging the life cycle. The experimental results show that the energy consumption of the operation can be effectively reduced by using the proposed method.

Medical images are blurred and noised due to various reasons in the acquirement, transmission and storage. In order to improve the restoration quality of medical images, a regular super-resolution restoration algorithm based on fuzzy similarity fusion is proposed. Based on maintained similarity in multiple scales, the fused similarity of the medical images is computed by fuzzy similarity fusion. First, fuzzy similarity is determined by the regional features. The images with certain similarity are obtained according to the maximum value, and the fused image is obtained by all obvious regional features. Then, an adaptive regularized restoration algorithm is employed. In order to ensure the objective function has a global optimal solution, regularized parameters of the global minimum solution of nonlinear function are solved iteratively. Finally, experimental results show that mean square error (MSE) and peak signal-to-noise ratio (PSNR) of the restored image are visibly improved. The restored image also has an obvious improvement in the burr of local edge. Moreover, the algorithm has good stability with significantly enhanced PSNR.

In order to effectively identify the pattern of personalized adaptive learning in online education and improve the recommendation satisfaction of personalized learning resources in online education platform, this paper studies the pattern recognition method of personalized adaptive learning in online education. The learning behavior pattern data in the online education platform are mined, preprocessed, clustered and made correlation analysis, and the obtained data are used to construct the learner’s personalized adaptive learning characteristics model; on this basis, the framework of learning pattern recognition model is constructed to recognize the personalized adaptive learning pattern from four aspects: cognitive level, learning style, interactive behavior pattern characteristics and online social learning characteristics. The experimental test results show that this method can effectively identify the personalized adaptive learning patterns of learners, including interactive learning behavior patterns and online social learning patterns. The personalized learning resources recommended by the online education platform according to the identification results of this paper have obtained the learners’ satisfaction score of a high level at 93.27%.

INTRODUCTION: \"Improving the employment rate of college students\" directly affects the stability of the country and society and the healthy development of the industry market. The traditional graduate employment rate model only predicts the future employment rate based on changes in historical employment data in previous years.OBJECTIVES: Quantify the employment factors and solve the employment problems in colleges and universities in a targeted manner.METHODS: We construct a credible employment prediction model for college graduates based on LightGBM.RESULTS: We use the model to predict the employment status of students and obtain the special importance which is important to employment of college students.CONCLUSION: The final result shows that our Model performs well in the two indicators of accuracy and model quality.

Diabetic retinopathy, an inflammatory condition, is one of the devastating complication associated with diabetes that can lead to irreversible blindness. Gentiopicroside (GP), a secoiridoid glycoside, exhibits anti-inflammatory and antioxidant activity. The investigation was carried out to explore whether GP could attenuate diabetic retinopathy in diabetic rats. Diabetes was induced by injecting streptozotocin (STZ) (65 mg/kg) intraperitoneally in 8-weeks-old male rats (200–240 g). The treatment group received GP (20, 40, 80 mg/kg) orally for a duration of 10 weeks in diabetic rats (n = 10), and the diabetic group animals received phosphate buffer solution (n = 20). Effect of GP on cell viability study was performed by 3-(4,5-dimethyl-2-thiazolyl)-2,5-diphenyl-2H-tetrazolium bromide (MTT) assay. Oxidative stress markers, inflammatory mediators, and angiogenic factors were quantified in the retinal tissues of diabetic animals. All data were analyzed by one-way analysis of variance (ANOVA) at P < 0.05. Cytoprotective effect of GP was observed in MTT assay. GP effectively downregulated inflammatory cytokine, nuclear factor κB (NF-κB), tumor necrosis factor-α (TNF-α), interleukin 1 beta (IL-1β), and intercellular adhesion molecules-1 (ICAM-1), and upregulated antioxidant markers glutathione (GSH), superoxide dismutase (SOD), and catalase (CAT) in the retina of diabetic rats. GP equilibrated the disturbed angiogenic factors in the diabetic retinal tissues. Results clearly indicated defensive role of GP in the treatment of diabetic retinopathy by inhibition of NF-κB and oxidative stress.

Objective. To observe the orbital volume changes and the analysis of surgical effect of Graves orbitopathy (GO) after endoscopic medial wall decompression combined with muscle cone fat. Methods. Twenty-two patients (30 eyes) with Graves orbital disease who visited the Department of Ophthalmology of Ningbo Medical Center from December 2019 to September 2021 were retrospectively collected. All patients were diagnosed as nonorganic active stage before operation, and all of them received endoscopic transethmoidal decompression of the medial orbital wall combined with intramuscular orbital fat decompression due to decreased vision, visual field defect or color vision disorder, and concomitant proptosis. Regular follow-up after operation. The curative effect is judged according to the degree of improvement of visual acuity, color vision, degree of correction of exophthalmos, diplopia, and other complications at 9 months after operation. Orbital CT combined with computer aided measurement software (Mimics 21) was used to measure the changes of orbital volume before and after exophthalmos surgery. The relationship between the value and eyeball regression is analyzed. Results. Preoperative exophthalmos ranged from 17.4 mm to 27.6 mm, with an average of (22.08±2.86) mm. The postoperative exophthalmos was 14-25 mm, with an average of (19.52±3.10) mm. Among them, 7 eyes (23.3%) had exophthalmos regression less than 1 mm, 6 eyes (20%) had a regression of 1-2 mm, 7 eyes (23.3%) had a regression of 2-3 mm, 5 eyes (16.7%) had a regression of 3-4 mm, and 5 eyes (16.7%) had a regression of 4-5.3 mm. The exophthalmos after operation was significantly lower than that before operation, and the difference was statistically significant (t=9.909, P<0.05). The preoperative orbital volume was 18.6 cm3-25.3 cm3 with an average of (22.39±1.91) cm3. The postoperative orbital volume was 19.8 cm3-26.6 cm3, with an average of (23.89±1.90) cm3.The orbital volume change range is 0.1 cm3-3.8 cm3, and the average orbital volume change is (1.51±1.00) cm3. Compared with preoperative orbital volume, the difference was statistically significant (t=−8.074, P<0.05). Conclusion. Endoscopic decompression of the medial orbital wall through the ethmoid approach combined with decompression of the orbital fat within the muscle cone can effectively correct the exophthalmos while decompressing the orbital apex, and it is minimally invasive and has no facial scars. It has the advantages of extremely low incidence of postoperative diplopia and eye shift. There is a significant correlation between orbital volume changes and the regression of exophthalmos, which can provide reference for clinical guidance of surgical methods and prediction of surgical results.