Search

Federated learning （FL） is a distributed machine learning technology that enables joint construction of machine learning models by transmitting intermediate results （e.g., model parameters, parameter gradients, embedding representation, etc.） applied to data distributed across various institutions.FL reduces the risk of privacy leakage, since raw data is not allowed to leave the institution.According to the difference in data distribution between institutions, FL is usually divided into horizontal federated learning （HFL）, vertical federated learning （VFL）, and federal transfer learning （TFL）.VFL is suitable for scenarios where institutions have the same sample space but different feature spaces and is widely used in fields such as medical diagnosis, financial and security of VFL.Although VFL performs well in real-world applications, it still faces many privacy and security challenges.To the best of our knowledge, no comprehensive survey has been conducted on privacy and security methods.The existing VFL was analyzed from four perspectives: the basic framework, communication mechanism, alignment mechanism, and label processing mechanism.Then the privacy and security risks faced by VFL and the related defense methods were introduced and analyzed.Additionally, the common data sets and indicators suitable for VFL and platform framework were presented.Considering the existing challenges and problems, the future direction and development trend of VFL were outlined, to provide a reference for the theoretical research of building an efficient, robust and safe VFL.

Based on the large-scale application of high technology such as the Internet of Things, cloud computing, big data, artificial intelligence in the mining industry and the rapid development of intelligent mining.This paper analyzes the current development situation of intelligent mining and the talent training models of mining engineering major at home and abroad, as well as the existing problems of China's talent training mode. From the three perspectives of government policy support, school teaching system and enterprise talent demand, it puts forward some suggestions on the establishment of a talent training model that adapts to intelligent mining, so as to cultivate innovative talents and realize the scientific application and development of intelligent mining.

Laser speckle is a new technology for non-destructive detection in agriculture. When laser light with good coherence irradiates on the optically rough surface or the surface with some kind of activity, the scattering light will interfere with each other and form a mottled pattern called laser speckle. The laser speckle contains various information of the reflector, such as the roughness, the particle's motion and the temperature information. Huangguan pears were used as the object in this research to investigate the possibility of identifying the defects from the stem/calyx and the sound area of pears based on laser speckle technology. A laser speckle imaging system was established which contained a semiconductor laser (635 nm, 50 mw) applied as the light source and a digital signal generator applied as the trigger source of the CCD (charge coupled device) camera. Two hundred pears including one hundred sound pears and one hundred pears with the defect (rot) were tested. The speckle images of defect (rot) parts and good parts (calyx/stem, sound area) of the pears were collected under the same condition. First of all, the speckle images were converted into the grayscale images using Matlab 2011b. The method of Fujii and the weighted generalized differences method (WGD) were used to analyze the grayscale speckle images to get the images of Fujii and WGD. Then gray level co-occurrence matrix (GLCM) was used to extract the mean and the standard deviation values of the angular second moment (ASM), entropy (ENT), moment of inertia (INE) and correlation (COR) from the images of Fujii and WGD, respectively. Therefore, in total, 16 features were extracted. The performance of each feature was evaluated by the receiver operator characteristic (ROC) curve. According to the ROC curves, the features whose values of the area under the curves (AUC) were higher than 0.5 were chosen for further analysis. The best threshold value of each selected feature was calculated by Youden's index. The classification analysis based on single feature was tested using the best threshold value. Besides, the classification analysis based on multiple features was carried out by the binary logistic regression. The combination of every two features was tested to get better classification accuracy. The results showed that there were seven features whose AUC values were bigger than 0.5. In classification of single feature, the ASM extracted from WGD image had the best performance whose overall accuracies of calibration and validation sets were 96.4% and 96.7% respectively. In classification of multiple features, the combination of the ASM and standard deviation of correlation extracted from WGD image had the best performance whose overall accuracies of calibration and validation sets were both 97.5%. In order to find out the causes of the error, the original RGB (red, green and blue) images of the misjudged samples were studied. It turned out that the defect area which was misjudged to be normal was not obvious. Besides, the defect area was larger than the light spot whose diameter was 20 mm which could not cover the defect area completely. Therefore, the texture features of laser speckle images of misjudged samples were closer to the sound area than the defect area, which led to the miscalculation. This research shows that the method of laser speckle imaging is feasible in the detection of pear defect (rot) and stem/calyx. [ABSTRACT FROM AUTHOR]

Objective: To find out the vitamin A intake in middle-aged and aged females, and to investigate the relationship between retinol intake and bone mineral density (BMD)., Methods: Two hundred and fifty women aged 45 to 66 were enrolled and received physical examination and BMD scanning, and their fasting blood samples and dietary records were collected. Serum retinol and beta-carotene were analyzed by HPLC. Assays for bone turnover markers (such as bone specific alkaline phosphatase, osteocalcin and 25-(OH) D3) in serum were performed by using commercially available kits. Subjects were divided into normal BMD group and low BMD group, and the dietary RE intakes and serum retinol were compared., Results: The average RE intake was 455.8 microg (n = 169), which reached 65.1% of RNI. Serum retinol and beta-carotene in normal BMD group were a little bit higher than the low BMD group, but there was no statistic difference. Vitamin A intake of normal BMD group was 53.0 microg, which was lower than the low BMD group, and carotene intake of normal BMD group was 107.6 microg, which was higher than the low BMD group. The ratio of plant sourced retinol in normal BMD group was higher than the low BMD group. Bivariate correlation analysis on BMD and dietary RE intake showed no statistic correlation, but with a slight negative trend (P = 0.203, r = -0.140). There was a significantly difference in age, bone mineral contents, BMI and BSAP between low BMD group and normal BMD group (P < 0.001 or P < 0.01), and bivariate correlation analysis showed that the age (P < 0.001, r = -0.380), BMI (P < 0.001, r = 0.394) menopausal age (P < 0.05, r = 0.244) and body weight (P < 0.001, r = 0.434) were significantly correlated with BMD. The result of stepwise linear regression analysis showed that the age, menopausal years and BSAP were entered into the regression equation (R2 = 0.552, F = 24.661, P < 0.001), which indicated a strong connection with BMD., Conclusion: (a) RE intake did not reach RNI, and the use of supplements was not common (32.5%). (b) The intake of milk and milk products and beans and bean products was low, and the calcium intake did not reach 50% of AI. (c) Higher serum retinol in normal range might maintain BMD. (d) Too much RE intake might associate with decreased BMD, especially the BMD in femoral bone.

The analysis on the balance of nutrient's profit and loss in crop-fruit ecosystems of three villges in middle-south Loess Plateau showed that fertilization was the main input of nutrients, of which, chemical fertilizer occupied a larger proportion, while organic manure was relatively insufficient. The quantity of N, P and K spent in interior circulation was far less than that exported from the ecosystem. The ratio of nutrient's output and input in three test villages was differed, but all at a low level.

With the Xipo, Feimahe and Nangou villages as test objects, the productive characteristics of crop-fruit ecological agriculture in the middle-south Loess Plateau were investigated. The results showed that the biomass productivity of a plant was different with its organs, the highest for grain or fruit, and followed by stem, leaf and root. In the crop-fruit ecological agriculture, the higher ratio the crop subsystem, the higher productivity its biomass, the lower economic productivity and lower economic value was; while the fruit subsystem was on the contrary. The productivity of livestock farming subsystem was in a lower level, which restricted the increase of the total ecosystem's productivity. Based on these results, a countermeasure of increasing the ecosystem productivity was put forward.