Search

Let G be a finite group. Inspired by the properties of D(G), we define the D*-norm, denoted by D*(G), to be the intersection of the normalizers of the derived subgroups of all subgroups H of G such...

This paper focuses on the comparison of dimensionality reduction effect between LightGBM and XGBoost-FA. With respect to XGBoost, LightGBM can be built in the effect of dimensionality reduction via both Gradient-based One-Side Sampling(GOSS) and Exclusive Feature Bundling(EFB) algorithms, while XGBoost coupling with traditional dimensionality reduction tool Factor Analysis (XGBoost-FA) may also have dimensionality reduction effect. To present the empirical comparison, the prediagnosis dataset for the 2018 Kaggle competition Acute Liver Failure has been chosen as the research object. And pairwise comparison has been conducted among XGBoost, LightGBM, XGBoost-FA and LightGBM-FA. Concerning the test set, the vector (accuracy, log loss function, training time) of the above first four prediagnostic models are (0.75014, 0.569707, 10.5s), (0.75811, 0.576059,15.1s), (0.67786,0.663924,5.7s) and (0.67274,0.676019, 4.1s) respectively. It’s been found that the training time of XGBoost-FA (external dimensionality reduction) is shorter than that of LightGBM (build-in dimensionality reduction). Considering (accuracy, training time) being (0.82, 3.1s) published on Kaggle, the algorithm (logogram as K2a) is better than the four XGBoost-FA and LightGBM in both training time and accuracy. However, K2a removes more than 50% samples with missing values and only performs binary classification. For multi-class classification or data with a large number of missing values, XGBoost-FA is more suggested if higher operational time is required, while LightGBM is preferred if higher predictive accuracy is required. With XGBoost-FA or LightGBM being employed in AI medical services, doctors are more productive in diagnosis and treatment due to much more data support and less workload. Both complement each other.

The P2P online lending industry has gradually developed with the rise of the Internet. As the main source of funds for the industry, the capital contribution of investors affects the sustainable and stable development of the industry. A scientific and reasonable prediction of the willingness to invest can be used for the operation and decision-making of online lending platforms. In order to avoid the bias of using the capital contribution S to measure the willingness to invest, this paper progressively proposes three evaluation indexes ρ 1 , ρ 2 , ρ 3 that integrate the borrower’s lending amount D, lending interest rate r and investment risk p to measure the willingness of P2P online lending. According to the above three indexes, the ANN-LR method is used to predict the willingness to lending. Firstly, the Logistic Regression (LR) method is used to predict the capital contribution risk P of each bid, and then the three progressive and relative indexes are used to predict the willingness of P2P online lending. The predicted results show that, in the prediction of the willingness to invest in P2P online lending, if more accurate the prediction result is required, you can choose ρ 1 . If you want to shorten the total duration of learning while ensuring the accuracy of the results, you can choose ρ 2 for comprehensive consideration. The results obtained are more scientific and reasonable, and more realistic, and ρ 3 can be selected.

Estimating reference evapotranspiration (ET0) is a fundamental requirement of agricultural water management. The FAO Penman–Monteith (FAO-PM) equation has been used as the standard for ET0 estimation. However, the lack of necessary meteorological data makes it difficult to estimate spatially distributed ET0 using the FAO-PM method in the wider ungauged areas. In this study, the aim is to explore the methodology for estimating reference evapotranspiration based on remote sensing data. In this method, remote sensing data are combined with machine learning algorithms to establish a model for spatially distributed ET0 estimation. Three machine learning algorithms were tested, including support vector machine (SVM), back-propagation neural network (BP), and adaptive neuro fuzzy inference system (ANFIS). Results showed this method had good ability in estimating ET0. Application of the method in Northwest China indicated that the land surface temperature (LST) can be used to accurately estimate ET0 with high correlation coefficients (r2 of 0.897–0.915). The surface reflectance has potential for estimating ET0 with LST and can slightly improve model accuracy based on LST. Evaluation showed LST was more essential than surface reflectance and the model only based on LST had satisfactory performance. This method could be applicability in worldwide with available remote sensing and meteorological data due to the relationship between LST and ET0.

The traditional comprehensive evaluation is difficult to model when dealing with large data with large parameters and complex structure, and it cannot adapt to the update of data. In order to improve this situation, this paper draws on the Adaptive Learning Adaboost perspective in statistical learning to develop a data-driven integrated evaluation model that updates the weight of sample weights and weak evaluation models with data. Three specific weak evaluation models were selected: data-driven Topsis method, principal component analysis method and factor analysis method. Taking the ranking of WeChat public account as an example, the results show that the accuracy of the integrated evaluation model is 88.57%, which is 17.14%, 31.43% and 28.57% higher than the data-driven Topsis method, principal component method and factor analysis method.

The exchange rate is one of the important indicators to measure macroeconomic fluctuations. The exchange rate of the US dollar against the RMB reflects the currency exchange rates of the world’s two largest economies. As a global emergency, the new coronavirus pneumonia (Corona Virus Disease 2019, COVID-19) has a significant impact on all aspects of society, so fluctuations in the exchange rate market cannot be ignored. This article uses the daily exchange rate of USD to RMB published on the official website of China Merchants Bank as the dependent variable representing the economic situation. The daily new confirmed cases of new coronavirus pneumonia confirmed by the National Health Commission, the number of new deaths each day, and the number of new cured cases each day are the influencing variables, and the Shanghai Interbank Offered Rate is used as the control variable. In order to explore the relationship between variables and predict and analyze exchange rate fluctuations accordingly, multiple linear regression and quantile regression are used for impact analysis. Comparing the prediction results of the multiple linear regression and the K nearest neighbor model, it is found that daily new confirmed cases, daily new cured cases, and market interest rates harm the exchange rate. At 0.5 quintile, the number of newly diagnosed cases per day increases by 1 unit, and the exchange rate of the U.S. dollar to the renminbi will correspondingly decrease by 0.00001%. At the 0.75 quantiles, new cured cases will change by one unit every day, and the exchange rate will change. The percentage is -0.00003%, the market interest rate changes by one unit, and the percentage of exchange rate changes are -0.037%, which is significant. And after comparison, it is found that the prediction effect obtained by the K nearest neighbor model is better than the multiple linear regression model. At the beginning of the epidemic, the exchange rate fluctuated by 1.78%. After the government took a series of prevention and control measures against major emergencies, the epidemic was effectively controlled, worries gradually eased, and the exchange rate has returned to a relatively stable state.

This paper selects the open dataset of the auction, combines the factor analysis with XGBoost, analyzes the dimension of the pre-processed high-dimensional data with factor analysis, and then uses XGBoost to predict the investment level of P2P online loan investors, and analyzes and quantifies the willingness to invest. The relationship with specific influencing factors. The main factors affecting the willingness to contribute through the ranking of the characteristic factors of the factor analysis and the reduction of the common factors include: the borrowing rate and the initial rating, the real name certification on the borrower’s mobile phone, and the repaid principal and interest paid. The model prediction results show that the XGBoost method combined with factor analysis predicts that the error rate of the investment level on the training set is train-merror: 0.03829, and the error rate on the test set is test-merror: 0.050386. Compared with the method using XGBoost alone, the prediction error rate based on factor analysis and XGBoost on the training set and the test set is reduced by 0.020706 and 0.0152, respectively, which significantly reduces the error rate; and shortens the operation time by 18 seconds. The conclusions obtained in this paper provide reference for the stable development of the P2P industry and the decision-making of investors.

We describe an image denoising algorithm to improve the denoising performance and the time efficiency, while keeping the edge texture of the image from being blurred. First, the algorithm discriminates the pixel whether is an edge pixel or a noise pixel according to the similarity region values of the neighborhoods, and calculates the adaptive diffusion coefficients to construct an adaptive influence function, which can control the noise and the edges to have different diffusion speeds. Then, a 5-layer feedback convolution network with 16 small filters in each layer generates the reconstructed image through convolution, diffusion and deconvolution. Last, the algorithm uses multiple noise levels training sets to train and optimize the network parameters, and generates the finial image denoising model. The experimental results show that the proposed algorithm using adaptive diffusion coefficients can maintain the edges and the smaller filter can improve the time efficiency. The algorithm also has higher denoising accuracy for images with unknown noise level by training on multiple-noise-level training sets.

The reliable and accurate prediction of groundwater levels is important to improve water-use efficiency in the development and management of water resources. Three nonlinear time-series intelligence hybrid models were proposed to predict groundwater level fluctuations through a combination of ensemble empirical mode decomposition (EEMD) and data-driven models (i.e., artificial neural networks (ANN), support vector machines (SVM) and adaptive neuro fuzzy inference systems (ANFIS)), respectively. The prediction capability of EEMD-ANN, EEMD-SVM, and EEMD-ANFIS hybrid models was investigated using a monthly groundwater level time series collected from two observation wells near Lake Okeechobee in Florida. The statistical parameters correlation coefficient (R), normalized mean square error (NMSE), root mean square error (RMSE), Nash&ndash, Sutcliffe efficiency coefficient (NS), and Akaike information criteria (AIC) were used to assess the performance of the EEMD-ANN, EEMD-SVM and EEMD-ANFIS models. The results achieved from the EEMD-ANN, EEMD-SVM and EEMD-ANFIS models were compared with those from the ANN, SVM and ANFIS models. The three hybrid models (i.e., EEMD-ANN, EEMD-SVM, and EEMD-ANFIS) proved to be applicable to forecast the groundwater level fluctuations. The values of the statistical parameters indicated that the EEMD-ANFIS and EEMD-SVM models achieved better prediction results than the EEMD-ANN model. Meanwhile, the three models coupled with EEMD were found have better prediction results than the models that were not. The findings from this study indicate that the proposed nonlinear time-series intelligence hybrid models could improve the prediction capability in forecasting groundwater level fluctuations, and serve as useful and helpful guidelines for the management of sustainable water resources.

Accurate and reliable prediction of groundwater level is essential for water resource development and management. This study was carried out to test the validity of three nonlinear time-series intelligence models, artificial neural networks (ANN), support vector machines (SVM) and adaptive neuro fuzzy inference system (ANFIS) in the prediction of the groundwater level when taking the interaction between surface water and groundwater into consideration. These three models were developed and applied for two wells near Lake Okeechobee in Florida, United States. 10 years data-sets including hydrological parameters such as precipitation (P), temperature (T), past groundwater level (G) and lake level (L) were used as input data to forecast groundwater level. Five quantitative standard statistical performance evaluation measures, correlation coefficient (R), normalized mean square error (NMSE), root mean squared error (RMSE), Nash-Sutcliffe efficiency coefficient (NS) and Akaike information criteria (AIC), were employed to evaluate the performances of these models. The conclusions achieved from this research would be beneficial to the water resources management, it proved the necessity and effect of considering the surface water-groundwater interaction in the prediction of groundwater level. These three models were proved applicable to the prediction of groundwater level one, two and three months ahead for the area that is close to the surface water, for example, the lake area. The models using P, T, G and L achieved better prediction result than that using P, T and G only. At the same time, results from ANFIS and SVM models were more accurate than that from ANN model.

Response time, describing how quickly a disturbed system would reach a new equilibrium, has been helpful to hydrogeologists in characterizing and understanding the hydrogeological systems. This study examined the complex response times associated with lake–groundwater perturbed by climate. Simulated hydraulic heads and lake stage values derived from a 3-D, MODFLOW-based model were used to calculate the response times for a closed, groundwater-fed lake system. Although obviously coupled, the response times of the lake and groundwater systems were different from one another. Typically, the adjustments in hydraulic heads occurred more rapidly than lake stage. Response times for groundwaters close to the lake were controlled by the lake because of the slow transient response in stage. However, the influence of the lake declined toward the basin boundaries. This behavior occurred because critical parameters controlling the response-time behavior of the groundwater system (e.g., recharge rate) differed from those controlling the response-time behavior of the lake (e.g., bed leakance). An improved understanding of lake–groundwater behaviors have the potential to evaluate how lakes function as systems for recording paleoclimates.

Eco-compensation is the most important form of compensatory conservation in China. However, this compensatory mechanism is criticized for vague definition and massive government participation. For better understanding of eco-compensation in China, this paper compares theories and practices of compensatory mechanisms in China and abroad. The analysis of theoretical backgrounds shows that eco-compensation in China is a combination of 'ecological compensation' and 'payments for ecosystem services'. Ten compensatory projects in China and abroad are assessed to reveal characteristics and problems of eco-compensation in China. The results show that compensatory projects in China lagged behind mature foreign compensatory projects in clarity of property rights, responsibility fulfillment, executive efficiency, effectiveness, sustainability and equality. The massive participation of the government is the major reason for the poor performance of compensatory projects in China. However, government participation is necessary at the present stage in China for the income gap and beneficiaries' low willingness to pay. For the improvement of eco-compensation in China, suggestions are given on the choice of non-market valuation methods, the creation of property rights and the establishment of market mechanisms.

Acetylcholinesterase (AChE) expression may be induced during apoptosis in various cell types. Here, we used the C-terminal of AChE to screen the human fetal brain library and found that it interacted with Ran-binding protein in the microtubule-organizing center (RanBPM). This interaction was further confirmed by coimmunoprecipitation analysis. In HEK293T cells, RanBPM and AChE were heterogeneously expressed in the cisplatin-untreated cytoplasmic extracts and in the cisplatin-treated cytoplasmic or nuclear extracts. Our previous studies performed using morphologic methods have shown that AChE translocates from the cytoplasm to the nucleus during apoptosis. Taken together, these results suggest that RanBPM is an AChE-interacting protein that is translocated from the cytoplasm into the nucleus during apoptosis, similar to the translocation observed in case of AChE.

By extending Gini coefficient in the classical economics, we put forward the concept “the steel capacity competitiveness - capacity income Gini coefficient”, namely TCC, to reveal the non-equilibrium problems. Considering the comprehensive factors which influence steel industry competitiveness capacity, AHP was used to construct the evaluation model of steel industry capacity competitiveness. The numerical computation is done by Matlab to calculate the weight of each factor. The computation value of TCC of Chinese steel industry in 2006 is 0.4192. As the revenue Gini coffeicient, now it indicates the deviation of capacity competitiveness contribution income between is bigger. By the TCC analysis, there are only 3 enterprises, Jiangsu steel and Baosteel and Capital steel,whose Tcc is greater than 1. And the contribution of these three enterprises are biggest. TCC provides an downsized index to improve steel industry overcapacity.