Novel Early-Warning Model for Customer Churn of Credit Card Based on GSAIBAS-Cat Boost

As the banking industry gradually steps into the digital era of Bank 4.0,business competition is becoming increasingly fierce,and banks are also facing the problem of massive customer churn.To better maintain their customer resources,it is crucial for banks to accurately predict customers with a tendency to churn.Aiming at the typical binary classification problem like customer churn,this paper establishes an early-warning model for credit card customer churn.That is a dual search algorithm named GSAIBAS by incorporating Golden Sine Algorithm(GSA)and an Improved Beetle Antennae Search(IBAS)is proposed to optimize the parameters of the CatBoost algorithm,which forms the GSAIBAS-CatBoost model.Especially,considering that the BAS algorithm has simple parameters and is easy to fall into local optimum,the Sigmoid nonlinear convergence factor and the lane flight equation are introduced to adjust the fixed step size of beetle.Then this improved BAS algorithm with variable step size is fused with the GSA to form a GSAIBAS algorithm which can achieve dual optimization.Moreover,an empirical analysis is made according to the data set of credit card customers from Analyttica official platform.The empirical results show that the values of Area Under Curve(AUC)and recall of the proposedmodel in this paper reach 96.15%and 95.56%,respectively,which are significantly better than the other 9 common machine learning models.Compared with several existing optimization algorithms,GSAIBAS algorithm has higher precision in the parameter optimization for CatBoost.Combined with two other customer churn data sets on Kaggle data platform,it is further verified that the model proposed in this paper is also valid and feasible.

The Contribution of United States Aircraft Reconnaissance Data to the China Meteorological Administration Tropical Cyclone Intensity Data:An Evaluation of Homogeneity

This paper investigates the homogeneity of United States aircraft reconnaissance data and the impact of these data on the homogeneity of the tropical cyclone(TC)best track data for the seasons 1949-1987 generated by the China Meteorological Administration(CMA).The evaluation of the reconnaissance data shows that the minimum central sea level pressure(MCP)data are relatively homogeneous,whereas the maximum sustained wind(MSW)data show both overestimations and spurious abrupt changes.Statistical comparisons suggest that both the reconnaissance MCP and MSW were well incorporated into the CMA TC best track dataset.Although no spurious abrupt changes were evident in the reconnaissance-related best track MCP data,two spurious changepoints were identified in the remainder of the best-track MCP data.Furthermore,the influence of the reconnaissance MSWs seems to extend to the best track MSWs unrelated to reconnaissance,which might reflect the optimistic confidence in making higher estimates due to the overestimated extreme wind“observations”.In addition,the overestimation of either the reconnaissance MSWs or the best track MSWs was greater during the early decades compared to later decades,which reflects the important influence of reconnaissance data on the CMA TC best track dataset.The wind-pressure relationship(WPR)used in the CMA TC best track dataset is also evaluated and is found to overestimate the MSW,which may lead to inhomogeneity within the dataset between the aircraft reconnaissance era and the satellite era.

Asbestos Exposure during Gasket Removal from Aircraft Engine

We have previously evaluated asbestos exposure associated with various maintenance procedures on light aircraft. The purpose of this study was to evaluate asbestos exposure during engine maintenance on light aircraft. This test was designed to evaluate the potential for asbestos exposure to mechanics and others who remove asbestos-containing engine gaskets from reciprocating style aircraft engines. Utilized in this test was an air cooled, horizontally opposed, aviation gasoline burning engine, assembled during 1986 and operated intermittently up into 2015, having accumulated 1680 hours run time. Nearly 75% of the asbestos-containing gaskets installed during 1986 were still in place at the time of testing. Chrysotile asbestos contents of such gaskets ranged from 55% to 60% by area, for those of sheet style and 5% by area, for the spiral wound metal/asbestos style. Despite the levels of effort required to effect gasket removals, the professional aircraft mechanic was not exposed to airborne asbestos fibers at the lower limits of sampling and analytical detection achieved;all of which were substantially less than the current Occupational Safety and Health Administration Permissible Exposure Limits for asbestos. The results of this testing indicate an absence of gasket related asbestos exposure risk to mechanics who work with light aircraft engines, including those having asbestos-containing gaskets. These results are consistent with the findings of Mlyarek and Van Orden who studied the asbestos exposure risk occasioned during overhaul of larger radial style reciprocating aircraft engines [1].

Analysis and Research on Aerodynamic Characteristics of Quad Tilt Rotor Aircraft

For the quad tilt rotor aircraft, a computational fluid dynamics method based on multiple reference frames (MRF) was used to analyze the influence of aerodynamic layout parameters on the aerodynamic characteristics of the quad tilt rotor aircraft. Firstly, a numerical simulation method for the interference flow field of the quad tilt rotor aircraft is established. Based on this method, the aerodynamic characteristics of isolated rotors, rotor combinations at different lateral positions on the wing, and rotor rotation directions under different inflow velocities were calculated and analyzed, in order to grasp their aerodynamic interference laws and provide reference for the design and control theory research of such aircraft.

Assessment of Meteorological Threats to the Coordinated Search and Rescue of Unmanned/Manned Aircraft

The architecture and working principle of coordinated search and rescue system of unmanned/manned aircraft,which is composed of manned/unmanned aircraft and manned aircraft,were first introduced,and they can cooperate with each other to complete a search and rescue task.Secondly,a threat assessment method based on meteorological data was proposed,and potential meteorological threats,such as storms and rainfall,can be predicted by collecting and analyzing meteorological data.Finally,an experiment was carried out to evaluate the performance of the proposed method in different scenarios.The experimental results show that the coordinated search and rescue system of unmanned/manned aircraft can be used to effectively assess meteorological threats and provide accurate search and rescue guidance.

China agricultural outlook for 2015–2024 based on China Agricultural Monitoring and Early-warning System(CAMES)

The primary goal of Chinese agricultural development is to guarantee national food security and supply of major agricultural products. Hence, the scientiifc work on agricultural monitoring and early warning as wel as agricultural outlook must be strengthened. In this study, we develop the China Agricultural Monitoring and Early-warning System (CAMES) on the basis of a comparative study of domestic and international agricultural outlook models. The system is a dynamic and multi-market partial equilibrium model that integrates biological mechanisms with economic mechanisms. This system, which includes 11 categories of 953 kinds of agricultural products, could dynamical y project agricultural market supply and demand, assess food security, and conduct scenario analysis at different spatial levels, time scale levels, and macro-micro levels. Based on the CAMES, the production, consumption, and trade of the major agricultural products in China over the next decade are projected. The fol owing conclusions are drawn:i) The production of major agricultural products wil continue to grow steadily, mainly because of the increase in yield. i ) The growth of agricultural consumption wil be slightly higher than that of agricultural production. Meanwhile, a high self-sufifciency rate is expected for cereals such as rice, wheat, and maize, with the rate being stable at around 97%. i i) Agricultural trade wil continue to thrive. The growth of soybean and milk im-ports wil slow down, but the growth of traditional agricultural exports such as vegetables and fruits is expected to continue.

Deformation early-warning index for heightened gravity dam during impoundment period

The mechanical parameters of materials in a dam body and dam foundation tend to change when dams are reinforced in aging processes.It is important to use an early-warning index to reflect the safety status of dams,particularly of heightened projects in the impoundment period.Herein,a new method for monitoring the safety status of heightened dams is proposed based on the deformation monitoring data of a dam structure,a statistical model,and finite-element numerical simulation.First,a fast optimization inversion method for estimation of dam mechanical parameters was developed,which used the water pressure component extracted from a statistical model,an improved inversion objective function,and a genetic optimization iterative algorithm.Then,a finite element model of a heightened concrete gravity dam was established,and the deformation behavior of the dam with rising water levels in the impoundment period was simulated.Subsequently,mechanical parameters of aged dam parts were calculated using the fast optimization inversion method with simulated deformation and the water pressure deformation component obtained by the statistical model under the same conditions of water pressure change.Finally,a new earlywarning index of dam deformation was constructed by means of the forward-simulated deformation and other components of the statistical model.The early-warning index is useful for forecasting dam deformation under different water levels,especially high water levels.

A new early-warning prediction system for monitoring shear force of fault plane in the active fault

The most common method used to describe earthquake activity is based on the changes in physical parameters of the earth＇s surface such as displacement of active fault and seismic wave.However,such approach is not successful in forecasting the movement behaviors of faults.In the present study,a new mechanical model of fault activity,considering the shear strength on the fault plane and the influence of the resistance force,is established based on the occurrence condition of earthquake.A remote real-time monitoring system is correspondingly developed to obtain the changes in mechanical components within fault.Taking into consideration the local geological conditions and the history of fault activity in Zhangjiakou of China,an active fault exposed in the region of Zhangjiakou is selected to be directly monitored by the real-time monitoring technique.A thorough investigation on local fault structures results in the selection of two suitable sites for monitoring potential active tectonic movements of Zhangjiakou fault.Two monitoring curves of shear strength,recorded during a monitoring period of 6 months,turn out to be steady,which indicates that the potential seismic activities hardly occur in the adjacent region in the near future.This monitoring technique can be used for early-warning prediction of the movement of active fault,and can help to further gain an insight into the interaction between fault activity and relevant mechanisms.

Risk Early-Warning Method for Natural Disasters Based on Integration of Entropy and DEA Model

Risk early-warning of natural disasters is a very intricate non-deterministic prediction, and it was difficult to resolve the conflicts and incompatibility of the risk structure. Risk early-warning factors of natural disasters were differentiated into essential attributes and external characters, and its workflow mode was established on risk early-warning structure with integrated Entropy and DEA model, whose steps were put forward. On the basis of standard risk early-warning DEA model of natural disasters, weight coefficient of risk early-warning factors was determined with Information Entropy method, which improved standard risk early-warning DEA model with non-Archimedean infinitesimal, and established risk early-warning preference DEA model based on integrated entropy weight and DEA Model. Finally, model was applied into landslide risk early-warning case in earthquake-damaged emergency process on slope engineering, which exemplified the outcome could reflect more risk information than the method of standard DEA model, and reflected the rationality, feasibility, and impersonality, revealing its better ability on comprehensive safety and structure risk.

The Innovation Research of Financial Early-Warning Index Measurement

The period economic fluctuation is vital for an enterprise to exist and further develop, it directly affect the enterprise financial health. So, it is significant to build up financial early-warning index and measure the warning condition that the enterprise faces and take the effective measures to eliminate. We criticize Altman’sZ calculating model and build up some new indexes for enterprise financial early-warning condition measuring and making sound decision.

Early-warning signals for an outbreak of the influenza pandemic

Over the course of human history, influenza pandemics have been seen as major disasters, so studies on the influenza virus have become an important issue for many experts and scholars. Comprehensive research has been performed over the years on the biological properties, chemical characteristics, external environmental factors and other aspects of the virus, and some results have been achieved. Based on the chaos game representation walk model, this paper uses the time series analysis method to study the DNA sequences of the influenza virus from 1913 to 2010, and works out the early-warning signals indicator value for the outbreak of an influenza pandemic. The variances in the CCR wall〈 sequences for the pandemic years （or ＋ -1 to 2 years） are significantly higher than those for the adjacent years, while those in the non-pandemic years are usually smaller. In this way we can provide an influenza early-warning mechanism so that people can take precautions and be well prepared prior to a pandemic.

A study on the early-warning technique concerning debris flow disasters

According to the principle of the eruption of debris flows, the new torrent classification techniques are brought forward. The torrent there can be divided into 4 types such as the debris flow torrent with high destructive strength, the debris flow torrent, high sand-carrying capacity flush flood torrent and common flush flood by the techniques. In this paper, the classification indices system and the quantitative rating methods are presented. Based on torrent classification, debris flow torrent hazard zone mapping techniques by which the debris flow disaster early-warning object can be ascertained accurately are identified. The key techniques of building the debris flow disaster neural network (NN) real time forecasting model are given detailed explanations in this paper, including the determination of neural node at the input layer, the output layer and the implicit layer, the construction of knowledge source and the initial weight value and so on. With this technique, the debris flow disaster real-time forecasting neural network model is built according to the rainfall features of the historical debris flow disasters, which includes multiple rain factors such as rainfall of the disaster day, the rainfall of 15 days before the disaster day, the maximal rate of rainfall in one hour and ten minutes. It can forecast the probability, critical rainfall of eruption of the debris flows, through the real-time rainfall monitoring or weather forecasting. Based on the torrent classification and hazard zone mapping, combined with rainfall monitoring in the rainy season and real-time forecasting models, the debris flow disaster early-warning system is built. In this system, the GIS technique, the advanced international software and hardware are applied, which makes the system’s performance steady with good expansibility. The system is a visual information system that serves management and decision-making, which can facilitate timely inspect of the variation of the torrent type and hazardous zone, the torrent management, the early-warning of disasters and the disaster reduction and prevention.

The Management Platform for Online Rate of Meteorological Early-warning Loudspeakers

The meteorological early-warning loudspeaker is a specific initiative for the meteorological departments to address the issues concerning issues concerning agriculture,countryside and farmers.Its significance is that it can promptly deliver the early-warning information concerning some meteorological disasters(such as torrential rains,typhoons,cold wave,hail)to the areas affected,so as to provide reference and protection for agricultural production and effectively reduce the loss of agricultural producers.Up to now,the meteorological early-warning loudspeakers in Benxi have covered the villages.However,due to irregular occurrence of meteorological disasters,the listeners will turn off the information receivers of meteorological early-warning loudspeakers when they fail to receive meteorological information for a long time,so that the users can not promptly know the early-warning information regarding some sudden meteorological disasters.In view of this,the meteorological departments have introduced a series of management measures,such as the daily use of loudspeakers to publish weather forecast information,aimed at improving the online rate and usage rate of meteorological loudspeakers.And the management platform for online rate of meteorological early-warning loudspeakers is an important part of the management system.

SAR-AIRcraft-1.0:高分辨率SAR飞机检测识别数据集

针对合成孔径雷达(SAR)图像中飞机散射点离散以及背景强干扰造成虚警的问题,该文提出了一种结合散射感知的SAR飞机检测识别方法。一方面,通过上下文引导的特征金字塔模块来增强全局信息,减弱复杂场景中强干扰的影响,提高检测识别的准确率。另一方面,利用散射关键点对目标进行定位,设计散射感知检测模块实现对回归框的细化校正,增强目标的定位精度。为了验证方法有效性、同时促进SAR飞机检测识别领域的研究发展,该文制作并公开了一个高分辨率SAR-AIRcraft-1.0数据集。该数据集图像来自高分三号卫星,包含4,368张图片和16,463个飞机目标实例,涵盖A220,A320/321,A330,ARJ21,Boeing737,Boeing787和other共7个类别。该文将提出的方法和常见深度学习算法在构建的数据集上进行实验,实验结果证明了散射感知方法的优异性能,并且形成了该数据集在SAR飞机检测、细粒度识别、检测识别一体化等不同任务中性能指标的基准。

A bi-population immune algorithm for weapon transportation support scheduling problem with pickup and delivery on aircraft carrier deck

The weapon transportation support scheduling problem on aircraft carrier deck is the key to restricting the sortie rate and combat capability of carrier-based aircraft.This paper studies the problem and presents a novel solution architecture.Taking the interference of the carrier-based aircraft deck layout on the weapon transportation route and precedence constraint into consideration,a mixed integer formulation is established to minimize the total objective,which is constituted of makespan,load variance and accumulative transfer time of support unit.Solution approach is developed for the model.Firstly,based on modeling the carrier aircraft parked on deck as convex obstacles,the path library of weapon transportation is constructed through visibility graph and Warshall-Floyd methods.We then propose a bi-population immune algorithm in which a population-based forward/backward scheduling technique,local search schemes and a chaotic catastrophe operator are embedded.Besides,the randomkey solution representation and serial scheduling generation scheme are adopted to conveniently obtain a better solution.The Taguchi method is additionally employed to determine key parameters of the algorithm.Finally,on a set of generated realistic instances,we demonstrate that the proposed algorithm outperforms all compared algorithms designed for similar optimization problems and can significantly improve the efficiency,and that the established model and the bi-population immune algorithm can effectively respond to the weapon support requirements of carrier-based aircraft under different sortie missions.

Refined Aerodynamic Test of Wide-Bodied Aircraft and Its Application

The large dual-channel wide-bodied aircraft has a long range and a high cruise Mach number.Therefore,its aerodynamic design requires a high level ofwind tunnel test refinement.Based on the requirements of aerodynamic design for the future wide-bodied aircraft and the characteristics of high-speed wind tunnel tests,the error theory is introduced to analyze the factors affecting the accuracy of the test data.This study carries out a series of research on the improvement of refined aerodynamic test technology in an FL-26 wind tunnel,including design and optimization of the support system of wide-bodied aircraft,model attitude angle measurement,Mach number control accuracy,measurement and control system stability,test data correction and perfection,high-precision force balance and standard model development.In addition,the effect of the standard specification of the refined aerodynamic test is investigated to improve the data quality.The research findings have been applied in the standard model test and subsequent models of wide-bodied aircraft.The results show that whenMach numbers are less than 0.9,the control accuracy of Mach numbers in the FL-26 wind tunnel is smaller than 0.001 and the measurement error of attack angle is smaller than 0.01°.Therefore,it has the ability to correct the data influenced by factors,such as support/wall interference,model deformation,floating resistance and airflow deflection angle.The repeatability accuracy of the standard model’s comparison test shows that the lift coefficient is less than or equal to 0.0012,the drag coefficient is less than or equal to 0.00004,pitching moment coefficient is less than or equal to 0.0004.The bending resolution of the model’s deformation measurement is less than 0.2 mm,and the tensional deformation is smaller than 0.04°.The revised aerodynamic data and model deformation measurement results have good agreement with that of the ETW wind tunnel.The results demonstrate that the improved technology presented in this paper can significantly enhance the refined aerodynamic test of wide-bodied aircraft.

Mechanical Dispatch Reliability Prediction for Civil Aircraft Considering Operational Parameters

To effectively predict the mechanical dispatch reliability(MDR),the artificial neural networks method combined with aircraft operation health status parameters is proposed,which introduces the real civil aircraft operation data for verification,to improve the modeling precision and computing efficiency.Grey relational analysis can identify the degree of correlation between aircraft system health status(such as the unscheduled maintenance event,unit report event,and services number)and dispatch release and screen out themost closely related systems to determine the set of input parameters required for the prediction model.The artificial neural network using radial basis function(RBF)as a kernel function,has the best applicability in the prediction of multidimensional,small sample problems.Health status parameters of related systems are used as the input to predict the changing trend ofMDR,under the artificial neural network modeling framework.The case study collects real operation data for a certain civil aircraft over the past five years to validate the performance of the model which meets the requirements of the application.The results show that the prediction quadratic error Ep of the model reaches 6.9×10−8.That is to say,in the existing operating environment,the prediction of the number of delay&cancel events per month can be less than once.The accuracy of RBF ANN,BP ANN and GA-BP ANN are compared further,and the results show that RBF ANN has better adaptability to such multidimensional small sample problems.The efforts of this paper provide a highly efficientmethod for theMDR prediction through aircraft system health state parameters,which is a promising model to enhance the prediction and controllability of the dispatch release,providing support for the construction of the civil aircraft operation system.

Anti-Disturbance Control for Tethered Aircraft System With Deferred Output Constraints

In this paper,we investigate the peaking issue of extended state observers and the anti-disturbance control problem of tethered aircraft systems subject to the unstable flight of the main aircraft,airflow disturbances and deferred output constraints.Independent of exact initial values,a modified extended state observer is constructed from a shifting function such that not only the peaking issue inherently in the observer is circumvented completely but also the accurate estimation of the lumped disturbance is guaranteed.Meanwhile,to deal with deferred output constraints,an improved output constrained controller is employed by integrating the shifting function into the barrier Lyapunov function.Then,by combining the modified observer and the improved controller,an anti-disturbance control scheme is presented,which ensures that the outputs with any bounded initial conditions satisfy the constraints after a pre-specified finite time,and the tethered aircraft tracks the desired trajectory accurately.Finally,both a theoretical proof and simulation results verify the effectiveness of the proposed control scheme.

Research on Technology Early-Warning System Based on Dynamic Information Monitoring

Relying on the advanced information technologies, such as information monitoring, data mining, natural language processing etc., the dynamic technology early-warning system is constructed. The system consists of technology information automatic retrieval, technology information monitoring, technology threat evaluation, and crisis response and management subsystem, which implements uninterrupted dynamic monitoring, trace and crisis early-warning to the specific technology. Empirical study testifies that the system improves the accuracy, timeliness and reliability of technology early-warning.

Financial crisis early-warning model of listed companies based on predicted value

To establish a financial early-warning model with high accuracy of discrimination and achieve the aim of long-term prediction, principal component analysis (PCA), Fisher discriminant, together with grey forecasting models are used at the same time. 110 A-share companies listed on the Shanghai and Shenzhen stock exchange are selected as research samples. And 10 extractive factors with 89.746% of all the original information are determined by applying PCA, which obtains the goal of dimension reduction without information loss. Based on the index system, the early-warning model is constructed according to the Fisher rules. And then the GM(1,1) is adopted to predict financial ratios in 2004, according to 40 testing samples from 2000 to 2003. Finally, two different methods, a self-validated and a forecasting-validated, are used to test the validity of the financial crisis warning model. The empirical results show that the model has better predictability and feasibility, and GM(1,1) contributes to the ability to make long-term predictions.