Federated Learning Model for Auto Insurance Rate Setting Based on Tweedie Distribution

In the assessment of car insurance claims,the claim rate for car insurance presents a highly skewed probability distribution,which is typically modeled using Tweedie distribution.The traditional approach to obtaining the Tweedie regression model involves training on a centralized dataset,when the data is provided by multiple parties,training a privacy-preserving Tweedie regression model without exchanging raw data becomes a challenge.To address this issue,this study introduces a novel vertical federated learning-based Tweedie regression algorithm for multi-party auto insurance rate setting in data silos.The algorithm can keep sensitive data locally and uses privacy-preserving techniques to achieve intersection operations between the two parties holding the data.After determining which entities are shared,the participants train the model locally using the shared entity data to obtain the local generalized linear model intermediate parameters.The homomorphic encryption algorithms are introduced to interact with and update the model intermediate parameters to collaboratively complete the joint training of the car insurance rate-setting model.Performance tests on two publicly available datasets show that the proposed federated Tweedie regression algorithm can effectively generate Tweedie regression models that leverage the value of data fromboth partieswithout exchanging data.The assessment results of the scheme approach those of the Tweedie regressionmodel learned fromcentralized data,and outperformthe Tweedie regressionmodel learned independently by a single party.

Quantitative Damage Detection for Planetary Gear Sets Based on Physical Models

Planetary gear set is the critical component in helicopter transmission train, and an important problem in condition monitoring and health management of planetary gear set is quantitative damage detection. In order to resolve this problem, an approach based on physical models is presented to detect damage quantitatively in planetary gear set. A particular emphasis is put on a feature generation and selection method, which is used for sun gear tooth breakage damage detection quantitatively in planetary gear box of helicopter transmission system. In this feature generation procedure, the pure torsional dynamical models of 2K-H planetary gear set is established for healthy case and sun gear tooth-breakage case. Then, a feature based on the spectrum of simulation signals of the dynamical models is generated. Aiming at selecting the best feature suitable for quantitative damage detection, a two-sample Z-test procedure is used to analyze the performance of features on damage evolution tracing. A feature named SR, which had better performance in tracking damage, is proposed to detect damage in planetary gear set. Meanwhile, the sun gear tooth-chipped seeded experiments with different severity are designed to validate the method above, and then the test vibration signal is picked up and used for damage detection. With the results of several experiments for quantitative damage detection, the feasibility and the effect of this approach are verified. The proposed method can supply an effective tool for degradation state identification in condition monitoring and health management of helicopter transmission system.

A Fuzzy Set-Based Approach for Model-Based Internet-Banking System Security Risk Assessment

A fuzzy set-based evaluation approach is demonstrated to assess the security risks for internet-banking System. The Internet-banking system is semi-formally described using Unified Modeling Language （UML） to specify the behavior and state of the system on the base of analyzing the existing qualitative risk assessment methods. And a quantitative method based on fuzzy set is used to measure security risks of the system, A case study was performed on the WEB server of the Internet-banking System using fuzzy-set based assessment algorithm to quantitatively compute the security risk severity. The numeric result also provides a method to decide the most critical component which should amuse the system administrator enough attention to take the appropriate security measure or controls to alleviate the risk severity. The experiments show this method can be used to quantify the security properties for the Internet-banking System in practice.

Mathematical Model and Geometrical Model of Double Pitch ZN-type Worm Gear Set Based on Generation Mechanism

The current researches on the tooth surface mathematical equations and the theory of gearing mainly pay attention to the ordinary type worm gear set（e.g., ZN, ZA, or ZK）. The research of forming mechanism and three-dimensional modeling method for the double pitch worm gear set is not enough. So there are some difficulties in mathematical model deducing and geometry modeling of double pitch ZN-type worm gear set based on generation mechanism. In order to establish the mathematical model and the precise geometric model of double pitch ZN-type worm gear set, the structural characteristics and generation mechanism of the double pitch ZN-type worm gear set are investigated. Mathematical model of the ZN-type worm gear set is derived based on its generation mechanism and the theory of gearing. According to the mathematical model of the worm gear set which has been developed, a geometry modeling method of the double pitch ZN-type worm and worm gear is presented. Furthermore, a geometrical precision calculate method is proposed to evaluate the geometrical quality of the double pitch worm gear set. As a result, the maximum error is less than 6′10–4 mm in magnitude, thus the model of the double pitch ZN-type worm gear set is available to meet the requirements of finite element analysis and engineering application. The derived mathematical model and the proposed geometrical modeling method are helpful to guiding the design, manufacture and contact analysis of the worm gear set.

Density-based rough set model for hesitant node clustering in overlapping community detection

Overlapping community detection in a network is a challenging issue which attracts lots of attention in recent years.A notion of hesitant node（HN） is proposed. An HN contacts with multiple communities while the communications are not strong or even accidental, thus the HN holds an implicit community structure.However, HNs are not rare in the real world network. It is important to identify them because they can be efficient hubs which form the overlapping portions of communities or simple attached nodes to some communities. Current approaches have difficulties in identifying and clustering HNs. A density-based rough set model（DBRSM） is proposed by combining the virtue of densitybased algorithms and rough set models. It incorporates the macro perspective of the community structure of the whole network and the micro perspective of the local information held by HNs, which would facilitate the further ＂growth＂ of HNs in community. We offer a theoretical support for this model from the point of strength of the trust path. The experiments on the real-world and synthetic datasets show the practical significance of analyzing and clustering the HNs based on DBRSM. Besides, the clustering based on DBRSM promotes the modularity optimization.

Calculation Model of Equivalent Strength for Induced Crack Based on Double-K Fracture Theory and Its Optimizing Setting in RCC Arch Dam

By means of fracture testing on roller-compacted concrete （RCC） three-point bending beams with two different specimen sizes, the P-CMOD complete curve for RCC was gained. Furthermore, by applying double-K fracture theory, KiniⅠC,KunⅠC, as well as the critical effective crack length and the critical crack tip opening displacement, were evaluated. Based on the double-K fracture parameters above, the calculation model of equivalent strength for induced crack was established, thus the calculation method on its initiation, stable propagation and unstable fracture was ascertained. Moreover, the finite element simulation analysis of stress field in ShaPai arch dam and the on-site observational splaying points of induced crack at different altitudes validated the reliability of the model. Finally, crack inducer′s optimal setting in RCC arch dam was studied. It improves the design level of induced crack in RCC arch dam and satisfies the necessity of engineering practice.

Transient Model for Shafting Vibration of Hydro Turbine Generating Sets

The shafting vibration is closely related to the rotational angular speed.The angular speed of hydro turbine generating sets(HTGS)is rapidly change in fault transient,it maybe reduce the shafting damage.By means of energy analysis,the differential equation of shafting vibration for the HTGS is derived,in which include the equation of generator rotor and hydro turbine runner,it can be applied to transient analysis.Shafting model is transformed into first order differential equation groups,and is combined with the motion equation of HTGS to build integrated model.Various additional forces of shafting are taken as input inspire in proposed model,the generality of model is good.At last,the shafting vibration in emergency stop transient is simulated.

Multiple-model Bayesian filtering with random finite set observation

The finite set statistics provides a mathematically rig- orous single target Bayesian filter （STBF） for tracking a target that generates multiple measurements in a cluttered environment. However, the target maneuvers may lead to the degraded track- ing performance and even track loss when using the STBF. The multiple-model technique has been generally considered as the mainstream approach to maneuvering the target tracking. Moti- vated by the above observations, we propose the multiple-model extension of the original STBF, called MM-STBF, to accommodate the possible target maneuvering behavior. Since the derived MM- STBF involve multiple integrals with no closed form in general, a sequential Monte Carlo implementation （for generic models） and a Gaussian mixture implementation （for linear Gaussian models） are presented. Simulation results show that the proposed MM-STBF outperforms the STBF in terms of root mean squared errors of dynamic state estimates.

A vague-set-based fuzzy multi-objective decision making model for bidding purchase

A vague-set-based fuzzy multi-objective decision making model is developed for evaluating bidding plans in a bid- ding purchase process. A group of decision-makers (DMs) first independently assess bidding plans according to their experience and preferences, and these assessments may be expressed as linguistic terms, which are then converted to fuzzy numbers. The resulting decision matrices are then transformed to objective membership grade matrices. The lower bound of satisfaction and upper bound of dissatisfaction are used to determine each bidding plan’s supporting, opposing, and neutral objective sets, which together determine the vague value of a bidding plan. Finally, a score function is employed to rank all bidding plans. A new score function based on vague sets is introduced in the model and a novel method is presented for calculating the lower bound of sat- isfaction and upper bound of dissatisfaction. In a vague-set-based fuzzy multi-objective decision making model, different valua- tions for upper and lower bounds of satisfaction usually lead to distinct ranking results. Therefore, it is crucial to effectively contain DMs’ arbitrariness and subjectivity when these values are determined.

Finite-Control-Set Model Predictive Control of Permanent Magnet Synchronous Motor Drive Systems——An Overview

Permanent magnet synchronous motors(PMSMs)have been widely employed in the industry. Finite-control-set model predictive control(FCS-MPC), as an advanced control scheme, has been developed and applied to improve the performance and efficiency of the holistic PMSM drive systems. Based on the three elements of model predictive control, this paper provides an overview of the superiority of the FCS-MPC control scheme and its shortcomings in current applications. The problems of parameter mismatch, computational burden, and unfixed switching frequency are summarized. Moreover, other performance improvement schemes, such as the multi-vector application strategy, delay compensation scheme, and weight factor adjustment, are reviewed. Finally, future trends in this field is discussed, and several promising research topics are highlighted.

A NEW DEFORMABLE MODEL USING LEVEL SETS FOR SHAPE SEGMENTATION

In this paper, we present a new deformable model for shape segmentation, which makes two modifications to the original level set implementation of deformable models.The modifications are motivated by difficulties that we have encountered in applying deformable models to segmentation of medical images.The level set algorithm has some advantages over the classical snake deformable models.However, it could develop large gaps in the boundary and holes within the objects.Such boundary gaps and holes of objects can cause inaccurate segmentation that requires manual correction.The proposed method in this paper possesses an inherent property to detect gaps and holes within the object with a single initial contour and also does not require specific initialization.The first modification is to replace the edge detector by some area constraint, and the second modification utilizes weighted length constraint to regularize the curve under evolution.The proposed method has been applied to both synthetic and real images with promising results.

Comprehensive Evaluation Model of Reservoir Operation Based on Improved Set Pair Analysis

A comprehensive evaluation model based on improved set pair analysis is established. Considering the complexity in decision-making process, the model combines the certainties and uncertainties in the schemes, i.e., identical degree, different degree and opposite degree. The relations among different schemes are studied, and the traditional way of solving uncertainty problem is improved. By using the gray correlation to determine the difference degree, the problem of less evaluation indexes and inapparent linear relationship is solved. The difference between the evaluation parameters is smaller in both the fuzzy comprehensive evaluation model and fuzzy matter-element method, and the dipartite degree of the evaluation result is unobvious. However, the difference between each integrated connection degree is distinct in the improved set pair analysis. Results show that the proposed method is feasible and it obtains better effects than the fuzzy comprehensive evaluation method and fuzzy matter-element method.

A Dual-mode Nonlinear Model Predictive Control with the Enlarged Terminal Constraint Sets

Aiming at a class of nonlinear systems with multiple equilibrium points, we present a dual-mode model predictive control algorithm with extended terminal constraint set combined with control invariant set and gain schedule. Local LQR control laws and the corresponding maximum control invariant sets can be designed for finite equilibrium points. It is guaranteed that control invariant sets are overlapped each other. The union of the control invariant sets is treated as the terminal constraint set of predictive control. The feasibility and stability of the novel dual-mode model predictive control are investigated with both variable and fixed horizon. Because of the introduction of extended terminal constrained set, the feasibility of optimization can be guaranteed with short prediction horizon. In this way, the size of the optimization problem is reduced so it is computationally efficient. Finally, a simulation example illustrating the algorithm is presented.

Finite Control Set Model Predictive Current Control of a Five-Phase PMSM with Virtual Voltage Vectors and Adaptive Control Set

This paper presents an improved finite control set model predictive current control(FCS-MPCC)of a five-phase permanent magnet synchronous motor(PMSM).First,to avoid including all the 32 voltage vectors provided by a two-level five-phase inverter into the control set,virtual voltage vectors are adopted.As the third current harmonics can be much reduced by virtual voltage vectors automatically,the harmonic items in the cost function of conventional FCS-MPCC are not considered.Furthermore,an adaptive control set is proposed based on voltage prediction.Best control set with proper voltage vector amplitude corresponding to different rotor speed can be achieved by this method.Consequently,current ripples can be largely reduced and the system performs much better.At last,simulations are established to verify the steady and transient performance of the proposed FCS-MPCC,and experiments based on a 2 kW five-phase motor are carried out.The results have validated the performance improvement of the proposed control strategy.

Multi-objective linear fractional inventory model with possibility and necessity constraints under generalised intuitionistic fuzzy set environment

This study presented a multi-objective linear fractional inventory (LFI) problem with generalised intuitionistic fuzzy numbers. In modelling, the authors have assumed the ambiances where generalised trapezoidal intuitionistic fuzzy numbers (GTIFNs) used to handle the uncertain information in the data. Then, the given multi-objective generalised intuitionistic fuzzy LFI model was transformed into its equivalent deterministic linear fractional programming problem by employing the possibility and necessity measures. Finally, the applicability of the model is demonstrated with a numerical example and the sensitivity analysis under several parameters is investigated to explore the study.

An Improved Mumford-Shah Model and Its Applications to Image Processing with the Piecewise Constant Level Set Method

为快分割并且降噪，提高 penalization 学期的古典 Mumford-Shah (MS ) 模型需要，即增加 penalization 参数，它导致目标的渐渐的消失。在这份报纸，我们建议一个改进 Mumford-Shah (IMS ) 模型避免现象，并且采用 piecewise 常数水平集合方法(PCLSM ) 和坡度降下方法解决最小化问题。数字实验被给显示出新模型和算法的效率和优点。

Optimal Selection Model of Equipment Design Scheme Based on Set Pair Analysis

Selecting the optimal one from similar schemes is a paramount work in equipment design.In consideration of similarity of schemes and repetition of characteristic indices,the theory of set pair analysis(SPA)is proposed,and then an optimal selection model is established.In order to improve the accuracy and flexibility,the model is modified by the contribution degree.At last,this model has been validated by an example,and the result demonstrates the method is feasible and valuable for practical usage.

Parametric estimation for the simple linear regression model under moving extremes ranked set sampling design

Cost effective sampling design is a major concern in some experiments especially when the measurement of the characteristic of interest is costly or painful or time consuming.Ranked set sampling(RSS)was first proposed by McIntyre[1952.A method for unbiased selective sampling,using ranked sets.Australian Journal of Agricultural Research 3,385-390]as an effective way to estimate the pasture mean.In the current paper,a modification of ranked set sampling called moving extremes ranked set sampling(MERSS)is considered for the best linear unbiased estimators(BLUEs)for the simple linear regression model.The BLUEs for this model under MERSS are derived.The BLUEs under MERSS are shown to be markedly more efficient for normal data when compared with the BLUEs under simple random sampling.

GIS-Hydrogeochemical Model of the YaoundéFractured Rock Aquifer, Cameroon: Aquifer Setting, Seasonal Variations in Groundwater-Rock Interaction and Water Quality

This study of the gneiss-fractured-rock aquifer in Yaoundé capital of Cameroon determines: the aquifer setting-flow systems, the aquifer type, seasonal variations in rock-water interactions, evolution of the hydrogeochemical processes, physicochemical parameters and the suitability for domestic-agro-industrial use of the groundwater. Physicochemical field tests were carried out on 445 wells during four seasons for EC, pH, TDS, Temperature and static water level from July 2016 to May 2017. 90 well samples were analyzed 45 samples per season: wet/dry. 38 borewell logs were used together with structural data to determine the aquifer setting. The field physico-chemical and laboratory analysis data of well samples were mounted unto various GIS software platforms: Global mapper, AqQa, Aquachem, Rockworks, Logplot7, Surfer and ArcGIS, to get indices/parameters/figures, by use of Durov’s, Piper’s and Gibbs diagrams, Water quality index WQI, USSL ratio, Sodium Absorption ratio SAR, Percent sodium %Na, Kelly Ratio KR, Magnesium Absorption Ratio MAR, Total Hardness TH, Residual Sodium Carbonate RSC and Permeability Index PI that were determined. The process of groundwater ions acquisition is three-fold: by recharge through atmospheric precipitation, by ion exchange/simple dissolution between the rock-groundwater and by groundwater mixing in its flow path. Water types are Ca-HCO3, Mg-HCO3 and Mg-Cl while hydrogeochemical facies are Ca-Mg-HCO3 and Ca-Mg-Cl-SO4. Most water samples are fresh, potable and soft all seasons. The hydrogeological conceptual model is that of a three-layered single phreatic fractured-rock-aquifer while other researchers postulated a two-aquifer, phreatic and semi-confined, two-layered model.