A hybrid model for predicting spatial distribution of soil organic matter in a bamboo forest based on general regression neural network and interative algorithm

A general regression neural network model,combined with an interative algorithm(GRNNI)using sparsely distributed samples and auxiliary environmental variables was proposed to predict both spatial distribution and variability of soil organic matter(SOM)in a bamboo forest.The auxiliary environmental variables were:elevation,slope,mean annual temperature,mean annual precipitation,and normalized difference vegetation index.The prediction accuracy of this model was assessed via three accuracy indices,mean error(ME),mean absolute error(MAE),and root mean squared error(RMSE)for validation in sampling sites.Both the prediction accuracy and reliability of this model were compared to those of regression kriging(RK)and ordinary kriging(OK).The results show that the prediction accuracy of the GRNNI model was higher than that of both RK and OK.The three accuracy indices(ME,MAE,and RMSE)of the GRNNI model were lower than those of RK and OK.Relative improvements of RMSE of the GRNNI model compared with RK and OK were 13.6%and 17.5%,respectively.In addition,a more realistic spatial pattern of SOM was produced by the model because the GRNNI model was more suitable than multiple linear regression to capture the nonlinear relationship between SOM and the auxiliary environmental variables.Therefore,the GRNNI model can improve both prediction accuracy and reliability for determining spatial distribution and variability of SOM.

EXISTENCE AND ALGORITHM OF SOLUTIONS FOR GENERAL MULTIVALUED MIXED IMPLICIT QUASI-VARIATIONAL INEQUALITIES

A new class of general multivalued mixed implicit quasi-variational inequalities in a real Hilbert space was introduced, which includes the known class of generalized mixed implicit quasi-variational inequalities as a special case , introduced and studied by Ding Xie-ping . The auxiliary variational principle technique was applied to solve this class of general multivalued mixed implicit quasi-variational inequalities. Firstly, a new auxiliary variational inequality with a proper convex , lower semicontinuous , binary functional was defined and a suitable functional was chosen so that its unique minimum point is equivalent to the solution of such an auxiliary variational inequality . Secondly , this auxiliary variational inequality was utilized to construct a new iterative algorithm for computing approximate solutions to general multivalued mixed implicit quasi-variational inequalities . Here , the equivalence guarantees that the algorithm can generate a sequence of approximate solutions. Finally, the existence of solutions and convergence of approximate solutions for general multivalued mixed implicit quasi-variational inequalities are proved. Moreover, the new convergerce criteria for the algorithm were provided. Therefore, the results give an affirmative answer to the open question raised by M. A . Noor, and extend and improve the earlier and recent results for various variational inequalities and complementarity problems including the corresponding results for mixed variational inequalities, mixed quasi-variational inequalities and quasi-complementarity problems involving the single-valued and set- valued mappings in the recent literature .

Convergence analysis of a nonlinear Lagrange algorithm for general nonlinear constrained optimization problems

The convergence analysis of a nonlinear Lagrange algorithm for solving nonlinear constrained optimization problems with both inequality and equality constraints is explored in detail. The estimates for the derivatives of the multiplier mapping and the solution mapping of the proposed algorithm are discussed via the technique of the singular value decomposition of matrix. Based on the estimates, the local convergence results and the rate of convergence of the algorithm are presented when the penalty parameter is less than a threshold under a set of suitable conditions on problem functions. Furthermore, the condition number of the Hessian of the nonlinear Lagrange function with respect to the decision variables is analyzed, which is closely related to efficiency of the algorithm. Finally, the preliminary numericM results for several typical test problems are reported.

New analytical imaging algorithm for general case airborne bistatic SAR

This paper focuses on the general case （GC） airborne bistatic synthetic aperture radar （SAR） data processing, and a new analytical imaging algorithm based on the extended Loffeld＇s bistatic formula （ELBF） is proposed. According to the bistatic SAR geometry, the track decoupling formulas that convert the bistatic geometry to the receiver-referenced geometry in a concise way are derived firstly. Then phase terms of ELBF are decomposed into two independent phase terms as the range phase term and the azimuth phase term in a new way. To get the focusing result, the bistatic deformation （BD） term is compensated in the two-dimensional （2- D） frequency domain, and the space-variances of the range phase term and the azimuth phase term are eliminated by chirp scaling （CS） and chirp z-transform （CZT）, respectively. The effectiveness of the proposed algorithm is verified by the simulation results.

Companies’ E-waste Estimation Based on General Equilibrium The­ory Context and Random Forest Regression Algorithm in Cameroon: Case Study of SMEs Implementing ISO 14001:2015

Given the challenge of estimating or calculating quantities of waste electrical and electronic equipment(WEEE)in developing countries,this article focuses on predicting the WEEE generated by Cameroonian small and medium enterprises(SMEs)that are engaged in ISO 14001:2015 initiatives and consume electrical and electronic equipment(EEE)to enhance their performance and profitability.The methodology employed an exploratory approach involving the application of general equilibrium theory(GET)to contextualize the study and generate relevant parameters for deploying the random forest regression learning algorithm for predictions.Machine learning was applied to 80%of the samples for training,while simulation was conducted on the remaining 20%of samples based on quantities of EEE utilized over a specific period,utilization rates,repair rates,and average lifespans.The results demonstrate that the model’s predicted values are significantly close to the actual quantities of generated WEEE,and the model’s performance was evaluated using the mean squared error(MSE)and yielding satisfactory results.Based on this model,both companies and stakeholders can set realistic objectives for managing companies’WEEE,fostering sustainable socio-environmental practices.

Improved algorithms to plan missions for agile earth observation satellites

This study concentrates of the new generation of the agile （AEOS）. AEOS is a key study object on management problems earth observation satellite in many countries because of its many advantages over non-agile satellites. Hence, the mission planning and scheduling of AEOS is a popular research problem. This research investigates AEOS characteristics and establishes a mission planning model based on the working principle and constraints of AEOS as per analysis. To solve the scheduling issue of AEOS, several improved algorithms are developed. Simulation results suggest that these algorithms are effective.

Progressive failure processes of reinforced slopes based on general particle dynamic method

In order to resolve grid distortions in finite element method(FEM), the meshless numerical method which is called general particle dynamics(GPD) was presented to simulate the large deformation and failure of geomaterials. The Mohr-Coulomb strength criterion was implemented into the code to describe the elasto-brittle behaviours of geomaterials while the solid-structure(reinforcing pile) interaction was simulated as an elasto-brittle material. The Weibull statistical approach was applied to describing the heterogeneity of geomaterials. As an application of general particle dynamics to slopes, the interaction between the slopes and the reinforcing pile was modelled. The contact between the geomaterials and the reinforcing pile was modelled by using the coupling condition associated with a Lennard-Jones repulsive force. The safety factor, corresponding to the minimum shear strength reduction factor "R", was obtained, and the slip surface of the slope was determined. The numerical results are in good agreement with those obtained from limit equilibrium method and finite element method. It indicates that the proposed geomaterial-structure interaction algorithm works well in the GPD framework.

A New Algorithm for Resource Constraint Project Scheduling Problem Based on Multi-Agent Systems

The resource constrained project scheduling problem (RCPSP) and a decision-making model based on multi-agent systems (MAS) and general equilibrium marketing are proposed. An algorithm leading to the resource allocation decision involved in RCPSP has also been developed. And this algorithm can be used in the multi-project scheduling field as well.Finally, an illustration is given.

Yarn Quality Prediction for Small Samples Based on AdaBoost Algorithm

In order to solve the problems of weak prediction stability and generalization ability of a neural network algorithm model in the yarn quality prediction research for small samples,a prediction model based on an AdaBoost algorithm(AdaBoost model) was established.A prediction model based on a linear regression algorithm(LR model) and a prediction model based on a multi-layer perceptron neural network algorithm(MLP model) were established for comparison.The prediction experiments of the yarn evenness and the yarn strength were implemented.Determination coefficients and prediction errors were used to evaluate the prediction accuracy of these models,and the K-fold cross validation was used to evaluate the generalization ability of these models.In the prediction experiments,the determination coefficient of the yarn evenness prediction result of the AdaBoost model is 76% and 87% higher than that of the LR model and the MLP model,respectively.The determination coefficient of the yarn strength prediction result of the AdaBoost model is slightly higher than that of the other two models.Considering that the yarn evenness dataset has a weaker linear relationship with the cotton dataset than that of the yarn strength dataset in this paper,the AdaBoost model has the best adaptability for the nonlinear dataset among the three models.In addition,the AdaBoost model shows generally better results in the cross-validation experiments and the series of prediction experiments at eight different training set sample sizes.It is proved that the AdaBoost model not only has good prediction accuracy but also has good prediction stability and generalization ability for small samples.

An Inductive Method with Genetic Algorithm for Learning Phrase－structure－rule of Natural Language

This paper describes an Inductive method with gnnetic search which learns attribute based phraserllle of natural laguage from set of preclassified examples. Every example is described with some attributes/values. This algorithm takes an example as a seed, generalizes it by genetic process, and makes it cover as many examples as possible. We use genetic operator in population to perform a probabilistic parallel search in rule space and it will reduce greatly possibe rule search space compared with many other inductive methods. In this paper, we give description of attribute, word, dictionary and rule at first. then we describe learning algoritm and genetic search Proctess, and at last, we give a computing method abour quility of roule C(r).

REESSE Unified Recursive Algorithm for Solving Three Computational Problems

Different from the extended Euclidean algorithm which can compute directly only the multiplicative inverse of an element in Zm^＊ and the greatest common divisor of two integers, a recursive algorithm called REESSE is designed by the authors, which can not only seek directly the multiplicative inverse and the greatest common divisor, but also solve directly a simple congruence for general solutions. This paper presents the definition and the two valuable properties of a simple congruence, analyzes in detail the reduction and recursion process of solving simple congruences, induces the recursive formula for solving simple congruences, and describes formally and implements in C language the recursive algorithm. At last, the paper compares REESSE with the extended Euclidean algorithm in thought, applicability and time complexity.

General scheduling framework in computational Grid based on Petri net

A general scheduling framework (GSF) for independent tasks in computational Grid is proposed in this paper, which modeled by Petri net and located on the layer of Grid scheduler. Furthermore, a new mapping algorithm aimed at time and cost is designed on the basis of this framework. The algorithm uses weighted average fuzzy applicability to express the matching degree between available machines and independent tasks. Some existent heuristic algorithms are tested in GSF, and the results of simulation and comparison not only show good flexibility and adaptability of GSF, but also prove that, given a certain aim, the new algorithm can consider the factors of time and cost as a whole and its performance is higher than those mentioned algorithms.

ALGORITHM OF SOLUTIONS FOR MIXEDNONLINEAR VARIATIONAL-LIKE INEQUALITIES IN REFLEXIVE BANACH SPACE

In this paper, the author studies a class of mixed nonlinear variational-like inequalities in reflexive Banach space. By applying a minimax inequality obtained by the author, some existence uniqueness theorems of solutions for the mixed nonlinear variational-like inequalities are proved. Next, by applying the auxiliary problem technique, rite author suggests an innovative iterative algorithm to compute the approximate solutions of the mixed nonlinear variational-like inequalities. Finally, the convergence criteria is also discussed.

The Fuzzy Modeling Algorithm for Complex Systems Based on Stochastic Neural Network

A fuzzy modeling method for complex systems is studied. The notation of general stochastic neural network (GSNN) is presented and a new modeling method is given based on the combination of the modified Takagi and Sugeno's (MTS) fuzzy model and one-order GSNN. Using expectation-maximization(EM) algorithm, parameter estimation and model selection procedures are given. It avoids the shortcomings brought by other methods such as BP algorithm, when the number of parameters is large, BP algorithm is still difficult to apply directly without fine tuning and subjective tinkering. Finally, the simulated example demonstrates the effectiveness.

Heuristic Backtrack Algorithm for Structural Match and Its Applications

The concept WALKING on structures is proposed, and the partial ordering between a structure and a query structure (substructure) is also created by means of WALKING. Based upon the above concepts, authors create the Heuristic-Backtracking Algorithm (HBA) of structural match with high performance. In the last part of the paper, the applications of HBA in molecular graphics, synthetic planning, spectrum simulation , the representation and recognition of general structures are discussed.

Neural Network Pruning Algorithm with Penalty OBS Process

Aimed at the great computing complexity of optimal brain surgeon (OBS) process, a pruning algorithm with penalty OBS process is presented. Compared with sensitive and regularized methods, the penalty OBS algorithm not only avoids time-consuming defect and low pruning efficiency in OBS process, but also keeps higher generalization and pruning accuracy than Levenberg-Marquardt method.

Multiscalar Geomorphometric Generalization for Soil-Landscape Modeling by Random Forest: A Case Study in the Eastern Amazon

Multiscalar topography influence on soil distribution has a complex pattern that is related to overlay of pedological processes which occurred at different times, and these driving forces are correlated with many geomorphologic scales. In this sense, the present study tested the hypothesis whether multiscale geomorphometric generalized covariables can improve pedometric modeling. To achieve this goal, this case study applied the Random Forest algorithm to a multiscale geomorphometric database to predict soil surface attributes. The study area is in phanerozoic sedimentary basins, in the Alter do Chão geological formation, Eastern Amazon, Brazil. The multiscale geomorphometric generalization was applied at general and specific geomorphometric covariables, producing groups for each scale combination. The modeling was run using Random Forest for A-horizon thickness, pH, silt and sand content. For model evaluation, visual analysis of digital maps, metrics of forest structures and effect of variables on prediction were used. For evaluation of soil textural classifications, the confusion matrix with a Kappa index, and the user’s and producer’s accuracies were employed. The geomorphometry generalization tends to smooth curvatures and produces identifiable geomorphic representations at sub-watershed and watershed levels. The forest structures and effect of variables on prediction are in agreement with pedological knowledge. The multiscale geomorphometric generalized covariables improved accuracy metrics of soil surface texture classification, with the Kappa Index going from 43% to 62%. Therefore, it can be argued that topography influences soil distribution at combined coarser spatial scales and is able to predict soil particle size contents in the studied watershed. Future development of the multiscale geomorphometric generalization framework could include generalization methods concerning preservation of features, landform classification adaptable at multiple scales.

Research on Site Planning of Mobile Communication Network

In this paper,considering the cost of base station,coverage,call quality,and other practical factors,a multi-objective optimal site planning scheme is proposed.Firstly,based on practical needs,mathematical modeling methods were used to establish mathematical expressions for the three sub-objectives of cost objectives,coverage objectives,and quality objectives.Then,a multi-objective optimization model was established by combining threshold and traffic volume constraints.In order to reduce the time complexity of optimization,a non-dominated sorting genetic algorithm(NSGA)is used to solve the multi-objective optimization problem of site planning.Finally,a strategy for clustering and optimizing weak coverage areas was proposed.In order to avoid redundant neighborhood retrieval during cluster expansion,the Fast Density-Based Spatial Clustering of Applications with Noise(FDBSCAN)clustering method was adopted.With different sub-objectives as the main objectives,this paper obtained the distribution map of weak coverage areas before and after the establishment of new base stations,as well as relevant site planning maps,and provided three planning schemes for different main objectives.The simulation results show that the traffic coverage of the three station planning schemes is above 90%.The change in the main optimization objective will result in a significant difference between the cost of the three solutions and the coverage of weak coverage points.

基于果蝇算法优化广义回归神经网络的机枪枪管初速衰减建模与预测

机枪枪管初速衰减预测是一个复杂的非线性问题。广义回归神经网络方法被广泛应用于非线性问题的建模,但其平滑因子取值对神经网络的预测性能有较大影响。采用果蝇算法对广义回归神经网络的参数进行优化选取,提出了基于果蝇算法优化广义回归神经网络的机枪枪管初速衰减建模方法。基于机枪枪管初速衰减试验数据,建立在不同使用环境下随着累计射弹量的增加,以初速降为特征量的机枪枪管初速衰减预测模型,预测结果与试验结果基本一致,证实了所提方法的可行性。通过与未经优化的广义回归神经网络方法和反向传播神经网络方法建立的预测模型进行比较,其性能明显优于另外两种方法,验证了基于果蝇算法优化的广义回归神经网络方法在建立机枪枪管初速衰减模型中的有效性。

基于广义相关系数自适应随机共振的液压泵振动信号预处理方法

针对液压泵故障振动信号信噪比低,故障特征难以提取的问题,对液压泵振动信号预处理方法进行研究。针对现有自适应随机共振优化算法及其目标函数存在的问题,将量子遗传算法(Quantum Genetic Algorithm,QGA)引入自适应随机共振中,提出一种改进的自适应随机共振的信号预处理方法。该方法以广义相关系数为目标函数,采用QGA算法对随机共振系统的结构参数进行优化,从而实现对信号的降噪预处理。仿真及实验结果表明,该方法能够有效提取强噪声背景下的液压泵振动信号频率特征,是液压泵故障特征提取及故障诊断中信号预处理的有效方法,可进一步发展至实际工程应用。