基于RBF神经网络的软件成本估算模型

软件成本估算是软件开发过程中一项非常重要的活动,但现有的方法在准确估算软件成本方面还存在不足。针对软件成本估算不够准确的现状,提出了一种基于RBF神经网络的软件成本估算模型。该模型采用样本聚类的方法确定隐含层节点数,利用遗传算法对隐层节点中心值和高斯函数的宽度进行优化,利用线性最小二乘法训练网络的权值。实验证明,该模型能够准确有效地估算软件成本。     

林木固碳释氧量预测的BP神经网络模型研究

为了实现林木固碳释氧量的数字化估算,针对现有估算方法的不足,提出了基于BP神经网络的林木固碳释氧量的预测模型。基于对神经网络理论和固碳释氧量估算模型的研究,分析了林木在生长季节的CO2通量变化趋势,采用规范化方法对训练样本预处理,进行BP神经网络训练,并结合弛豫涡旋积累法和箱式法,建立了CO2通量神经网络模型。实验结果表明,所建模型具有较好的泛化性能,能够比较准确地估算出林木的固碳释氧量。     

基于加权类比的软件成本估算方法

软件成本估算是软件项目开发周期、管理决策和软件项目质量中最重要的问题之一。针对软件研发成本估算在软件行业中普遍存在不准确、难以估算的问题,提出一种基于加权类比的软件成本估算方法,将相似度距离定义为具有相关性的马氏距离,通过优化的粒子群算法优化后得到权值,并用类比法估算软件成本。实验结果表明,该方法 具有 比非加权类比、神经网络等非计算模型方法更高的精确度。实际案例测试表明,该方法在软件开发初期基于需求分析的软件成本估算比专家估算有更精确的评估结果。     

基于组合模糊神经网络的建设工程成本估算方法

快速准确地进行工程成本估算对建筑企业至关重要。传统的工程成本估算方法工作量大、估算速度慢;难以满足估算精度的要求。为符合实际,文章将影响成本的特征因素分为精确量和模糊变量,利用模糊神经网络(FNN)的自组织和自学习,对模糊网络的隶属度和推理规则进行学习和优化。提出了基于组合模糊神经网络的方法,进行建设工程成本估算。通过计算实例表明该方法是有效的,为工程成本估算提供了有价值的参考依据。     

深度堆栈自编码网络在船舶重量估算中的应用

传统的船舶重量估算方法多数存在误差大、成本高等问题。为此,提出一种基于深度学习的船舶重量估算算法。利用多层神经网络逐层无监督学习训练初始化参数,通过反向梯度下降的方式微调参数。运用深度堆栈自编码网络挖掘深层次的数据特征,并在ShipWE自建数据库上进行分析。实验结果表明,与传统吃水估算方法相比,该算法具有更强的稳定性和更高的准确性,与BP神经网络算法和径向基函数神经网络算法相比,该算法的精度更高,能有效解决船舶估算可信度低的问题。     

软件成本估算技术比较及趋势分析

总结软件成本估算的研究应用情况, 对比分析软件成本估算的6种估算方法、6种建模技术、12种估算工具,在此基础上,提出软件成本估算的发展趋势,为关联研究和应用提供了参考.     

基于大数据的5G基站退服成本估算

随着5G技术的快速发展,5G基站的数量和密度将远超4G,基站的建设和维护也成为不可忽视的问题。因此,全面分析了5G基站退服情况,并提出一种基于大数据的5G基站退服成本估算方案。凭借基站历史退服数据,采用LSTM神经网络建立基站退服预测模型,然后构建了5G基站退服成本估算模型,对预测的5G基站退服进行成本估算。最后通过实验分析,说明了方案的有效性,并提出建议。     

软件成本估算方法及应用

软件成本估算从20世纪60年代发展至今,在软件开发过程中一直扮演着重要角色.按照基于算法模型的方法、非基于算法模型的方法以及组合方法的分类方式,全面回顾、分析了软件成本估算的各种代表性方法,也归纳讨论了与成本估算强相关的软件规模度量问题.在此基础上,进一步研究了软件成本估算方法的评价标准,并给出了一个应用实例及其分析.最后,从估算模型、估算演进、估算应用、估算内容、工具支持和人为因素6个方面,指出了软件成本估算方法下一步的主要发展趋势.     

跨组织数据的软件成本估算方法

软件成本估算一直是软件项目管理的重要部分。经过半个多世纪的研究和工业实践,成本估算方法、模型得到了极大的丰富。这些方法、模型也衍生出了各种成本估算工具。但是,成本估算方法和模型的基础是历史项目数据。没有历史项目数据的公司和组织只能利用其他公司或组织的数据来进行自己项目的成本估算。如何利用跨组织数据进行有效的成本估算成为更具现实意义的问题。针对这一问题,提出了一种有效利用跨组织数据进行成本估算的方法,并通过实验说明了方法的有效性。     

基于无迹卡尔曼滤波估算电池SOC

为了实现在线估计汽车动力电池的荷电状态（SOC）,提出了结合神经网络的无迹卡尔曼滤波算法。以Thevenin电路为等效电路模型,建立了状态空间表达式,采用最小二乘算法对模型参数进行辨识。在此基础上,利用神经网络算法拟合电池的荷电状态与模型各个参数之间的函数关系,经过多次实验,确定了神经网络算法的收敛曲线,此方法比传统的曲线拟合精度高。介绍了扩展卡尔曼滤波和无迹卡尔曼滤波的原理,并设计了等效电路模型验证实验、电池的SOC测试实验和算法的收敛性实验。实验结果表明,在不同的工况环境下,该方法估计SOC具有可在线估算、估算精度高和环境适应度高等优点,最大误差小于4%。最后验证了结合神经网络的无迹卡尔曼滤波的算法具有较好的收敛性和鲁棒性,可以有效解决初值估算不准确和累计误差的问题。     

Optimal software release scheduling based on artificial neural networks

The determination of the optimal software release schedule plays an important role in supplying sufficiently reliable software products to actual market or users. In the existing methods, the optimal software release schedule was determined by assuming the stochastic and/or statistical model called software reliability growth model. In this paper, we propose a new method to estimate the optimal software release timing which minimizes the relevant cost criterion via artificial neural networks. Recently, artificial neural networks are actively studied with many practical applications and are applied to assess the software product reliability. First, we interpret the underlying cost minimization problem as a graphical one and show that it can be reduced to a simple time series forecasting problem. Secondly, artificial neural networks are used to estimate the fault-detection time in future. In numerical examples with actual field data, we compare the new method based on the neural networks with existing parametric methods using some software reliability growth models and illustrate its benefit in terms of predictive performance. A comprehensive bibliography on the software release problem is presented. This revised version was published online in June 2006 with corrections to the Cover Date.     

A learning algorithm based estimation method for maintenance cost of product concepts

Life cycle concerns have been realized a major issue of increasing importance. Life cycle cost as analytical method has been developed to enable comprehensive cost analysis to improve economic performance of products during their life cycle. This paper present a learning algorithm based estimation method for maintenance cost as life cycle cost of product concepts. In order to develop the proposed method, we identify some attributes that represent corrective maintainability of product concepts and add them to the product attributes used to make a selection amongst product concepts. From the list of all the product attributes, 24 product attributes strongly correlated with maintenance cost are chosen. To estimate maintenance cost of product concepts, the selected product attributes are used as inputs and maintenance cost are used as outputs in a learning model based on based on artificial neural networks. The proposed approach does not replace the detailed cost estimation but it would give some cost-effective decision making for product concepts.     

PSO-based back-propagation artificial neural network for product and mold cost estimation of plastic injection molding

To simplify complicated traditional cost estimation flow, this study emphasizes the cost estimation approach for plastic injection products and molds. It is expected designers and R&D specialists can consider the competitiveness of product cost in the early stage of product design to reduce product development time and cost resulting from repetitive modification. Therefore, the proposed cost estimation approach combines factor analysis (FA), particle swarm optimization (PSO) and artificial neural network with two back-propagation networks, called FAPSO-TBP. In addition, another artificial neural network estimation approach with a single back-propagation network, called FAPSO-SBP, is also established. To verify the proposed FAPSO-TBP approach, comparisons with the FAPSO-SBP and general back-propagation artificial neural network (GBP) are made. The computational results show the proposed FAPSO-TBP approach is very competitive for the product and mold cost estimation problems of plastic injection molding.     

人工神经网络在建设工程造价估算系统中的应用

介绍了人工神经网络技术的发展和分类,针对建设工程造价估算技术的发展及面临的问题,提出了在建设工程造价估算系统中应用人工神经网络技术来提高估算精确度,并给出了系统的设计模型。     

Regression models for estimating product life cycle cost

Product life cycle cost (LCC) is defined as the cost that is incurred in all stages of the life cycle of a product, including product creation, use and disposal. In recent years, LCC has become as crucial as product quality and functionality in deciding the success of a product in the market. In order to estimate LCC of new products, researchers have employed several (parametric) regression analysis models and artificial neural networks (ANN) on historical life cycle data with known costs. In this article, we conduct an empirical study on performance of five popular non-parametric regression models for estimating LCC under different simulated environments. These environments are set by varying the number of cost drivers (independent variables), the size of sample data, the noise degree of sample data, and the bias degree of sample data. Statistical analysis of the results recommend best LCC estimation models for variable environments in stages of the product life cycle. These findings are validated with real-world data from previous work.     

State estimation for delayed neural networks

In this letter, the state estimation problem is studied for neural networks with time-varying delays. The interconnection matrix and the activation functions are assumed to be norm-bounded. The problem addressed is to estimate the neuron states, through available output measurements, such that for all admissible time-delays, the dynamics of the estimation error is globally exponentially stable. An effective linear matrix inequality approach is developed to solve the neuron state estimation problem. In particular, we derive the conditions for the existence of the desired estimators for the delayed neural networks. We also parameterize the explicit expression of the set of desired estimators in terms of linear matrix inequalities (LMIs). Finally, it is shown that the main results can be easily extended to cope with the traditional stability analysis problem for delayed neural networks. Numerical examples are included to illustrate the applicability of the proposed design method.     

Data-driven soft sensor development based on deep learning technique

In industrial process control, some product qualities and key variables are always difficult to measure online due to technical or economic limitations. As an effective solution, data-driven soft sensors provide stable and reliable online estimation of these variables based on historical measurements of easy-to-measure process variables. Deep learning, as a novel training strategy for deep neural networks, has recently become a popular data-driven approach in the area of machine learning. In the present study, the deep learning technique is employed to build soft sensors and applied to an industrial case to estimate the heavy diesel 95% cut point of a crude distillation unit (CDU). The comparison of modeling results demonstrates that the deep learning technique is especially suitable for soft sensor modeling because of the following advantages over traditional methods. First, with a complex multi-layer structure, the deep neural network is able to contain richer information and yield improved representation ability compared with traditional data-driven models. Second, deep neural networks are established as latent variable models that help to describe highly correlated process variables. Third, the deep learning is semi-supervised so that all available process data can be utilized. Fourth, the deep learning technique is particularly efficient dealing with massive data in practice.     

基于实数编码遗传算法的神经网络成本预测模型及其应用

在生产过程中,影响产品成本的因素多而复杂,因素之间相互影响,存在耦合现象,因此准确预测成本是一个重要又难以解决的问题.通过遗传算法(Genetic Algorithm)与误差反向传播(Error Back Propagation)神经网络相结合,提出了用实数编码的自适应变异遗传算法训练神经网络权重的混合算法,避免了传统神经网络易陷入局部极小的缺点.以矩阵形式表示产品成本组成,建立了产品成本组成模型,以此为基础建立了考虑成本因素之间互相影响的神经网络产品成本预测模型,并成功应用于某钢铁企业产品成本的预测,提高了预测精度.     

Kernel Width Optimization for Faulty RBF Neural Networks with Multi-node Open Fault

Many researches have been devoted to select the kernel parameters, including the centers, kernel width and weights, for fault-free radial basis function (RBF) neural networks. However, most are concerned with the centers and weights identification, and fewer focus on the kernel width selection. Moreover, to our knowledge, almost no literature has proposed the effective and applied method to select the optimal kernel width for faulty RBF neural networks. As is known that the node faults inevitably take place in real applications, which results in a great many of faulty networks, it will take a lot of time to calculate the mean prediction error (MPE) for the traditional method, i.e., the test set method. Thus, the letter derives a formula to estimate the MPE of each candidate width value and then use it to select the optimal one with the lowest MPE value for faulty RBF neural networks with multi-node open fault. Simulation results show that the chosen optimal kernel width by our proposed MPE formula is very close to the actual one by the conventional method. Moreover, our proposed MPE formula outperforms other selection methods used for fault-free neural networks.     

Artificial neural networks and the accounting method choice in the oil and gas industry

On three occasions, accounting regulators considered eliminating full cost accounting as an acceptable method and at the same time requiring all oil and gas producing companies to adopt successful efforts accounting. In response, full cost companies appealed to the Securities and Exchange Commission to allow the continued use of full cost accounting arguing that companies using each method are different. They outlined three primary variables along which full cost and successful efforts companies can be differentiated: exploration aggressiveness, political costs, and debt-recontracting costs. Prior studies used these variables to explain the accounting method choice by oil and gas producers. Although these variables were significant from the standpoint of model development, the overall classification error rate for the traditional statistical models used by these studies has ranged from 28% to 57%. We propose that the high classification error is driven by strong non-linearities and high interactions among the posited variables and/or by the inability of binary statistical models to properly model the accounting method choice dynamics. On the other hand, the ability of artificial neural networks to model non-linear dynamics and to deal with noisy data make them potentially useful for this type of application. In this paper, we develop three supervised artificial neural networks (general regression, backpropagation, and probabilistic) to predict the accounting method choice by oil and gas producing companies. We compare the prediction accuracy generated by the artificial neural networks with those generated using logit regressions and multiple discriminant analysis. Consistent with the findings of prior studies, the overall prediction error for logit regressions and multiple discriminant analysis has ranged from 32% to 46%. Threelayer backpropagation and three-layer probabilistic networks performed no better than their equivalent traditional statistical models with the overall prediction error ranging from 24% to 43%. On the other hand, our three-layer general regression network performed much better with the overall prediction error ranging from 8% to 11%. More importantly, our general regression network performed extremely well in predicting both full cost and successful efforts companies.