Learning Perceptrons and Piecewise Linear Classifiers Sensitive to Example Dependent Costs

This article considers the cost dependent construction of linear and piecewise linear classifiers. Classical learning algorithms from the fields of artificial neural networks and machine learning consider either no costs at all or allow only costs that depend on the classes of the examples that are used for learning. In contrast to class dependent costs, we consider costs that are example, i.e. feature and class dependent. We present a cost sensitive extension of a modified version of the well-known perceptron algorithm that can also be applied in cases, where the classes are linearly non-separable. We also present an extended version of the hybrid learning algorithm DIPOL, that can be applied in the case of linear non-separability, multi-modal class distributions, and multi-class learning problems. We show that the consideration of example dependent costs is a true extension of class dependent costs. The approach is general and can be extended to other neural network architectures like multi-layer perceptrons and radial basis function networks.     

A contribution to the development of strategic control and planning instruments: An acquisition case study

The present paper is part of the efforts made by the authors in recent years to develop strategic control and planning instruments in corporations using OR‐techniques like system dynamics, control theory, and group multicriteria decision aid. A more general framework called ‘adaptive control methodology’ (ACM) combines all these techniques. It has been presented in several papers. The objective of the present analysis is to calibrate this instrument and to tune it to the corporate needs by analysing real‐world applications. More specifically, several case studies have been investigated in large multinational organisations in the food sector. An acquisition case has been used for the calibration purpose. It is analysed in the paper from the ACM perspective to provide additional material for revisiting and improving the methodology.     

石泉水库主汛期拦蓄洪尾超蓄运用的风险分析

针对水资源匮乏和汛期水库大量弃水的矛盾，提出了有效的解决途径——汛期通过适时拦蓄洪尾超蓄运用的方式来充分利用洪水资源。拦蓄洪尾超蓄运用存在一定的风险，本文就超蓄运用的风险因素进行了识别分析，并从水文频率分析角度提出了计算超蓄风险率的方法；通过对石泉水库不同超蓄水位的风险率进行计算，结合可接受风险率值，得出了该水库拦蓄洪尾超蓄运用的期望水位。     

SVM算法及其在乳腺X片微钙化点 自动检测中的应用

支持矢量机(SVM)是一种新的统计学习方法,其学习原则是使结构风险最小,而非经典学习方法所遵循经验风险最小原则.这使得SVM具有更强的泛化能力.并且,由于SVM求解的是凸二次优化问题,使之能保证所找到的极值解就是全局最优解.本文首次将SVM算法用于乳腺X影像微钙化点自动检测中,对临床实际病例的试用结果表明,同目前常用的基于经验风险最小的人工神经网络(ANN)分类方法相比,SVM具有更高的识别率,值得应用推广.     

裂纹转子弯扭耦合瞬态振动影响因素研究

针对两端刚性支承的Jeffcott转子，推导了裂纹转子的弯扭耦合振动非线性微分方程，通过数值仿真手段，分析了升速过程中弯振和扭振的瞬态特性，并详细探讨了加速度、裂纹减小刚度、裂纹夹角、质量偏心以及阻尼系数等因素对弯扭耦合振动瞬态特性的影响。研究表明，升速过程中，随着加速度增大，弯振和扭振各共振峰值减小，而对应转速增加。各共振峰值均随着△kq的增加而增大，当△kq超过某值后，峰值急剧增加。β在0～2π范围内变化时，各共振峰值呈现不同周期的正余弦变化。质量偏心主要影响临界峰值，对其它各峰值影响很小。各峰值均随阻尼系数的增加而降低，阻尼系数较小时，峰值减小率更大。     

维氏硬度曲面修正系数的计算机拟合

根据GB／T 4340．1-1999所附的各类曲面维氏硬度修正系数表，基于多项式拟合技术，给出了曲面维氏硬度修正系数关于压痕对角线长度与曲面直径比值的解析函数表达式，并对维氏硬度值的修约规律进行了总结。     

CaO基粉剂铁水脱硫影响因素研究

在实验室条件下对不同配比的CaO基粉剂进行铁水脱硫实验，结果表明，适宜的CaO基铁水脱硫剂组分为：m(CaCO3)／m(CaO)=0．20～0．40，w(CaF2)=6％～10％及叫w(C)≤10％。在宝钢的铁水脱硫实际中，铁水温度、铁水初始硫含量、喷粉速度等都会影响脱硫率。     

CDIC颌面及颅外科用钛骨固定器的安全风险分析方法

本文根据国家有关规定和相关标准，对三类医疗器械产品CDIC颌面及颅外科用钛骨固定器进行安全风险分析方法进行了介绍，应用该方法分析后，结论是产品的潜在风险均分布在广泛可接受区和合理可降低区，合理可降低区的潜在风险，只要实施了降低／控制风险措施，即可将风险降到最低。产品的受益远大于潜在风险，由产品造成的潜在风险是可以接受的，临床使用是安全的。     

钛酸锶压敏陶瓷及其性能影响因素

为了提高SrTi03压敏陶瓷的性能，对其影响性能的因素进行了论述，指出主要影响因素是配方体系及制造工艺中的绕结工艺，并指出改善SrTi03综合性能的途径是进一步提高瓷料配方的适应能力并完善制造工艺。