Learning a decision maker's utility function from (possibly) inconsistent behavior

When modeling a decision problem using the influence diagram framework, the quantitative part rests on two principal components: probabilities for representing the decision maker's uncertainty about the domain and utilities for representing preferences. Over the last decade, several methods have been developed for learning the probabilities from a database. However, methods for learning the utilities have only received limited attention in the computer science community.

A promising approach for learning a decision maker's utility function is to take outset in the decision maker's observed behavioral patterns, and then find a utility function which (together with a domain model) can explain this behavior. That is, it is assumed that decision maker's preferences are reflected in the behavior. Standard learning algorithms also assume that the decision maker is behavioral consistent, i.e., given a model of the decision problem, there exists a utility function which can account for all the observed behavior. Unfortunately, this assumption is rarely valid in real-world decision problems, and in these situations existing learning methods may only identify a trivial utility function. In this paper we relax this consistency assumption, and propose two algorithms for learning a decision maker's utility function from possibly inconsistent behavior; inconsistent behavior is interpreted as random deviations from an underlying (true) utility function. The main difference between the two algorithms is that the first facilitates a form of batch learning whereas the second focuses on adaptation and is particularly well-suited for scenarios where the DM's preferences change over time. Empirical results demonstrate the tractability of the algorithms, and they also show that the algorithms converge toward the true utility function for even very small sets of observations.     

基于神神经元网络的电厂锅炉燃烧优化系统

介绍应用于某200MW机组锅炉、基于神经元网络在线辨识技术的锅炉燃烧优化系统的结构和实现方式，讨论基于神经元网络的优化模型和优化算法，并在同类型仿真机上进行了仿真实验，证明了锅炉燃烧优化系统的正确性和有效性。     

降低回转式空气预热器漏风率的技术措施

分析荆门热电厂3号锅炉的受热面回转式空气预热器漏风率大的原因，综合比较各种改进方案后提出改进措施。改造后漏风率降低到12％以下，经济效益及投资收益显著。     

An estimation approach for dividable multiattribute utility of housing via questionnaires of consumers'' ordinal multicriteria preferences

multi-function characteristic. How to evaluate the multi-functional nature of housing is very useful in both theory and in application, yet it is often ignored in China. This paper introduces an approach to estimate the muhicriteria function of housing using multiattribute utility theory (MAUT) based on consumers' ordinal multicriteria peferences as determined via questionnaires. When compared with the classic framework in which MAUT is applied, this approach needs less prior information and subjective comparisons and thus can allay many of the operational difficulties involved in assessment. Some potential applications to the China housing market are also discussed.     

基于风险态度可变的投机行为研究

本文通过分析不同风险条件下人们对待风险持不同态度这一观测事实，建立了一个新的风险态度描述模型，该模型可以解释当前我国危害性投机行为广泛存在这一现象．在认识风险态度的基础上，分析投机行为的实质和诱导因素，并据此给出关于防范危害性投机行为及鼓励风险承担的创新行为的对策思考．     

Mitigating expropriation risk through vertical separation of public utilities: The case of Argentina

In 2002, Argentina devalued its currency and froze public utility rates thus breaching the guarantees granted to investors the decade before. Those guarantees had lowered investors' cost of capital by substantially reducing expropriation risk. This paper looks into the governance structure chosen by Argentina for the privatization process and potential alternatives after a decade of contract breaches. Future governance should be market-oriented, involving vertically separated companies with former public utilities voluntarily acting as operating companies or OpCos, and NetCos in charge of all network expansions under the structure of PPPs created for such purposes.     

Single‐Stage ZVS‐PWM AC‐AC Power Converter Using All SiC Power Module for High‐Frequency Induction Heating Applications

This paper presents a novel prototype of a single‐stage zero voltage soft‐switching pulse‐width modulation ‐controlled ac‐ac converter with a silicon carbide (SiC)‐MOSFET/SiC‐SBD power module for high‐frequency (HF) induction heating (IH) applications. The newly developed ac‐ac converter can achieve higher efficiency than a Si‐IGBT/Si‐PN diode power module‐based prototype due to a low ON‐resistance of SiC‐MOSFET and a low forward voltage of SiC‐SBD under the condition of HF switching. The performances of the new prototype converter are evaluated by experiment with a single‐phase IH utensil of ferromagnetic stainless metal, after which the high‐efficiency and low switching noise characteristics due to the all SiC power module are actually demonstrated.     

Stakeholder engagement by an Italian water utility company: Insight from participant observation of dialogism

This paper focuses on the level of dialogism between organizations and participants. The unit of analysis is a water utility's direct engagement with its household customers. Through participant observation and Bebbington et al.’s (2007) model, we analyzed engagement factors to detect elements occasioning a dialogic experience and its determinants. This contribution to the public utilities and social accounting literature outlines interrelated factors impacting barriers to and opportunities for creating dialogism. It enhances public utility business reputation and drives sustainability innovations. Managerially, we identified enablers and limits of an effective stakeholder engagement process.     

Levels of incomplete information in group decision models – A comprehensive simulation study

We present a comprehensive computational study on the effects of providing different forms of incomplete preference information in additive group decision models. We consider different types of information on individual preferences, and on weights of the group members, and study their effects on conclusiveness, efficiency and fairness of outcomes at the group level. Furthermore, we analyze possible violations of the axiom of independence of irrelevant alternatives (IIA) as well as the impact of problem characteristics, in particular initial agreement between group members. Our results indicate that providing information in the form of a ranking of differences between consecutive alternatives comes close to providing exact cardinal preference information in several outcome dimensions. However, group decision procedures based on incomplete preference information also show a significant amount of violations of the IIA axiom.