带优化参数的SVR模型及在软件成本估算中的应用

随着社会各行各业对软件开发投资的日益增长,产业界和学术界越来越关注可靠的软件成本估算,以有效控制软件开发过程中相关风险.为了能更准确地估算软件成本,提出一种带遗传算法优化参数的支持向量回归机模型,用遗传算法来优化支持向量回归机模型中的参数集(C,γ,ε),可以避免参数选择的盲目性,能显著提高支持向量回归机模型的预测能力.分别用IBM DP、Kemerer和Hallmark三个数据库来验证模型的有效性,并与常用的线性回归模型进行对比,结果显示采用遗传算法优化的支持向量回归机模型具有很好的学习精度和推广能力,在MMRE和Pred(0.25)两个标准上都优于线性回归模型.     

原料为易腐的生产贮存 控制中的随机需求问题

本文讨论了原料为易腐的生产贮存控制中的需求为随机变量的问题, 给出了最优的生产点、批量生 产时间、( S , s)策略中最优的 S 和s 所应该满足的条件.     

Local Rules and Fitness Landscapes: A Catastrophe Model

This paper examines the imposition of local rules in five mail delivery centres of Australia Post. Local rules are patterns of behaviour used by subunits of an organization to optimise their payoff. These local rules may ultimately benefit the total organization. Fitness landscapes are used to examine the emergence of local rules in this workplace. This research examined the relationship between the time taken to sort the mail and the volume of this mail. Work rates show a clear catastrophe shift; that is, work rates suddenly drop when the volume of mail exceeds a certain level, as Postal Delivery Officers apply local rules to maximise gains inherent in the pay structures. Such behaviour is close to that predicted by Kauffman (1995) in computer simulations of lattices and may be indicative of the application of local rules in organizations. The implications of the use of local rules are that behaviour in social systems may be dictated by systemic and emergent processes which are outside immediate management control. A further implication is that organizations may be structured to a significant extent by such local rules.     

Flexible software reliability growth model with testing effort dependent learning process

A lot of importance has been attached to the testing phase of the Software Development Life Cycle (SDLC). It is during this phase it is checked whether the software product meets user requirements or not. Any discrepancies that are identified are removed. But testing needs to be monitored to increase its effectiveness. Software Reliability Growth Models (SRGMs) that specify mathematical relationships between the failure phenomenon and time have proved useful. SRGMs that include factors that affect failure process are more realistic and useful. Software fault detection and removal during the testing phase of SDLC depend on how testing resources (test cases, manpower and time) are used and also on previously identified faults. With this motivation a Non-Homogeneous Poisson Process (NHPP) based SRGM is proposed in this paper which is flexible enough to describe various software failure/reliability curves. Both testing efforts and time dependent fault detection rate (FDR) are considered for software reliability modeling. The time lag between fault identification and removal has also been depicted. The applicability of our model is shown by validating it on software failure data sets obtained from different real software development projects. The comparisons with established models in terms of goodness of fit, the Akaike Information Criterion (AIC), Mean of Squared Errors (MSE), etc. have been presented.     

手机广告链中移动运营商的努力动机研究与仿真

建立了由单手机广告主、手机广告代理商和移动运营商构成的三级广告产业链之间的基于协作的收益共享契约模型,分析了在以移动运营商为主导的手机广告链中,移动运营商的努力动机受收益共享和努力成本补偿参数的影响.采用量化分析和模拟仿真结合的方法,得出契约参数只有在满足一定条件下,移动运营商所做出的最优努力水平投入决策,将使得整个手机产业链收益最大化,实现多方共赢.     

基于委托代理理论的医疗激励契约研究

医患之间的高度信息不对称性是导致医患矛盾的重要原因。现有研究基于信息不对称情况下医患之间的委托代理关系模式,针对可能导致的道德风险问题设计了不同的医疗激励机制,但是没有充分考虑医疗服务的不确定性和异质性。本文考虑医方努力的不同动机,提出二维努力水平的概念,以医患双方效益最大化为目标,对患方就医过程中的医患博弈时序进行研究,在医方具有信息优势的条件下设计了不同情况下的医疗激励契约模型。数值分析结果表明,医方的固定医疗收益、收益提成比例和二维努力水平等激励参数与医方努力产出的边际收支系数、医患双方的风险偏好程度以及随机因素的扰动程度等均存在显著的相关关系。     

The effects of time constraints on phonatory stability in normally speaking adult women

Forty normally speaking women sustained /a/ five times in two conditions,untimed and timed. In the untimed condition, phonation began whenever the subject felt ready. The timed task required subjects to begin phonation as quickly as possible after the examiner's signal. Conditions were counterbalanced across subjects. Jitter and shimmer values were obtained on a Kay Elemetrics Computerized Speech Lab (Pine Brook, NJ). Three distinct patterns of change emerged for fitter and shimmer from the untimed to the timed condition, reflecting either decreases, increases, or no change in values. These changes in jitter and shimmer values across conditions are related to a reaction time model of “bias toward accuracy.”     

Comfortable effort level revisited

The purpose of this study was to measure the variability of frequency and intensity of speech, using multiple voice samples obtained over a period of time at a speaker's “comfortable effort level.” Variability in vocal output within and across several experimental sessions was assessed from measures of speaking fundamental frequency (SFF) and vocal intensity for utterances repeated three times a day over a 3-day period. Three distinct age groups of men and women—young, middle-aged and elderly—repeated the vowel /a/, read a standard passage, and spoke extemporaneously during each experimental session. Results indicated that variability in SFF and intensity were present across experimental sessions, age groups, gender, and speaking samples. Generally, group means indicated that ±1 semitone of variability for SFF and 2 db sound pressure level (SPL) variation in vocal intensity from any one experimental session to the next could be expected; individual variations within any group may reach two semitones and 6 db SPL.