采用扩展的条件概率方法处理非确定的模糊信息

本文介绍了条件概率的一种扩展方法及其应用。这种方法是将条件概率扩展成含有一个值为α(0≤α<1)的非确定命题。经扩展后的条件概率可以用来表示检索中非确定的询问和制定检索策略,并利用已有信息对模糊的和非确定的信息进行间接推理或推测。     

建构友好人工智能

在人工智能得到高度重视并飞速发展的时代背景中,我们应该努力建构一种友好人工智能,使其更好地为人类服务,避免或减少负面影响。从政府管理层面看,需要加大人工智能社会影响研究,实现智能社会的公平正义,加强对人工智能科技的监管与调控。从技术层面上,需要保证人工智能技术的安全性、可控性、稳健性与人性化,实现人工智能算法的公正性与透明性。从公众层面上看,需要积极应对人工智能对就业的影响,正确认识人工智能威胁论,克服人工智能技术恐惧思想。从关系层面看,需要完善相关法律法规,加强对人工智能的国际治理。人工智能研究应该以"友好人工智能"为出发点与落脚点,建构友好人工智能应该成为全社会的非常明确的努力目标。     

北京市人工智能企业全要素生产率测度及差异性研究

人工智能的发展已成为衡量一个国家科技水平和经济智能化程度的重要标志。北京市作为国际科创中心，人工智能产业规模增长迅速，但仍处于发展初期，人工智能企业生产率的提升关系到人工智能产业的整体发展水平。本文运用DEA-Malmquist指数方法对2016-2018年114家北京市人工智能企业的全要素生产率进行测度，结果显示，北京市人工智能企业全要素生产率年均增长率为0.70%，技术效率是企业全要素生产效率提升的主要动力。此外，上市企业的全要素生产率水平高于非上市企业，且行业间差异明显，信息传输、计算机服务和软件业的全要素增长率最高，教育行业的全要素增长率最低。     

REARING DRIED FRUIT BEETLE Carpophilus hemipterus ON AN ARTIFICIAL DIET

Dried fruit beetles can be cultured easily using an artificial diet,therefore it is notnecessary to provide fruit.The ingredient are:Torula yeast,54g:Dried carrot,162g;Nipagin,2.4g;HCL Conc.7ml;Rain water,800ml.About60g of diet in pressed against one side of ahalf litre yogurt and sprinkled with a teaspoonful of active yeast.Two teaspoons full of diet ontop of the gauze lid and sprinkled with active yeast granules for the adults to eat and also to layeggs into.Up to2000 larvae should be produced from400 parents each week.About200 eggscan be collected,when making observations.The culture is rejuvenated each year with beetlescollected from the wild,kept isolated to avoid contamination of the culture room with mites.     

Prediction of hot deformation behavior in Ni-based alloy considering the effect of initial microstructure

High temperature heat treatments were conducted for as-cast N08028 alloy to obtain various microstructures with different amounts of σ-phase,and then hot compression tests were carried out using Gleeble-3500 thermo-mechanical simulator in deformation temperature range from 1100 to1200 ℃ and strain rate range from 0.01 to 1 s-1. For the same initial microstructure, the flow stress was observed to increase with increasing the strain rate and decreasing the deformation temperature, while for the same deformation condition, the flow stress was found to increase with increasing the amount of σ-phase in the initial microstructure. Moreover, dynamic recrystallization was found to be the main dynamic soften mechanism. On this basis, Arrhenius-type constitutive equations and artificial neural network(ANN) model with back-propagation learning algorithm were established to predict hot deformation behavior of the alloy. Furthermore, the parameters of constitutive equations were found to be dependent on the initial microstructure, which was also as one of the inputs for the ANN model. Suitability of the two models was evaluated by comparing the accuracy, correlation coefficient and average absolute relative error, of the prediction. It is concluded that the ANN model is more accurately than the constitutive equations.     

Levy人工蜂群在钢铁企业供应端的优化

根据钢铁企业供应端中配送成本高、运营效率低、管理不科学等问题,提出了一种以钢铁企业实际为中心,并以供应成本最低为目的的配送车辆路径模型。利用Levy飞行对改进的人工蜂群进行优化,用以求解最低成本、最优路径的钢铁企业供应问题。以某钢铁企业设计实现的供应配送管理系统为依托,研究了场外物流调度的执行情况,建立了适合钢铁企业的车辆路径问题数学模型;并通过与传统方法进行模拟计算和比较,验证了新型优化算法计算效率高、求解速度快;并且该模型求出的解可节省成本,降低损耗,从而指导钢铁企业供应以提高企业利润。     

未知环境中机器人避障路径规划研究

针对人工势场法机器人路径规划具有目标不可达与存在局部极小值点等问题,提出了改进后的人工势场法模型,将未知环境中的障碍以网格地图的形式设计出来,使机器人通过感知来规避障碍朝目标移动。运用MATLAB GUI设定形成一个包含障碍与目标点的二维坐标系统环境,在其平面地图中使机器人从初始位置到期望位置进行最优轨迹移动仿真试验。试验显示,改进后的人工势场法能使移动机器人在未知环境中导航避开障碍并找出合适路径,以达到无碰撞要求。仿真结果接近预期效果,表明该方法能有效提高移动机器人在未知环境中路径规划的可行性及其避障的有效性。     

用人工智能和神经网络的方法组建数据压缩系统

数据压缩是现代信息处理的基础课题之一．文中对数据压缩的设计思路作了分析和拓展，从系统的角度对数据压缩与人工智能、神经网络的结合作了一些大胆的、初步的尝试，并对这个研究方向作了一些功能上和性能上的分析，提出了再压缩的概念．     

蕨的人工有性繁殖及复壮技术

为适应当今绿色食品之一－蕨菜Ｐｔｅｒｉｄｉｕｍａｑｕｉｌｉｎｕｍ（Ｌ．）Ｋｕｈｎｖａｒ．ｌａｔｉｕｓｃｕｉｕｍ（Ｄｅｓｖ．）Ｕｎｄｅｒｗ．ｅｘＨｅｌｌｅｒ资源的开发利用。本文报道了蕨菜的人工繁殖及复壮技术，并讨论屯其经济价值和应用前景。