An Interactive Expert System Based Decision Making Model for the Management of Transit System Alternate Fuel Vehicle Assets

Traditionally, the process used by public transportation entities to determine the acquisition strategy for new vehicle asset is based upon a broad range of criteria. Vehicle cost has been cited as one of the more critical factors which decision makers consider. It is currently a common practice to consider other factors (life-cycle cost, fuel efficiency, vehicle reliability, environmental effects, etc.) that contribute to a more comprehensive approach. This study investigates the next generation of advancements in decision making tools in the area of the application of methods to quantify and manage uncertainty. In particular, the uncertainty comes from the public policy arena where future policy and regulations are not always based upon logical and predictable processes. The fleet decision making process in most governmental agencies is a very complex and interdependent activity. There are always competing forces and agendas within the view of the decision maker. Rarely is the decision maker a single person although, within the transit environment, there is often one person charged with the responsibility of fleet management. The focus of this research examines the decision making of the general transit agency community via the development of an expert systems prototype tool. A computer-based prototype system is developed which provide an expert knowledge-based recommendation, based upon variable user inputs. The results shown in this study show that a decision making tool for the management of transit system alternate fuel vehicle assets can be modeled and tested. The direct users of this research are the transit agency administrations. The results can be used by the management teams as a reliable input to inform their urban transit buses expansion decision making process.

Study on the System Design of Multiple Expert Systems Integrated Decision Support System

There has been an increasing interest in integrating decision support systems (DSS) and expert systems (ES) to provide decision makers a more accessible, productive and domain-independent information and computing environment. This paper is aimed at designing a multiple expert systems integrated decision support system (MESIDSS) to enhance decision makers' ability in more complex cases. The basic framework, management system of multiple ESs, and functions of MESIDSS are presented. The applications of MESIDSS in large-scale decision making processes are discussed from the following aspects of problem decomposing, dynamic combination of multiple ESs, link of multiple bases and decision coordinating. Finally, a summary and some ideas for the future are presented.

How reliable is online diffusion of medical information targeting patients and families?

AIM: To determine whether online diffusion of the "Ten Warning Signs of Primary Immunodeficiency Diseases(PID)'' adheres to accepted scientific standards.METHODS: We analyzed how reproducible is online diffusion of a unique instrument, the "Ten Warning Signs of PID", created by the Jeffrey Modell Foundation(JMF),by Google-assisted searches among highly visited sites from professional, academic and scientific organizations;governmental agencies; and patient support/advocacy organizations. We examined the diffusion, consistency of use and adequate referencing of this instrument.Where applicable, variant versions of the instrument were examined for changes in factual content that would have practical impact on physicians or on patients and their families.RESULTS: Among the first 100 sites identified by Google search, 85 faithfully reproduced the JMF model, and correctly referenced to its source. By contrast, the other15 also referenced the JMF source but presented one or more changes in content relative to their purported model and therefore represent uncontrolled variants, of unknown origin. Discrepancies identified in the latter included changes in factual content of the original JMF list(C), as well as removal(R) and introduction(I) of novel signs(Table 2), all made without reference to any scientific publications that might account for the drastic changes in factual content. Factual changes include changes inthe number of infectious episodes considered necessary to raise suspicion of PID, as well as the inclusion of various medical conditions not mentioned in the original.Together, these changes will affect the way physicians use the instrument to consult or to inform patients,and the way patients and families think about the need for specialist consultation in view of a possible PID diagnosis.CONCLUSION: The retrieved adaptations and variants,which significantly depart from the original instrument,raise concerns about standards for scientific information provided online to physicians, patients and families.

学习带边信息专家意见的在线投资组合策略

针对以往学习专家意见的在线投资组合策略中专家策略并未考虑有助于提高投资者收益的边信息的不足,选取在相同边信息状态下投资相同单只股票、不同边信息状态下可能投资不同单只股票的策略为专家意见,基于指数加权平均算法(EWA)提出了学习带边信息专家意见的在线投资组合策略(EWAES).然后,从理论上证明了对任何的股票价格序列该策略都能够追踪最优专家意见.最后,采用中美金融市场实际股票数据对EWAES策略进行了数值分析,结果说明了该策略的有效性.

基于本体和语义网的中医专家问诊信息模型构建与呼吸科应用示范研究

目的通过梳理中医专家问诊思维导图,采用本体和语义网技术探索构建中医专家问诊信息模型的方法。方法中医专家问诊信息模型是由中医专家问诊数据采集信息模型和中医专家问诊知识库本体两部分组成,基于对中医专家问诊思维导图的梳理,结合已发表的论文和专著中所载各类中医病-证-症量表、已发布的各专病标准数据集、中医和中西医指南/专家共识、高校教材、中医问诊相关国家标准和行业标准等,对研究素材中的中医专家问诊数据采集相关信息框架提炼,完成中医专家问诊数据采集信息模型的构建;参考复用中医药语言系统(Traditional Chinese Medicine language systems,TCMLS)、中医临床术语系统(Traditional Chinese Medicine clinical terminological systems,TCMCTS)、国标、行标中的术语进行筛选、合并、分类,确立领域概念,结合中医临床问诊实际情况和呼吸科专病中医问诊思维导图,采用人工知识抽取方法,构建中医专家问诊知识库相关语义关系,采用七步法及protégé本体工具构建中医专家问诊知识库本体,实现中医专家问诊信息的知识推理表示。结果成功绘制了中医专家问诊思维导图,初步完成了中医专家问诊信息模型的构建,实现了中医专家问诊知识库的结构化表达。结论整合了中医专家问诊相关知识,构建了中医专家问诊信息模型,规范了中医专家问诊知识库信息化表达,为中医临床专科问诊信息化研究的创新发展提供了借鉴和参考。

医疗机构门急诊处方信息化审核专家共识

保证医疗机构的合理用药是国家卫生健康委为加强医疗卫生服务综合监管水平做出的重要指示。随着我国医疗水平的快速提升、门急诊就诊规模的不断扩大,处方数量急剧增长,基于合理用药数据库的处方信息化审核系统成为药学服务的重要工具。由北京药学会智慧药学与智能化管理专业委员会、中国老年保健医学研究会合理用药与综合评价分会、中国药师协会区域药学服务促进工作委员会、中国智慧药学联盟共同组织相关医疗机构专家撰写了《医疗机构门急诊处方信息化审核专家共识》。本共识旨在为各级医疗机构所开展的门急诊处方信息化审核工作的规范化提供参考,助力医疗机构构建标准统一、合理用药数据库完善的处方信息化审核系统,提升处方审核准确率和医患接受度,进一步提升我国医疗机构的合理用药水平,促进医院药学服务信息化和智慧化发展。

农业知识图谱技术研究现状与展望

在当前农业信息化的发展进程中,多数农业子领域面临着数据资源分散、信息整合难度大、知识利用效率低等问题。作为近年来新兴的一种知识表示技术,知识图谱已在部分农业特定领域展现出了强大的语义推理和数据整合能力,同时帮助一些农业上层应用提高了性能。为系统总结近年来农业知识图谱构建与应用方面的研究成果,本文首先阐述了知识图谱基础和农业知识图谱的构建流程,并从本体建模、信息抽取、知识融合以及知识加工4方面总结了构建农业知识图谱所涉及的关键技术。将当前农业知识图谱的应用分为信息检索、问答系统、推荐系统、专家诊断系统和作物预测5方面,并对这些应用工作进行了梳理。最后,对当前农业知识图谱的研究现状进行了总结,并认为未来农业知识图谱可以从多模态知识推理、强时效性知识更新、多语言知识查询、跨领域数据融合以及子领域知识图谱构建等方面加以研究。

融合关键信息与专家网络的生成式文本摘要

针对现有生成式摘要模型生成过程中存在原文本关键信息缺失和内容难控制的问题,提出一种结合抽取方法引导的生成式文本摘要方法.该方法首先通过抽取模型从原文本中获取关键句,然后采用双编码策略,分别编码关键句和新闻文本,使关键信息在解码过程中引导生成摘要,最后引入专家网络在解码时筛选信息,以进一步引导摘要生成.在数据集CNN/Daily Mail和XSum上的实验结果表明,该模型可有效改进生成式文本摘要的性能.该方法 在一定程度上提高了生成摘要对原文本关键信息的包含量,同时缓解了生成内容难控制的问题.

Student Academic Performance Predictive Model Based on Dual-stream Deep Network

Blended teaching is one of the essential teaching methods with the development of information technology.Constructing a learning effect evaluation model is helpful to improve students’academic performance and helps teachers to better implement course teaching.However,a lack of evaluation models for the fusion of temporal and non-temporal behavioral data leads to an unsatisfactory evaluation effect.To meet the demand for predicting students’academic performance through learning behavior data,this study proposes a learning effect evaluation method that integrates expert perspective indicators to predict academic performance by constructing a dual-stream network that combines temporal behavior data and non-temporal behavior data in the learning process.In this paper,firstly,the Delphi method is used to analyze and process the course learning behavior data of students and establish an effective evaluation index system of learning behavior with universality;secondly,the Mann-Whitney U-test and the complex correlation analysis are used to analyze further and validate the evaluation indexes;and lastly,a dual-stream information fusion model,which combines temporal and non-temporal features,is established.The learning effect evaluation model is built,and the results of the mean absolute error(MAE)and root mean square error(RMSE)indexes are 4.16 and 5.29,respectively.This study indicates that combining expert perspectives for evaluation index selection and further fusing temporal and non-temporal behavioral features that for learning effect evaluation and prediction is rationality,accuracy,and effectiveness,which provides a powerful help for the practical application of learning effect evaluation and prediction.

基于一种集控站监控信息预测和优化模型研究与分析

集控站作为电网运行的重要部分,连接着调度系统和变电站,其监控信息准确性和效能性的发挥尤为关键。为了更进一步提升集控站监控信息的审核效率,采用“专家库+改进蚁群算法”的方式,实现集控站监控信息表内容的预测和优化。通过构建集控站监控信息预测和优化模型,一方面面向信息行业属性,采用MapReduce分析机制,构建专家库,实现监控信息预测功能;另一方面依托蚁群算法建模,构建改进型信息全局优化模型。通过实验分析,该模型不仅提升了冗繁的监控信息分析预测能力,而且增强了电网集控场景下的监控信息优化效能。

基于强化迁移学习的继电保护设备信息异常自动识别方法

现有信息异常自动识别方法灵敏度较低,F值也较低,为此,提出基于强化迁移学习的继电保护设备信息异常自动识别方法。感知继电保护设备不同工况下的信息并对其进行预处理,结合专家经验采用“异常现象-异常演化路径-异常原因-异常解决措施”的逻辑过程建立信息异常识别知识库,通过强化迁移学习对知识库中的知识进行学习,提取设备信息异常特征,识别设备信息异常,实现基于强化迁移学习的继电保护设备信息异常自动识别。实验证明,本文方法灵敏度可达96%以上,F值可达97%以上,能够实现对继电保护设备信息异常精准自动识别。

变电站一键顺控不停电验收技术

提出一种基于“静态校核+虚拟仿真”验证的一键顺控不停电自动验收方法,通过专家文本语义识别算法对顺控主机预置库和运维典型操作票进行静态校核,然后通过基于SCD、CID、ICD模型文件构建的模型文件解析模块进行全景数字化虚拟仿真测试,进而验证一键顺控全站全间隔操作信息回路映射正确性,为传统人工验收向智能化不停电验收方法转变提供技术支撑。验证结果表明,该装置能大幅度提升一键顺控验收效率和质量,确保一键顺控上线应用100%正确。

规模化蛋鸡场现代化生产管理系统的建立与应用

为建立一个我国规模化蛋鸡场适用的生产管理系统 ,综合运用了多媒体技术、网络化管理、人工智能和自动化监控技术方法。通过人工神经网络与专家系统有机结合 ,改进鸡疾病专家系统 ;创建免疫接种备忘系统。由生产统计、生产计划、饲料配方、饲料库存、免疫接种和鸡病诊断专家系统构建成网络化软件系统。各子系统在数据库级别上达到企业数据资源的共享和利用 ,也可根据用户应用需求单独使用其中的子系统。同时 ,利用传感器、工控机和摄像机对鸡舍环境实行全方位的温湿度监测、移动摄像和鸡舍设备自动控制 ,实现鸡场远程管理。结果表明 :系统高度集成 ,运用多项计算机新技术 ,在一个系统研究中实现 ,并已在北京、上海和南京等规模化养鸡场示范应用。

电网故障诊断方法综述

介绍电网故障诊断问题的复杂性所在,并总结归纳近10多年来国内外学者在故障诊断领域提出的主要方法,包括专家系统方法、模糊集方法、数据挖掘和粗糙集方法、人工神经网络、Petri网、贝叶斯网、优化算法及信息理论方法等。说明各种方法的基本概念和方法思路,分析各种方法的特点和不足,探讨新形势下电网故障诊断技术的发展趋势。

泛在网络环境下公众网络健康信息可信度评价指标体系研究

[目的/意义]网络的自由性和开放性使其成为公众获取健康信息的重要途径,然而亦是其开放、自由和信息庞杂使网络健康信息质量成为公众健康信息查询和筛选值得关注的问题。因此,本研究在国内外网络健康信息质量评价相关研究基础上,建立以用户为评价主体的公众网络健康信息可信度评价指标体系,为公众网络健康信息查询和选择提供决策依据。[方法/过程]研究运用文献分析和专家咨询法构建指标体系,经专家对指标的重要性评分赋予指标权重;采用肯德尔和谐系数评价指标体系评价结果的稳定性。[结果/结论]共设计12项公众网络健康信息可信度评价指标,指标代表性、独立性和可操作性得到专家认可,权重在0.0717-0.0919之间,并制定指标量化评价方法。实证研究评价者之间肯德尔和谐系数为0.732。弥补了国内以用户为主体的网络健康信息可信度评价的空白,为国内公众网络健康信息查询和选择提供了科学评价工具。

农田图像采集与无线传输系统设计

结合ZigBee和GPRS,设计了农田图像采集与无线传输系统。系统由MESH型ZigBee图像采集网络和远程服务器构成,服务器与Z igBee网络的协调器通过GPRS网络进行数据传输。基于V4L技术采集了农田图像,阐述了JPEG压缩和解压缩流程,使用改进的离散余弦变换减小了图像压缩的运算量,并对压缩后的图像作了数据分组和校验,保证了数据传输的可靠性。在选定农田对系统进行实地测试,系统能够顺利采集图像,无线传输成功率为76%,同时分析了传输一幅图像的理论最短时间和实际平均传输时间产生的差异。

多传感器信息融合技术

多传感器信息融合是Ｃ３Ｉ系统和电子综合战系统中的关键技术．本文从信息融合分类出发，讨论了单传感器的信息融合决策理论和技术以及多传感器信息融合原理，提出了多传感器信息融合专家系统，着重讨论贝叶斯法用于二元检测的分布式多传感器信息融合的检测方式．

基于框架表示的玉米病虫草害诊治专家系统的构建及实现

由于农业生产的复杂性,玉米病虫草害的诊断对于农业技术人员经验的依赖很大。而玉米病虫草害诊断专家系统可以将这一复杂的工作变得更有成效。针对传统专家系统知识获取的"瓶颈"问题,在对玉米病虫草害症状框架描述的基础上,利用知识工程方法和技术,结合不确定性推理、匹配冲突消解策略和多媒体技术,实现了基于框架表示的玉米病虫草害诊治专家系统,用于模仿该领域专家思维,补充或代替农业专家指导玉米生产。本文主要阐述该系统的总体结构、知识表示、推理机制和系统实现与应用等方面问题。

智能化水产养殖信息系统的设计与初步实现

智能化水产养殖业信息系统以当今世界上主流的 Intranet技术 (服务器、浏览器 ) ,采用先进的 Client/Server/ Server (CSS)多层体系结构。以等图象处理软件为开发工具 ,以 Windows NT4.0 / Windows 98为应用软件平台 ,对水产养殖、网上专家、信息咨询、渔业环保、市场商情、观赏鱼、会员注册、相关站点等 8个基本模块进行了系统集成。实现了完善的专家决策支持功能。