题名科研安全平台安全预警方法研究
作者周生伟
学位类别硕士
答辩日期2013-05-24
授予单位中国科学院大学
授予地点北京
导师蒋同海
关键词安全预警数据挖掘 科研生产安全 关联规则 时序模式
学位专业计算机技术
中文摘要
危机的发生具有不确定性,避免危机发生的最好方法就是在危机发生之前对其进行风险预警,因此有效的预警措施对社会安全和稳定具有重要的意义。本文依托于中 科院新疆理化所“科研安全监管平台”项目,该项目获取了大量科研单位安全保障信息,为了进一步提高科研单位的安全工作,基于“科研安全监管平台”,进行安 全预警方法研究。研究的指导理论是安全预警理论,采用的技术手段是关联规则和时序模式数据挖掘,采用数据挖掘的原因是项目平台层数据库存正在积累大量有效 数据,并且迫切要将这些数据转换成有用的信息和知识,获取的信息知识可广泛的运用于各种科研保障工作,包括安全巡逻、科研设备保障、危化品和消防品监管。 论文通过对基于数据挖掘的安全预警方法的研究,介绍了安全预警和数据挖掘的相关理论技术,包括安全预警的概论、数学基础、技术应用和数据挖掘的关联规则、 时序模式等技术的概论、算法和应用。在此基础之上,研究了如何把关联规则挖掘和时序模式挖掘应用于科研安全监管平台进行安全预警。结合安全预警和数据挖掘 的相关理论技术,定义了预警关联规则、预警时序模式,设计了关联规则预警算法和时序模式预警算法,并以这两个算法为核心,构建了关联规则预警模型和时序模 式预警模型,并实现了基于科研安全平台的感知对象之间的关联规则预警,安保人员频繁项集渎职预警和感知对象的时序模式预警。
英文摘要Crisis ’coming is uncertain. The best way to avoid crisis is to do early safety warning predict before the real crisis. So, effective safety warning measures are important to social stability and security. This paper is based on the project of the supervision platform of research and manufacture safety of Xinjiang Institute of Physics and Chemistry. This project gets a lot of safety information of research and manufacture of institutes. In order to improve safety of research institute, this paper will have a deep research on early safety warning methods based on the supervision platform of research and manufacture safety. Early safety warning theory is the guide principle and technical approach is association rules and time sequent patterns of data mining. The reason why data mining is the data base on application layer has a large number of data and we urgent to convert these data into useful information and knowledge that can be widely used all kinds of safety job, including security patrols, scientific equipment protection, hazardous chemicals and fire-fighting equipment supervision.By the research on early safety warning methods based on data mining, this paper introduces the theory and technology of early safety warning and data mining, including the overview、mathematic foundation、technology application of early safety warning and the overview、algorithm、application of association rules and time sequent patterns of data mining. On this basis, this paper has a research on how to use association rules and time sequent patterns on supervision platform of research and manufacture safety to realize early safety warning predict. This paper defines warning association rules、warning time sequent mode and designs the algorithms of association rules prediction and time sequent patterns prediction on the guide of the theory of data mining and early safety warning. Based on the two prediction algorithms, the association rules prediction model and time sequent patterns are structured. Final, this paper implements the warning of association rules, security malfeasance from frequent item sets and the time sequent mode based on the supervision platform of research and manufacture safety.
公开日期2013-05-31
内容类型学位论文
源URL[http://ir.xjipc.cas.cn/handle/365002/2473]  
专题新疆理化技术研究所_多语种信息技术研究室
作者单位中国科学院新疆理化技术研究所
推荐引用方式
GB/T 7714
周生伟. 科研安全平台安全预警方法研究[D]. 北京. 中国科学院大学. 2013.
个性服务
查看访问统计
相关权益政策
暂无数据
收藏/分享
所有评论 (0)
暂无评论
 

除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。


©版权所有 ©2017 CSpace - Powered by CSpace