信息融合算法及其应用研究
合集下载
相关主题
- 1、下载文档前请自行甄别文档内容的完整性,平台不提供额外的编辑、内容补充、找答案等附加服务。
- 2、"仅部分预览"的文档,不可在线预览部分如存在完整性等问题,可反馈申请退款(可完整预览的文档不适用该条件!)。
- 3、如文档侵犯您的权益,请联系客服反馈,我们会尽快为您处理(人工客服工作时间:9:00-18:30)。
II
neural network, to determine the mapping relations between the monitored attributes. These relations are used to fuse multi-sensor data and determine the states of monitored attributes. Matlab simulation tool is used to verify the validity of the algorithm, the results show that the algorithm can descript the real state of attribute very well, and make a reasonable estimate of the original frequency distribution of the attribute data. To further verify the practicality of the proposed algorithm, a forest fire monitoring system is designed. DIFAT and FIFAS algorithm are used to give forest fire warning level.
Keywords: Information Fusion, Multi-sensor, Time-dimension, Spatial-dimension, Sliding window, Neural network
单位代码: 10293
密
级:
硕 士 学 位 论 文
论文题目:
信息融合算法及其应用研究
学 姓 导 学 研 科 究 专 方
号 名 师 业 向
1010041302 刘涛 李玲娟 教授 计算机软件与理论 基于网络的计算机软件应用技术 工学硕士 二 零 一 三 年 二 月
申请学位类别 论文提交日期
Research and Application of Information Fusion Algorithm
研究生签名:_____________ 日期:____________
Fra Baidu bibliotek
南京邮电大学学位论文使用授权声明
本人授权南京邮电大学可以保留并向国家有关部门或机构送交论文的复印件和电子文 档;允许论文被查阅和借阅;可以将学位论文的全部或部分内容编入有关数据库进行检索; 可以采用影印、缩印或扫描等复制手段保存、汇编本学位论文。本文电子文档的内容和纸质 论文的内容相一致。论文的公布(包括刊登)授权南京邮电大学研究生院办理。 涉密学位论文在解密后适用本授权书。
研究生签名:____________ 导师签名:____________ 日期:_____________
摘 要
随着无线传感网的日益广泛应用和物联网的产生与应用,信息融合技术已经逐渐融入到 社会生活当中,给人们生活带来了前所未有的便利。随着传感器数据来源越来越复杂,如何 全面、快速、准确的获取信息已成为研究热点,因此对信息融合方法的研究具有重要意义。 本文以多传感器的监测数据作为研究对象,从监测数据的时间和空间冗余性出发,利用 流数据模型构建了基于时间维的数据级信息融合模型和基于空间维的特征级信息融合模型, 提出了对应的信息融合方法,并将之应用于森林火灾监测系统中。具体研究内容如下: 为了更好的利用监测数据上下文的情景信息,提出了基于滑动窗口的信息融合模型,其 基本思想是利用窗口内连续数据序列的上下文情景信息,对属性在窗口内的变化进行估计, 并利用这种估计来表述属性的变化;同时利用同一属性不同窗口以及不同属性相同窗口的数 据序列之间存在的冗余信息,实现多传感器数据的关联和融合。 针对数 据级 的信 息融 合,提 出了 基于 时间 维的数 据级 信息 融合 算法 --DIFAT 算 法 (Data-Level Information Fusion Algorithm based on Time-Dimension),利用被监测对象自身存在 的变化规律,对窗口内数据序列进行时域和频域分析,建立被监测对象关于时间变化的模型, 并通过最优化方法给出被监测对象规律的最优估计。利用 Matlab 仿真工具,对该算法的有效 性进行了验证,结果表明该算法能有效地去除部分噪声,减少感知数据的不确定性,得到相 对可靠的对属性变化特性的估计。 针对特征级的信息融合,既考虑了同一属性不同传感器数据的融合,也考虑了不同属性 不同传感器的数据融合, 提出了基于空间维的特征级信息融合算法--FIFAS 算法(Feature-Level Information Fusion Algorithm based on Spatial-Dimension),通过数据关联、神经网络等方法确 定被监测属性之间的映射关系,并利用这种关系进行信息融合,确定被监测属性的状态。利 用 Matlab 仿真工具,对该算法的有效性进行了验证,结果表明该算法能很好的描述属性的真 实情况,对属性的原始的数据频域分布能做出合理的估计。 为了进一步验证所提出的算法的实用性,设计了各算法在森林火灾监测系统中的应用架 构,运用 DIFAT 算法和 FIFAS 算法给出森林火灾的预警等级。 关键字:信息融合,多传感器,时间维,空间维,滑动窗口,神经网络
Thesis Submitted to Nanjing University of Posts and Telecommunications for the Degree of Master of Engineering
By Liu Tao Supervisor: Prof. Li lingjuan February 2013
I
Abstract
With the increasingly widespread application of wireless sensor networks and the generation and application of the Internet of Things, information fusion technology has been gradually integrated into the social life, which brings unprecedented convenience to people's lives. With the more and more complicated of sensor data sources, how to obtain information comprehensively, rapidly and accurately has becomes a research focus. Therefore, the research of information fusion method has significant meaning. In this thesis, the monitoring data of multi-sensor is basic research object. By using the time and spatial redundant information of monitoring data, a data-level information fusion model based on time-dimension and a feature-level information fusion model based on spatial-dimension are built, and the corresponding information fusion methods is proposed and applied to forest fire monitoring system. The research contents are as follows: In order to make a better use of scene context information in the monitoring data, an information fusion model based on sliding window is proposed. The basic ideal of this model is estimating the change rule of attribute by using context information of continuous data sequence in window; using the estimate result to descript the change rule of the attribute, and associating and fusing multi-sensors data by using the redundant information between different windows of one attribute as well as that between the different attributes of the same window. For data-level information fusion, a Data-Level Information Fusion Algorithm based on Time-Dimension (DIFAT) is proposed. As the monitored object has its own change rules, after analyzing the time domain and frequency domain of data sequence in window, a model used to descript the change of monitored object is established. According to the model, optimization method gives the optimal estimation of rule of the monitored object. Matlab simulation tool is used to verify the validity of the algorithm, and the results show that the algorithm can effectively remove part of the noise, reduce uncertainty of perceptual data, and obtain reliable change rules of attributes. For feature-level information fusion, considering the multi-sensor data fusion of both one attribute and different attributes, a Feature-Level Information Fusion Algorithm based on Spatial-Dimension (FIFAS) is proposed. The FIFAS utilizes methods, such as data association and
南京邮电大学学位论文原创性声明
本人声明所呈交的学位论文是我个人在导师指导下进行的研究工作及取得 的研究成果。尽我所知,除了文中特别加以标注和致谢的地方外,论文中不包 含其他人已经发表或撰写过的研究成果,也不包含为获得南京邮电大学或其它 教育机构的学位或证书而使用过的材料。与我一同工作的同志对本研究所做的 任何贡献均已在论文中作了明确的说明并表示了谢意。 本人学位论文及涉及相关资料若有不实,愿意承担一切相关的法律责任。
neural network, to determine the mapping relations between the monitored attributes. These relations are used to fuse multi-sensor data and determine the states of monitored attributes. Matlab simulation tool is used to verify the validity of the algorithm, the results show that the algorithm can descript the real state of attribute very well, and make a reasonable estimate of the original frequency distribution of the attribute data. To further verify the practicality of the proposed algorithm, a forest fire monitoring system is designed. DIFAT and FIFAS algorithm are used to give forest fire warning level.
Keywords: Information Fusion, Multi-sensor, Time-dimension, Spatial-dimension, Sliding window, Neural network
单位代码: 10293
密
级:
硕 士 学 位 论 文
论文题目:
信息融合算法及其应用研究
学 姓 导 学 研 科 究 专 方
号 名 师 业 向
1010041302 刘涛 李玲娟 教授 计算机软件与理论 基于网络的计算机软件应用技术 工学硕士 二 零 一 三 年 二 月
申请学位类别 论文提交日期
Research and Application of Information Fusion Algorithm
研究生签名:_____________ 日期:____________
Fra Baidu bibliotek
南京邮电大学学位论文使用授权声明
本人授权南京邮电大学可以保留并向国家有关部门或机构送交论文的复印件和电子文 档;允许论文被查阅和借阅;可以将学位论文的全部或部分内容编入有关数据库进行检索; 可以采用影印、缩印或扫描等复制手段保存、汇编本学位论文。本文电子文档的内容和纸质 论文的内容相一致。论文的公布(包括刊登)授权南京邮电大学研究生院办理。 涉密学位论文在解密后适用本授权书。
研究生签名:____________ 导师签名:____________ 日期:_____________
摘 要
随着无线传感网的日益广泛应用和物联网的产生与应用,信息融合技术已经逐渐融入到 社会生活当中,给人们生活带来了前所未有的便利。随着传感器数据来源越来越复杂,如何 全面、快速、准确的获取信息已成为研究热点,因此对信息融合方法的研究具有重要意义。 本文以多传感器的监测数据作为研究对象,从监测数据的时间和空间冗余性出发,利用 流数据模型构建了基于时间维的数据级信息融合模型和基于空间维的特征级信息融合模型, 提出了对应的信息融合方法,并将之应用于森林火灾监测系统中。具体研究内容如下: 为了更好的利用监测数据上下文的情景信息,提出了基于滑动窗口的信息融合模型,其 基本思想是利用窗口内连续数据序列的上下文情景信息,对属性在窗口内的变化进行估计, 并利用这种估计来表述属性的变化;同时利用同一属性不同窗口以及不同属性相同窗口的数 据序列之间存在的冗余信息,实现多传感器数据的关联和融合。 针对数 据级 的信 息融 合,提 出了 基于 时间 维的数 据级 信息 融合 算法 --DIFAT 算 法 (Data-Level Information Fusion Algorithm based on Time-Dimension),利用被监测对象自身存在 的变化规律,对窗口内数据序列进行时域和频域分析,建立被监测对象关于时间变化的模型, 并通过最优化方法给出被监测对象规律的最优估计。利用 Matlab 仿真工具,对该算法的有效 性进行了验证,结果表明该算法能有效地去除部分噪声,减少感知数据的不确定性,得到相 对可靠的对属性变化特性的估计。 针对特征级的信息融合,既考虑了同一属性不同传感器数据的融合,也考虑了不同属性 不同传感器的数据融合, 提出了基于空间维的特征级信息融合算法--FIFAS 算法(Feature-Level Information Fusion Algorithm based on Spatial-Dimension),通过数据关联、神经网络等方法确 定被监测属性之间的映射关系,并利用这种关系进行信息融合,确定被监测属性的状态。利 用 Matlab 仿真工具,对该算法的有效性进行了验证,结果表明该算法能很好的描述属性的真 实情况,对属性的原始的数据频域分布能做出合理的估计。 为了进一步验证所提出的算法的实用性,设计了各算法在森林火灾监测系统中的应用架 构,运用 DIFAT 算法和 FIFAS 算法给出森林火灾的预警等级。 关键字:信息融合,多传感器,时间维,空间维,滑动窗口,神经网络
Thesis Submitted to Nanjing University of Posts and Telecommunications for the Degree of Master of Engineering
By Liu Tao Supervisor: Prof. Li lingjuan February 2013
I
Abstract
With the increasingly widespread application of wireless sensor networks and the generation and application of the Internet of Things, information fusion technology has been gradually integrated into the social life, which brings unprecedented convenience to people's lives. With the more and more complicated of sensor data sources, how to obtain information comprehensively, rapidly and accurately has becomes a research focus. Therefore, the research of information fusion method has significant meaning. In this thesis, the monitoring data of multi-sensor is basic research object. By using the time and spatial redundant information of monitoring data, a data-level information fusion model based on time-dimension and a feature-level information fusion model based on spatial-dimension are built, and the corresponding information fusion methods is proposed and applied to forest fire monitoring system. The research contents are as follows: In order to make a better use of scene context information in the monitoring data, an information fusion model based on sliding window is proposed. The basic ideal of this model is estimating the change rule of attribute by using context information of continuous data sequence in window; using the estimate result to descript the change rule of the attribute, and associating and fusing multi-sensors data by using the redundant information between different windows of one attribute as well as that between the different attributes of the same window. For data-level information fusion, a Data-Level Information Fusion Algorithm based on Time-Dimension (DIFAT) is proposed. As the monitored object has its own change rules, after analyzing the time domain and frequency domain of data sequence in window, a model used to descript the change of monitored object is established. According to the model, optimization method gives the optimal estimation of rule of the monitored object. Matlab simulation tool is used to verify the validity of the algorithm, and the results show that the algorithm can effectively remove part of the noise, reduce uncertainty of perceptual data, and obtain reliable change rules of attributes. For feature-level information fusion, considering the multi-sensor data fusion of both one attribute and different attributes, a Feature-Level Information Fusion Algorithm based on Spatial-Dimension (FIFAS) is proposed. The FIFAS utilizes methods, such as data association and
南京邮电大学学位论文原创性声明
本人声明所呈交的学位论文是我个人在导师指导下进行的研究工作及取得 的研究成果。尽我所知,除了文中特别加以标注和致谢的地方外,论文中不包 含其他人已经发表或撰写过的研究成果,也不包含为获得南京邮电大学或其它 教育机构的学位或证书而使用过的材料。与我一同工作的同志对本研究所做的 任何贡献均已在论文中作了明确的说明并表示了谢意。 本人学位论文及涉及相关资料若有不实,愿意承担一切相关的法律责任。