您的位置: 专家智库 > >

国家自然科学基金(61202111)

作品数:5 被引量:19H指数:2
相关作者:陶强刘莉更多>>
相关机构:上海大学山东商务职业学院鲁东大学更多>>
发文基金:国家自然科学基金山东省高等学校科技计划项目更多>>
相关领域:自动化与计算机技术更多>>

文献类型

  • 5篇中文期刊文章

领域

  • 5篇自动化与计算...

主题

  • 1篇数据集
  • 1篇水平集
  • 1篇图像
  • 1篇图像分割
  • 1篇图像分割方法
  • 1篇能量函数
  • 1篇曲率
  • 1篇鲁棒
  • 1篇模糊C-均值...
  • 1篇聚类
  • 1篇聚类算法
  • 1篇均值聚类
  • 1篇加速度
  • 1篇加速度计
  • 1篇MULTI-...
  • 1篇THINGS
  • 1篇TIME
  • 1篇TIME_D...
  • 1篇COLOR
  • 1篇CONTOU...

机构

  • 2篇鲁东大学
  • 2篇上海大学
  • 2篇山东商务职业...

作者

  • 2篇刘莉
  • 2篇陶强

传媒

  • 1篇电子测量技术
  • 1篇仪表技术
  • 1篇Journa...
  • 1篇IEEE/C...
  • 1篇Fronti...

年份

  • 1篇2019
  • 1篇2018
  • 3篇2016
5 条 记 录,以下是 1-5
排序方式:
Containment Control of Fractional Order Multi-Agent Systems With Time Delays被引量:6
2018年
In complex environments, many distributed multiagent systems are described with the fractional-order dynamics.In this paper, containment control of fractional-order multiagent systems with multiple leader agents are studied. Firstly,the collaborative control of fractional-order multi-agent systems(FOMAS) with multiple leaders is analyzed in a directed network without delays. Then, by using Laplace transform and frequency domain theorem, containment consensus of networked FOMAS with time delays is investigated in an undirected network, and a critical value of delays is obtained to ensure the containment consensus of FOMAS. Finally, numerical simulations are shown to verify the results.
Hongyong YangFuyong WangFujun Han
关键词:FRACTIONAL-ORDER
基于双区域演化水平集的图像分割方法被引量:11
2016年
针对图像由于光照不均引起的灰度不均匀导致图像精确分割困难的问题,提出了一种双区域水平集演化(DRE)方法用于图像分割。双区域水平集演化方法介绍了局部区域控制项和矩形的初始化轮廓,能够快速地分割灰度不均匀图像,加快曲线演化速率。为进一步消除噪声对图像的影响,分割方法采用高斯滤波算子和卷积计算,特别是提出的方法使用一种新的隐含的惩罚能量函数作为正则化项,该项嵌入到水平集演化公式里,增加了曲线演化梯度流的约束的条件,影响水平集演化曲线向双边扩展,这样提高了图像轮廓划分的计算效率和精度。通过实验结果对比,提出的水平集演化算法能够较好地划分图像轮廓,得到精确的图像分割结果。
陶强刘莉
关键词:图像分割曲率
Embedding Color Watermark Image into Color Host Image Based on Contourlet-Domain
2016年
A novel image blind watermarking scheme based on Contourlet transform was proposed to embed color watermark image into color host image,which was different from some existing works using the binary or gray-level image as watermark.In the process of embedding watermark,each color component of the color host image was decomposed by Contourlet transform.Then,the low-pass sub-band coefficients were divided to 4×4 non-overlapping blocks,and the coefficients in the selected block were quantified for embedding the watermark information.In the process of extraction watermark,the watermark could be extracted from the watermarked image without the help of the original host image or the original watermark image.Experimental results show that the proposed color image scheme has better invisibility and stronger robustness against most attacks such as image compression,filtering,adding noise,cropping,rotation,and scaling.
苏庆堂王刚张小峰吕高焕邓冠龙
关键词:CONTOURLET
The time model for event processing in internet of things被引量:1
2019年
The time management model for event processing in internet of things has a special and important requirement. Many events in real world applications are long-lasting events which have different time granularity with order or out-of-order. The temporal relationships among those events are often complex. An important issue of complex event processing is to extract patterns from event streams to support decision making in real-time. However, current time management model does not consider the unified solution about time granularity, time interval, time disorder, and the difference between workday calendar systems in different organizations. In this work, we analyze the preliminaries of temporal semantics of events. A tree-plan model of out-of-order durable events is proposed. A hybrid solution is correspondingly introduced. A case study is illustrated to explain the time constraints and the time optimization. Extensive experi? mental studies demonstrate the efficiency of our approach.
Chunjie ZHOUXiaoling WANGZhiwang ZHANGZhenxing ZHANGHaiping QU
关键词:TIMEEVENTTHINGSTIMEINTERVALTIMEDISORDER
一种鲁棒的聚类算法在加速度计数据集中的应用被引量:1
2016年
基于邻居搜索和模糊C均值方法,提出了一种新的鲁棒的聚类算法(NSFA)。该算法采用邻居搜索方法遍历相邻的数据,依据搜索距离确定聚类数目。NSFA方法引入内核函数,以提高其对噪声和异常点的鲁棒性。为了验证算法的鲁棒性,实验采用读取加速度计的数据,对比实验结果表明所提出的算法明显提高数据集的聚类性能,清晰划分加速度的变化趋势。
陶强刘莉
关键词:模糊C-均值聚类
共1页<1>
聚类工具0