Symmetrical Hierarchical Stochastic Searching on the Line in Informative and Deceptive Environments
Symmetrical Hierarchical Stochastic Searching on the Line in Informative and Deceptive Environments
复制标题
信息丰富和欺骗性环境中的对称分层随机搜索
DOI：
10.1109/tcyb.2016.2521859
复制
发表时间：
2017-03
影响因子：
11.8
通讯作者：
Zhou MengChu
中科院分区：
文献类型：
--
作者：
Zhang Junqi;Wang Yuheng;Wang Cheng;Zhou MengChu
A stochastic point location (SPL) problem aims to find a target parameter on a 1-D line by operating a controlled random walk and receiving information from a stochastic environment (SE). If the target parameter changes randomly, we call the parameter dynamic; otherwise static. SE can be 1) informative (<inline-formula> <tex-math notation="LaTeX">${p}{>}0.5$ </tex-math></inline-formula> where <inline-formula> <tex-math notation="LaTeX">${p}$ </tex-math></inline-formula> represents the probability for an environment providing a correct suggestion) and 2) deceptive (<inline-formula> <tex-math notation="LaTeX">${p} {<}0.5$ </tex-math></inline-formula>). Up till now, hierarchical stochastic searching on the line (HSSL) is the most efficient algorithms to catch static or dynamic parameter in an informative environment, but unable to locate the target parameter in a deceptive environment and to recognize an environment’s type (informative or deceptive). This paper presents a novel solution, named symmetrical HSSL, by extending an HSSL binary tree-based search structure to a symmetrical form. By means of this innovative way, the proposed learning mechanism is able to converge to a static or dynamic target parameter in the range of not only 0.618<xref rid="fn1" ref-type="fn"><sup>1</sup></xref> <inline-formula> <tex-math notation="LaTeX">${<}{p}{<}1$ </tex-math></inline-formula>, but also <inline-formula> <tex-math notation="LaTeX">$0 {<}{p} {<}0.382$ </tex-math></inline-formula>. Finally, the experimental results show that our scheme is efficient and feasible to solve the SPL problem in any SE.<fn id="fn1"><label><sup>1</sup></label><p>0.618 is an approximate value of the golden ratio conjugate <xref ref-type="bibr" rid="ref1">[1]</xref>.Yazidi <italic>et al.</italic> <xref ref-type="bibr" rid="ref2">[2]</xref> demonstrated that HSSL’s effective range must be greater than the value of golden ratio and they use 0.618 to substitute the value of golden ratio. Hereinafter, we also use quantity 0.618 to denote the conjugate of the golden ratio.
A stochastic point location (SPL) problem aims to find a target parameter on a 1-D line by operating a controlled random walk and receiving information from a stochastic environment (SE). If the target parameter changes randomly, we call the parameter dynamic; otherwise static. SE can be 1) informative (<inline-formula> <tex-math notation="LaTeX">${p}{>}0.5$ </tex-math></inline-formula> where <inline-formula> <tex-math notation="LaTeX">${p}$ </tex-math></inline-formula> represents the probability for an environment providing a correct suggestion) and 2) deceptive (<inline-formula> <tex-math notation="LaTeX">${p} {<}0.5$ </tex-math></inline-formula>). Up till now, hierarchical stochastic searching on the line (HSSL) is the most efficient algorithms to catch static or dynamic parameter in an informative environment, but unable to locate the target parameter in a deceptive environment and to recognize an environment’s type (informative or deceptive). This paper presents a novel solution, named symmetrical HSSL, by extending an HSSL binary tree-based search structure to a symmetrical form. By means of this innovative way, the proposed learning mechanism is able to converge to a static or dynamic target parameter in the range of not only 0.618<xref rid="fn1" ref-type="fn"><sup>1</sup></xref> <inline-formula> <tex-math notation="LaTeX">${<}{p}{<}1$ </tex-math></inline-formula>, but also <inline-formula> <tex-math notation="LaTeX">$0 {<}{p} {<}0.382$ </tex-math></inline-formula>. Finally, the experimental results show that our scheme is efficient and feasible to solve the SPL problem in any SE.<fn id="fn1"><label><sup>1</sup></label><p>0.618 is an approximate value of the golden ratio conjugate <xref ref-type="bibr" rid="ref1">[1]</xref>.Yazidi <italic>et al.</italic> <xref ref-type="bibr" rid="ref2">[2]</xref> demonstrated that HSSL’s effective range must be greater than the value of golden ratio and they use 0.618 to substitute the value of golden ratio. Hereinafter, we also use quantity 0.618 to denote the conjugate of the golden ratio.
登录
查看更多内容
基于协同过滤框架的高效蛋白质相互作用组图谱方法
影响因子：
4.6
作者：
Luo X;You Z;Zhou M;Li S;Leung H;Xia Y;Zhu Q
通讯作者：
Zhu Q
DOI：
10.1109/tsmca.2008.2010751
发表时间：
2009-03
期刊：
IEEE Trans. Syst. Man Cybern. Part A
影响因子：
--
作者：
Yuyue Du;Changjun Jiang;Mengchu Zhou
通讯作者：
Yuyue Du;Changjun Jiang;Mengchu Zhou
未知动态环境中的机会频谱访问：博弈论随机学习解决方案
影响因子：
10.4
作者：
Yuhua Xu;Jinlong Wang;Qihui Wu
通讯作者：
Qihui Wu
影响因子：
11.8
作者：
Junqi Zhang;Cheng Wang;Mengchu Zhou
通讯作者：
Junqi Zhang;Cheng Wang;Mengchu Zhou
DOI：
10.1109/tsmca.2007.902622
发表时间：
2007-09
期刊：
IEEE Transactions on Systems, Man, and Cybernetics - Part A: Systems and Humans
影响因子：
--
作者：
Yuyue Du;Changjun Jiang;Mengchu Zhou
通讯作者：
Yuyue Du;Changjun Jiang;Mengchu Zhou