考虑切换损失的多目标搜索策略

谌达; 胡波; 冯辉

Chinese

您当前的位置：

首页 >

文章列表页 >

考虑切换损失的多目标搜索策略

更新时间：2026-09-04

- 考虑切换损失的多目标搜索策略
- Multi-target search with switching cost
- 微电子学与计算机 2019年36卷第11期页码：89-94
- 作者机构：
  
  复旦大学信息科学与工程学院智慧网络与系统研究中心,上海,200433
- 作者简介：
- 基金信息：
  
  国家重点研发计划 213
- DOI：
  中图分类号：
- 纸质出版：2019
- 稿件说明：
移动端阅览
谌达, 胡波, 冯辉. 考虑切换损失的多目标搜索策略[J]. 微电子学与计算机, 2019, 36(11): 89-94.

CHEN Da, HU Bo, FENG Hui. Multi-target search with switching cost[J]. 2019, 36(11): 89-94.
谌达, 胡波, 冯辉. 考虑切换损失的多目标搜索策略[J]. 微电子学与计算机, 2019, 36(11): 89-94. DOI：

CHEN Da, HU Bo, FENG Hui. Multi-target search with switching cost[J]. 2019, 36(11): 89-94. DOI：

摘要

考虑在固定区域内进行多目标搜索的问题

搜索策略的性能不仅与观测次数、判决正确率有关

也会受切换观测区域时切换损失的影响.对此提出一种基于主动假设检验模型的多目标搜索策略

它能帮助决策者在很少的切换开销下快速找到所有目标.理论证明了所提策略可渐进最小化搜索的贝叶斯风险

且仿真表明在有限时间内

其性能也优于其他的对比算法.该策略可扩展至异常检测、欺诈扫描等多个应用领域.

Abstract

The problem that detecting multiple targets among a finite number of regions is considered. The performance of the search strategy is not only related to the number of observations and the detection error

but also costs associated with switching across regions. We propose a multi-target search strategy based on the active hypothesis testing

which can help decision makers find all targets quickly with little switching cost. Its proved that the policy is asymptotically optimal. Meanwhile

which offers better performance in finite regime by simulations. Our policy can also be applied to anomaly detection

fraud detection and other read-world scenarios.

关键词

Keywords

references

CHERNOFF H. Sequential design of experiments[J]. The Annals of Mathematical Statistics, 1959, 30(3): 755-770. DOI: 755

ABRAHAM W. Sequential analysis[M]. Courier Corporation, 1973.

CASTANON, DAVID A. Optimal search strategies in dynamic hypothesis testing[J]. IEEE transactions on systems, man, and cybernetics, 1995, 25(7): 1130-1138. DOI: 1130

HUANG B, COHEN K, ZHAO Q. Active anomaly detection in heterogeneous processes[C]// 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). Calgary, Alberta, Canada, 2018.

VAIDHIYAN N K, SUNDARESAN R. Active search with a cost for switching actions[C]// IEEE Information Theory and Applications Workshop (ITA). San Diego, California, USA, 2015: 17-24.

COHEN K, ZHAO Q. Active hypothesis testing for anomaly detection[J]. IEEE Transactions on Information Theory, 2015, 61(3): 1432-1450. DOI: 1432

NAGHSHVAR M, JAVIDI T. Sequentiality and adaptivity gains in active hypothesis testing[J]. IEEE J. Sel. Topics Signal Processing, 2013, 7(5): 768-782. DOI: 768

BESSLER S A. Theory and applications of the sequential design of experiments, k-actions and infinitely many experiments. part i. theory[R]. Stanford University Center for Applied Mathematics and Statistics Labs, 1960.

KASPI Y, SHAYEVITZ O, JAVIDI T. Searching with measurement dependent noise[J]. IEEE Transactions on Information Theory, 2018, 64(4): 2690-2705. DOI: 2690

NAGHSHVAR M, JAVIDI T. Active sequential hypothesis testing[J]. The Annals of Statistics, 2013, 41(6): 2703-2738. DOI: 2703

WANG C, ZHAO Q, COHEN K. Dynamic search on a tree with information-directed random walk[C]// IEEE 19th International Workshop on Signal Processing Advances in Wireless Communications (SPAWC). Kalamata, Greece, 2018: 1-5.

浏览量

下载量

CSCD

文章被引用时，请邮件提醒。

提交

工具集

关联资源

一种用于极低压boost系统的高效率电荷泵

基于反向体偏置的高增益稳定性高温运放设计

基于区块链的AI生成内容溯源框架设计研究

低功耗设计的双链电源关断策略的实现与验证

AlN/GaN混合缓冲层双异质结p-GaN HEMT直流特性仿真