Reconstruction of genetic networks is one of the key scientific challenges in functional genomics. This paper describes a novel approach for addressing the regulatory dependencies be-tween genes whose activities can b...Reconstruction of genetic networks is one of the key scientific challenges in functional genomics. This paper describes a novel approach for addressing the regulatory dependencies be-tween genes whose activities can be delayed by multiple units of time. The aim of the proposed ap-proach termed TdGRN (time-delayed gene regulatory networking) is to reversely engineer the dy-namic mechanisms of gene regulations, which is realized by identifying the time-delayed gene regu-lations through supervised decision-tree analysis of the newly designed time-delayed gene expres-sion matrix, derived from the original time-series microarray data. A permutation technique is used to determine the statistical classification threshold of a tree, from which a gene regulatory rule(s) is ex-tracted. The proposed TdGRN is a model-free approach that attempts to learn the underlying regula-tory rules without relying on any model assumptions. Compared with model-based approaches, it has several significant advantages: it requires neither any arbitrary threshold for discretization of gene transcriptional values nor the definition of the number of regulators (k). We have applied this novel method to the publicly available data for budding yeast cell cycling. The numerical results demonstrate that most of the identified time-delayed gene regulations have current biological knowledge supports.展开更多
Aim To find a more efficient learning method based on temporal difference learning for delayed reinforcement learning tasks. Methods A kind of Q learning algorithm based on truncated TD( λ ) with adaptive scheme...Aim To find a more efficient learning method based on temporal difference learning for delayed reinforcement learning tasks. Methods A kind of Q learning algorithm based on truncated TD( λ ) with adaptive schemes of λ value selection addressed to absorbing Markov decision processes was presented and implemented on computers. Results and Conclusion Simulations on the shortest path searching problems show that using adaptive λ in the Q learning based on TTD( λ ) can speed up its convergence.展开更多
Multiple earth observing satellites need to communicate with each other to observe plenty of targets on the Earth together. The factors, such as external interference, result in satellite information interaction delay...Multiple earth observing satellites need to communicate with each other to observe plenty of targets on the Earth together. The factors, such as external interference, result in satellite information interaction delays, which is unable to ensure the integrity and timeliness of the information on decision making for satellites. And the optimization of the planning result is affected. Therefore, the effect of communication delay is considered during the multi-satel ite coordinating process. For this problem, firstly, a distributed cooperative optimization problem for multiple satellites in the delayed communication environment is formulized. Secondly, based on both the analysis of the temporal sequence of tasks in a single satellite and the dynamically decoupled characteristics of the multi-satellite system, the environment information of multi-satellite distributed cooperative optimization is constructed on the basis of the directed acyclic graph（DAG）. Then, both a cooperative optimization decision making framework and a model are built according to the decentralized partial observable Markov decision process（DEC-POMDP）. After that, a satellite coordinating strategy aimed at different conditions of communication delay is mainly analyzed, and a unified processing strategy on communication delay is designed. An approximate cooperative optimization algorithm based on simulated annealing is proposed. Finally, the effectiveness and robustness of the method presented in this paper are verified via the simulation.展开更多
基金supported in part by the National High Tech Development Project of China,the 863 Program(Grant No.2003AA2Z2051)the National Natural Science Foundation of China(Grant Nos.30170515,30370798,30571034&30570424)+1 种基金Heilongjiang Province Science and Technology Key Project(Grant Nos.F0177&1055HG009)the 211 Project,the Tenth"Five-year"Plan,Harbin Medical University.
文摘Reconstruction of genetic networks is one of the key scientific challenges in functional genomics. This paper describes a novel approach for addressing the regulatory dependencies be-tween genes whose activities can be delayed by multiple units of time. The aim of the proposed ap-proach termed TdGRN (time-delayed gene regulatory networking) is to reversely engineer the dy-namic mechanisms of gene regulations, which is realized by identifying the time-delayed gene regu-lations through supervised decision-tree analysis of the newly designed time-delayed gene expres-sion matrix, derived from the original time-series microarray data. A permutation technique is used to determine the statistical classification threshold of a tree, from which a gene regulatory rule(s) is ex-tracted. The proposed TdGRN is a model-free approach that attempts to learn the underlying regula-tory rules without relying on any model assumptions. Compared with model-based approaches, it has several significant advantages: it requires neither any arbitrary threshold for discretization of gene transcriptional values nor the definition of the number of regulators (k). We have applied this novel method to the publicly available data for budding yeast cell cycling. The numerical results demonstrate that most of the identified time-delayed gene regulations have current biological knowledge supports.
文摘Aim To find a more efficient learning method based on temporal difference learning for delayed reinforcement learning tasks. Methods A kind of Q learning algorithm based on truncated TD( λ ) with adaptive schemes of λ value selection addressed to absorbing Markov decision processes was presented and implemented on computers. Results and Conclusion Simulations on the shortest path searching problems show that using adaptive λ in the Q learning based on TTD( λ ) can speed up its convergence.
基金supported by the National Science Foundation for Young Scholars of China(6130123471401175)
文摘Multiple earth observing satellites need to communicate with each other to observe plenty of targets on the Earth together. The factors, such as external interference, result in satellite information interaction delays, which is unable to ensure the integrity and timeliness of the information on decision making for satellites. And the optimization of the planning result is affected. Therefore, the effect of communication delay is considered during the multi-satel ite coordinating process. For this problem, firstly, a distributed cooperative optimization problem for multiple satellites in the delayed communication environment is formulized. Secondly, based on both the analysis of the temporal sequence of tasks in a single satellite and the dynamically decoupled characteristics of the multi-satellite system, the environment information of multi-satellite distributed cooperative optimization is constructed on the basis of the directed acyclic graph（DAG）. Then, both a cooperative optimization decision making framework and a model are built according to the decentralized partial observable Markov decision process（DEC-POMDP）. After that, a satellite coordinating strategy aimed at different conditions of communication delay is mainly analyzed, and a unified processing strategy on communication delay is designed. An approximate cooperative optimization algorithm based on simulated annealing is proposed. Finally, the effectiveness and robustness of the method presented in this paper are verified via the simulation.
