Zobrazeno 1 - 10
of 327
pro vyhledávání: '"Keiki Takadama"'
Autor:
Iko Nakari, Keiki Takadama
Publikováno v:
IEEE Access, Vol 12, Pp 12001-12009 (2024)
This paper focuses on Sleep Apnea Syndrome (SAS) and proposes the novel eXplainable AI (XAI) method that extracts characteristics of SAS by comparing the datasets of the SAS patients and the non-SAS subjects. For this issue, this paper (i) employs
Externí odkaz:
https://doaj.org/article/00d2b782db8148f59bbc2c590d4bfeff
Publikováno v:
IEEE Access, Vol 11, Pp 20619-20634 (2023)
This work introduces the following concepts of directional and estimated directional Pareto front to encourage multi-objective decision making, especially when the Pareto front exists in limited regions in the objective space. The general output of m
Externí odkaz:
https://doaj.org/article/568626166a4747d8ad5b3b5dcb49fb42
Autor:
Fumito Uwano, Keiki Takadama
Publikováno v:
SICE Journal of Control, Measurement, and System Integration, Vol 12, Iss 5, Pp 199-208 (2019)
This paper proposes a multi-agent reinforcement learning method without communication toward dynamic environments, called profit minimizing reinforcement learning with oblivion of memory (PMRL-OM). PMRL-OM is extended from PMRL and defines a memory r
Externí odkaz:
https://doaj.org/article/1872bfb37c5346bdb359153f2767566c
Autor:
Takato Tatsumi, Keiki Takadama
Publikováno v:
SICE Journal of Control, Measurement, and System Integration, Vol 12, Iss 3, Pp 124-132 (2019)
In data mining, it is important to clarify how effective the acquired rules are and which elements are affected by rule evaluation. Extended learning classifier system (XCS) reveals factors that affect the classifier (rule) evaluation by generalizing
Externí odkaz:
https://doaj.org/article/7e7a74557b4c49a59e8d052f873cc41f
Publikováno v:
SICE Journal of Control, Measurement, and System Integration, Vol 12, Iss 1, Pp 1-10 (2019)
This paper focuses on the artificial bee colony (ABC) algorithm as one of swarm optimization methods and proposes ABC-alis (ABC algorithm based on adaptive local information sharing) by improving the ABC algorithm for dynamic optimization problems (D
Externí odkaz:
https://doaj.org/article/a33f2bda6d9e41eaaf261cb1e34d8bda
Publikováno v:
SICE Journal of Control, Measurement, and System Integration, Vol 11, Iss 5, Pp 409-418 (2018)
This paper focuses on the aircraft landing problem (ALP) and proposes an optimization method for ALP which addresses both the landing routes of multiple aircraft and their landing sequence. The difficulty of solving ALP is to optimize both the landin
Externí odkaz:
https://doaj.org/article/0ea9230b33b34a878fddb6ed8d2aba6f
Publikováno v:
SICE Journal of Control, Measurement, and System Integration, Vol 11, Iss 4, Pp 321-330 (2018)
This paper introduces a reinforcement learning technique with an internal reward for a multi-agent cooperation task. The proposed methods is an extension of Q-learning which changes the ordinary (external) reward to the internal reward for agent-coop
Externí odkaz:
https://doaj.org/article/90b15bed24254bf3b66759fceb83b646
Publikováno v:
SICE Journal of Control, Measurement, and System Integration, Vol 11, Iss 4, Pp 331-340 (2018)
This paper proposes a weighted opinion-sharing method called conformity-autonomous adaptive tuning (C-AAT) that enables agents to communicate and share correct information in a small-world network even when the links and information change dynamicall
Externí odkaz:
https://doaj.org/article/da8db549c63e411a9cd24c80aa685905
Autor:
Masaya Nakata, Keiki Takadama
Publikováno v:
SICE Journal of Control, Measurement, and System Integration, Vol 11, Iss 3, Pp 239-248 (2018)
An action map is one of the most fundamental options in designing a learning classifier system (LCS), which defines how LCSs cover a state action space in a problem. It still remains unclear which action map can be adequate to solve which type of pro
Externí odkaz:
https://doaj.org/article/d47a9f6a5503401cb6fcb81397620d1a
Publikováno v:
SICE Journal of Control, Measurement, and System Integration, Vol 11, Iss 2, Pp 105-112 (2018)
This paper focuses on how to reduce the cognitive loads of air traffic controllers while solving the airport landing problem (ALP), which is the optimization of both aircraft landing routes and sequences. A method is proposed for adaptively changing
Externí odkaz:
https://doaj.org/article/1004f1b8707b49faa109e2321d717620