http://chineseinput.net/에서 pinyin(병음)방식으로 중국어를 변환할 수 있습니다.
변환된 중국어를 복사하여 사용하시면 됩니다.
Consensus Building using Deep Reinforcement Learning for Energy Management
Yuya Tarutani,Isato Oishi,Yukinobu Fukushima,Tokumi Yokohira 대한전자공학회 2022 IEIE Transactions on Smart Processing & Computing Vol.11 No.4
A variety of information is collected from IoT devices. As those devices become more familiar to users, network services must consider the influence of the user. We propose a method to maximize the value from power consumption and minimize the cost incurred to ensure user satisfaction. However, one problem is that user satisfaction cannot increase because it is considered a constraint on power consumption. In this paper, we propose a consensus building method to minimize power consumption and maximize user satisfaction. An exhaustive search incurs a large calculation overhead to determine device parameters. Thus, the proposed method uses reinforcement learning to solve this problem. From its evaluation, we clarify that the proposed method attains about 1.5 times the total reward compared with the conventional method. Moreover, we also clarify that 99.9% of the total reward can be achieved, compared to the exhaustive search.
Modification of Enigmail to Use Unique Cryptographic Algorithms in Email
Ryotaro Tani,Yukinobu Fukushima,Yuya Tarutani 대한전자공학회 2021 IEIE Transactions on Smart Processing & Computing Vol.10 No.5
In this paper, we modify an email client so that it can use unique cryptographic algorithms instead of general cryptographic algorithms for improved security. We use Thunderbird as an email client and modify Enigmail, which is an extension for Thunderbird, to use cryptographic algorithms implemented in GNU Privacy Guard (GnuPG). To achieve this goal, we first dynamically analyze the source code of Enigmail and identify the parts related to processing with GnuPG. Then, we modify the identified parts so that Enigmail can use unique cryptographic algorithms, which are assumed to be implemented in GnuPG. The experimental evaluation confirms that the modified Enigmail securely exchanges email messages using pseudo-unique cryptographic algorithms, and confirms that the processing overhead of the modified Enigmail is negligibly small.
Yukinobu Fukushima,Yuta Sagawa,Yuya Tarutani,Tokumi Yokohira 대한전자공학회 2024 IEIE Transactions on Smart Processing & Computing Vol.13 No.2
In this paper, we tackle a virtual network embedding problem in network virtualization. For this problem, an algorithm (VNE-TD) based on temporal difference learning has been proposed. VNE-TD, however, does not consider the node and link resource constraints in selecting the candidate solutions. Therefore, when attempting to construct a virtual network, the embedding of a virtual network may fail due to insufficient resources. In this paper, we modify VNE-TD to select only those candidate solutions that satisfy the node and link resource constraints. We add a function to check the satisfiability of the node and link resource constraints to VNE-TD. The simulation results show that our modified methods reduce the blocking ratio of virtual network requests by up to 80% compared to VNE-TD.