DSpace Collection: 2021-06-012021-06-01http://hdl.handle.net/10928/14292022-01-18T10:36:31Z2022-01-18T10:36:31Z分枝限定法とDeep Learningを組み合わせた並列タスクスケジューリング解法の開発小納, 惇平甲斐, 宗徳http://hdl.handle.net/10928/14312021-10-18T16:30:07Z2021-05-31T15:00:00ZTitle: 分枝限定法とDeep Learningを組み合わせた並列タスクスケジューリング解法の開発
Authors: 小納, 惇平; 甲斐, 宗徳
Abstract: Since the task scheduling problem belongs to the strong NP-hard combinatorial optimization problem, the search time for the optimum solution becomes enormous due to the increase in the scale of the problem. Deep Learning can be applied to this difficult problem. Deep Learning has the advantage that the required time to find a solution is short once learning is completed, but it has the disadvantage that the optimum solution is not always found. Therefore, in this paper, we prototype and evaluate a method for speeding up to find the optimal solution by scheduling that combines the search method based on branch-and-bound method and deep learning.2021-05-31T15:00:00Z抗がん剤投与による酸化ストレス由来細胞死誘導能の調査深澤, 真実井内, 勝哉久富, 寿http://hdl.handle.net/10928/14322021-10-18T16:30:07Z2021-05-31T15:00:00ZTitle: 抗がん剤投与による酸化ストレス由来細胞死誘導能の調査
Authors: 深澤, 真実; 井内, 勝哉; 久富, 寿2021-05-31T15:00:00ZDeep Learningを用いた階層的な部分タスクグラフ検出法の構築田邑, 大雅甲斐, 宗徳http://hdl.handle.net/10928/14332021-10-18T16:30:07Z2021-05-31T15:00:00ZTitle: Deep Learningを用いた階層的な部分タスクグラフ検出法の構築
Authors: 田邑, 大雅; 甲斐, 宗徳
Abstract: Since task scheduling problems belong to a class of the strong NP-hard combinatorial optimization problem, the required scheduling time increases exponentially as the number of tasks increases. Therefore, we find some small subtask graphs that can be optimally scheduled in the overall task graph, and solve them individually as a scheduling problem. Then, each subtask graph can be treated as one macro task in the whole task graph. This reduces the apparent number of tasks in the overall task graph, reduces the scale of the task graph, and significantly reduces the search time that depends on the number of tasks. We call this hierarchical scheduling. However, this partial task graph detection has a drawback that it becomes a combinatorial optimization problem by itself. Therefore, in this paper, we construct and evaluate a method for detecting partial task graphs using deep learning.2021-05-31T15:00:00Z分子系統樹によるスハマソウ属(Hepatica)の進化史の推定前田, 修佑大野, 好弘佐藤, 尚衛芳賀, 明日香清水, あやか井内, 勝哉久富, 寿http://hdl.handle.net/10928/14302021-10-18T16:30:07Z2021-05-31T15:00:00ZTitle: 分子系統樹によるスハマソウ属(Hepatica)の進化史の推定
Authors: 前田, 修佑; 大野, 好弘; 佐藤, 尚衛; 芳賀, 明日香; 清水, あやか; 井内, 勝哉; 久富, 寿
Abstract: There are 18 species of Hepatica in the world, there are 6 species of Hepatica in Japan. In the present study, to characterize variation in the chloroplast gene of Hepatica from various locations, we examined nucleotide sequences of the chloroplast from matK gene to psbA gene. We performed PCR of chloroplast gene using 18 specimens of Hepatica and compared the result from around the world using a neighbor jointing tree. Molecular phylogenetic tree of Hepatica from around the world revealed that all species of Hepatica in Japan belonged to a different group from Hepatica in Europe, China and Korea. Molecular phylogenetic trees showed that that Hepatica in Japan had the closest relationship with Hepatica in America. All scientific names of Hepatica in Japan are treated as subspecies of H. nobilis in Europe (e.g. H. nobilis var. japonica f. variegata). In this study, the molecular phylogenetic tree suggests that 6 species of Hepatica in Japan are unlikely to be subspecies of H. nobilis in Europe.2021-05-31T15:00:00Z