著者

高津 和紀 高田 宗樹 平田 隆幸

出版者

福井大学大学院工学研究科

雑誌

福井大学大学院工学研究科研究報告 (ISSN:2433815X)

巻号頁・発行日

no.68, pp.1-11, 2020-03

---

Sota Fujii is a professional shogi player who has achieved renewal of historical records. As Fujii is a young man, his brain is in the growing stage. Therefore his ability of shogi is improving with his brain growth. Analysis using shogi AI characterizes the future of the player's shogi quantitatively. There is a possibility that we can detect the rapid growth of the young player by analyzing only a few games. In this study, Fujii's ability was evaluated by analysis of records of shogi using multiple shogi AI.

著者

小松 大起 黒岩 丈介 小高 知宏 諏訪 いずみ 白井 治彦

出版者

福井大学大学院工学研究科

雑誌

福井大学 学術研究院工学系部門 研究報告 = Memoir of Faculty of Engineering, University of Fukui

巻号頁・発行日

vol.70, pp.29-36, 2021-10

---

In this paper, we investigate how to apply deep learnings for multimodal inputs. The target problem is the prediction of power consumption, which enable us to control the operating time of each power plant in the short term and adapt the necessary amount of fossil fuels and other resources in the long term. In this paper, therefore, we perform the prediction of power consumption by using LSTM, which is a model that can handle time-series data. We employ the combination of temperature,precipitation and/or weather as multimodal inputs, which should be meteorological factors for the power consumption. The prediction is depend on the model structure and the combination of data.

著者

佐藤 謙太 小高 知宏 黒岩 丈介 白井 治彦

出版者

福井大学大学院工学研究科

雑誌

福井大学大学院工学研究科研究報告 (ISSN:18821871)

巻号頁・発行日

vol.62, pp.75-86, 2015-03

---

In this study,we investigate the correlation between stock price and Web data.In previous research, it had been reported that there are some relation between the tweets of Twitter.Analysis of the Web data has shown that it is useful for the prediction of stock price from the result. We examine whether approach of previous research is useful for Web data in Japan.We also researched the correlation between stock price and Web data.We applay the negative-positive analysis to news articles of domestic news site. We quantified the article of domestic news sites to negative or positive of the two types of value emotional value,and analyzed the relationship between stock price.From the experimental results, we found that there is a certain tendency but it is difficult to show the correlation using only negativepositive analysis.