著者

平田 貴臣 呉本 尭 大林 正直 間普 真吾 小林 邦和

出版者

一般社団法人 電気学会

雑誌

電気学会論文誌C(電子・情報・システム部門誌) (ISSN:03854221)

巻号頁・発行日

vol.136, no.3, pp.348-356, 2016-03-01 (Released:2016-03-01)

参考文献数

16

被引用文献数

2

---

Since 1970s, linear models such as autoregressive (AR), moving average (MA), autoregressive integrated moving average (ARIMA), etc. have been popular for time series data analyze and prediction. Meanwhile, artificial neural networks (ANNs), inspired by connectionism bio-informatics, have been showing their powerful abilities of function approximation, pattern recognition, dimensionality reduction, and so on since 1980s. Recently, deep belief nets (DBNs) which use multiple restricted Boltzmann machines (RBMs) and multi-layered perceptron (MLP) are proposed as time series predictors. In this study, a hybrid prediction method using DBNs and ARIMA is proposed. The effectiveness of the proposed method was confirmed by the experiments using CATS benchmark data and chaotic time series data.

著者

村上 佳菜子 橋本 典明 木戸 尚治 平野 靖 間普 真吾 近藤 堅司 小澤 順

出版者

人工知能学会

雑誌

2018年度人工知能学会全国大会(第32回)

巻号頁・発行日

2018-04-12

---

近年,Deep Learningを用いた医用画像の解析の手法が多く提案されており,その中でも画像認識に優れているCNNが用いられることが多い.CNNを用いてびまん性肺疾患を識別する際,陰影ごとに関心領域を切り出す必要がある.しかし,びまん性肺疾患の診断においては識別とともに検出が重要である.そこで本研究では,関心領域を設定せず,CT画像からびまん性肺疾患の領域を検出・抽出する方法を提案する.本研究では,U-NetとFCNを用いて6つの陰影パターンの領域抽出を試み,CNNと比較した.

著者

間普 真吾 平澤 宏太郎 古月 敬之

出版者

一般社団法人 電気学会

雑誌

電気学会論文誌C(電子・情報・システム部門誌) (ISSN:03854221)

巻号頁・発行日

vol.127, no.7, pp.1061-1067, 2007-07-01 (Released:2007-09-01)

参考文献数

15

被引用文献数

8 7

---

Genetic Network Programming (GNP) is an evolutionary computation which represents its solutions using graph structures. Since GNP can create quite compact programs and has an implicit memory function, it has been clarified that GNP works well especially in dynamic environments. In addition, a study on creating trading rules on stock markets using GNP with Importance Index (GNP-IMX) has been done. IMX is a new element which is a criterion for decision making. In this paper, we combined GNP-IMX with Actor-Critic (GNP-IMX&AC) and create trading rules on stock markets. Evolution-based methods evolve their programs after enough period of time because they must calculate fitness values, however reinforcement learning can change programs during the period, therefore the trading rules can be created efficiently. In the simulation, the proposed method is trained using the stock prices of 10 brands in 2002 and 2003. Then the generalization ability is tested using the stock prices in 2004. The simulation results show that the proposed method can obtain larger profits than GNP-IMX without AC and Buy&Hold.

著者

嶋田 香 間普 真吾 森川 英治 平澤 宏太郎 古月 敬之

出版者

The Institute of Electrical Engineers of Japan

雑誌

電気学会論文誌. C, 電子・情報・システム部門誌 = The transactions of the Institute of Electrical Engineers of Japan. C, A publication of Electronics, Information and System Society (ISSN:03854221)

巻号頁・発行日

vol.128, no.5, pp.795-803, 2008-05-01

被引用文献数

2 1

---

A method of class association rule mining from incomplete databases is proposed using Genetic Network Programming (GNP). GNP is one of the evolutionary optimization techniques, which uses the directed graph structure. An incomplete database includes missing data in some tuples, however, the proposed method can extract important rules using these tuples, and users can define the conditions of important rules flexibly. Generally, it is not easy for Aprior-like methods to extract important rules from incomplete database, so we have estimated the performances of the rule extraction and classification of the proposed method using incomplete data set. The results showed that the accuracy of classification of the proposed method is favorable even if some tuples include missing data.