Our Interests & Research Subjects



Research Subjects

Our laboratory is currently involved in the following 6 research subjects:
  1. Sequential data mining and event sequence corpus generation 
  2. WEB intelligence: Intelligent WEB browsing and semi-automatic learning of WEB keyword spices
  3. Autonomous distributed control of the traffic with a multi-agent  system
  4. Developing SMT solvers that enable correctness verification of Hardware/Software
  5. Developing an efficient algorithm for non-monotone dualization
  6. Developing a visualization tool to help discovering knowledge in bio-chemical networks
In Subject (4) and (5), we are collaborating with Prof. N. Tamura in Kobe University, who is the project leader of the 2008 - 2011 Grant-in-Aid for Scientific Research (A) (20240003). In Subject (6), we are collaborating with Prof. K. Inoue in National Institute of Informatics, who is the project leader of the 2008 - 2011 Grant-in-Aid for Scientific Research (A) "Inference-based Hypothesis-finding and its Application to Systems Biology" (20240016).























WEB Intelligence

We have studied techniques to intellectually utilize a huge amount of web contents, such as semi-automatic translating XML from HTML by means of the prior contents [ (referred) 2, 3, 4, 5] and automatic tracking preferred documents or extracting time subtractions in those documents [ (referred) 1]. 

Recently, we are involved in issues on semi-automatic constructing domain-specific search engines [ (oral) 1, 4], helping web search and integrating multiple information represented in different formalizations [ (oral) 3]. 

【Referred papers】

  1. M. Nakamura, K. Iwanuma and H. Nabeshima: Detecting Two Sorts of Correspondences between HTML Documents for Extracting Temporal Differences, Proceedings of the Third IASTED International Conference on Artficial Intelligence and Applications (AIA2003), pp.611-616, 2003.
  2. 梅原雅之、岩沼宏治、鍋島英知：事例に基づくシリーズ型HTML文書の意味論理 構造の自動認識、人工知能学会論文誌、Vol.17, No.6E, pp.690-698, 2002.
  3. M. Umehara, K.Iwanuma and H.Nabeshima: A Case-Based Recognition of Semantic Structures in HTML Documents (An Automated Transformation from HTML to XML). In: Proceedings of Third International Conference on Intelligent Data Engineering and Automated Learning (IDEAL 2002), Manchester UK, August 2002, Lecture Notes in Computer Science Vol.2412, pp.141-147, 2002.
  4. 梅原雅之、岩沼宏治、永井宏和： 事例に基づくHTML文書からXML文書への半自動変換 人工知能学会論文誌、Vol.16, No.5, pp.408-416, 2001. （第17回電気通信普及財団賞 テレコムシステム技術学生賞受賞）
  5. M.Umehara and K.Iwanuma: A Case-Based Transformation from HTML to XML. In: Proceedings of the Second International Conference on Intelligent Data Engineering and Automated Learning (IDEAL 2000), Lecture Notes in A Artificial Intelligence, Vol.1983, pp.410-415, 2000.

【Oral presentations】

  1. 宮川礼子，岩沼宏治，鍋島英知： 専門検索エンジンの半自動生成と目的とした類似度に基づくWEB学習データの精製，電子情報通信学会技術研究報告 AI2005-47～52，2006.
  2. 藤枝直樹，岩沼宏治，鍋島英知： WEB文書の頻出情報を利用した解答検索システムの構築，電子情報通信学会技術研究報告 AI2005-47～52，pp25～29，2006.
  3. 須田真行，岩沼宏治，鍋島英知： 専門語彙テンプレートの自動生成とWebページの自動統合，電子情報通信学会技術研究報告 NLC2005-117, Vol.105, No.595, pp.19-24, 2006.
  4. 鈴木悠生，鍋島英知，岩沼宏治：精錬手法に基づく検索隠し味型専門検索エンジンの半自動生成，第４回情報科学技術フォーラム，L-83，pp.190-202, 2005.

Sequential Data Mining

We study issues on data mining in order to automatically generate a corpus of time series events that occur frequently in a quite long sequence of documents like newspapers. 

【Referred paper】

  1. K. Iwanuma, R. Ishihara, Y. Takano and H. Nabeshima: Extracting Frequent Subsequences from a Single Long Data Sequence: A Novel Anti-Monotonic Measure and a Simple On-Line Algorithm. Proceedings of The Fifth IEEE International Conference on Data Mining (ICDM2005). pp.186-193, 2005.
  2. 石原龍一，岩沼宏治，鍋島英知：大規模データ系列中に頻出する部分系列のオンライン抽出アルゴリズム，第４回情報科学技術レターズ LF-002，pp.89-92，2005.
  3. 高野洋，岩沼宏治，鍋島英知：　単一の長大なデータ系列上の系列パターンの出現尺度とその逆単調性， 第３回情報科学技術レターズ, LF-012, pp.115-118, 2004. （第３回情報科学技術フォーラム(FIT2004)優秀論文賞受賞）

【Oral presentations】

  1. 丸山育嗣，岩沼宏治，鍋島英知： 緩和法に基づく時系列データ中からの頻出部分系列の高速マイニング，人工知能学会研究会資料 SIG-KBS-A504，pp.27-32，2006.
  2. 広瀬千夏，岩沼宏治，鍋島英知： 背景記事集合の類似度に基づく新聞記事のクラスタリング，電子情報通信学会技術研究報告 NLC2005-110, Vol.105, No.594, pp. 25-30, 2006.
  3. 大塚尚貴，岩沼宏治，鍋島英知： 系列パターンマイニングにおけるアイテム集合間の関連強度による頻出部分系列の絞込み，電子情報通信学会技術研究報告 AI2005-1～6，pp.21-26，2005.

Knowledge Discovery in Bio-Chemical networks


We study issues on knowledge discovery in biochemical networks with inference-based machine learning techniques. Biochemical networks describe the prior background knowledge on life-systems. Though information on those systems is rapidly increasing, it is still incomplete in the sense that there are several experimental results such that cannot be explained with respect to the background theory. We then aim at seeking relevant hypotheses that account for those unexplained observations. Recently, we are also interested in natural computation.

【Referred paper since 2009】
 
Please see the personal site of Yoshitaka Yamamoto

      【Referred paper until 2009】

        1. Yoshitaka Yamamoto, Katsumi Inoue and Andrei Doncescu. Integrating Abduction and Induction in Biological Inference using CF-Induction. Huma Lodhi and Stephen Muggleton (eds.), Elements of Computational Systems Biology, Wiley Book Series on Bioinformatics, pages 213-234, John Wiley and Sons, Inc., 2009.
        2. Yoshitaka Yamamoto, Katsumi Inoue and Andrei Doncescu. Inferring inhibition and pathway rules using CF-induction. Poster presentation at: the 6th Asia Pacific Bioinformatics Conference (APBC 2008), Japan, 2008.
        3. Yoshitaka Yamamoto, Katsumi Inoue and Andrei Doncescu. Estimation of possible reaction states in metabolic pathways using inductive logic programming. Proceedings of the 22nd International Conference on Advanced Information Networking and Applications (AINA 2008), pages 808-813. IEEE Computer Society, 2008.
        4. Andrei Doncescu, Katsumi Inoue and Yoshitaka Yamamoto. Knowledge- based discovery in systems biology using CF-induction. New Trends in Applied Artificial Intelligence: Proceedings of the 20th International Conference on Industrial, Engineering and Other Applications of Applied Intelligent Systems (IEA/AIE 2007), Lecture Notes in Artificial Intelligence, volume 4570, pages 395-404, Springer, 2007.
        5. Andrei Doncescu, Yoshitaka Yamamoto and Katsumi Inoue. Biological systems analysis using Inductive Logic Programming. Proceedings of the 21st International Conference on Advanced Information Networking and Applications (AINA 2007), pages 690-695, IEEE Computer Society, 2007.


          Comments