Abstract

Data mining and big data analysis

We study fast and memory-efficient algorithms for pattern mining in transactional data streams.

Online processing for data mining

References

  1. T. Phungtua-eng, Y. Yamamoto, and S. Sako:
    Elastic Data Binning for Transient Pattern Analysis in Time-Domain Astrophysics. Proc of SIGSAC'23 (2023)
  2. Yoshitaka Yamamoto, Yasuo Tabei, Koji Iwanuma:
    Approximate-Closed-Itemset Mining for Streaming Data Under Resource Constraint, (2019)
  3. Yoshitaka Yamamoto, Koji Iwanuma, Shoshi Fukuda: “Resource-oriented approximation for frequent itemset mining from brusty data streams”, Proceeding of 2014 ACM SIGMOD International Conference on Management of Data (SIGMOD’14), pp. 205-216 (Utah), 2014.6

Funding

2021 - 2024: JSPS Grant-in-Aid for Scientific Research (A),
``Survey of the Universe changing on sec time scale by wide-field, high-cadence photometry and anomaly detection'' (Shigeyuki Sako)

2014 - 2018: JST PRESTO Research,
``Resource-oriented Approach for Extracting Deep Knowledge from Big Data Streams''
(In Advanced Core Techniques for Big Data Integration)

Data sketching and sequence prediction

We study lossy compression techniques for high-dimensional streaming data, called ``data sketching’’. These techniques are applicable for non-parametric prediction and learning in nature big data.

Condensed representation for massive data

Funding

2020 - 2022: JSPS Grant-in-Aid for Scientific Research (C),
``Sublinear Algorithms for Summarizing Streaming Big Data'' (Yoshitaka Yamamoto)

Hypothesis finding by inference

We study inductive learning along with background theory in AI. It is useful to infer a ``hypothesis’’ from new observations.Our proposed learning system, called CF-induction, is applied to systems biology in order to logically complete missing links in molecular networks.

Hypothesis finding in systems biology

References

  1. Yoshitaka Yamamoto, Katsumi Inoue and Koji Iwanuma:
    Inverse subsumption for complete explanatory induction,
    Journal of Machine Learning 86/1 115-139 （2011）
  2. Yoshitaka Yamamoto, Adrien Rougny, Hidetomo Nabeshima, Katsumi Inoue, Hisao Moriya, Christine Froidevaux, Koji Iwanuma:
    Completing SBGN-AF networks by logic-based hypothesis finding,
    Proceedings of the 1st International Conference on Formal Methods in Macro-Biology (FMMB2014), pp. 165-179 （2014）

Funding

2022 - 2023: JSPS Grant-in-Aid for Challenging Research (Exploratory),
``Cellar differentiation on the electronic semiconductor device induced by the electric stimulation'' (Jun Kano)

2013 - 2015: JSPS Grant-in-Aid for Young Scientists (B), ``Hypothesis-Finding based on Inverse Subsumption and its Applications to Systems Biology'' (Representative)
2014 - 2015: Strategic Collaborative Research Project with National Institute of Informatics (NII, Japan), ``Analyzing GPCRs with Inference in Molecular Networks'' (Representative)