https://kyushu-u.elsevierpure.com/en/persons/einoshin-suzuki
　Reseacher Profiling Tool　Kyushu University Pure

http://www.i.kyushu-u.ac.jp/~suzuki/
Professor Einoshin Suzuki (Data Mining, Machine Learning, Discovery Robot) .

Doctor of Engineering

No

Data Mining, Machine Learning, Discovery Robot, Knowledge Discovery

00years03months

I have been working on research including data mining, machine learning, and discovery robots.
My efficient discovery of exception rules with their corresponding normal rules is recognized as a pioneering piece of work. From 2001 to 2005, I was heading a team in Scientific Research on Priority Area “Data Mining” sponsored by MEXT and contributed to its success in various ways, especially through medical mining research. I was honored PRICAI 2021 Best Paper Award, VISAPPP 2020 Best Poster Award, and twice the best paper prize of JSAI. I have served to many international conferences including the Workshops Chair of ICDM-2002 and the PC Vice Chair of ICDM-2004.

Research Interests

• Anomalous/Exceptional Pattern Mining with Weak Label Information from Stream Data
  keyword : Anomaly/Exception Discovery, Stream Data Mining, Weak Label Learning, Patern Mining
  2018.04.
• Detection of Peculiar Facial Expression of Unspecified Persons Based on Sparse Coding
  keyword : Outlier detection, Human monitoring
  2015.04.
• Long-Term Monitoring by a Consumer Autonomous Mobile Robot
  keyword : Representative Example Selection, Autonomous Mobile Robot
  2012.04.
• Data Stream Management by Autonomous Mobile Robots
  keyword : Autonomous Mobile Robot, Data Mining, Database
  2011.03.
• Knowledge Discovery from a Huge Data Ensemble by Integrating Automatic Data Selection and Pattern Extraction
  keyword : Big Data, Data Mining
  2013.04.
• Multi-task data mining based on dynamic representation bias
  keyword : constructive induction, multi-task data mining
  2008.04Multi-task data mining based on dynamic representation bias.
• Structured data mining system that considers mutual interaction of structured rules
  keyword : data mining
  2006.04Structured data mining system that considers mutual interaction of structured rules.
• Integrating Symbolic Discovery with Numerical Machine Learning for Autonomous Swarm Control
  keyword : controlling swarm robots, machine learning, data mining
  2008.04～2012.09Integrating Symbolic Discovery with Numerical Machine Learning for Autonomous Swarm Control.

Current and Past Project

• Grants-in-Aid for Challenging Research (Exploratory)
• Grant-in-Aid for Scientific Research (B)
• Kaken Challenging Exploratory Research
• Grant-in-Aid for Scientific Research (B)
• Data Stream Management by Autonomous Mobile Robots
• Kaken Challenging Exploratory Research
• Grant-in-Aid for Scientific Research (B)
• Integrating Symbolic Discovery with Numerical Machine Learning for Autonomous Swarm Control

Academic Activities
Membership in Academic Society

• Japanese Society for Artificial Intelligence
• Information Processing Society of Japan
• AAAI

Awards

• GIAD: Generative Inpainting-Based Anomaly Detection via Self-Supervised Learning for Human Monitoring
• Detecting Anomalous Regions from an Image Based on Deep Captioning
• Worst-case Analysis of Rule Discovery Based on Generality and Accuracy
• Discovery of Exception Rules Based on the Reliability Evaluation
• Exceptional Knowledge Discovery in Databases Based on an Information-theoretic Approach
• Discovery System for Exception Knowledge Based on a Stochastic Confidence Evaluation Method

Educational Activities
Other Educational Activities

• 2006.12, Committee Member of Ph.D. thesis examination of Ms Marie Agier, University of Clermont-Ferrand 2, France.