Tetsuji Goto
| Faculty of Health and Medical Science,Department of Medical Course,Medical Engineering Course | Professor |
| Graduate School of Information Sciences,Major of Information Sciences | Professor |
Last Updated :2025/10/07
■Researcher basic information
Degree
Field Of Study
■Career
Career
■Research activity information
Paper
- Elucidation of the Linguistic Characteristics of Mild Cognitive Impairment Person by Visualizing the Inside of Neural Network
Goto, T.
Transactions of Japanese Society for Medical and Biological Engineering, Jun. 2025, [Reviewed] - A hierarchical neural network model for Japanese toward detecting mild cognitive impairment
Tetsuji Goto
Electronics and Communications in Japan, 21 Aug. 2023, [Reviewed]
Abstract
We found that some signs of mild cognitive impairment (MCI) might be presented in a structure of a sentence and a relation between sentences talked by a man, and develop a neural network model which has an analogy with the hierarchical structure of speakers, topics, sentences and words in Japanese. We build our model based on 2‐layered bi‐directional LSTM, corresponding to words‐sentences and sentences‐topics hierarchy. As a layer corresponding to speakers, we use a linear classifier with self‐attention. The test result shows a largely improved AUC, compared with another test by using the normal 2‐layered bi‐directional LSTM with TBPTT. The result also indicates that there are some characteristic patterns in a talk by an elderly person with MCI. We classify the character vectors of topics generated from our model through learning into clusters whose number is 1/10 of the number of persons in our data. Since these clusters have almost less than 10% or more than 90% rate of positive share, we conclude that we can develop a screening method based on a talk in Japanese by an elderly person in the near future. - Design of a Curriculum Covering Mathematics, Data Science and AI for a Course of Medical Science or Clinical Engineering
Tetsuji GOTO; Masazumi HAYASHI; Akihiro SUZUKI; Norihiro FUJII
Journal of Teikyo Heisei University, Mar. 2023 - A Study on Dynamic Epistemic Logic and its Application to the Precedents of Criminal Law
Tetsuji GOTO
doctoral thesis, Mar. 2019 - Dynamic Epistemic Reasoning with Awareness and Its Legal Application
Tetsuji Goto; Ryo Hatano; Satoshi Tojo
Vietnam Journal of Computer Science, 25 Feb. 2019, [Reviewed]
Concerning a software tool of legal reasoning, it is important to describe the prediction about the result of a criminal action, because a crime is often caused by the unpredictability of the result of the defendant. In the court, the judge needs to investigate the predictability and the intention of the agent. Previously, we have formalized the reasoning process of judgment by action model in dynamic epistemic logic (DEL) and have attempted to describe the precedents. However, the prediction in legal cases depends not only on the states of knowledge but also on the limited degree of attention by agents. In this paper, we employ DEL with awareness for multi-agent to represent the predictability and model the typical criminal precedents. We propose a revised semantics of action model with awareness which can define each basic action model to reproduce the agent’s considering process. To describe the legal reasoning we introduce an extension of modeling program DEMO to include the awareness (we call it DEMO[Formula: see text]) and present a GUI in this extended program to calculate the updated epistemic model easily and to classify precedents according to the degree of prediction. In the end, we calculate the epistemic models of typical criminal precedents by this newly developed tool and estimate them. - DYNAMIC EPISTEMIC REASONING SYSTEM WITH AWARENESS (DEMO+A) AND ITS LEGAL APPLICATION
Tetsuji Goto; Ryo Hatano; Satoshi Tojo
Big Data Analytics, Data Mining and Computational Intelligence, Jul. 2018, [Reviewed] - Modeling Predictability of Agent in Legal Cases
Tetsuji Goto; Katsuhiko Sano; Satoshi Tojo
2016 IEEE International Conference on Agents (ICA), Sep. 2016, [Reviewed] - Classification of Precedents by Modeling Tool for Action and Epistemic State: DEMO
Tetsuji Goto; Satoshi Tojo
Lecture Notes in Computer Science: New Frontiers in Artificial Intelligence, 25 Aug. 2015, [Reviewed] - Observation of boiling structures in high heat-flux boiling
Shigefumi Nishio; Tetsushi Gotoh; Niroh Nagai
International Journal of Heat and Mass Transfer, Nov. 1998, [Reviewed] - Boiling Structure in Quasi-Two-Dimensional Space. High-Heat-Flux Nucleate Boiling under Natural Convection Condition.
Shigefumi NISHIO; Tetsusi GOTOH; Niroh NAGAI
TRANSACTIONS OF THE JAPAN SOCIETY OF MECHANICAL ENGINEERS Series B, 1997, [Reviewed]
MISC
- Analysis of emotional movement of MCI person by NLP
Yuto SUZUKI; Yuko AKIYAMA; Tetsuji GOTO
09 Nov. 2024
Corresponding - Neural Network Model Corresponding to The Hierachical Structure of Japanese Sentences for MCI Screening
Tetsuji GOTO
Sep. 2022
Lead - DEMO+A: Epistemic Reasoning System with Awareness and its Legal Application
Tetsuji GOTO; Ryo HATANO; Satoshi TOJO
The 11th International Workshop on Juris-informatics, 14 Nov. 2017, [Reviewed]
Lead - Predictability of Agent in Legal Cases
Tetsuji GOTO; Satoshi TOJO
Proceedings of the 9th International Workshop on Juris-Informatics, Nov. 2015, [Reviewed]
Lead - Classification of precedents by modeling tool for action and epistemic state: Demo
Tetsuji GOTO; Satoshi TOJO
Proceedings of the 8th International Workshop on Juris-Informatics, Nov. 2014, [Reviewed]
Lead
Affiliated academic society
Research Themes
- 認知障害が関係する言語特性の解明とその機械的抽出方法の開発
01 Apr. 2025 - 31 Mar. 2027 - 地域医療を支える無線通信インフラ構築に関する研究開発
Aug. 2025 - Mar. 2026
■University education and qualification information
