Updated on 2025/04/26

写真a

 
Mori Naoki
 
Organization
Graduate School of Informatics Department of Core Informatics Professor
School of Engineering Department of Information Science
Title
Professor
Affiliation
Institute of Informatics

Position

  • Graduate School of Informatics Department of Core Informatics 

    Professor  2022.04 - Now

  • School of Engineering Department of Information Science 

    Professor  2022.04 - Now

Degree

  • 博士(工学) ( Others )

Research Areas

  • Informatics / Kansei informatics  / Machine Learning

  • Informatics / Kansei informatics  / Artificial Intelligence

  • Informatics / Kansei informatics  / Evolutionary Computation

  • Informatics / Soft computing  / Evolutionary Computation

  • Informatics / Soft computing  / Large Language Model

Research Interests

  • Machine

  • Natural Language Processing

  • Artificial Intteligence

  • Evolustionary Computation

  • Evolustionary Computation

Research subject summary

  • 自然言語処理

  • 自動株取引システム

  • 機械学習

  • 人工知能システム

  • 進化型計算

Research Career

  • 生成AI の進化的獲得手法の研究

    生成AI、大規模言語モデル、AutoML、NAS 

Professional Memberships

  • 人工知能学会

    2017.04 - Now   Domestic

  • 電気学会

    2014.01 - Now   Domestic

  • 計測自動制御学会

    2001.04 - Now   Domestic

  • 日本シミュレーション&ゲーミング学会

    2001.04 - Now   Domestic

  • システム制御情報学会

    1997.04 - Now   Domestic

Awards

  • Honorable Mention Award

    N. Aoki, N. Mori, M. Okada

    2023.12   15th IIAI-AAI-Winter IEEE   Analysis of LLM-Based Narrative Generation using the Agent-based Simulation

  • Competitive Paper Award

    H. Yamato, M. Okada, N. Mori

    2023.12   15th IIAI-AAI-Winter IEEE   Trainable Weighted Pooling Method for Text Classification with BERT,

  • 電気学会2023年電子・情報・システム部門大会奨励賞

    鷲野拓海,森 直樹

    2023.09   電気学会   適応度空間を推定するSurrogate Modelを導入したTDGA AutoAugment の提案

Papers

  • Proposal for Representation and Use of Knowledge Graphs for Disaster Data in Regional Materials

    HORIMOTO Ryusei, OKADA Makoto, MORI Naoki

    Joho Chishiki Gakkaishi   34 ( 4 )   357 - 360   2024.11( ISSN:09171436 ( eISSN:18817661

     More details

    <p> In recent years, artificial intelligence technology has rapidly developed, with knowledge graphs, which represent human knowledge in a graph structure, gaining significant attention. These graphs are utilized as foundational technologies in various fields and tools. Knowledge graphs effectively integrate information from diverse data sources and clarify the relationships between them. This study proposes a method for managing disaster data in the preservation and inheritance of regional materials using knowledge graphs. By representing various past disaster events and their interrelations through a unified structure, knowledge graphs are expected to facilitate the integration of multiple sources of information, thereby enhancing data reuse and knowledge transfer. Furthermore, by visualizing the interrelationships between individual disaster data, this approach is anticipated to contribute to future disaster risk assessments and improve disaster response strategies.</p>

    DOI: 10.2964/jsik_2024_034

  • Emotional Analysis of Persona-designated Character with LLM

    MURAKAMI Kazuma, MORI Naoki, OKADA Makoto

    Proceedings of the Annual Conference of JSAI   JSAI2024 ( 0 )   4K1GS903 - 4K1GS903   2024( eISSN:27587347

     More details

    <p>Research on Large Language Models (LLMs) like ChatGPT has gained momentum in recent years. These advanced LLMs can produce high-quality outputs, leading to significant achievements in more complex tasks. However, ChatGPT, which currently leads in performance, has yet to disclose internal specifications, making the construction of an LLM independently a costly endeavor. As a result, there is a growing trend in research focusing on the behavior of these models rather than improving the models themselves. This study forcuses on dialogues with characters whose interactions have been substantially enhanced by LLMs, aiming to achieve more relevant and interactive conversations with the real world. In this process, a character persona was assigned, and the decision whether to speak was based on assumed visual information and the character's internal state. Moreover, LLMs were utilized to numerically assess the character's emotions based on these contextual factors. Using the emotion vectors evaluated by the LLM and the author's assessments, the character's propensity to speak was framed as a binary classification problem, inputting the emotion vectors. Numerical results indicated that the emotional assessments successfully reflected the designated personas, and the determination to speak or not showed significant results compared to baseline models.</p>

    DOI: 10.11517/pjsai.jsai2024.0_4k1gs903

  • Co-living Simulation System with AI Characters Reflecting User Preferences

    MURAKAMI Kazuma, MORI Naoki

    Proceedings of Summer Conference, Digital Game Research Association JAPAN   2024 ( 0 )   19 - 24   2024( eISSN:27584801

     More details

    Recent advancements in AI, driven by Large Language Models (LLMs) and diffusion -based generative models have significantly enhanced the field. These models produce creative outputs comparable to human creations, expanding possibilities for automated creativity. While generative AI is used in game development, research on integrating automatic dialogue and environment generation as core game elements is limited. This study constructs a game system with dynamic scene transitions in response to user input. Specifically, we develop an adventure game that defines scene transitions and generates natural sequences in user-character dialogues for personalized dialog to create comfortable user experience, offering a co-living experience with AI agents reflecting user preferences.

    DOI: 10.57518/digrajprocsummer.2024.0_19

  • A Solution Approach to Energy Plant Operation Planning Problems Using Transformers

    SUZUKI Tomohiro, OZEKI Takumi, MORI Naoki, HIRANO Hideaki, KITAMURA Shoichi, MORI Kazuyuki

    Proceedings of the Annual Conference of JSAI   JSAI2024 ( 0 )   2I5GS1005 - 2I5GS1005   2024( eISSN:27587347

     More details

    <p>Energy plants account for most energy consumption in factories and other facilities. Benchmark problems for energy plant operation planning have been proposed for energy conservation. However, to apply the benchmark problem to real energy plants, it is necessary to have a general-purpose and fast operational planning method that can not only search for solutions to the benchmark problem but also deal with different situations. In this study, we propose a method for regression prediction of solutions to similar problems using a deep learning model Transformer with Positional Embedding, representing time series information. In numerical experiments, we compared the solutions generated by the Transformer and the comparison method in terms of energy purchase cost and constraint violation and confirmed the effectiveness of the proposed method.</p>

    DOI: 10.11517/pjsai.jsai2024.0_2i5gs1005

  • Proposing an Extension Method for tdgaCNN Based on the Introduction of Skip Connections

    TAIRA Tomotaka, MORI Naoki, OKADA Makoto

    Proceedings of the Annual Conference of JSAI   JSAI2024 ( 0 )   2D4GS203 - 2D4GS203   2024( eISSN:27587347

     More details

    <p>Machine learning-based image recognition has gained significant attention, mainly using Convolutional Neural Networks (CNNs). As the complexity of problems increases, so does the complexity of CNN architectures. This makes finding the optimal CNN structure a challenging combinatorial optimization problem. Manual settings are time-consuming and labor-intensive. To address this, the field of AutoML has introduced gaCNN, which uses a genetic algorithm for CNN structure search, and tdgaCNN, which applies thermodynamic selection rules. These methods have shown superiority over traditional ones. In this study, we propose a tdgaCNN extension that incorporates skip connections to enhance performance. Its effectiveness is demonstrated on an image benchmark dataset.</p>

    DOI: 10.11517/pjsai.jsai2024.0_2d4gs203

  • Learning Methods for LLMs on Game Data Using RLHF

    MURATA Tomoya, MORI Naoki, OKADA Makoto

    Proceedings of the Annual Conference of JSAI   JSAI2024 ( 0 )   4A1GS602 - 4A1GS602   2024( eISSN:27587347

     More details

    <p>Recent advancements in Large Language Models (LLMs) within the artificial intelligence domain have shown exceptional performance across various natural language processing tasks. Amidst these developments, aligning the values and objectives of LLMs with human perspectives has become increasingly important. Reinforcement Learning from Human Feedback (RLHF) has gained notable interest as a method for such alignment adjustments. This study explored a learning approach for LLMs using RLHF, employing scenarios from the romance simulation game 'Tokimeki Memorial 3' as the game scenario data. Specifically, the research involved an experiment where sentences were generated following five Japanese characters, tailored to align with the personalities of the game characters. While subjective, this evaluation demonstrated the capability of producing sentences that appropriately matched the distinct characters in the game.</p>

    DOI: 10.11517/pjsai.jsai2024.0_4a1gs602

  • Investigating Knowledge Graph Completion Techniques Using Masked Language Modeling

    HORIMOTO Ryusei, OKADA Makoto, MORI Naoki

    Proceedings of the Annual Conference of JSAI   JSAI2024 ( 0 )   4F1GS304 - 4F1GS304   2024( eISSN:27587347

     More details

    <p>In recent years, with the rapid development of artificial intelligence technology, Knowledge Graph, which systematically connects various kinds of human knowledge and expresses their relationships in a graph structure, has attracted much attention and is used as a fundamental technology for artificial intelligence in various fields. In this context, there is a need for an automatic complementation method of Knowledge Graphs to meet the demand for adding new knowledge to existing Knowledge Graphs. The problem with conventional Knowledge Graph completion methods such as TransE and ComplEx is that they focus on knowledge relationships and do not effectively capture the semantic information of the knowledge itself. In this study, we proposed an automatic Knowledge Graph completion method using Masked Language Modeling by BERT, which is a deep language model, to effectively capture the semantic information of knowledge itself, and verified its effectiveness through evaluation experiments.</p>

    DOI: 10.11517/pjsai.jsai2024.0_4f1gs304

  • ストーリー解析のための文の分散表現に基づく小説の自動セグメンテーション手法の提案 Reviewed

    福田清人, 森直樹, 松本啓之亮, 岡田真

    芸術科学会論文誌 雑誌   2020.01

  • Evolutionary Deep Learning based on Deep Convolutional Neural Network for Anime Storyboard Recognition Reviewed

    S. Fujino, N. Mori, T. Hatanaka, K. Matsumoto

    Neurocomputing 雑誌   338 ( 4 )   393 - 398   2019.04

     More details

    Kind of work:Joint Work  

  • Intelligent Software Development Method Based on Model Driven Architecture Reviewed

    K. Matsumoto, K. Nakoshi, N. Mori

    International Journal on Advances in Software 雑誌   11 ( 6 )   88 - 96   2018.06

     More details

    Kind of work:Joint Work  

  • 多層個体群を有する遺伝的プログラミングの提案およびBoolean問題への適用 Reviewed

    長谷川 拓, 森 直樹, 松本 啓之亮

    進化計算学会論文誌 雑誌   8 ( 2 )   52 - 60   2017.02

     More details

    Kind of work:Joint Work  

  • Learning Method by Sharing Activity Histories in Multiagent Environment Reviewed

    K. Matsumoto, T. Gohara, N. Mori

    International Journal on Advances in Intelligent Systems 雑誌   10 ( 2 )   71 - 80   2017.02

     More details

    Kind of work:Joint Work  

  • 多層個体群を有する遺伝的プログラミングの提案およびBoolean問題への適用 Reviewed

    長谷川 拓, 森 直樹, 松本 啓之亮

    進化計算学会論文誌 雑誌   8 ( 2 )   52 - 60   2017.02

     More details

    Kind of work:Joint Work  

  • 劣個体分布に基づく DII analysis の提案と応用 Reviewed

    長谷川 拓, 井上 和之, 荒木 悠太, 森 直樹, 松本 啓之亮

    進化計算学会論文誌 雑誌   7 ( 2 )   13 - 23   2016.02

     More details

    Kind of work:Joint Work  

  • 劣個体分布に基づく DII analysis の提案と応用 Reviewed

    長谷川 拓, 井上 和之, 荒木 悠太, 森 直樹, 松本 啓之亮

    進化計算学会論文誌 雑誌   7 ( 2 )   13 - 23   2016.02

     More details

    Kind of work:Joint Work  

  • 機械学習アルゴリズムを導入した適応度景観推定型進化型計算の提案 Reviewed

    長谷川 拓, 森 直樹,松本 啓之亮

    システム制御情報学会論文誌 雑誌   28 ( 5 )   189 - 197   2015.05

     More details

    Kind of work:Joint Work  

  • 機械学習アルゴリズムを導入した適応度景観推定型進化型計算の提案 Reviewed

    長谷川 拓, 森 直樹, 松本 啓之亮

    システム制御情報学会論文誌 雑誌   28 ( 5 )   189 - 197   2015.05

     More details

    Kind of work:Joint Work  

  • Round-Trip Engineering Approach to Keep Activity Diagrams Synchronized with Source Code Reviewed

    K. Matsumoto, R. Uenishi, N. Mori

    International Journal on Advances in Intelligent Systems 雑誌   8 ( 4 )   448 - 457   2015.04

     More details

    Kind of work:Joint Work  

  • Casook : Creative Animating Sketchbook Reviewed

    M. Ueno, K. Fukuda, A. Yasui, N. Mori, K. Matsumoto

    Advances in Intelligent Systems and Computing 雑誌   373 ( 1 )   175 - 182   2015.01

     More details

    Kind of work:Joint Work  

  • 追跡問題におけるゴールデンクロスを利用した切り換えQ学習 Reviewed

    伊木 美太輔, 松本 啓之亮, 森 直樹

    電気学会論文誌C 雑誌   134 ( 9 )   1318 - 1324   2014.09

     More details

    Kind of work:Joint Work  

  • Picture Models for 2-Scene Comics Creating System Reviewed

    M. Ueno, N. Mori, K. Matsumoto

    Advances in Distributed Computing and Artificial Intelligence Journal 雑誌   3 ( 2 )   53 - 64   2014.02

     More details

    Kind of work:Joint Work  

  • モデル駆動ソフトウェア開発へのコンポーネントベース技術の適用 Reviewed

    水野 友貴, 松本 啓之亮, 森 直樹

    電気学会論文誌C 雑誌   133 ( 12 )   2275 - 2281   2013.12

     More details

    Kind of work:Joint Work  

▼display all

Books and Other Publications

  • Computational and Cognitive Approaches to Narratology

    M. Ueno, K. Fukuda, N. Mori( Role: Joint author)

    IGI Global  2016.07 

     More details

    Responsible for pages:chapter 6  

  • Realistic Simulation of Financial Markets

    H. Kita, N. Mori et al.( Role: Joint author)

    Springer  2016.07 

     More details

    Responsible for pages:chapter 4  

  • 人工市場で学ぶマーケットメカニズム |U-Mart工学編

    喜多 一, 森 直樹, 小野 功, 佐藤 浩, 小山 友介, 秋元 圭人( Role: Joint author)

    共立出版  2009.05 

Collaborative research (seeds) keywords

  • 生成AIに関する技術

  • 画像処理に関する技術

  • 機械学習に関する技術

  • 感性工学に関する研究

  • 自然言語処理システム

  • 株の自動取引に関する研究

  • 人工知能に関する技術

  • 最適化に関する問題

▼display all

Outline of collaborative research (seeds)

  • 生成AIに関する研究

     More details

    Request for collaborative research:The private sector, such as other institutions

    Type of research exchange:Technical consultation, Contract research, Joint research, Lecture

    企業案件への生成AIの適用に関する全般

Grant-in-Aid for Scientific Research

  • Understanding of creations by evolutionary AutoML

    Grant-in-Aid for Scientific Research(C)  2027

  • Understanding of creations by evolutionary AutoML

    Grant-in-Aid for Scientific Research(C)  2026

  • Understanding of creations by evolutionary AutoML

    Grant-in-Aid for Scientific Research(C)  2025

  • Understanding of creations by evolutionary AutoML

    Grant-in-Aid for Scientific Research(C)  2024

Charge of on-campus class subject

  • ソフトウェア工学

    2024   Weekly class   Undergraduate

  • 情報工学基礎演習1

    2024   Weekly class   Undergraduate

  • 基幹情報学特別演習1

    2024   Weekly class   Graduate school

  • 言語情報学

    2024   Weekly class   Graduate school

  • 基幹情報学特別研究2

    2024   Intensive lecture   Graduate school

  • 基幹情報学特別研究1

    2024   Intensive lecture   Graduate school

  • 基幹情報学特別演習I-1

    2024   Intensive lecture   Graduate school

  • 基幹情報学特別研究8

    2024   Intensive lecture   Graduate school

  • 基幹情報学特別研究7

    2024   Intensive lecture   Graduate school

  • 基幹情報学特別研究5

    2024   Intensive lecture   Graduate school

  • 基幹情報学特別研究3

    2024   Intensive lecture   Graduate school

  • 情報工学実験2

    2024   Weekly class   Undergraduate

  • 基幹情報学特別演習2

    2024   Weekly class   Graduate school

  • 社会情報学

    2024   Weekly class   Graduate school

  • 基幹情報学セミナー

    2024   Weekly class   Graduate school

  • 基幹情報学特別研究2

    2024   Intensive lecture   Graduate school

  • 基幹情報学特別研究1

    2024   Intensive lecture   Graduate school

  • 基幹情報学特別演習I-2

    2024   Intensive lecture   Graduate school

  • 基幹情報学特別研究8

    2024   Intensive lecture   Graduate school

  • 基幹情報学特別研究6

    2024   Intensive lecture   Graduate school

  • 基幹情報学特別研究4

    2024   Intensive lecture   Graduate school

  • Undergraduate Project in Computer Science

    2021    

  • Technical English for Computer Science

    2021    

  • Special Project in Electrical Engineering and Information Science IV

    2021    

  • Special Project in Electrical Engineering and Information Science III

    2021    

  • Advanced Seminar in Electrical Engineering and Information Science IV

    2021    

  • Advanced Seminar in Electrical Engineering and Information Science III

    2021    

  • Advanced Internship in Computer Science and Intelligent Systems

    2021   Practical Training  

  • Special Project in Electrical Engineering and Information Science II

    2021    

  • Special Project in Electrical Engineering and Information Science I

    2021    

  • Advanced Seminar in Electrical Engineering and Information Science II

    2021    

  • Advanced Seminar in Electrical Engineering and Information Science I

    2021    

  • Undergraduate Project in Computer Science

    2021    

  • Technical English for Computer Science

    2021    

  • College of Engineering Internship

    2021   Practical Training  

  • Fundamentals in Electrical and Electronic Engineering I

    2021    

  • Fundamentals in Electrical and Electronic Engineering I

    2021    

  • Advanced Machine Learning

    2021    

  • Advanced Evolutionary Computation

    2021    

  • Advanced Software Systems

    2021    

  • Software Engineering

    2021    

  • Advanced Intelligent Information Systems I

    2021    

  • Laboratory in Computer Science II

    2021   Practical Training  

▼display all

Number of instructed thesis, researches

  • 2021

    Number of instructed the graduation thesis: