C-RECS （Creative Repository of Electro-Communications)
Not a member yet
9371 research outputs found
Sort by
Single-Ion Magnet Behavior and Crystal Field Analysis in Bilayered Lanthanide Squarate Hydrates
No full text電気通信大学博士（理学）2025doctoral thesi
Development of Virtual Reality Interfaces That Do Not Require Movement of the Body using Kinesthetic Illusions
No full text電気通信大学博士（工学）2025doctoral thesi
Perturbation and Learning in Game Theory: Convergence, Robustness, and Equilibrium Computation
No full text電気通信大学2025doctoral thesi
A study on real-time radiometric compensation applicable to continuously deforming non-rigid objects
No full text電気通信大学2025doctoral thesi
Data Structures for Computing Unique Palindromes in Static and Non-Static Strings
Get PDFjournal articl
Diverse Level Generation for Tile-based Video Game Using Generative Adversarial Networks from Few Samples
Get PDFビデオゲームにおけるステージの生成は，ゲームの楽しさの向上や制作コストの軽減を目的として長年自動生成の研究が行われており，近年では深層学習を用いた手法が研究されるようになってきている．深層学習によるステージ生成では，タイルベースのビデオゲームにおいてGANによる手法が成果をあげているが，その学習データの用意は課題である．そこで，本研究では少数のサンプルのみからGANを学習し，多様なステージを生成可能なモデルを獲得する手法を提案する．本研究では，GANによるステージ生成の先行研究で用いられていた手法を改善した手法およびGANの学習時の損失関数に多様性を向上させる正則化項を加えて学習を行う手法を提案する．3つのタイルベースの2Dゲーム環境において，提案する手法により生成したステージ群に対し，その多様性を評価する評価指標を用意し，それにより定量的な評価を行った．その結果，従来手法によるモデルよりも制約を満たすステージの生成率は低下したものの，多様なステージが生成できることが確認できた．Automatic level generation for video games has been studied for many years in order to improve game enjoyment and reduce production costs. Although GAN-based methods have been successful in deep learning level generation for tile-based video games, the preparation of training data is a issue. In this study, we propose a method for learning GANs from a small number of samples to obtain a model that can generate a variety of levels. We propose a method that improves on the method used in previous studies of level generation using GANs, and a method that adds a regularization term to the loss function during GAN training to improve diversity. We evaluated the diversity of the levels generated by the proposed method in 3 tile-based 2D game environments using a quantitative evaluation metric. The results showed that the proposed method was able to generate more diverse levels than the existing method, although the rate of levels satisfying the constraints was lower than that of the existing model.journal articl
Proposal of Model for Modifying Positioning of Football by Genetic Algorithm
Get PDFサッカーのポジショニングは，少しの違いで失点のリスクが大きく変わるため解釈が難しい．そこで本研究では，ポジショニングを数値的に評価する手法（Pitch Risk）を導入した，ポジショニング修正モデルを提案する．アマチュアの選手の試合後の振り返りでの利用などを想定している．Pitch Riskは，ピッチの支配状況を示すPitch Control，ゴールの確率を示すxG，アシストの確率を示すSxAを用いて，確率計算を基に算出した．サッカー経験者7人が局面において失点のリスクが高いと回答したエリアとのJS-divergenceは，Pitch Controlの118.18に対して，Pitch Riskは0.14であることから，Pitch Riskは失点のリスクをより表現できている．ポジショニング修正モデルにはGAを用いた．守備側11選手の距離と方向の計22変数を遺伝子とし，評価関数にはPitch Riskを用いた．GAで生成した個体数分ランダム生成した結果と比較すると，約3%の数値的改善が生じた．また，11選手分の学習を同時に進めたことで選手が連動した改善が見られた．モデル改善による精度向上により，ポジショニングの解釈を幅広い人々に提供できると考える．The positioning of soccer is difficult to interpret because a little difference can significantly change the risk of conceding a goal. Therefore, we introduce a method for quantifying the risk of conceding a goal (Pitch Risk) and propose a model to output the modification of positioning in a phase based on the method. The model is intended for use by amateur athletes in their post-game review. Pitch Risk is calculated based on a fundamental rule of probability using Pitch Control, which indicates pitch dominance, xG, which indicates the probability of a goal, and SxA, which indicates the probability of an assist. Pitch Risk is a better representation of the risk of conceding a goal since the JS-divergence with the areas where the seven experienced soccer players reported a higher risk of conceding a goal in the phase is 0.14 for Pitch Risk compared to 118.18 for Pitch Control. We use GA for the Positioning Modification model. A total of 22 variables of distance and direction for the 11 defending players were used as chromosomes, and Pitch Risk was used as the evaluation function. Improvement of about 3% occurred when compared to the best of randomly generated. In addition, there was a player-linked improvement due to the simultaneous learning of 11 players. We believe that the improvement of accuracy for the model provides positioning interpretations to a wider number of people.journal articl
Overview and Insights of Dementia Elderly Problem (BPSD) Solutions Using UEC Self-evolving Smart Society Model
Get PDF本稿では，新たな社会問題解決アプローチの基盤的な考え方である電気通信大学の「共創進化スマート社会」について説明し，次にこのコンセプトを認知症高齢者問題（BPSD）へ適用した「東京都BPSDプロジェクト」の概要を説明し，最後に現在得られている知見と今後の展望について報告する．This paper explains the foundational concept of the “Self-evolving Smart Society” of the University of Electro-Communications as a new approach to solving social issues. It then describes the outline of the “Tokyo BPSD Project” which applies this concept to the issue of elderly individuals with dementia (BPSD), and finally reports on the current findings and future prospects.journal articl