横幹連合コンファレンス予稿集
最新号
選択された号の論文の64件中1~50を表示しています
第11回横幹連合コンファレンス プログラム
A 1 データサイエンス教育の現状と今後
A 2 データサイエンス教育と社会連携
A 3 ポストコロナ未来社会と横幹知
A 4 計算社会科学
  • 水野 貴之, 土井 翔平
    セッションID: A-4
    発行日: 2020年
    公開日: 2020/11/21
    会議録・要旨集 オープンアクセス
    Most interdisciplinary research has been limited to the fusion of two fields, such as physics and economics, statistics and political science, and etc. In contrast, fusion in the computational social science involves multiple fields. The social system has become more and more complex with globalization, and social issues can only be solved by tackling them in multiple fields. Using the example of economic security in an increasingly complex global shareholding network, we will show that it is difficult to solve social issues without the fusion of economics, political science, and information science. Furthermore, this paper shows the history of the fusion of political science, economics, and information science, and we will discuss how computational social sciences have a significant place in economic security.
  • 鳥海 不二夫
    セッションID: A-4
    発行日: 2020年
    公開日: 2020/11/21
    会議録・要旨集 オープンアクセス
    In 2019, COVID-19 began to spread in Wuhan, China, and became a pandemic that spread around the world. In the information society, various information is able to be diffused through social media. In such a situation, the diffusion of inappropriate information is called Infodemic, which has become a major social problem. In this paper, we investigate the diffusion of information on social media, which is a new information source in the modern information society. We have clarified how we shared and spread information under COVID-19. The results allowed us to capture shifts in topics of interest, which indicates that people may be losing interest in COVID-19 infection prevention information. We also found that “anger” emotions were often diffused on a large scale, which indicates that social anxiety may be increasing.
A 5 コロナ禍のもとでの新たな防災に向けて
B 1 Marketing4.0 や産学連携を踏まえた上でのサステナブル・イ ノベーション
B 2 未来戦略デザインの展望
B 3 経営高度化への MATRIX アプローチと意思決定プロセス化 の研究Ⅲ
B 4 質的研究法とテキストマイニングによる概念形成法
B 5 深層学習を使った偏微分方程式の導出と求解
  • 龍 雨, 小山田 耕二
    セッションID: B-5
    発行日: 2020年
    公開日: 2020/11/21
    会議録・要旨集 オープンアクセス
    The explanation model using the existing partial differential equation (PDE) is very important for utilizing big data obtained from various new phenomena such as new corona infection. The academic question in this research is “how can a partial differential equation be derived from given big data?” In this research, we clarify whether PDE can be derived more accurately than big data if we can construct an appropriate deep learning model that explains the given big data. If the neural network model is accurate enough, the chain rule can be used to compute the exact partial derivative term sampling, automatic differentiation was performed in the class called Gradient Tape of Tensor Flow, and the relationship between PDE derivation accuracy and partial differential term accuracy was clarified.
C 1 ニューノーマル 新常態 におけるリスク未然防止と信頼・安 心
C 2 第 3 回コトつくり至宝発掘~コトつくりコレクションの選出~
  • 木内 正光, 永井 一志, 丸山 一彦, 渡辺 喜道, 棟近 雅彦
    セッションID: C-2
    発行日: 2020年
    公開日: 2020/11/21
    会議録・要旨集 オープンアクセス
    Quality Function Deployment (QFD) is a methodology systematized by Dr. Shigeru Mizuno and Dr. Yoji Akao in 1978. In QFD, customer needs and expectations are first refined, and then refined information is reliably transferred into the product and service development process. With this, QFD can give some opportunities to improve the quality of products and services. Today, QFD is used by many companies and organizations in Japan and abroad, and QFD is a methodology that Japan is proud of, which has enabled it to provide products and services with high customer satisfaction.
  • 生駒 哲一
    セッションID: C-2
    発行日: 2020年
    公開日: 2020/11/21
    会議録・要旨集 オープンアクセス
    State space representation of dynamical system is widely used in prediction and control, etc., and state estimation is a fundamental problem to be solved in this formulation. While analytical state estimations via Kalman filter, etc., are available for systems consisting of linear equations and Gaussian distributions, there is no analytical solution to the state estimation problem for nonlinear and/or non-Gaussian state space models in general case. As a breakthrough to this issue, in early 1990s, a particle filter called “Monte Carlo Filter” has been proposed in Japan as the first universal approximation method of state estimation for nonlinear and/or non-Gaussian models by utilizing many realizations in the state space to represent probability distribution of posterior state. Due to the universal property and allowed flexibility in modeling, now, particle filters have become standard methods in many fields, such as natural science, social science, engineering, and so on.
C 3 自動運転など自動車産業における数理科学: 文部科学省「数学アドバンストイノベーションプラットフォーム」
  • 萩原 一郎, ディアゴ ルイス, 安部 博枝
    セッションID: C-3
    発行日: 2020年
    公開日: 2020/11/21
    会議録・要旨集 オープンアクセス
    Especially in the case of auto-driving level 3, causable machine learning has an important role. If the auto-driving car has the ability for risk prediction and danger avoidance based on causable machine Learning , it is very useful to support for elderly driver support. To realize this support .it will also be discussed how to get the car accident mathematical model from driving record.
  • ドライバー状態と安全な運転引継ぎのための検討
    北﨑 智之
    セッションID: C-3
    発行日: 2020年
    公開日: 2020/11/21
    会議録・要旨集 オープンアクセス
    One of the expectations towards the automated driving technology is dramatic reduction of road crashes. The background hypothesis is that replacing the human driver by a computer will eliminate crashes that are currently caused by human errors. However, complication of the systems and new tasks imposed on the driver may generate new risks, system-induced problems. The main focus of human factors research in automated driving is to reduce the system-induced problems. The research project was conducted from FY2016 to FY2018 with the funding awarded by Cabinet Office and SIP-adus Phase 1. One of the three tasks of the project aimed at understanding effects of cognitive states of the driver on his/her takeover performance and extracting metrics of the influential driver states for driver monitoring systems. It was found that different driver states influenced takeover performance in different ways. Some metrics for the influencing states were identified. These findings are being discussed and applied to International Standards.
  • 内田 博志
    セッションID: C-3
    発行日: 2020年
    公開日: 2020/11/21
    会議録・要旨集 オープンアクセス
    Energy optimal control (EOC) is applied to the case in that the hybrid electric vehicle performs position control. A virtual drive system driven by the position error signal is added to the model of the controlled object, and the power consumption is added to the evaluation function to derive the optimal control law. It is shown that good control is possible even when position control and energy allocation cannot be coordinated well with ordinary control.
  • 今関 隆志, 菅沢 深, 趙 開開, 望月 悠登, 毛利 宏
    セッションID: C-3
    発行日: 2020年
    公開日: 2020/11/21
    会議録・要旨集 オープンアクセス
    Near-miss database consists of video data of real-world dangerous situations. It can be classified into the overt dangerous situation, which is obviously approaching accident, the potentially dangerous situation which has probability to get into the overt dangerous situation, and the normal driving situation. In order to assure safety driving of autonomous vehicle, it is necessary to evaluate whether the vehicle would be operated according to the scenarios which avoid not only the overt dangerous situations but also the potentially dangerous situations. In this paper, using technologies of object detection and measurement on the near-miss video data, and using theoretical concept of potential risk indicator, rear-end type near-miss data were analyzed, the potential risk indicators were calculated, and the potentially dangerous situations were defined. Then, a novel evaluation method of safer autonomous driving vehicles is proposed.
feedback
Top