| 田井中 渓志 | D, 中間発表 | インタラクティブメディア設計学 | 加藤 博一, | 清川 清, | 神原 誠之, | 藤本 雄一郎, | 澤邊 太志 |
|
title: Creating an Information Design Supporting Tool for AR Task Support System.
abstract: Despite the fact that various papers have shown that the application of augmented reality AR technology for work support has positive effects on work efficiency, such as increased cognitive speed ande reduced working time and error rates, AR has not been widely used in factories, such as in the manufacturing industry. I believe that one of the reasons for this is the problem that it is difficult to design information for a good AR work support system because the worker who are creating work procedure manuals and supposed to create the AR work support system have little knowledge and experience in AR. I am tring to solve this problem by developing an supporting tool for the information design. I will show progress of this research. language of the presentation: Japanese 発表題目: *** この部分を発表題目に *** 発表概要: *** この部分を発表概要に *** | |||||||
| CHI ZIHAO | M, 2回目発表 | インタラクティブメディア設計学 | 加藤 博一, | 清川 清, | 神原 誠之, | 藤本 雄一郎, | 澤邊 太志 |
|
title: Development of Map Data Management Framework for Visual SLAM-based Augmented Reality
abstract:Visual Simultaneous Localization and Mapping (Visual SLAM) based Augmented Reality (AR) Navigation is becoming more and more attractive. One of the problem is the map generated by Visual SLAM cannot be be saved and reused. When the environment changes, the map of the environment is not updated and couldn’t be used for navigation. Based on that, my research goal is to develop a map data management framework for mobile AR application based on Visual SLAM. For effective map management, a Server-Client system to collect new map data from AR Client has been built. And method for precisely merge the collected map data on Server is proposed. language of the presentation: English | |||||||
| LIU JIA | M, 2回目発表 | インタラクティブメディア設計学 | 加藤 博一, | 清川 清, | 神原 誠之, | 藤本 雄一郎, | 澤邊 太志 |
|
title: Scene-aware Interaction between Virtual Characters and Real Scene in Augmented Reality
abstract: How to interact more naturally with the real enviroment has always been a crucial issue in AR. In order for virtual characters to better interact with real scene, scene understanding is an indispensable part. This research is mainly divided into two parts, the first part is how to perceive and understand the scene. The proposed method is to map the results of semantic segmentation back to the scene model obtained by V-SLAM; the second part is how to design the behavior of virtual characters according to the real scene, such as decision trees or other behavioral design methods. language of the presentation: English | |||||||
| YU MIAO | M, 2回目発表 | インタラクティブメディア設計学 | 加藤 博一, | 清川 清, | 神原 誠之, | 藤本 雄一郎, | 澤邊 太志 |
|
title: Comparison of First-Person and Third-Person Views in Observation of Ideal Posture for VR Body Movement Training
abstract: Improper training postures can cause serious harm to muscles and the body. To correct understanding the movement posture is important. For the self-training scenario, virtual reality(VR) head-mounted display(HMD) helps the user understand better the 3d movement posture than a 2d monitor. However, different observation perspectives impact on the understanding of movement posture. We conduct a user study that allows the user to imitate a series of pre-made movement postures to evaluate the cognitive changes of users in VR physical movement training through the difference of observer's perspective. language of the presentation: English | |||||||
| 田口 雄大 | M, 2回目発表 | 計算システムズ生物学 | 金谷 重彦, | 松本 健一, | 小野 直亮, | MD.ALTAF-UL-AMIN, | 黄 銘 |
|
title: Learning Distributed Representation of Natural Product-derived Chemical Fragments using Node Embeddings
abstract: In drug discovery, in order to find a lead compound that exhibits the desired biological activity likely to be useful, organic chemists perform Structure Activity Relationships (SAR) analysis to predict the biological activities from natural products. However, due to their structural diversity, it is challenging to represent their chemical structure by conventional methods. In this study, we aim to more accurately represent the structural features of natural products. We develop a novel distributed representation of natural product-derived chemical fragments using node embedding to embed chemical information about the molecular scaffolds and the relative position of functional groups. language of the presentation: Japanese | |||||||
| GAO PEI | M, 2回目発表 | 計算システムズ生物学 | 金谷 重彦, | 松本 健一, | 小野 直亮, | MD.ALTAF-UL-AMIN, | 黄 銘 |
|
title: On Finding Natural Antibiotics based on TCM Formulae
abstract: This research looks for latent natural products (NP) -derived antibiotics by making full use of the sizable empirical data of traditional medicine like Traditional Chinese Medicine (TCM). A network-based approach is constructed to screen and validate the NP-level TCM formulae effective against many types of infectious diseases. Taking infectious diseases as bridge, the many-to-many correspondence between antibiotics, bacteria, formulae, NP, and metabolite compounds is shown in the form of network. Antibacterial NP are screened out via network searching and statistical analysis. And the antibacterial potential of candidate NP-derived metabolites will be evaluated with chemoinformatics analysis. language of the presentation: English | |||||||
| TIAN HAOYU | M, 2回目発表 | 計算システムズ生物学 | 金谷 重彦, | 松本 健一, | 小野 直亮, | MD.ALTAF-UL-AMIN, | 黄 銘 |
|
Title: Real-time Human Activity Recognition System Based on the Wearable Intelligent Device
Abstract: At present, the recognition of human activities based on sensors has become more and more important in personal healthcare. For example, a doctor can give a more effective treatment plan for the patient's biological signals. Although from the current point of view, some problems such as signal feature extraction, resource consumption when model building and other problems have been solved or improved. However, the real-time and accurate monitoring system for ultra-long time (24 hours or more) is still lacking. We proposed a prototype of a real-time monitoring system based on a single sensor unit of the wrist, and listed the current problems and corresponding solutions. Language of the presentation: English | |||||||
| AICHER ANNALENA BEA | D, 中間発表 | ユビキタスコンピューティングシステム | 安本 慶一, | 中村 哲, | 松田 裕貴 | ||
|
title:
Towards Balanced Engaging Argumentation (BEA) - Detecting and Breaking the Personal Filter Bubble
abstract: The phenomenon of “Personal Filter Bubbles” (PFB), in state-of-the-art literature also described as “confirmation bias” describes the tendency of humans to search for, interpret, favor, and recall information such that prior beliefs or values are confirmed. This bias is displayed when people select information that supports their views, ignoring contrary information, or when they interpret ambiguous evidence as supporting their existing attitudes. In order to combat this Personal Filter Bubble an approach to model and break the former is proposed. The argumentative dialogue system BEA (‘Balanced Engaging Argumentation’) is introduced, which displays a natural and intuitive way to explore arguments on controversial topics. It combines state-of-the-art argument mining and retrieval systems with a flexible I/O, intelligent decision making and four-dimensional Personal Filter Bubble Model. These system components are coordinated with each other using machine learning approaches, i.e. reinforcement learning. To maximize the users’ willingness and engagement to cooperatively explore arguments with diverging viewpoints from their own, the system adapts its dialogue policy to the users. In particular, it estimates their interest, preferences and uses meta-argument structures to determine which content and manner to present the former is chosen. Therefore, especially the social signals and implicit user behavior is analyzed with the goal to maximize the task success (breaking the PFB) and user satisfaction. language of the presentation: English | |||||||