| 吉上 康平 | M, 2回目発表 | ソフトウェア工学 | 松本 健一, 安本 慶一, 石尾 隆, 畑 秀明 |
|
title: Inter-organization data sharing for ensuring software traceability using blockchain
abstract: Software traceability is one of the important indicators to ensure the quality of software. In software development between multiple organizations, it is important to share software traceability. However, in existing research, information sharing among multiple organizations has not been studied much. In this study, we propose a framework that enables software traceability sharing among multiple organizations using blockchain. language of the presentation: Japanese | |||
| WANG DONG | M, 2回目発表 | ソフトウェア工学 | 松本 健一, 安本 慶一, 石尾 隆, Raula G. Kula |
|
title: How similar patch impact reviewing efforts: A study of automated detection on Modern Code Review
abstract: Due to the distributed nature of Modern Code Review (MCR) tools, developers risk submitting similar reviews (i.e., reviews that attempt to achieve similar objectives), thus potentially causing extra efforts both the contributor and reviewers. Although research on other duplicate software artifact exists, there is no prior work that explores the impact of such similar reviews in MCR. In this research we conduct an empirical study to understand the impact of similar reviews on reviewing efforts in MCR. language of the presentation:English | |||
| 齋藤 俊 | M, 2回目発表 | 計算システムズ生物学 | 金谷 重彦, 安本 慶一, MD.ALTAF-UL-AMIN, 黄 銘, 小野 直亮 |
|
title:Drug target interaction prediction based on molecular graph topology
abstract: In pharmacology, identifying interaction between compound and target protein plays a significant role in drug screening and machine learning approaches have been widely applied to the process. This research takes advantage of molecular geometrical information for convolutional neural networks by representing compounds as undirected graphs. In this study, we focus on compounds for target proteins binding to curcumin, which is indicated to have anticancer properties.We assess the performance of graph convolutional approach and conventional methods, and demontrate the effectiveness of the graph-based method for prediction of anticancer drug target interaction. language of the presentation:Japanese | |||
| 日朝 祐太 | D, 中間発表 | 生体医用画像 | 佐藤 嘉伸, 向川 康博, 大竹 義人, Soufi Mazen |
|
title: Recovery of patient-specific anatomy and kinematics of musculoskeletal regions from medical images.
abstract: The patient-specific anatomy and kinematics are important for preoperative planning, rehabilitation, biomechanical simulation, and so on. In this study, we aim at followings: 1) Recovery of three-dimensional rib motion from dynamic chest radiograph. 2) Automatic segmentation of hip and thigh muscles from CT and MR Images using convolutional neural networks and image synthesis technique. language of the presentation: Japanese | |||
| 井上 裕太 | M, 2回目発表 | 光メディアインタフェース | 向川 康博, 清川 清, 舩冨 卓哉, 田中 賢一郎, 久保 尋之 |
|
title: Analysis of inconsistency between shape and shading using time-of-flight
abstract: Time-of-Flight (ToF) camera is a device for measuring depth and reflected light intensity by irradiating intensity-modulated light and looking at the amplitude and phase changes of the reflected light. However, there is a problem that the measured shape can be distorted depending on the material such as translucency with subsurface scattering. In this research, we focus on that the shape is distorted while the shading in reflected light intensity is correct. We tackle a recognition task of translucent materials from the inconsistency between shading from distorted shape and correct shading. In this presentation, we describe the details of the proposed method and experiments. language of the presentation: Japanese | |||
| 連 孟 | M, 2回目発表 | 光メディアインタフェース | 向川 康博, 清川 清, 舩冨 卓哉, 田中 賢一郎, 久保 尋之 |
|
title: Correction of Depth Distortion Caused by Fog Using Multiple Modulation Frequencies in Time-of-Flight
abstract: In self-driving cars, accurate distance measurement using a time-of-flight camera in fog is indispensable. In this study, we perform that clustering of pixels can be regarded as the same distance in the scene by using multiple modulation frequencies of the Time-of-Flight camera. We show that the distance independent of the influence of fog can be computed from the same cluster. We confirmed the effectiveness of our method in simulation and real environment experiments. language of the presentation: Japanese 発表題目: Time-of-Flightにおける複数の変調周波数を用いた霧による距離計測歪みの補正 発表概要: 自動運転の実用化にあたり、霧中のような悪天候におけるTime-of-Flightカメラを用いた正確な距離計測は必要不可欠である。本研究では、Time-of-Flightカメラの複数の変調周波数を利用することで、シーン中における同一距離とみなせる点のクラスタ推定を行う。さらに、同一クラスタと推定された点群から霧の影響に依らない距離が算出できることを示す。最後に、シミュレーションと実環境実験において本手法の有効性を確認した。 | |||