ゼミナール発表

日時: 09月29日(金)3限(13:30-15:00)


会場: L1

司会: 樫原 茂
森田 達弥 1651114: M, 2回目発表 ユビキタスコンピューティングシステム 安本 慶一, 小笠原 司, 荒川 豊, 諏訪 博彦, 藤本 まなと
title: Development of a Daily Report Creation Support System Using BLE Beacon in a Nursing Home
abstract: Recently, as elderly people population grows, the burdens on carers are getting larger.In nursing homes, carers make a daily report aiming to improve the resident's Quality of Life.However, in the present situation, it is difficult for caretakers to record the resident's activity in detail, since each carer needs to take care of several residents at the same time.To reduce the burden of carers, many elderly monitoring systems have been proposed so far, but most of them are not practical in the sense that they force the residents to use dedicated devices such as smart phone and/or particular applications that are obtrusive. In this reserch, we propose a daily report creation support system which can monitor activity of residents in nursing homes.Our proposed system estimates multiple locations (areas) where residents are located with the BLE beacon, by utilizing RSSI of the Bluetooth radio wave.In the experiments, evaluation was conducted by a leave-one-person-out cross-validation for multiple residents.Evaluation result showed that our system estimated the subject's present area with F-measure: 80%.
language of the presentation: Japanese
 
音田 恭宏 1651029: M, 2回目発表 ユビキタスコンピューティングシステム 安本 慶一, 松本 健一, 荒川 豊, 諏訪 博彦, 水本 旭洋
title: Development of Smart Sensing Chair and Functional Enhancement of a Working Space
abstract: Continuously undesirable or same sitting position for a long time causes the burden on the waist and shoulders, leads to mental stress, reduces work efficiency. Therefore, it is important to measure their sitting situation, improve the sitting pose, change the posture periodically, and move from the seat. Consequently, we developed a sensing chair satisfying those conditions. This sensing chair has a function to classify the sitting posture of workers with the accuracy of 80.2%.
language of the presentation: Japanese
 
千住 琴音 1651066: M, 2回目発表 ユビキタスコンピューティングシステム 安本 慶一, 松本 健一, 荒川 豊, 諏訪 博彦, 水本 旭洋
title: Resolving distribution of parking vehicles by requesting user new trip in one-way carsharing
abstract: Recentrly, one-way carsharing service that allows a user to drop the vehicle off at the destination has been started. However, it doesn't become widespread because it can't assure the existence of both an available vehicle at the start place and a vacant parking slot at the destination place. At this moment, the company staff moves vehicles to certain places manually. However, it is so costly. In addition, in previous work, the author asks me change to ride(division ride or carpool). However, it success only the departure and destination place. In order to solve this problem in one-way carsharing service, we propose to involve a future potential user to move vehicles. We assume that there exist some requested one-way trips. Our method inserts a new trip among the existing trips for maximizing the number of succeeded trips. This trip is called "a system request trip". We assume that the system request trip can be realized by changing a future schedule or asking future potential users who want to get some rewards. In this presentation, we explain the effectiveness of the proposed method through case study in surrounding area of our university.
language of the presentation: Japanese
逋コ陦ィ鬘檎岼:ワンウェイ方式カーシェアリングにおける利用者へのトリップ依頼による車両偏在削減手法
発表概要: 近年,移動先で車を乗り捨てるワンウェイ方式カーシェアリングのサービスが開始されつつある.しかしながら,出発地に利用できる車車両があることと目的地に駐車できる空きスペースがあることの両方が保証できないため,普及が遅れている. 現在のサービスでは,運営会社の社員が手動で,ある場所に車車両を動かすが,それではコストがかかってしまう.また既存研究では,利用者に分割乗車や相乗りに依頼をするが,その場合その利用者の出発地と目的地のみしか対応できない. そこで本研究では,ワンウェイ方式カーシェアリングサービスにおける問題を解決するために,潜在的利用者に車車両を動かしてもらう(利用してもらう)手法を提案する. 本手法では,片道トリップの需要があると仮定し,"要求トリップ"というあらかじめ利用者の予約しているトリップに"依頼トリップ"という新たなトリップを追加することで,要求トリップ成立数の最大化を実現する.依頼トリップは,カーシェアリングのスケジュール変更や報酬を得たい潜在的利用者へ依頼することで実現できる. 本発表では,本学付近でのケーススタディを通して,提案手法の有効性を述べる.
 

会場: L2

司会: 畑 秀明
末長 和馬 1651061: M, 2回目発表 生体医用画像 佐藤 嘉伸, 金谷 重彦, 大竹 義人, 横田 太

title: Training data extension by postoperative CT for automatic surgery planning system

abstract: We have been developing an automatic preoperative planning system for total hip arthroplasty (THA). This system employs a statistical atlas, which was constructed with a large number of past preoperative plans (used as training datasets) prepared by an experienced surgeon, in order to model the expertise. This implementation enables to determine the optimal size, position, and rotation of the artificial joint from CT images. However, it is desirable to use not only the preoperative data but also the postoperative data for more detailed modeling of surgery. We propose a method for determination of cup position cup position from postoperative CT with metal artifact reduction for the expansion of training data for automatic surgical planning of the artificial joint cup. We apply this method to 9 cases and cup positions are compared between pre and post- operation. However, the average bone residue thickness in the acetabular back direction was 3.53 mm in preoperative and 5.69 mm in postoperative. From these results, it was confirmed that postoperative cup placement has margin in residual thickness of acetabular bone. In the future, we will analyze this factor and carry out detailed modeling of cup installation.

language of the presentation: Japanese

 
SINGH MADHURYA 1651131: M, 2回目発表 生体医用画像 佐藤 嘉伸, 金谷 重彦, 大竹 義人, 横田 太

title: Prostate cancer area precise estimation by integration of MR images and intraoperative biopsy information

abstract: A precise localization of a cancer from a medical image is a major challenge for a minimally invasive therapy which aims to preserve healthy tissues as much as possible and to remove tumors completely. In an area of urology, magnetic resonance imaging (MRI) is used for image diagnosis of a prostate cancer because MRI can give a very clear picture of the prostate. There are some studies for an automated segmentation of the prostate cancer from a multi-parametric MRI with a machine learning technic. However an intensity in MRI is not standardized likes CT images, there is fear that a learned classifier from a dataset of one facility can not suitably work for an image from other facilities. Therefore, we propose an automated segmentation method which is robust to difference of an imaging condition by combining MP-MRI data and a biopsy. The biopsy which is a procedure taking tissue from a patient by needle is definite diagnosis but very sparse than MRI. We believe that the combination of the biopsy and MRI leads more correct segmentation. In this presentation, I talk about current progress and remaining tasks.

language of the presentation: Japanese

 
上村 恭平 1661002: D, 中間発表 ソフトウェア設計学 飯田 元, 井上 美智子, 市川 昊平, 崔 恩瀞, 畑 秀明
title: Quantitative investigation of code clones in hardware description language.
abstract: A hardware description language (HDL) is a computer language used to describe the structure and behavior of digital logic circuits including field programmable gate arrays (FPGAs). The rapid growth of FPGA usage requires us to make circuit development involving HDLs more efficient. In this study, I focus on code clones in HDLs. Code clones are the similar segments of code that are typically created when the code is copied from one place to another. In software development, code clones are considered to decrease development efficiency. To study code clones in HDLs, I developed a code clone detection method for Verilog HDL, which is the most popular HDL. In this method, I apply simple conversion rules to the Verilog HDL code so that I can use existing code clone detection tools for traditional programming languages. The experiments showed that the accuracy of the proposed detection method was about 90\%. I compared code clones in Verilog HDL with those in Java and C based on the metrics to identify the differences among languages. I found that the tool support for consistent modification over clone setss is also useful for Verilog HDL. However, aggregating clone sets in Verilog HDL must take into consideration the trade-offs between computational parallelism and circuit footprints.
language of the presentation: Japanese