Details of a Researcher - Shida, Keisuke

Shida, Keisuke

写真a

Affiliation: Faculty of Science and Technology, Department of Industrial and Systems Engineering (Yagami)

Position: Associate Professor

Page Top ▲

Career 【 Display / hide 】

2003.04

-

2007.03

青山学院大学, 理工学部経営システム工学科, 助手
2007.04

-

2007.09

青山学院大学, 理工学部経営システム工学科, 助教
2007.10

-

2014.03

国立大学法人長岡技術科学大学, 工学部経営情報系, 准教授
2014.04

-

Present

慶應義塾大学, 理工学部管理工学科, 准教授

Page Top ▲

Academic Degrees 【 Display / hide 】

博士（工学）, Keio University, Coursework, 2006.03

Page Top ▲

Books 【 Display / hide 】

ヒューマンエラー対策事例集　－独自性のある仕組みづくり,効果のある教育法－

情報技術協会, 2013.01

Original author：志田敬介

Page Top ▲

Papers 【 Display / hide 】

Clarifying the Timing of Mold Maintenance in Resin Molding

YAMAZAKI Tomoaki, SAKAKIBARA Arata, NAKADA Yoshiharu, SHIDA Keisuke

Journal of Japan Industrial Management Association (Japan Industrial Management Association) 75 ( 2 ) 76 - 87 2024.08

Research paper (scientific journal), Last author, Accepted, ISSN 13422618

　View Summary

Gas burning that occurs during the resin molding process is fundamentally due to the improper venting of gas. However, finding a solution is extremely difficult as the phenomenon arises from a complex interplay of numerous factors. In the maintenance of molding machines and molds, carrying out regular inspections, replacing parts, cleaning, and maintaining the machine condition are practical and effective measures. During quality control, it is important to perform maintenance at the appropriate timing, but the timing is often determined based on experience and intuition, meaning that there is a lack of clear standards. This paper proposes a method using a deep learning classification model to clarify the timing at which maintenance should be performed based on the perspectives of quality and efficiency. In the proposed method, first, the cosine similarity between images of an initially molded product, which serves as a standard, and images of each subsequent product is calculated. Then, transfer learning of the deep learning model is performed in which classification is performed based on similarity. Finally, fine-tuning is performed. Emphasis is placed on the utilization of a loss function that directly controls the feature values during the fine-tuning.
- Access to Document (DOI)
- CiNii Research
A Study on Automation of Work Measurement in Assembly Work Using Region of Interest and Deep Learning

NAKANO Takumi, SHIDA Keisuke

Journal of Japan Industrial Management Association (Japan Industrial Management Association) 74 ( 2 ) 53 - 60 2023.04

Research paper (scientific journal), Last author, Accepted, ISSN 13422618

　View Summary

This paper focuses on the automation of work measurement using a camera to capture workers' hands in an assembly factory and analyzing the image to estimate the work content. In recent years, the technology to collect, analyze, and visualize manufacturing data from various devices installed in processing machines has been improving. However, it has not yet reached the point where workers' manual operations can be analyzed and visualized in real time. In this study, it is proposed that high estimate accuracy can be achieved using two analysis procedures to analyze a worker's image with deep learning: setting the region of interest and estimating the work content from the features in the region of interest. As a result of an evaluation experiment conducted at an actual factory using the proposed method, 99.5% of the work was correctly estimated. Based on these results, the method proposed in this study is now being examined in anticipation of introducing it for practical application.
- Access to Document (DOI)
- CiNii Research
A Research on Two-Stage Production Line Building Problems for Processed Cheese Manufacturing

MATSUMOTO Takao, KUBODERA Shizuka, SHIDA Keisuke, MATSUKAWA Hiroaki

Journal of Japan Industrial Management Association (Japan Industrial Management Association) 72 ( 1 ) 65 - 74 2021.04

Research paper (scientific journal), Accepted, ISSN 13422618

　View Summary

Production line design is one of the important research topics for constructing smart factories. Many research papers have been published concerning smart factories; however, most of them are focus on subjects such as automation, IoT (Internet of Things), AI (Artificial Intelligence) and other new technologies that are introduced to increase the eﬃciency of existing manufacturing lines based on the so-called philosophy of “ status-quo improvement ”. In this research, we consider a design problem for a new production line taking into consideration investment cost, operation cost, synchronization penalty and ﬂexibility penalty. We emphasize synchronization and ﬂexibility as new key performance indices to evaluate the level of intelligenced to the smart factory, in which a multiple number of equipment in two production processes can provide the proper number of combinations to satisfy the external demand remove. Based on a real case involving a major player in the dairy product processing industry in Japan, we focus on two core production processes in a processed cheese manufacturing line; melting process and filling process. We design the process to include investing in a multiple number of machines with diﬀerent capacities, while minimizing the total cost giving consideration to investment, operations, synchronization and ﬂexibility. Two types of decision variables are introduced representing investment and operation. Through numerical experiments and the case study, we show that the proper number of equipment and capacity can be obtained applying the proposed model. The proposed model can also be applied to those companies considering further investment in factory or production line.
- Access to Document (DOI)
- CiNii Research
Development of Automatic Work Analysis for Assembly Work using Motion Picture Analysis of Hand Position and Motion

NAKANO Takumi, YAMAZAKI Tomoaki, SHIDA Keisuke

Journal of Japan Industrial Management Association (Japan Industrial Management Association) 71 ( 4E ) 233 - 240 2021.01

Research paper (scientific journal), Last author, Corresponding author, Accepted, ISSN 13422618

　View Summary

This study presents a video analysis method for assembly factories. In recent years, there has been an increasing demand to collect manufacturing data in the manufacturing industry. While visualizing manufacturing data in real time to analyze practical manual work has not yet been realized, technologies for data collection, analysis and visualization have made progress using many kinds of machines and sensors. The introduction of various sensors and machines has resulted in changes in processes for visualizing the collection of manufacturing data in real time and analyzing it, as well as the collection and analysis of data. While difficult to do manually, the real-time monitoring of production data can help to quickly respond to problems, investigate causes, and improve operations. Therefore the authors propose a work analysis method that uses videos to analyze hand movement and position and product position. As a result, an analysis accuracy of 99.3% is obtained when studying standardized work in an ideal capture environment, and the cause of the reduction in accuracy is clarified.
- Access to Document (DOI)
- CiNii Research
目視検査における欠点色と背景色が周辺視野での欠点検出に及ぼす影響

志田敬介

ヒューマンファクターズ 23 ( 2 ) 57 - 67 2019.02

Research paper (scientific journal), Lead author, Corresponding author, Accepted

display all >>

Page Top ▲

Papers, etc., Registered in KOARA 【 Display / hide 】

An empirical study on skill assessment of workers on skill transfer

Shida, Keisuke

科学研究費補助金研究成果報告書 2018
A study on process control using image analysis to reduce work error

Shida, Keisuke

科学研究費補助金研究成果報告書 2016

Page Top ▲

Reviews, Commentaries, etc. 【 Display / hide 】

管理工学におけるIE研究

志田敬介

オペレーションズ・リサーチ 66 ( 3 ) 176 - 180 2021.03

Article, review, commentary, editorial, etc. (scientific journal), Single Work, Lead author, Corresponding author

Page Top ▲

Presentations 【 Display / hide 】

深層学習を用いた組立作業管理システムの導入支援に関する研究

多田竣汰, 中野匠, 中嶋良介, 志田敬介

日本経営工学会2024年春季大会,

2024.05
,
Oral presentation (general)
深層学習を用いた組立作業における作業データの収集とその応用に関する実証的研究

中野匠, 志田敬介

日本経営工学会2023年春季大会,

2023.06
,
Oral presentation (general)
A Fundamental Study on Automation of Visual Inspection by Deep Learning

Hirotomo Oshima, Tomoaki Yamazaki, Keisuke Shida

The Asia Pacific Industrial Engineering & Management Systems Conference 2018,

2018.12
,
Oral presentation (general)
Practice of Predicting Product Quality through Long Short-Term Memory Networks Using Manufacturing Process Data

Tomoaki Yamazaki, Keisuke Shida

The Asia Pacific Industrial Engineering & Management Systems Conference 2018,

2018.12
,
Oral presentation (general)
A Study on the Method for Evaluation of Learning Level Based on Brain Activity

Naoki Motohama, Tomoaki Yamazaki, Keisuke Shida

The Asia Pacific Industrial Engineering & Management Systems Conference 2018,

2018.12
,
Oral presentation (general)

display all >>

Page Top ▲

Research Projects of Competitive Funds, etc. 【 Display / hide 】

A Study on the Evaluation and Enhancement of Judgment Skills in the Transfer of Skills

2023.04

-

2026.03

文部科学省・日本学術振興会, Grants-in-Aid for Scientific Research, Grant-in-Aid for Scientific Research (B), Principal investigator

　View Summary

わが国の製造業における高付加価値、高品質な製品は、設備や道具を高い技能で操作する作業者によって支えられている。本研究は、その様な技能者を育成する訓練に着目して研究を進める。優れた技能を習得するには、作業を成功に導く最適な身体動作を理解するとともに、その遂行が正しくなされているかを適切に判断する技術が作業者には求められる。
訓練中は、様々な試行錯誤の帰結として動作のバラツキが大きくなり、作業にミスが生じる。この身体動作のバラツキを適切に判断できる技術が、作業技能の習得に及ぼす影響すると考えており、本研究で実証的に検証し、技能伝承の解明について深化させる。
A study on changes in physiological response of workers during the skill transfer process

2020.04

-

2023.03

MEXT,JSPS, Grant-in-Aid for Scientific Research, SHIDA KEISUKE, Grant-in-Aid for Scientific Research (B), Principal investigator

　View Summary

This study attempted to evaluate the level of skill acquisition of workers based on changes in physiological response characteristics using functional Near Infrared Spectroscopy (fNIRS), which measures brain activity states. As a result, it was possible to assess the qualitative aspects of skill acquisition, such as task accuracy, based on the brain's activity states. Furthermore, to promote skill acquisition, the timing of providing verbal cues to the workers was evaluated, and it was found that providing cues immediately after a task error occurred was effective. Additionally, in order to assess the level of skill acquisition of workers, a task analysis system utilizing deep learning was developed, and its effectiveness was confirmed in an actual factory.
An Empirical Study on Skill Assessment of Workers on Skill Transfer

2016.04

-

2019.03

MEXT,JSPS, Grant-in-Aid for Scientific Research, Shida Keisuke, Grant-in-Aid for Scientific Research (B), Principal investigator

　View Summary

High skills can be acquired in long-term training. Among the skills are many implicit knowledge. Past study on work learning focused on working time. However, just only working time is difficult to assess for implicit knowledge acquisition.
In this study, acquisition of implicit knowledge in the process of work learning is evaluated using functional Near Infrared Spectroscopy (NIRS). As a result, we are able to evaluate the state of implicit knowledge acquisition from the state of the worker's brain activity.
A study on process control using image analysis to reduce work error

2015.04

-

2017.03

MEXT,JSPS, Grant-in-Aid for Scientific Research, Grant-in-Aid for Challenging Exploratory Research, Principal investigator

　View Summary

The purpose of this study is to reduce a work error such as an error in the assembly order of parts, a forgetting to install the parts. In particular, in this research, we examined the camera position to capture the work in two ways. One is estimating work contents by installing the camera on the ceiling and analyzing the image. The other is estimating work contents by the wearable camera and analyzing the image.
目視検査における頭部運動が欠点検出に及ぼす影響に関する研究

2013.04

-

2014.03

（財）エヌ・エス知覚科学振興会, Principal investigator