Keynote Speakers
Tuesday, September 10, 2024
Conference Welcome and Opening: Tuesday, September 10, 2024, 9:30 – 9:40 am
Opening Keynote I: Tuesday, September 10, 2024, 9:40 – 10:20 am
Prof. Dr. Mitsuo Gen
Fuzzy Logic Systems Institute (FLSI): Senior Research Scientist
Tokyo University of Science (TUS), Research Inst. of Sci. & Tech.: Visiting Prof.
Fellows of Society: SOFT and APIEMS
Field Chief Editor: Frontiers in Industrial Engineering
Presentation Title: Enhancing Multiobjective Metaheuristics with Machine Learning for Scheduling: Case Study of High-Speed Train Scheduling on GPU
Mitsuo Gen received his PhD in Engineering from Kogakuin University, PhD degree in Informatics from Kyoto University and is now Senior Research Scientist at FLSI and Visiting Prof. at TUS. He was faculties at Ashikaga Institute of Tech. for 1974-2003, at Waseda University for 2003-2010. He was visiting faculties at University of California at Berkeley for 1999.8-2000.3, Texas A&M University for 2000.1-3 & 2000.8-9, Hanyang University in S. Korea for 2010-2012 and National Tsing Hua Univ. in Taiwan for 2012-2014. His research field is Evolutionary Computation, Manufacturing Scheduling and Logistics Systems. He is a coauthor of the following books: Genetic Algorithms and Engineering Design, 1997 and Genetic Algorithms and Engineering Optimization, 2000, John Wiley & Sons, New York; Network Models and Optimization: Multiobjective Genetic Algorithm Approach, 2008 and Introduction to Evolutionary Algorithms, 2010, Springer, London. He is one of Area Editors of Computers & Industrial Engineering and Field Chief Editor of Frontiers in Industrial Engineering.
Abstract:
Many real-world applications for complex design problems could be modeled as optimization problems. These problems are often characterized by complex features such as multi-modality, dynamics, discontinuity, and nonlinearity. There problems are combinatorial optimization problems (COPs) imposing on more complex structure, nonlinear constraints, multiple objectives and uncertainty. The COPs make the problem intractable to the traditional approaches because of NP-hard ones. As one of the most typical scheduling problems, flexible jobshop scheduling problem (FJSP) is a generalization of the jobshop and parallel machine environment, which provides closer real manufacturing and logistics systems.
In order to develop an efficient algorithm whose reasonable computational time for NP-hard multiobjective COPs, we have to consider 1) quality of solution, 2) computational time and 3) effectiveness of the nondominated solutions for the multiobjective COP. As the most typical metaheuristics, genetic algorithm (GA) is a population-based metaheuristic, and it is a very powerful and broadly applicable stochastic search and optimization technique which is effective for solving various NP hard problems in Industrial Engineering problems.
In this talk, multiobjective hybrid GA and machine learning (ML) for high-speed train scheduling with GPU will be introduced. As the railway networks have become larger and more complex with increasing passenger demand, both aspects from the passenger satisfaction and operational cost need to be satisfied. We incorporate a learning-based algorithm into a mutation process. The evaluation process is divided into sub-process and calculated by a parallel computational unit using GPU CUDA framework. Two sets of numerical experiments based on a small-scale case of Thailand ARL transit line, a larger case of BTS transit network and high-speed train scheduling problems in Japan are implemented to verify the effectiveness of the proposed approaches. The experimental results show the effectiveness of the proposed algorithm comparing to sequential CPU computational and two classical MoGA with ML.
Keynote II: Tuesday, September 10, 2024, 10:20 – 11:00 am
Ilkyeong Moon, Ph.D., P.E.
Professor
Editor-in-Chief (2023- ), European Journal of Industrial Engineering
Former President (2019-2020), Korean Institute of Industrial Engineers (KIIE)
Department of Industrial Engineering
Seoul National University
Seoul 08826, KOREA
Presentation Title: Some research issues on the smart SCM
Ilkyeong Moon is a Professor of Industrial Engineering at Seoul National University in Korea. He received his B.S. and M.S. in Industrial Engineering from Seoul National University, and Ph.D. in Operations Research from Columbia University. His research interests include supply chain management, logistics, and inventory management. He published over 170 papers in international journals. He was a president of KIIE in which he had served from 2019 to 2020. He currently serves as an editor-in-chief for European Journal of IE. He is a fellow of Asia Pacific Industrial Engineering and Management Society and a board member for International Federation for Production Research.
Keynote III: Tuesday, September 10, 2024, 11:00 am – 11:40 am
Katsuki Fujisawa, Professor, Ph.D. (Sci.)
Professor
Institute of Innovate Research
Digital Twin Unit, Research Unit Leader
School of Computing
Department of Mathematical and Computing Science
Tokyo Institute of Technology
Tokyo, Japan
Presentation Title: Mathematical Optimization Models for Smart Factory Construction and Applications to the Field
Dr. Katsuki Fujisawa has held positions as a Professor at both the Institute of Innovative Research at Tokyo Institute of Technology and the Institute of Mathematics for Industry at Kyushu University, Japan. He received his Ph. D. from the Tokyo Institute of Technology in 1998. The major objective of our project is to develop an advanced computing and optimization infrastructure for extremely large-scale graphs on post peta-scale supercomputers. In recent years, these results have been used to promote large-scale industry-academia collaborations with many companies. His project team commenced our research project for developing the Urban OS (Operating System) for a large-scale city in 2013. The Urban OS, which is regarded as one of the emerging applications of the cyber- physical system (CPS), gathers big data sets of the distribution of people and transportation movements by utilizing sensor technologies and storing them in the cloud storage system. In the next step, they apply optimization, simulation and deep learning techniques to solve them and check the validity of solutions obtained on the cyber space. His project team has challenged the Graph500 benchmark, which is designed to measure the performance of a computer system for applications that require irregular memory and network access patterns. In 2014 to 2024, his project team was a winner at the eighth, 10th to 18th, and 20th-26th Graph500 benchmark. In 2017, He received the Prize for Science and Technology (Research Category), Commendation for Science and Technology by the Minister of Education, Culture, Sports, Science and Technology, Japan.
Abstract
Efforts are underway to solve various issues faced by cities, regions, and industries by utilizing the latest mathematical and information technologies to construct digital twins that encompass both physical and cyber spaces. In this talk, I explain the research on the latest mathematical optimization models for realizing digital twins, along with specific application examples in the industry. I also introduce ongoing smart factory construction projects in Japan and the United States.
Keynote IV: Tuesday, September 10, 2024, 11:40 – 12:20 pm
Dr. Masanobu Matsumaru
Visiting Researcher
Research Institute for Engineering
Kanagawa University
Kanagawa, Japan
Presentation Title: Bankruptcy discrimination model using machine learning with consideration of feature selection
Dr. Masanobu Matsumaru is currently visiting researcher in research institute for engineering and was former professor in Department of Industrial Engineering and Management Faculty of Engineering, Kanagawa University, Japan. He earned Bachelor of Engineering in Faculty of Science and Engineering from Waseda University, Japan, Master of Engineering in Master Course Graduate school of Science and Engineering from Waseda University and Doctor of Engineering from Tokai University. He has published journal and conference papers. Dr. Matsumaru research interests include development of scientific and engineering management technology to solve the management problems in manufacturing. Research field is management engineering. Research Overview is the development of scientific and engineering management technology to solve the management problems in manufacturing. Research Subjects are management quality and cost reduction in manufacturing, development of business management techniques and modeling in supply chain. Conventional Research Subjects are management quality and cost reduction in manufacturing, development of business management techniques and modeling in supply chain. Recent Research Subjects are bankruptcy prediction and corporate credit rating estimation using machine learning.
Abstract
Abstract: In the current climate of uncertainty, corporate management is extremely challenging, and the risk of bankruptcy is increasing due to deteriorating business performance. Corporate bankruptcies cause losses to stakeholders such as business partners, investors, and financial institutions, necessitating the development of models that can prevent or detect bankruptcies early. While many studies, including Altman’s research, have been conducted on bankruptcy discrimination models, machine learning models, which offer objective and highly accurate predictions, have become mainstream in recent years. I focus on the number of feature and construct bankruptcy discriminant model using two machine learning methods, Random Forest(hereafter: RF) and Light Gradient Boosting Machine (hereafter: Light GBM) , and study the effect of differences in the number of features on the discrimination accuracy of machine learning methods. The target data consists of publicly traded companies in the six industries with the highest number of bankruptcies, based on the Tokyo Stock Exchange’s 33-sector classification. These industries are Construction, Real Estate, Services, Retail, Electric Equipment, and Wholesale, excluding Electric Power and Gas, Banking, Securities and Commodity Futures, Insurance, and Other Financial industries. Financial indicators were obtained using Nikkei NEEDS-Financial QUEST, a comprehensive economic database service by Nikkei Inc. The dataset was created from the financial indicator data of companies in the six industries with the highest number of bankruptcies between 1990 and 2021.For features, financial indicators and NW indicators were used. Considering comprehensiveness, there were 161 financial indicators and 12 NW indicators, totaling 173 indicators. In this study, we create three types of datasets with various numbers of features to train machine learning models. In many cases, datasets are an essential element for improving the performance and accuracy of AI models with the development of AI technology, and the importance of datasets is increasing. The first is dataset using only financial indicators (hereafter: financial dataset). The second is dataset using both financial indicators and NW indicators (hereafter: investment dataset). In this case, companies for which NW indicators could not be calculated were excluded from the analysis. Therefore, the amount of data is smaller than that of financial data. The third is dataset excluding NW indicators from investment data (hereafter: comparative dataset). Next, I describe the overall picture of the constructed model. A total of 108 models combining six types of industries, three types of features, three resampling methods to address imbalanced data, and two machine learning methods were constructed. The resampling methods include k-means under sampling (hereafter: k-means), SMOTE, and SMOTE + Edited Nearest Neighbor (hereafter: SMOTE+ENN). I used RF and Light GBM as machine learning methods. Recall is particularly emphasized in the model evaluation. Recall is defined as Recall = TP / (TP + FN), using True Positive (TP) and False Negative (FN). This study focuses on the number of TPs to determine the features for bankruptcy discrimination. In other words, the model with the highest number of TPs is determined to be the optimal bankruptcy discrimination model. In doing so, the selected and useful financial indicators and NW indicators will be confirmed. Next, the combination of useful machine learning methods and resampling methods for each industry will be verified. To obtain a highly accurate bankruptcy discrimination mode, the number of features will be gradually reduced. Specifically, we conduct bankruptcy discriminant analysis while gradually reducing the number of indicators from 173 to 2, compare the accuracy after changing the number of features, and determine the optimal number of features. As a result of the bankruptcy discrimination analysis, the model with seven features using Random Forest had the best recall and achieved the highest number of true positives (TP). These seven features were cash flow to net interest-bearing debt ratio, net working capital amount, dividend to cash flow ratio, cash flow to long-term debt ratio, net interest burden to sales ratio, interest and discount fee to sales ratio, cash flow to fixed liabilities ratio, equity growth rate. The dataset with the highest recall used only financial data. The second highest used both financial and NW indicators, while the worst was the comparative data excluding NW indicators from the investment data. The method used was SMOTE+ENN, which proved to be the best, followed by the k-means method and SMOTE alone. Briefly touching on industry-specific results, the recall for the electric equipment industry was 82.61%, correctly identifying 19 out of 23 bankrupt companies, using a dataset with 9013 non-bankrupt and 23 bankrupt companies. These results confirm that creating appropriate datasets and determining the optimal number of features can improve the accuracy of bankruptcy discrimination.
Keynote IV: Tuesday, September 10, 2024, 12:20 – 1:00 pm
Dr. Yuki Kinoshita
Assistant Professor
Department of Informatics
Faculty of Engineering
Kindai University
Hiroshima, Japan
Presentation title: Sustainable Manufacturing Challenges and Approaches: Material Circulation with Integration of Supply Chain and Disassembly
Yuki Kinoshita is an Assistant Professor, Department of Informatics, Faculty of Engineering, Kindai University, Hiroshima, Japan. He received his B.S., M.S. and Dr. Eng. in research on Environmentally Conscious Manufacturing from The University of Electro-Communications. He was a research fellow (DC2) of Japan Society for the Promotion of Science (JSPS) from April 2018 to March 2020. He was a researcher at a Japanese largest security company “SECOM” from April 2020 to March 2023. Additionally, he stayed in Boston, USA for 3 months to conduct international collaboration research with Prof. Surendra M. Gupta at Northeastern University supported by JSPS Overseas Challenge Program for Young Researchers. His research interests include global low-carbon supply chain, disassembly production, warranty fraud and security issues in remanufactured products, and material selection. His works appear in International Journal of Production Economics, Sustainability, International Journal of Sustainable Manufacturing. He is the first Japanese winner of International Foundation for Production Research (IFPR) Early Career Researchers Mentoring Award.
Abstract:
Sustainable manufacturing has been required to realize carbon neutrality and circular economy. Material circulation through remanufacturing, component reuse, and material recycling contributes to reduction of Greenhouse gas (GHG) emissions because of saving virgin material production. To design global low-carbon supply chain, it needs to evaluate different GHG emissions, cost, and carbon policies such as carbon tax and carbon cap-and-trade for each country or region. The carbon policies are reported needs of stricter in near future. On the other hand, disassembly includes uncertainty of end-of-life products, selection of suitable recovery options, and disassembly production scheduling. Compared to assembly, selective and destructive disassembly are allowed depending on recovery options. In addition to uncertainty and variety of recovery options, this leads to complex management in disassembly production. This talk introduces challenges for sustainable manufacturing to reduce GHG emissions and waste economically. Focusing on materials, relationships among GHG emissions, waste, and costs in product life cycle are summarized. In this talk, perspective of material circulation with integration of these approaches are also discussed.
Wednesday, September 11, 2024
Keynote V: Wednesday, September 11, 2024, 9:40 – 10:20 am
Prof. Kenji Watanabe, Dr., MBA
Professor
Department of Architecture, Civil Engineering and Industrial Management Engineering
Nagoya Institute of Technology
Aichi, Japan
Presentation Title: Regional Resilience Enhancement through Establishment of Area-BCM at Industry Complexes in Thailand
Kenji Watanabe is a professor at the Graduate School of Social Engineering, and also the Head of Disaster & Safety Management of the Nagoya Institute of Technology, with major research areas in risk management, business continuity management (BCM), and critical infrastructure protection (CIP). He has almost 20 years of business experience at the Mizuho Bank, PricewaterhouseCoopers, and IBM Business Consulting Services in financial business and risk management fields. He is also a chair or a professional member of several Japanese governmental committees at the Critical Infrastructure Protection Council (Cabinet Secretariat), the Food Security Advisory Board (Ministry of Agriculture, Forestry and Fisheries), the Transportation Safety Council (Ministry of Land, Infrastructure, Transport and Tourism), and others. As international activities, he is a member of the Future Vision Committee (DRII: Disaster Recovery Institute International), the head of delegates of Japan for ISO/TC292(Security and resilience), editorial committee member of the International Journal of Critical Infrastructure Protection (IJCIP) and the Journal of Disaster Research (JDR). He has executed many disaster management related projects including the Area-BCM project in Thailand sponsored by JICA to enhance regional disaster resilience at industry complexes. (2017-2024). He holds PhD (Waseda University) and MBA (Southern Methodist University).
Abstract:
This project aims to contribute to sustainable social and economic development in Thailand by strengthening regional resilience through the establishment of “Area-BCM” framework in Thailand’s industrial clusters, and to disseminate to ASEAN and other countries through ISO standardization. As the 2011 Chao Phraya River severe floods revealed, the causes of damage escalation were triggered by natural phenomena and involved a complex set of technological, social, economic, and political factors. This shows that a one-way approach from natural science and engineering is not sufficient to contribute to disaster mitigation, but a practical and comprehensive approach from multiple fields that encompasses social sciences and transcends professional boundaries is necessary. Therefore, this project aims to construct Area-BCM through collaboration among experts in the natural, engineering, and social sciences, as well as stakeholders, in order to strengthen “local resilience,” which is essential for disaster-resistant local communities.
For the social implementation of the results of this project, it is essential to establish an information sharing mechanism (information needs among stakeholders in terms of content, granularity, timing, and methods of information) and a coordination function among stakeholders based on public-private partnerships among stakeholders in the areas subject to Area-BCM. In addition, since the Area-BCM framework must continue to be improved as a management cycle even after implementation, human resource development over the medium to long term and the continuous development of science and technology as tools are essential.
Keynote VI: Wednesday, September 11, 2024, 10:20 – 11:00 am
Tomohiro Kojima
Principal of Salesian Polytechnic
Tokyo, Japan
Presentation Title: Introduction to College of Technology (KOSEN) system in Japan
Tomohiro Kojima, Principal of Salesian Polytechnic College, Catholic priest, member of the Salesian Order. After graduating from the Faculty of Theology at Sophia University in 1996, he received a Master of Theology from the Pontifical Josephinum college in 1998. He was ordained a priest in the same year.
Abstract:
In 2022, the technical college system celebrated 60th anniversary. The history of technical colleges overlaps with the history of Japan’s industrial development. During the period of high economic growth that began in the 1950s, demanded for engineers involved in heavy and chemical industrialization increased, and technical colleges were born as the government responded to the shortage of engineers. At the beginning, senior engineers were university graduates involved in research, while intermediate engineers responsible for solving specific problems at companies were graduates of technical colleges. Currently, research is being conducted at technical colleges, and many companies look to technical colleges to produce excellent engineers who can work immediately. In an OECD review conducted in 2009, the educational system of technical colleges was highly praised. You will have time to receive specialized education for 5 years, or 7 years if you include an advanced course. Additionally, upon graduation, students have many options to choose from, such as majoring in an advanced course, going to university, or getting a job. Practical education is also provided through contests such as robot contests. In Japan, technical colleges are affectionately known as technical colleges (KOSEN). This presentation will look back on the history of technical college education and the role that technical colleges have played in industry. Furthermore, we will introduce the current content of technical college education, what is expected from industry, and the role that technical colleges will play in the future.
Keynote VII: Wednesday, September 11, 2024, 11:00 – 11:40 am
Satoru Hommo
Senior Manager, Global Repair Procurement, Global ESD & Repair, Procurement
Olympus Corporation
Tokyo, Japan
Presentation Title: A case study of service parts supply chain
Satoru Hommo received his B.E. and M.E. degrees in Industrial Engineering from Nagaoka University of Technology, Niigata, Japan. He started his professional career as a production planner of medical devices. He has developed a supply chain skill set in capacity planning, repair parts inventory planning, and business planning. He is currently responsible for global procurement strategy in the service and repair business area. His research and job interests include supply chain, engineering chain, project management, and mathematical optimization.
Abstract:
Efficient service parts management is vital to enhance customer satisfaction. Necessary repair parts should be delivered in a timely manner in response to customer requirements. However, the management and operation of service parts supply chain is much more complicated than the general supply chain for finished products. Direct applications of general supply chain methodology to that field might lower the management efficiency. It is thus important to optimize the inventory level of service parts to meet customer demands for service parts. In this talk, a case study of service parts supply chain will be presented. The methodology developed by Olympus Corporation is shown to be a best practice example.
Keynote VIII: Wednesday, September 11, 2024, 11:40 am – 12:20 pm
Dr. Eng. Andi Cakravastia Arisaputra Raja, S.T., M.T.
Associate Professor in Industrial Engineering
Institut Teknologi Bandung (ITB)
Bandung, Indonesia
Presentation Title: Modeling Activities and Collaboration in an e-Commerce Based Supply Chain
Dr. Andi Cakravastia is an Associate Professor in Faculty of Industrial Technology, Bandung Institute of Technology. Dr. Andi Cakravastia has published numerous publications in various international peer-reviewed journals and presented scientific papers across the world. Because of the active association with different societies and academies as well as the contributions, Dr. Andi Cakravastia have been recognized by the subject experts around the world. Dr. Andi Cakravastia clinical research and teaching interests include Supply Chain System Integration, Operation Research and Decision Science. Now, Dr. Andi Cakravastia appointed as Director University Development Bandung Institute of Technology. He is now serving as Vice President APIEMS – Asia Pacific Industrial Engineering and Management Society, Academic & Curriculum Coordinator BKSTI – Coordination Body of Industrial Engineering Higher Education Institution, Academic Coordinator – Institute of Supply Chain and Logistics Indonesia.
Wednesday, September 11, 2024, 12:20 – 1:00 pm
Karl Hans Greimel, Jr.
Asia Editor
Automotive News, Crain Communications Inc.
Tokyo, Japan
Presentation Title: Automotive Culture Wars
Hans Greimel is an award-winning American business journalist and author, specializing in Japanese, Korean, and other Asian automakers. He is the Asia Editor at Automotive News in Tokyo. Greimel co-authored Collision Course: Carlos Ghosn and the Culture Wars That Upended an Auto Empire, published in 2022 by Harvard Business Review Press. The book offers a fast-paced chronicle of the spectacular downfall of Carlos Ghosn, the legendary auto executive who rescued Nissan Motor Co. from bankruptcy, only to be charged with multiple counts of financial misconduct during his time at the top.
Greimel has reported on Nissan for over a decade and conducted multiple interviews with Ghosn, the indicted former Nissan-Renault Chairman. He also traveled to Beirut, Lebanon, in January 2020 to cover Ghosn’s first press conference following his dramatic escape from Japan. Greimel’s comprehensive coverage of the Ghosn scandal earned him the 2019 Folio Eddie Award for Best Series of Articles.
As an international journalist, Greimel has reported stories from 19 countries across four continents. Before joining Automotive News in 2007, he served as a foreign correspondent for The Associated Press, with assignments in Japan, South Korea, and Germany. His notable work includes coverage of the arrest of Carlos Ghosn, the rise of China’s auto industry, Toyota President Akio Toyoda’s leadership style, Toyota’s unintended acceleration-recall crisis, the 2011 earthquake-tsunami-nuclear meltdown disaster in Japan, and a groundbreaking exposé on rampant price-fixing among Japanese auto parts suppliers.
Born near Detroit, Michigan, Greimel holds a bachelor’s degree in political science and philosophy from the University of Michigan and a master’s degree in international affairs from Columbia University in New York. He frequently provides expert commentary on the global automotive industry for international broadcasters such as BBC, ABC, Bloomberg TV, Al Jazeera, and Reuters TV, as well as Japanese networks TV Tokyo, NHK and TBS. Since 2009, Greimel has been a part-time instructor at Waseda University’s Graduate School of Journalism, where he teaches two courses on international journalism.
Automotive News, based in Detroit and founded in 1925, is the leading source of automotive news and the newspaper of record for the global industry.
Thursday, September 12, 2024
Keynote IX: Thursday, September 12, 2024, 9:40 – 10:20 am
Dr. Ashir Ahmed
Associate Professor
Department of Advanced Information Technology
Faculty of Information Science and Electrical Engineering
Kyushu University
Fukuoka, Japan
Presentation Title: Innovating Healthcare Delivery to Achieve SDG 3.8: A Roadmap for Universal Health Coverage
Dr. Ashir Ahmed is an associate professor at the department of advanced information technology in Kyushu University, Japan, the director of GCC project in Grameen Communications, Bangladesh and the founder and CTO of SocialTech, Japan. His research aims to produce and promote ICT based social services for the unreached community in the world. In 2007, he joined Kyushu University as a guest associate professor under the research superstar program by Japan Science and Technology Agency. Through this program, he developed a joint collaboration with Grameen and Kyushu University and produced numerous international projects e.g. GramWeb (a village information platform), ePassbook (an electronic gadget for unreached community), $300 portable clinic and IGPF (Income Generation Project for Farmers using ICT). Inside Kyushu University, he developed a team of multi-disciplinary researchers which ultimately produced two research organizations e.g. GCL (Grameen Creative Lab) and GTL (Grameen Technology Lab) in 2009. In 2011, a social business research institute has been established in the university. He volunteered establishing several social business joint ventures. Ashir worked for NTT Communications to develop SIP based applications for home electronic devices and represented NTT Communications in International forum namely IETF to standardize NTT’s technology. He worked as an MTS1 in Avaya Labs, Japan to R&D Avaya’s SIP based products for Japanese market. Ashir was a visiting researcher at JGN (Japan Gigabit Network) project under the Telecommunication Advancement Organization and successfully setup regional TAO office in Sendai, Japan. Ashir received his Ph.D. in Information Sciences from Tohoku University in 1999.
Specialties: Social Technologies, Disruptive Technologies, Rural Information, ICT4D, ICT, SIP, VoIP, Social Business
Keynote X: Thursday, September 12, 2024, 10:20 – 11:00 am
Ziang Liu, Ph.D.
Faculty of Environmental, Life, Natural Science and Technology
Okayama University
Okayama, Japan
Presentation Title: Integrating Machine Learning and Optimization for Decision Making in Supply Chain Management
Ziang Liu is an assistant professor at Okayama University, Japan. He received his Ph.D. degree in Engineering from Osaka University in 2019. His research interests include supply chain management, optimization, and machine learning.
Abstract:
Optimization methods have been widely used to solve decision-making problems in supply chain management. In recent years, machine learning techniques have been increasingly applied to assist optimization methods. This talk will introduce how machine learning can be integrated with optimization to improve decision-making in supply chain management. We will discuss integrating machine learning and optimization in two aspects: surrogate-assisted optimization and reinforcement learning. Surrogate-assisted optimization uses machine learning models to approximate the objective function or constraints of optimization problems. Reinforcement learning is a machine learning technique that learns to make decisions by interacting with the environment. We will discuss how these techniques can be applied to solve decision-making problems in supply chain management. Furthermore, we will discuss the challenges and opportunities of integrating machine learning and optimization, including explainability, scalability, and privacy issues.
Keynote XI: Thursday, September 12, 2024, 11:00 am – 11:40 am
Kenji Amagai, Professor, Dr. Eng.
Division of Mechanical Science and Technology
Graduate School of Science and Technology
Director, Center for Research on Adoption of NextGen Transportation Systems (CRANTS)
Gunma University, Japan
Presentation Title: Development and social implementation of a low-speed electric bus for the revitalization of local community
Biography:
Kenji Amagai is a Professor at Gunma University in Japan. He received a Bachelor of Engineering in 1985 and a Master of Engineering in 1987 for research on mechanical engineering from The University of Electro-Communications. He also received a Doctor of Engineering from Tohoku University in 1992. He was a research fellow of the Japan Society for the Promotion of Science (JSPS) from 1990 to 1992. In 1992, he became an assistant professor at Gunma University. In 2008, he was appointed to his current position. He is also currently the Director of the Center for Research on the Introduction of Next-Generation Transportation Systems (CRANTS) at Gunma University. His research fields are thermo-fluid dynamics, flow visualization, and CMP processes of semiconductor wafers. He is also studying the new mobility utilization at local area revitalization.
Abstract:
Depopulation and aging are currently problems in many regional cities in Japan. In these areas, it becomes difficult to maintain public transport services and ensure mobility for residents. This leads to reduced communication among residents and a lower quality of life. Projects to provide sustainable mobility for the residents in these areas are important. To solve these local problems, the author’s group has developed low-speed electric community buses (LSECBs) and researched their social implementation. The LSECBs are electric vehicles that can travel on public roads at speeds of 5.56 m/s (20 km/h) or less. The LSECBs were jointly developed with the participation of local companies, local authorities, universities, and residents. LSECBs are suitable for short-distance operations within small regional areas. The LSECBs can promote human connections and communication and improve quality of life. This study examines the effectiveness of LSECBs in enhancing the sustainability of local communities.
Keynote XII: Thursday, September 12, 2024, 11:40 am – 12:20 pm
Baoding Liu, Ph.D.
Professor
Department of Mathematical Sciences
Tsinghua University
Beijing, China
Presentation Title: Uncertainty Theory
Biography: Baoding Liu received his B.S. degree in 1986 from Nankai University, and his M.S. degree in 1989 and Ph.D. degree in 1993 from Chinese Academy of Sciences. He began his academic career at Ashikaga Institute of Technology, Japan as a postdoctor in 1993. From there he moved to Tsinghua University as an associate professor in 1996 and became a professor of mathematics in 1998. Dr. Liu founded uncertainty theory that is a branch of mathematics concerned with the analysis of uncertain phenomena, and subsequently developed uncertain statistics, uncertain programming, uncertain logic, uncertain process, uncertain calculus, uncertain differential equation, as well as uncertain finance.
Abstract:
Something is called random if its frequency of occurrence is known. Otherwise, it is called uncertain. The outcome of tossing a coin is an example of randomness since the frequency that the coin will come up heads is known. The outcome of a falling cake is an example of uncertainty since the frequency that the cake will land butter-side down is unknown. In order to rationally deal with those phenomena, there exist two mathematical systems, one is probability theory and the other is uncertainty theory. Probability theory is a branch of mathematics concerned with the analysis of random phenomena, while uncertainty theory is a branch of mathematics concerned with the analysis of uncertain phenomena. In order to use them to handle some quantity (e.g., stock price) in practice, the first action is to produce a distribution function representing the possibility that the quantity falls into the left side of the current point. If you believe the distribution function is close enough to the future frequency, then you should use probability theory. Otherwise, you have to use uncertainty theory. Numerous empirical studies show that the real world is far from frequency stability. This fact makes the distribution function obtained in practice usually deviate from the future frequency even when numerous observed data are available, and consequently provides a motivation to learn and use uncertainty theory.
This presentation is based on the speaker’s book Uncertainty Theory published by Springer-Verlag, Berlin.