イベント

開催内容

第11回 神戸大学CMDS先端セミナー

タイトル

Optimal Retail Electricity Tariff Design with Prosumers: Pursuing Equity at the Expenses of Economic Efficiencies?

講演者

Prof. Yihsu Chen (Department of the Baskin School of Engineering, University of California Santa Cruz)

日時

2024年11月22日（金）15:00-16:00

場所

瀧川記念学術交流会　大会議室

形式

ハイブリッド形式(瀧川記念学術交流会　大会議室、Zoom)

概要

Distributed renewable resources owned by prosumers can be an effective way to strengthen the resilience of the grid and enhance sustainability. However, prosumers serve their own interests, and their objectives are unlikely to align with those of society. This article develops a bilevel model to study the optimal design of retail electricity tariffs considering the balance between economic efficiency and energy equity. The retail tariff entails a fixed charge and a volumetric charge tied to electricity usage to recover utilities’ fixed costs. We analyze the solution properties of the bilevel problem and prove an optimal rate design, which is to use fixed charges to recover fixed costs and to balance energy equity among different income groups. That is, the first-best policy is to leave the wholesale power market intact; any recovery based on a volumetric principle is likely to be inefficient. This suggests that programs similar to CARE (California Alternative Rate of Energy), which offer lower retail rates to low-income households, are unlikely to be efficient, even if they are politically appealing.

参加フォーム

https://forms.gle/apDYAKXZSZBwNdZh6 ※11/15入力〆切

第10回 神戸大学CMDS先端セミナー

タイトル

Adversarial Deep Learning

講演者

Dr. Wei Liu（University of Technology Sydney、UTS)

日時

2024年11月19日（火）15:00-16:00

場所

工学研究科 電気電子セミナー室（2E-202）

形式

ハイブリッド形式 ZOOMリンク

概要

Deep learning models are susceptible to adversarial attacks, where small and carefully crafted changes to input data can cause significant errors even in well-trained models. As these models become central to various critical applications, it is crucial to address the security implications of such vulnerabilities. This seminar explores adversarial attacks in computer vision and natural language processing domains and examines the unique challenges each domain presents. The talk will highlight how subtle manipulations can disrupt model predictions in visual recognition systems and text-based classifiers. It will discuss the underlying principles of adversarial learning, introducing strategies to design attacks while emphasizing the importance of maintaining semantic integrity. Furthermore, the talk covers innovative adaptive approaches that expand the attack scope while balancing imperceptibility and effectiveness. Additionally, the talk will address defense mechanisms and future research directions aimed at mitigating these vulnerabilities.

第9回 神戸大学CMDS先端セミナー

タイトル

Hyperconnected City Logistics

講演者

Prof. Russell Thompson (The University of Melbourne, Australia)

日時

2024年11月1日（金）11:00-11:45

場所

梅木Yホール、神戸大学深江キャンパス（Umeki Y Hall, Fukae Campus, Kobe University）

形式

対面のみ

概要

Hyperconnected city logistics is an innovative approach to managing urban freight and delivery systems. It aims to improve efficiency, sustainability, and responsiveness in urban environments by leveraging advanced technologies and seamless interconnectivity. In the seminar, Prof. Russell will present recent research projects on parcel lockers, last-mile delivery, crowdsourced delivery and multimodal transport.

略歴

Russell is a professor of Transport Engineering at the University of Melbourne. He holds a PhD in Transport Engineering (University of Melbourne). Over the past 20 years he has been involved in numerous local freight studies, including Melbourne's Freight Movement Model and the Victorian Freight and Logistics Plan. Russell heads the Physical Internet Lab at the University of Melbourne and is Vice President of the Institute for City Logistics based in Kyoto, Japan. He is currently conducting research studies on the benefits of the physical internet, parcel lockers, logistics sprawl, collaborative freight systems, road pricing, urban consolidation centers and multimodal freight systems.

第8回 神戸大学CMDS先端セミナー

タイトル

Data for Cybersecurity

講演者

Prof. Ali A. Ghorbani (Canadian Institute for Cybersecurity, University of New Brunswick)

日時

2024年9月6日(金) 14:00 - 15:00

場所

工学研究科本館 セミナー室（2E-202）

形式

ハイブリッド　※対面参加を歓迎します。

概要

The Canadian Institute for Cybersecurity (CIC) conducts research and development in various areas, including network security (such as intrusion detection and prevention, Dark Web, and malware analysis), systems security (covering mobile, software, and IoT), security analysis and risk management, security visualization, IoT-Big data security and privacy, critical infrastructure protection, and human-centric cybersecurity. Network-based IDSs require diverse datasets that represent a wide range of network behaviors and attack types. Finding and collecting representative data can be challenging, and datasets may be imbalanced, making it difficult to effectively train models. Generating synthetic network traffic data can help mitigate privacy and security concerns associated with real-world data. Dr. Ghorbani will discuss the datasets developed by his team at CIC over the past 15 years, which are used for training and testing cybersecurity solutions. The presentation will also include updates on CIC's latest R&D projects, project details, and research findings.

略歴

Dr. Ghorbani is the Tier 1 Canada Research Chair in Cybersecurity and founding director of the Canadian Institute for Cybersecurity he established in 2016. In addition, he served as the Dean of the Faculty of Computer Science at the University of New Brunswick from 2008 to 2017. He is the co-inventor of four awarded and one filed patent in Cybersecurity and Web Intelligence. He has published over three hundred peer-reviewed articles during his career. In addition, he has supervised over 250 research associates, postdoctoral fellows, and students. Dr. Ghorbani developed several technologies adopted by high-tech companies and co-founded three startups: Sentrant Security, EyesOver Technologies, and Cydarien Security, in 2013, 2015, and 2019. He co-founded the UNB-NRC Cybersecurity Collaboration Consortium and the National Cybersecurity Consortium (NCC) in 2019 and 2020, respectively. He co-founded the Privacy, Security, Trust (PST) Network in Canada and its annual international conference. Dr. Ghorbani served as the co-Editor-in-Chief of "Computational Intelligence: An International Journal" from 2007 to 2017. His achievements include receiving the 2017 Startup Canada Senior Entrepreneur Award, being named one of Canada's top 25 Canadian immigrants of 2019, and being recognized as one of the 40 inspiring Canadians in the book 'Forty Brilliant Canadians and Their Vision for the Nation' by Mark Bulgutch (2022). In addition, he received the 2024 Lifetime Achievement Award from CAIAC - the Canadian Artificial Intelligence Association.

第7回 神戸大学CMDS先端セミナー

タイトル

Spatiotemporal Graph Neural Networks

講演者

Prof. Cesare Alippi (Professor of Information Processing Systems, Politecnico di Milano)

日時

2024年7月11日(木) 15:00 - 16:00

場所

六甲台第２キャンパス 工学部　C4-301

形式

ハイブリッド　※できるだけ対面参加をお願いします。
参加 Zoom ミーティング

概要

Machine learning research on graph-based structured data is booming, with thousands of papers released in the past years. The increased production does not only shows the interest in foundational research but the relevance in applications too, as graphs with their information entities and relational dependencies are everywhere. The seminar will open views on spatiotemporal neural graph processing, i.e., in research/application frameworks where, in addition to “space” relations we exploit those that emerge over the time dimension. Applications enabling such processing are e.g., those associated with sensor networks in domains nowadays named smart grids, smart cities, IoT, Industry 40. The focus will mostly be on the prediction and the imputation tasks within a deep relational processing.

略歴

CESARE ALIPPI received the degree in electronic engineering cum laude in 1990 and the PhD in 1995 from Politecnico di Milano, Italy. Currently, he is a Professor with the Politecnico di Milano, Milano, Italy and Università della Svizzera italiana, Lugano, Switzerland. He has been a visiting researcher at UCL (UK), MIT (USA), ESPCI (F), CASIA (RC), A*STAR (SIN), GDUT (RC). Alippi is an IEEE Fellow, an ELLIS Fellow and an AAIA Fellow, Past Board of Governors member of the International Neural Network Society, past Vice-President education and Administrative Committee member of the IEEE Computational Intelligence Society, past associate editor of the IEEE Transactions on Emerging topics in computational intelligence, the IEEE Computational Intelligence Magazine, the IEEE-Transactions on Instrumentation and Measurements, the IEEE-Transactions on Neural Networks. He received the 2024 IEEE CIS Enrique Ruspini Meritorious Award, 2018 IEEE CIS Outstanding Computational Intelligence Magazine Award, the 2016 Gabor award from the International Neural Networks Society and the 2013 IEEE CIS Outstanding Transactions on Neural Networks and Learning Systems Paper Award, the IBM Faculty award, the 2004 IEEE Instrumentation and Measurement Society Young Engineer Award. Current research activity addresses graph processing, intelligence for embedded IoT, adaptation and learning in non-stationary environments and cyber-physical systems. He holds 8 patents, has published one monograph book, 7 edited books and more than 250 papers in international journals and conference proceedings.

第6回 神戸大学CMDS先端セミナー

タイトル

The State of the Art of Collaborative Neurodynamic Optimization

講演者

Prof. Jun Wang (Department of Computer Science & School of Data Science, City University of Hong Kong)

日時

2024年5月27日（月）　15:00-16:00

場所

工学研究科 LR-402 教室

概要

The past four decades witnessed the birth and growth of neurodynamic optimization, which has emerged as a potentially powerful problem-solving tool for constrained optimization due to its inherent nature of biological plausibility and parallel and distributed information processing. Despite the success, almost all existing neurodynamic approaches a few years ago worked well only for optimization problems with convex or generalized convex functions. Effective neurodynamic approaches to optimization problems with nonconvex functions and discrete variables are rarely available. In this talk, the advances in neurodynamic optimization will be presented. Specifically, In the proposed collaborative neurodynamic optimization framework, multiple neurodynamic optimization models with different initial states are employed for scattered searches. In addition, a meta-heuristic rule in swarm intelligence (such as PSO) is used to reposition neuronal searches upon their local convergence to escape local minima toward global optima. Problem formulations and experimental results will be elaborated to substantiate the viability and efficacy of several specific paradigms in this framework for supervised/semi-supervised feature selection, supervised learning, vehicle-task assignment, model predictive control, energy load dispatching, and financial portfolio selection.

開催報告

【講演概要】
香港城市大学のJun Wang教授に動的ニューラルネットによる協調型最適化手法の最新動向について、ご講演頂きました。まず、人の脳で行われている最適化の仕組みがフィードバック結合を有するニューラルネットの動的な特性を利用していることについて述べられ、そのパイオニアとしてJohn J. Hopfieldを紹介されました。そして、最適化問題の種類やその解法、特に非線形最適化問題を解くためのニューラルネットモデルと最適化問題への定式化、収束条件などを説明され、本講演の中心となるCollaborative Neurodynamicsの概念について詳細な説明がありました。

【発表形式】ハイブリッド（対面＋オンライン）
【参加者】教員・学生 44名（対面参加者15名、オンライン参加者29名）
【担当者】小澤誠一（数理・データサイエンスセンター）

第１回～第５回は，2018年度，2019年度のイベント履歴をご覧ください

問い合わせ先
こちらをご参照ください。