主题演讲人
Shyi-Ming Chen
Chair Professor
National Taiwan University of Science and Technology
演讲标题:Fuzzy Forecasting Based on High-Order Fuzzy Time Series and Genetic Algorithms
摘要: In our daily life, we often use forecasting techniques to predict the weather, the earthquakes, the stock, the temperature, .., etc. Many methods have been presented to deal with forecasting problems. The drawbacks of the traditional forecasting methods are that they cannot deal with forecasting problems whose historical data are linguistic values and their forecasting accuracy rates are not good enough. In this talk, we present a method to forecast the temperature and the TAIFEX (Taiwan Futures Exchange) based on the two-factors high-order fuzzy time series. We also present a method for temperature prediction and TAIFEX forecasting based on genetic algorithms and two-factors high-order fuzzy time series. The proposed methods get higher forecasting accuracy rates than the ones of the existing methods.
简历: Shyi-Ming Chen 是国立台湾科技大学计算机科学与信息工程系的讲座教授。他于1991年6月在台湾国立台湾大学获得电气工程博士学位。他是IEEE Fellow、IET Fellow、IFSA Fellow、AAIA Fellow、IETI杰出Fellow以及巴基斯坦工程科学院院士。他曾是金文科技大学电气工程与计算机科学学院院长，国立台中教育大学的副校长。他曾是台湾人工智能学会（TAAI）和台湾消费电子学会（TACE）的会长。他在期刊、会议论文集和书籍章节中发表了超过600篇论文。他的研究兴趣包括模糊系统、智能系统、模糊决策、计算智能、基于知识的系统、机器学习、数据挖掘、大数据分析、遗传算法以及粒子群优化技术。他是《Granular Computing》的主编，IEEE Transactions on Fuzzy Systems的副主编，IEEE Transactions on Cybernetics的副主编，IEEE Transactions on Artificial Intelligence的副主编，IEEE Access的副主编，Information Sciences的副主编，Knowledge-Based Systems的副主编，Applied Intelligence的副主编，Information Fusion的编委会成员，Journal of Intelligent & Fuzzy Systems的副主编，International Journal on Artificial Intelligence Tools的副主编，International Journal of Pattern Recognition and Artificial Intelligence的副主编，International Journal of Fuzzy Systems的副主编，Journal of Information Science and Engineering的副主编，Fuzzy Optimization and Decision Making的副主编，Knowledge and Information Systems的副主编，International Journal of Intelligent Systems的编辑，Mathematical Problems in Engineering的编辑，以及Engineering applications of Artificial Intelligence的编辑。
武庆庆
Associate Professor
上海交通大学
演讲标题:Intelligent Reflecting Surface Empowered 6G Wireless Networks
摘要: Deepfakes are artificially created media posing as actual video recordings and are a potential source of fake news or disinformation. Although research has been done in developing algorithms for the automatic detection of deepfakes, there needs to be more work conducted on how users identify deep fakes. This is a critical missing link because algorithms are currently not performing at a level where human judgement is unneeded. This presentation will discuss the verification strategies users adopt when engaging with content from deepfakes and the implications on businesses and societies.In this talk, we introduce a new wireless research paradigm by employing a massive number of low-cost passive reflecting elements with controllable phase, named intelligent reflecting surface (IRS), which is able to smartly change the wireless signal propagation to enable various functions such as beamforming and interference nulling/cancelation. We illustrate the main applications of IRS in achieving spectrum and energy efficient as well as secure and sustainable wireless networks in the future, and its advantages as compared to existing technologies such as massive MIMO and active relaying. We then present the signal and channel model of IRS by taking into account its hardware limitation in practice. Next, we focus on discussing the main design challenges in IRS-aided wireless networks, including joint active and passive beamforming optimization, channel estimation, etc., and highlight important directions for sensing, powering and computing.
简历:武庆庆，上海交通大学，副教授。他目前的研究兴趣包括智能反射表面（IRS）、无人机通信和MIMO收发器设计。他与他人合著了100多篇IEEE期刊论文，其中包括30多篇被ESI高度引用论文和9篇ESI热门论文，共获得了超过26,000次谷歌引用。他分别于2022年和2021年被列为Clarivate ESI高被引研究员，2021年获得Aminer颁发的AI-2000最具影响力学者奖，并于2020年和2021年被斯坦福大学评为世界顶尖2%的科学家。
他曾获得IEEE通信学会Fred Ellersick奖、2023年IEEE最佳教程论文奖、2022年亚太地区最佳青年研究员奖和优秀论文奖、2021年年轻作者最佳论文奖、2017年中国通信学会优秀博士论文奖、2021年IEEE ICCC最佳论文奖和2015年IEEE WCSP最佳论文奖。他曾被评为2019年IEEE Communications Letters优秀编辑，并担任多个IEEE期刊的优秀审稿人。他现任IEEE Transactions on Communications、IEEE Communications Letters、IEEE Wireless Communications Letters的副编辑。他还担任IEEE Journal on Selected Areas in Communications首席客座编辑，是IEEE ICC 2019-2023和IEEE GLOBECOM 2020的研讨会联席主席，IEEE通信学会亚太地区青年协会主席。
Mohammad Reza Ghavidel Aghdam
博士
Özyeğin University
演讲标题:Toward Enhanced Wireless Communications: Leveraging Reconfigurable Intelligent Surfaces (RIS) and End-to-End Machine Learning
摘要: In the rapidly evolving landscape of wireless communication networks, the emergence of Reconfigurable Intelligent Surfaces (RIS) stands as a game-changer. These surfaces, empowered by intelligent algorithms, offer unprecedented control over electromagnetic wave propagation, promising to revolutionize communication efficiency and coverage. RIS introduces a paradigm shift in the way we conceive and implement wireless communication systems. By strategically deploying passive reflecting elements, RIS optimizes signal transmission, mitigates interference, and enhances overall network performance. However, to fully unlock the capabilities of RIS, seamless integration with machine learning is imperative.
End-to-end (E2E) machine learning algorithms provide a holistic approach to optimizing the performance of RIS-enabled communication networks. These algorithms leverage vast amounts of data to autonomously adapt RIS configurations, channel allocation, and beamforming strategies, thereby achieving optimal performance under dynamic and complex operating environments. Through E2E machine learning, RIS networks can continuously learn from real-world interactions, evolving to meet evolving communication demands.
In this presentation, we will explore the key challenges and opportunities in deploying RIS with E2E machine learning. We will discuss the intricacies of training machine learning models to effectively harness the capabilities of RIS, ensuring seamless integration with existing network infrastructures. Moreover, we will highlight promising applications of RIS-E2E machine learning in various domains, including 5G/6G networks, IoT connectivity, and smart city initiatives. Join us as we embark on a journey to unlock the full potential of RIS through E2E machine learning. Discover how this convergence of technologies is poised to redefine the future of wireless communication networks, ushering in an era of unprecedented connectivity, efficiency, and innovation.
简历: Dr. Mohammad Reza Ghavidel Aghdam 是一位杰出的学者和研究员，专门从事通信工程和无线通信领域。他于2014年从乌尔米亚大学获得电气工程学士学位，随后于2016年和2020年分别从伊朗的大不里士大学获得通信工程硕士和通信工程博士学位。从2017年开始，作为电气工程系的客座助理教授，在伊朗伊斯兰阿扎德大学伊尔希奇分校工程学院开始了他的学术之旅，Ghavidel Aghdam 博士迅速确立了自己作为一名敬业的教育者和研究员的地位。他对卓越的承诺和对推动该领域进步的热情，使他于2022年10月加入位于土耳其伊斯坦布尔的Özyeğin大学，成为备受推崇的通信理论与技术（CT&T）研究小组的博士后研究员。
Ghavidel Aghdam 博士的研究兴趣涵盖无线通信中一系列前沿话题，包括但不限于信号处理技术、智能反射表面（IRSs）或可重构智能表面（RISs）、机器学习应用、大规模多输入多输出（mMIMO）、毫米波（mmWave）通信以及非正交多址接入（NOMA）。他在这些领域的贡献显著推进了无线通信系统的理解和实施，为现代通信网络中的性能、效率和可扩展性的提升铺平了道路。
Yipeng Zhou
博士
Özyeğin University
演讲标题:Enhancing Federated Learning by Sparsifying Transmitted Model Updates
摘要:Federated learning facilitates the collaborative training of a machine learning model among geographically dispersed clients by exchanging model updates with a central server via Internet communication. However, transmitting these updates between the server and numerous decentralized clients over the Internet consumes considerable bandwidth and is susceptible to malicious attacks. This presentation showcases our various contributions aimed at improving communication efficiency and preserving privacy in federated learning. Our focus lies in sparsifying the transmission of model updates between the server and clients. By meticulously evaluating both the learning value, communication cost and privacy cost of transmitting each individual model update, we effectively mitigate the exposure of low-value updates to minimize communication and privacy costs. Extensive experiments conducted on real datasets demonstrate that our algorithms can significantly reduce communication costs and bolster privacy protection compared to the state-of-the-art federated learning baselines.
简历: Yipeng Zhou博士目前是澳大利亚麦考瑞大学科学与工程学院计算学院的高级讲师。在加入麦考瑞大学之前，他曾分别在南澳大学担任研究员和深圳大学担任讲师。他分别从香港中文大学获得博士和哲学硕士学位，以及从中国科学技术大学获得学士学位。他获得了2023年麦考瑞大学副校长研究卓越奖创新技术高度赞扬奖，以及2023年IEEE通信学会开放期刊最佳编辑奖。他还是2018年澳大利亚研究理事会发现早期职业研究者奖（DECRA）的获得者。他的研究兴趣包括联邦学习、数据隐私保护、网络等领域。他在顶级会议和期刊上发表了120多篇论文，包括IEEE INFOCOM、IJCAI、ICNP、IWQoS、IEEE ToN、JSAC、TPDS、TMC、TMM等