About shirleyfong

This author has not yet filled in any details.
So far shirleyfong has created 0 blog entries.
9 2024-04

IOTSC TALK SERIES: Assessing Urban Flooding Risks Using Numerical Model and Digital Twin Technology

2024-05-09T00:00:10+08:00

Dear Colleagues and Students,
The State Key Laboratory of Internet of Things for Smart City would like to invite you to join our “IOTSC Talk Series” on 12/04/2024 (Friday). We are pleased to invite Prof. Liang GAO from IOTSC and FST as the speaker.

Assessing Urban Flooding Risks Using Numerical Model and Digital Twin Technology
Speaker: Prof. Liang GAO, State Key Laboratory of Internet of Things for Smart City and Faculty of Science and Technology, University of Macau
Date: 12/04/2024 (Friday)
Time: 16:00 – 17:00
Language: English
Venue: N21-5007 (Exhibition Hall)

Abstract:
A tropical cyclone or rainstorm event may pose severe threat of flooding hazard to coastal cities. In this seminar, a multi-scale hydrological and hydrodynamic coupled numerical model will be introduced. The model could accurately capture the storm surge and the following overtopping/dam breach flooding processes, yielding accurate prediction of river discharges, water level fluctuations, and the compound floods. The future scenarios of compound floods under the impact of tropical cyclone and rainfall are comprehensively analyzed. The information, simulated hazard scenarios and simulation methods are compiled, embedded and displayed on a digital twin platform with an interactive interface for the users, which is expected to be useful for early warning and hazard prevention.

Speaker’s Bio:
Dr. Liang GAO is currently an assistant professor with the SKL-IOTSC, University of Macau. Her research interests focus on numerical modelling of multi-hazards in coastal mountainous area. She serves as the reviewer of many journals such as JH, RSE, WRR and so on, and she is the editorial board member of Georisk (SCI, JCR:Q1), Underground Space (SCI, JCR:Q1), and Journal of Intelligent Construction.

For enquiries: Tel: 8822 9141
Email: shirleyfong@um.edu.mo

Best Regards,
State Key Laboratory of Internet of Things for Smart City

IOTSC TALK SERIES: Assessing Urban Flooding Risks Using Numerical Model and Digital Twin Technology2024-05-09T00:00:10+08:00
19 2024-03

[Submission Deadline: 1 May 2024] Call for Extended Abstract & Poster: The 4th Macao International Conference on Smart City Technologies 2024

2024-04-18T00:00:35+08:00

Dear All,

We are delighted to share with you that SKL-IOTSC is calling for extended abstract & poster for The 4th Macao International Conference on Smart City Technologies 2024 from 22 – 24 August 2024. For details of the conference, please visit: https://mcsct.skliotsc.um.edu.mo/.

We cordially invite you to submit your extended abstract and / or posters related to the 5 technical tasks on or before 1st May 2024. Participants will have the opportunity to showcase their research and contribute to the advancement of smart city technologies. Additionally, outstanding participants will be recognised through different awards. Thanks!

5 Technical Tasks:

  • Sensing and Communications
  • Al and Big Data
  • Smart Energy
  • Intelligent Transportation
  • Urban Public Safety and Disaster Prevention

To submit your work, kindly visit: https://mcsct.skliotsc.um.edu.mo/

For any inquiries, please contact: iotsc.mcsct@um.edu.mo

State Key Laboratories of Internet of Things for Smart City
University of Macau 

[Submission Deadline: 1 May 2024] Call for Extended Abstract & Poster: The 4th Macao International Conference on Smart City Technologies 20242024-04-18T00:00:35+08:00
11 2024-03

IOTSC Postgraduate Forum: Urban Bia Data and intelligent Technology

2024-04-11T00:00:30+08:00

Dear Colleagues and Students,
The State Key Laboratory of Internet of Things for Smart City would like to invite you to join our “IOTSC Postgraduate Forum” on 25/04/2024 (Thursday). The event aims to bring together postgraduate students from various disciplines to share their research, exchange ideas, and engage in meaningful discussions. We are pleased to invite four outstanding PhD students to give presentations related to Urban Bia Data and intelligent Technology.

IOTSC Postgraduate Forum: Urban Bia Data and intelligent Technology
Date: 25/04/2024 (Thursday)
Time: 14:00 – 16:30
Language: English
Venue: N21-5007 (Exhibition Hall)
Host: Prof. Xiaowei WU 

Presenters Abstract
Xingguo PANG

Expeditious MicroVM SnapStart in PM via Augmented Hypervisor

In the era of cloud computing, the industry has embraced snapshotting as a technique to tackle cold starts and efficiently manage numerous short-lived functions. Traditional methods often stumble on ‘page faults,’ disruptions that occur when the memory required is not immediately accessible. This talk introduces PASS, a cutting-edge system that leverages byte-addressable persistent memory (PMEM) for cost-effective and highly concurrent execution of MicroVM SnapStart. PASS functions as a PMEM-aware augmented hypervisor in the user space, revolutionizing MicroVM memory restoration. In this talk, we will discuss how PASS stands as a beacon of innovation, promising to revolutionize cloud function execution. Attendees will gain insights into the challenges faced by existing solutions and how PASS addresses them through its novel approach, ultimately paving the way for more efficient and scalable cloud computing environments.
Mengting ZHOU

Data Augmentation Algorithm for Class-Imbalanced Node Classification

Graph neural networks (GNNs) have achieved great success in node classification tasks. However, existing GNNs naturally bias towards the majority classes with more labelled data and ignore those minority classes with relatively few labelled ones. The traditional techniques often resort over sampling methods, but they may cause overfitting problem. More recently, some works propose to synthesize additional nodes for minority classes from the labelled nodes, however, there is no any guarantee if those generated nodes really stand for the corresponding minority classes. In fact, improperly synthesized nodes may result in insufficient generalization of the algorithm. To resolve the problem, in this paper we seek to automatically augment the minority classes from the massive unlabelled nodes of the graph. Specifically, we propose \textit{GraphSR}, a novel self-training strategy to augment the minority classes with significant diversity of unlabelled nodes, which is based on a Similarity-based selection module and a Reinforcement Learning (RL) selection module. The first module finds a subset of unlabelled nodes which are most similar to those labelled minority nodes, and the second one further determines the representative and reliable nodes from the subset via RL technique. Furthermore, the RL-based module can adaptively determine the sampling scale according to current training data. This strategy is general and can be easily combined with different GNNs models. Our experiments demonstrate the proposed approach outperforms the state-of-the-art baselines on various class-imbalanced datasets.
Jun LIU

Adversarial Examples and its Applications to Privacy Protection

While Deep Neural Networks (DNNs) have achieved tremendous success in various image processing tasks such as classification, segmentation, denoising, and more, they are vulnerable when applied to Adversarial Examples (AEs). AEs are manipulated images that deceive the model by adding perturbations to normal images, capable of aiding in the detection and enhancement of DNNs’ robustness. Numerous methods for generating AEs have emerged, but in the practical black-box setting where attackers lack access to DNNs’ architecture, parameters or even training datasets, they can only obtain prediction scores or labels of images by querying the DNN. Current state-of-the-art black-box attack methods still face challenges with excessive query counts and relatively low attack success rate (ASR). In this talk, I will introduce our proposed algorithm aimed at enhancing the query efficiency and ASR of black-box attack methods. Additionally, I will discuss two other approaches we have designed for image privacy protection using AEs. One improves the accuracy of privacy-preserving image classification while allowing for ciphertext recovery under authorized access. The other allows human recognition of images while preventing DNNs from extracting image information, regardless of whether images are transmitted over online social networks

For enquiries: Tel: 8822 9159
Email: frankielei@um.edu.mo

Best Regards,
State Key Laboratory of Internet of Things for Smart City (University of Macau)

IOTSC Postgraduate Forum: Urban Bia Data and intelligent Technology2024-04-11T00:00:30+08:00
1 2024-03

IOTSC TALK SERIES: Navigating the Shadows: Unraveling Variable Subset Forecasting

2024-04-01T00:01:19+08:00

Dear Colleagues and Students,
The State Key Laboratory of Internet of Things for Smart City would like to invite you to join our “IOTSC Talk Series” on 22/03/2024 (Friday). We are pleased to invite Prof. Pengyang WANG from IOTSC and FST as the speaker.

Navigating the Shadows: Unraveling Variable Subset Forecasting
Speaker: Prof. Pengyang WANG, State Key Laboratory of Internet of Things for Smart City and Faculty of Science and Technology, University of Macau
Date: 22/03/2024 (Friday)
Time: 15:00 – 16:00
Language: English
Venue: N21-5007 (Exhibition Hall)

Abstract:
Variable Subset Forecasting (VSF) is a unique and challenging scenario in time series forecasting, where some of the variables presented during the training phase are entirely missing when making inferences. Unlike typical cases of missing data, where only a few ad hoc data points are absent, VSF involves the complete absence of certain variables during the inference phase, forcing the model to rely on a limited subset of the data it was originally trained on. The occurrence of VSF is often observed in contexts such as the Internet of Things (IoT), where sensor networks are prevalent. In this talk, I will introduce the definitions and challenges of VSF, recent works of my group, and future directions.

Speaker’s Bio:
Dr. Pengyang WANG’s research interests are in data mining, machine learning and big data analytics, especially in representation learning for Spatial-Temporal Graph-Structured data, with applications to smart cities, transportation, user/system behavior modeling, critical infrastructure defense, and complex network analysis.

For enquiries: Tel: 8822 9141
Email: shirleyfong@um.edu.mo

Best Regards,
State Key Laboratory of Internet of Things for Smart City

IOTSC TALK SERIES: Navigating the Shadows: Unraveling Variable Subset Forecasting2024-04-01T00:01:19+08:00
26 2024-01

IOTSC Talk Series: Multi-modality Multimedia Information Analysis and Compression

2024-02-26T00:00:16+08:00

Dear Colleagues and Students,
The State Key Laboratory of Internet of Things for Smart City would like to invite you to join our “IOTSC Talk Series” on 31/01/2024 (Wednesday). We are pleased to invite Prof. Weiyao LIN from Shanghai Jiao Tong University as the speaker.

Multi-modality Multimedia Information Analysis and Compression
Speaker: Prof. Weiyao LIN, Professor, Department of Electronic Engineering, Shanghai Jiao Tong University
Date: 31/01/2024 (Wednesday)
Time: 10:30 – 11:30
Language: English
Venue: N21-5005

Abstract:
The rapid growth of multimedia applications has increased the importance of semantic information, such as objects’ motion, action, and property. This has led to a demand for efficient extraction and compression of semantic information. This talk will introduce works on multi-modality multimedia information analysis and compression, including object activity and interaction recognition, multi-modality multimedia analysis, and semantic information compression. The authors will present a new model for describing spatial-temporal redundancies in semantic data and design an architecture capable of compressing over 70% of semantic data.

Speaker’s Bio:
Dr. Weiyao LIN received the B.E. degree from Shanghai Jiao Tong University, China, in 2003, the M.E. degree from Shanghai Jiao Tong University, China, in 2005, and the Ph.D degree from the University of Washington, Seattle, USA, in 2010, all in electrical engineering. He is currently a Professor with the Department of Electronic Engineering, Shanghai Jiao Tong University, China. He has authored or coauthored 100+ technical papers on top journals/conferences including TPAMI, IJCV, CVPR, and ICCV. He holds 20+ patents and has 10+ under reviewing patents. His research interests include multimedia content understanding, computer vision, video/image compression, and video/image processing applications.

For enquiries: Tel: 8822 9141
Email: shirleyfong@um.edu.mo

Best Regards,
State Key Laboratory of Internet of Things for Smart City

IOTSC Talk Series: Multi-modality Multimedia Information Analysis and Compression2024-02-26T00:00:16+08:00
22 2024-01

IOTSC Talk Series: AFEPack: A C++ Library for Numerical Solutions of PDEs

2024-02-19T00:00:15+08:00

Dear Colleagues and Students,
The State Key Laboratory of Internet of Things for Smart City would like to invite you to join our “IOTSC Talk Series” on 26/01/2024 (Friday). We are pleased to invite Prof. Guanghui HU from IOTSC and FST as the speaker.

AFEPack: A C++ Library for Numerical Solutions of PDEs
Speaker: Prof. Guanghui HU, State Key Laboratory of Internet of Things for Smart City and Faculty of Science and Technology, University of Macau
Date: 26/01/2024 (Friday)
Time: 16:00 – 17:00
Language: English
Venue: N21-5007 (Exhibition Hall)

Abstract:
Numerical solutions of partial differential equations (PDEs) have been playing an indispensable role in both scientific exploration and engineering applications. In this talk, challenges on numerically solving PDEs will be briefly reviewed. Then a C++ library AFEPack, for numerical solutions of PDEs, will be introduced in detail, including the design philosophy, algorithms and data structures, features such as mesh adaptivity, pre- and post-processing components, etc. The installation of the library, as well as applications on solving benchmark problems will be demonstrated. Potential applications of the library will also be discussed.

Speaker’s Bio:
Dr. HU obtained BSc (2003) and MSc (2006) from SCU, and PhD (2010) from HKBU. He joined UM in 2012 after a postdoc at MSU. His research focuses on numerical methods of PDEs, supported by NSFC, FDCT. He is the editor of journals CiCP, AAMM, and Mathematica Numerica Sinica.

For enquiries: Tel: 8822 9141
Email: shirleyfong@um.edu.mo

Best Regards,
State Key Laboratory of Internet of Things for Smart City

IOTSC Talk Series: AFEPack: A C++ Library for Numerical Solutions of PDEs2024-02-19T00:00:15+08:00
17 2024-01

IOTSC Talk Series: Reconfigurable Intelligent Surface Assisted Covert Communications

2024-02-17T00:00:16+08:00

Dear Colleagues and Students,
The State Key Laboratory of Internet of Things for Smart City would like to invite you to join our “IOTSC Talk Series” on 22/01/2024 (Monday). We are pleased to invite Prof. Bin XIA from Shanghai Jiao Tong University as the speaker.

Reconfigurable Intelligent Surface Assisted Covert Communications
Speaker: Prof. Bin XIA, Professor, Shanghai Jiao Tong University
Date: 22/01/2024 (Monday)
Time: 11:00 – 12:00
Language: English
Venue: N21-5010

Abstract:
This talk discusses the use of reconfigurable intelligent surfaces (RIS) to enhance communication security, particularly in wireless communication. It highlights the potential of RIS-assisted covert communication, which can improve performance by reconstructing wireless channels. The talk introduces the background of covert communications, discusses embedded technologies, and identifies the fundamental issues in covert communications, including transmission covertness, reliability, latency, and throughput. The gains brought by RIS in covert communications are quantified, revealing constraints on these performance indicators.

Speaker’s Bio:
Dr. Bin XIA is a Professor at Shanghai Jiao Tong University’s Department of Electronic Engineering. He has experience in the Mobile Communication Group at Alcatel Co., Ltd, as a Senior System Engineer for the first commercial WiMAX system, and in the Wireless Research Department at Huawei Technologies Co., Ltd. He holds a Ph.D. in Communication Engineering from Hong Kong University. Dr. Xia’s research interests include coded modulation, MIMO, OFDM, crosslayer design, and radio network architecture. He is a senior member of IEEE and has served as publicity chair of IEEE WCNC2013, general co-chair of IEEE ICCC2014, workshop co-chair of IEEE ICC2015, and executive co-chair of IEEE ICC2019.

For enquiries: Tel: 8822 9141
Email: shirleyfong@um.edu.mo

Best Regards,
State Key Laboratory of Internet of Things for Smart City

IOTSC Talk Series: Reconfigurable Intelligent Surface Assisted Covert Communications2024-02-17T00:00:16+08:00
15 2024-01

IOTSC Talk Series: “ILL-Posed” Computer Vision Tasks

2024-02-15T00:00:14+08:00

Dear Colleagues and Students,
The State Key Laboratory of Internet of Things for Smart City would like to invite you to join our “IOTSC Talk Series” on 18/01/2024 (Thursday). We are pleased to invite Prof. Xiaochun CAO from Sun Yat-Sen University as the speaker.

“ILL-Posed” Computer Vision Tasks
Speaker: Prof. Xiaochun CAO, Professor and Dean from School of Cyber Science and Technology, Sun Yat-Sen University
Date: 18/01/2024 (Thursday)
Time: 10:00 – 11:00
Language: English
Venue: N21-5005

Abstract:
Computer vision tasks range from the simple perspective projection matrix estimation in a traditional camera calibration application to the large-scale foundation model fitting in a contemporary object detection cloud service. One may solve most computer vision tasks through fitting functions mapping the dense, if not continuous due to quantization, visual input to a discrete and meaningful output space, including categories, bounding boxes, and depths. Due to the significant difference in cardinalities of the domain and codomain, these mapping functions fail to meet one of the three Hadamard criteria for being well-posed. In other words, the unstable computer vision solution does not depend continuously on the parameters or input data. Many researchers are trying their best to design or learn computer vision algorithms being sufficiently robust to complex perturbations such as occlusion, smoke, rain, and fog. There are also scholars looking for dedicated but powerful adversarial perturbations. Does there exist an invariant backdoor perturbation that is capable to push an arbitrary image across the decision boundary in a classification task? Are all perturbations adversarial? In this talk, I will introduce these questions our team is exploring and briefly outline some of the progress. However, much still remains unclear in spite of our efforts, and we reiterate that there might not have the answers we’re looking for before AI undergoes a brand new paradigm.

Speaker’s Bio:
Dr. Xiaochun CAO is a Professor and Dean of School of Cyber Science and Technology, Shenzhen Campus of Sun Yat-sen University. He received the B.E. and M.E. degrees both in computer science from Beihang University (BUAA), China, and the Ph.D. degree in computer science from the University of Central Florida, USA, with his dissertation nominated for the university level Outstanding Dissertation Award. After graduation, he spent about three years at ObjectVideo Inc. as a Research Scientist. From 2008 to 2012, he was a professor at Tianjin University. Before joining SYSU, he was a professor at Institute of Information Engineering, Chinese Academy of Sciences. He has authored and coauthored over 200 journal and conference papers. In 2004 and 2010, he was the recipients of the Piero Zamperoni best student paper award at the International Conference on Pattern Recognition. He is on the editorial boards of IEEE Transactions on Pattern Analysis and Machine Intelligence and IEEE Transactions on Image Processing, and was on the editorial boards of IEEE Transactions on Circuits and Systems for Video Technology and IEEE Transactions on Multimedia.  

For enquiries: Tel: 8822 9141
Email: shirleyfong@um.edu.mo

Best Regards,
State Key Laboratory of Internet of Things for Smart City

IOTSC Talk Series: “ILL-Posed” Computer Vision Tasks2024-02-15T00:00:14+08:00
15 2024-01

(18 Jan, 14:30, N6-G010) Invitation to the Smart City Sustainable Development Seminar [1 Smart Point, 15 CS]

2024-02-15T00:00:15+08:00

Dear Colleagues and Students,

We are pleased to announce that IOTSC is organizing an upcoming seminar titled “The Smart City Sustainable Development (智慧城市可持續發展研討會)”. This seminar aims to provide valuable insights and foster interdisciplinary discussions. We are honored to welcome five distinguished scholars who will be delivering engaging talks and leading interactive sessions. 

All members of the UM community are cordially invited to this splendid event. Details of the event are as below:

Date: 18 January 2024, Thursday
Time: 14:30 am
Venue: Ho Yin Conference Hall, N6-G010
Language: Mandarin

Registration: https://isw.um.edu.mo/evm/register/scsd0118

For enquiry, please contact us at 8822 9141, email: shirleyfong@um.edu.mo. Thank you!

Best Regards,

State Key Laboratory of Internet of Things for Smart City


Important notice:

For participants who have registered and attended the seminar, Smart Point / CS will be given and it is considered attending a RC activity (“Knowledge Integration”). 

 

 

 


Please observe the following guidelines of Smart Point scheme:

  1. Students who attend the WHOLE activity and arrive ON TIME will be given one Smart Point, 20 “Knowledge Integration” (CS).
  2. Students who arrive late or leave early within 10 minutes will be given only half a Smart Point.
  3. Students who arrive late or leave early over 10 minutes will NOT be given any Smart Point.
  4. Students who leave the venue during the activity for over 15 minutes will NOT be given any Smart Point.
  5. Students are required to check in/out of the activity with their valid Student ID Card.
  6. For those who do not respect the activity or ignore the staff’s guidance, Student Affairs Office (SAO) reserves the right to cancel his/her Smart Point. SAO also reserves the right to interpret and process the Smart Point scheme.
(18 Jan, 14:30, N6-G010) Invitation to the Smart City Sustainable Development Seminar [1 Smart Point, 15 CS]2024-02-15T00:00:15+08:00
15 2023-12

IOTSC Talk Series: Seminar on Allocation Algorithms

2024-01-15T00:00:13+08:00

Dear Colleagues and Students,
The State Key Laboratory of Internet of Things for Smart City would like to invite you to join our “IOTSC Talk Series” on 19/12/2023 (Tuesday). We are pleased to invite three scholars as the speakers.

Seminar on Allocation Algorithms
Host by Prof. Xiaowei WU
Speakers:
– Prof. Xiaohui BEI, Associate Professor, Nanyang Technological University
– Prof. Zhiyi HUANG, Associate Professor, The University of Hong Kong
– Mr. Shengwei ZHOU, PhD Candidate, University of Macau

Date: 19/12/2023 (Tuesday)
Time: 14:00 – 16:30
Language: English
Venue: N21-5010

For enquiries: Tel: 8822 9141
Email: shirleyfong@um.edu.mo

Best Regards,
State Key Laboratory of Internet of Things for Smart City

IOTSC Talk Series: Seminar on Allocation Algorithms2024-01-15T00:00:13+08:00
© University of Macau
Go to Top