Workshop

Workshop 1
Title: Environmental Perception and State Estimation Based on Multi-sensor Fusion for Autonomous Driving

Currently, intelligent vehicles have been extensively studied, and accurate environmental perception and state estimation are key technologies for autonomous driving. However, commonly used in-vehicle sensors have their own drawbacks. For example, cameras are easily affected by illumination changes, the sparseness of point cloud limits the application of LIDAR for long-distance objects recognition, the millimeter-wave Radar cannot be used for low-speed targets detection, and the satellite's signals of integrated navigation systems are easily blocked. Therefore, a single vehicle-mounted sensor is difficult to deal with complex traffic scenarios for autonomous driving. Multi-sensor information fusion refers to the integration of data from multiple sensors to produce more reliable, more accurate or more precise environmental perception information. The multi-sensor fusion perception system can accurately reflect the characteristics of the detected targets, eliminate the uncertainty of information, improve the reliability of the perception system.The aim of this workshop is to bring together the research accomplishments provided by researchers from academia and the industry, as well as to show the latest research results in the field of environmental perception and state estimation based on multi-sensor fusion for autonomous driving. We encourage authors to submit related distinguished research papers on the subject of both: theoretical approaches and practical case reviews.
Autonomous driving, Artificial intelligence, Deep learning, Environmental perception, Multi-sensor fusion, State estimation

Keke Geng received his Ph.D. degree in Automatic Control Systems from Bauman Moscow State Technical University and is now an associate professor in the Department of Vehicle Engineering, School of Mechanical Engineering, Southeast University. His research interests include Autonomous Driving, Intelligent Environmental Perception, Multi-sensor fusion and State Estimation.
He has participated in projects such as National Natural Science Foundation, National Key Projects, National Key Research and Development Project, Natural Science Foundation of Jiangsu Province, and Jiangsu Key Science and Technology Research Projects. Based on these projects, he has published many academic papers.

Workshop 2
Title: Machine Learning and Computer Vision in Big Data

Emerging technologies such as machine learning and computer vision are expected to leverage the accessibility of big data, and big data accelerates the technologies of machine learning and computer vision.To enhance and assess the performance of machine learning and computer techniques for different types of problemstowards big data, there are many promising research directions. The areas the workshop will focus on are: (1) big data acquisitionin intelligent manufacturing and advanced sensing technology;(2) big data classification, visualization analysis techniques;(3) multi-modal data fusion methods;(4) object detection, recognition and tracking;(5) machine learning (especially deep learning)algorithms in big data analytics; (6) various applications of machine learning and computer vision techniques in big data.The aim of this workshop is to bring together the research accomplishments provided by researchers from academia and the industry, as well as to show the latest research results in the field of machine learning and computer vision in big data. We encourage authors to submit distinguished research papers on the subjects within the scope of the aforementioned list.
Machine learning, Computer vision, Deep learning, Big data, Multi-modal data fusion, Object detection, Object recognition
Duzhen Zhang received his Ph.D. degree from Nanjing University of Science and Technology. He is now an associate professor in the Department of AI Science and Technology, School of Computer Science and Technology, Jiangsu Normal University. His research interests include machine learning and computer vision, and he has published many papers in these areas.
He has participated in some projects such as National Natural Science Foundation and Natural Science Foundation of Jiangsu Province. He worked as a reviewer in several international conferences.

Workshop 3
Title: Intelligent Implementations in Digitalized Real World

As digital sensors become cheaper and more prevalent, the growing amount of available data helps to digitalize the real world while improving the requirement for the accompanied intelligent implementations, which are able to finish expected tasks qualitatively, efficiently and robustly.  The reasons for this are multi-fold. Firstly, compared with the human-designed implementations, the intelligent ones are adaptive to the different deployed environments, which produces customized solution and leads to more qualitative performance. Secondly, different from the fixed strategies in conventional implementations, the intelligent ones are teachable; this ability of self-evolution helps to explore the more efficient solutions automatedly. Thirdly, unlike the traditional implementations that fully focus on the available data, the intelligent ones have the ability of possible future prediction, which leads to the consideration of consequential situations and provides more robust solutions.
In this Workshop, we therefore propose a dedicated theme on “Intelligent Implementations in Digitalized Real World”, which aims to arouse the research attention on qualitative, efficient and robust intelligent solutions including, but not limited to, system design, framework implementation, data processing, task formulation, performance evaluation, theory reasoning and software design.
Intelligent System Design, Intelligent Data Processing, Intelligent Task Fformulation, Performance Evaluation, Artificial Intelligence Theory Reasoning, Software Design

Ruiheng Zhang, received a Dual Ph.D. degree from University of Technology Sydney and Beijing Institute of Technology. He worked as a associate professor at the School of Mechatronical Engineering, Beijing Institute of Technology. His research interests include computer vision and deep learning.
He participated in the National Natural Science Foundation, National Defense Science Technology Foundation, etc. Based on these projects, he published more than 30 papers in IEEE Trans, Remote Sensing of Environment, Pattern Recognition and other journals/conferences.


Qi Zhang has been doing research in the field of remote sensing and earth observation for 8 years. She received her Ph.D. degree in Geospatial Engineering from the University of New South Wales (UNSW) in 2022. She developed a forest height estimation framework based on the synergy of Polarimetric Synthetic Aperture Radar (SAR) Interferometry and LiDAR data, a burned area mapping framework based on the synergy of SAR, Synthetic Aperture Radar Interferometry (InSAR), and multi-spectral data, and an active fire detection framework using multi-spectral images. Related methodologies and results have been published in journals such as RSE, ISPRS journal of photogrammetry and remote sensing, Remote Sensing. Her research interests include the deep-learning-based algorithm design and its applications on the earth observation of SAR and multi-spectral remote sensing.

Workshop 4
Title: Multi-Goal Decision Making Techniques and its Applications

In practical applications in nature and society, semi-structured and unstructured decision-making issues involve multiple criteria (or goals) that may conflict with each other. The success of decision-making lies in whether mangers, administrators, supervisors, and other decision makers can comprehensively consider and understand the insight of future for making the best decision-making planning and choice. Multiple-criteria decision making (MCDM), multiple-objective decision making (MODM), multiple-attribute decision making (MADM) are used to lead decision makers to analyze multiple-goal optimization issues from various perspectives. 
The evaluation and selection methods (e.g. analytical hierarchy process (AHP), fuzzy AHP, analytical network process (ANP), fuzzy ANP, decision making trial and evaluation laboratory (DEMATEL), fuzzy DEMATEL, Choquet integral, etc.) are important tools for MCDM, MODM, and MADM. Furthermore, these methods can be employed to explore the relationship structure among criteria for a variety of related issues arising from the nature and society fields. For instance, MCDM, MODM, and MADM methods can be applied to the evaluation of new technologies adoption based on limited resources, the evaluation of new development investments, the priority of resource allocation, etc.
This workshop named “Multi-Goal Decision Making for Applications” in IMASBD 2022 will solicit papers on various disciplines of multi-goal decision making applications, including but not limited to:
Applications of multiple-criteria decision making methods
Applications of multiple-objective decision making methods
Applications of multiple-attribute decision making methods
Applications of other multiple-goal optimization methods
Optimization of multiple-criteria decision making methods
Optimization of multiple-objective decision making methods
Optimization of multiple-attribute decision making methods
Optimization of other multiple-goal optimization methods
Bo-Wei Zhu is the assistant professor at the Faculty of Humanities and Arts in Macau University of Science and Technology. Her research interests focus on management of built environment, multiple attribute decision making of environmental design, and housing assessment for healthy aging. She has published several articles in international journals (e.g., Religions, Mathematics, Sustainability, International Journal of Environmental Research and Public Health, etc.) on multiple attribute decision making of environmental design. She serves/served as a technique program committee member for several international conferences (e.g., AAAI-22 Workshop, WWW’22 Workshop, IEEE BIBM 2021 Workshop, IEEE TrustCom 2021 Workshop, and so on).
Lei Xiong received his Ph.D. degree in the College of Creative Design of Asia University.He is a lecturer forthe School of Architecture and Allied Art of Guangzhou Academy of Fine Arts.He has published several articles in international journals(SCI/SSCI/A&HCI). His research interests include urban design, multiple attribute decision making, architectural design,and design management.He has been serving as the Guest Editor of several Q2/Q3 SCI journals as well as the General Co-Chair/Session Chair of several international conferences/workshops.
Feng-Jang Hwang is the Senior Lecturer (Level C, Associate Professorship equivalency in the North American academic system), the Leading PI of the Industrial Optimisation Group, and the Programme Director (Maths/Stats) at the School of Mathematical and Physical Sciences; Transport Research Centre, University of Technology Sydney. He is the winner of the 2017 Albert Nelson Marquis Achievement Award. His research interests center around data-driven optimization, intelligent logistics, and computational intelligence. F.J. has published in the leading journals and been serving as the Guest Editor of several Q1/Q2 SCI journals as well as the General Co-Chair/Session Chair of several international conferences/workshops.   

Chi-Hua Chen is a professor at Fuzhou University. He has published over 300 journal articles, conference articles, and patents. His contributions were published in IEEE Internet of Things Journal, IEICE Transactions, and so on. Some of his publications have been recognised as highly cited papers from Essential Science Indicators. He serves as an editor for several international journals (e.g., Scientific Data (Nature), IEEE Access, and so on). He also serves as a chair for several international conferences (e.g., AAAI-22 Workshop, WWW’21 Workshop, IEEE ICC 2020, and so on). His research interests include the Internet of things and machine learning.

Workshop 5
Title: Towards the Internet of Underwater Things

The innovative concept of Internet of Underwater Things (IoUT) has widespread applications such as collecting real-time aquatic information, naval military applications, maritime security, natural disaster prediction and control, archaeological expeditions, oil and gas exploration, shipwrecks discovery, water contamination, marine life observation and underwater monitoring. IoUT has become a powerful technology to support these applications and it has great potential to develop a smart Ocean. It is a novel and vibrant paradigm for the Blue Economy sector bringing the ability to communicate autonomous underwater vehicles (AUVs), sensing, actuating and transferring this data to control centers using regular Internet speeds through low cost technologies. The possible network architecture of IoUT is naturally heterogeneous and must be flexible enough to work under unpredicted ocean conditions. The IoUT framework incorporates several underwater communication technologies based on magnetic induction, optical signals, radio signals and acoustic signals. In addition, edge computing, optical wireless communication, data analytics, blockchain and machine learning are viewed as promising techniques to support IoUT. This workshop addresses most recent frontier research investigations and associated practical solutions for IoUT. It aims to bring together the research accomplishments provided by leading researchers from academia and the industrial experts. To further promote the development of IoUT and relevant areas such as underwater wireless sensor networks (UWSN) or underwater acoustic sensor networks (UASN), we invite researchers to contribute original research manuscripts as well as review articles on recent advances in IoUT. Articles dedicated to the integration of cutting-edge technologies such as Blockchain, Mobile Edge Computing (MEC), Cloud Computing, Machine Learning (ML), Deep Learning (DL), Optical Wireless Communication (OWC), Intelligent Reflecting Surfaces (IRS) and Data Analysis with IoUT are highly preferred. Articles discussing role of autonomous vehicles in IoUT, Marine Big Data (MBD), applications and security issues of IoUT will be considered as well.
Internet of Underwater Things, Autonomous underwater vehicles, Blockchain, Big marine data, Smart ocean

Dr. S.A.H. Mohsan has worked as a peer reviewer for Chinese Optics Letter, Optical and Quantum Electronics, Photonics, Sensors, Energies, Electronics, Applied Sciences and several other journals. He has served as a TPC member for several International Conferences. He has delivered invited talks in three international conferences. His research interests include Underwater Wireless Sensor Networks, Internet of Underwater Things, Optical Wireless Communication, Wireless Power Transfer, Optical Wireless Hybrid Networks, NOMA and 5G/6G technology. He has published more than 30 papers in Springer Nature, OSA, IEEE, SPIE and several other Journals/Conferences.

Workshop 6
Title: Employ Artificial Intelligence Approaches for Classification and Segmentation of Different Abnormalities

Artificial intelligence (AI) is a wide-ranging branch of computer science concerned with building smart machines capable of performing tasks that typically require human intelligence. Machine learning feeds a computer data and uses statistical techniques to help it "learn" how to get progressively better at a task, without having been specifically programmed for that task, eliminating the need for millions of lines of written code. Machine learning consists of both supervised learning (using labeled data sets) and unsupervised learning (using unlabeled data sets). Deep learning is a type of machine learning that runs inputs through a biologically-inspired neural network architecture. The neural networks contain a number of hidden layers through which the data is processed, allowing the machine to go "deep" in its learning, making connections and weighting input for the best results.
The aim of this workshop is to bring together the research accomplishments provided by researchers from academia and the industry. The other goal is to show the latest research results in the field of Deep learning and artificial intelligence. We encourage prospective authors to submit related distinguished research papers on the subject of both: theoretical approaches and practical case reviews.
 Artificial intelligence, computer vision, computer aided diagnosis, medical imaging, big data, machine learning, deep learning.

Samira Lafraxo received her Master degree in Distributed Systems from The University of Ibn Zohr, Agadir, Morocco in 2016. She is currently a Ph.D. candidate in the LabSIV laboratory, Ibn Zohr University. Her main research interests include image processing, computer vision, artificial intelligence and medical imaging.

Workshop 7
Title: Digital Twin Driven Smart Manufacturing

With the rapid development of the Industrial 4.0 enabling technologies (Internet of Things, Cloud Computing, Big Data Analytics, and Artificial Intelligence, etc.), the Smart Manufacturing era has arrived. New trends and challenges are being traced thanks to the cyber-physical fusion of production technologies and software tools heading towards smarter, reliable and efficient manufacturing systems. In this context, the Digital Twin is defined as a high-fidelity digital mirror model of manufacturing resources that – combined with new technologies – allows to better accomplish complex tasks. This workshop collects research papers and application papers examining the background, latest research, and application models for digital twin technology in manufacturing, and aims at showing how the digital twin can be central to a smart manufacturing process. Topics of interest include, but are not limited to:
Digital Twin ApplicationsDigital Twin Driven Prognostics and Health ManagementCyber-Physical Fusion in Digital Twin Shop FloorDigital Twin and Cloud, Fog, Edge ComputingDigital Twin and Big DataDigital Twin and Virtual/Augmented/Mixed RealityIoT in Digital Twin-Based Cyber-Physical SystemsService-oriented Smart ManufacturingDigital Twin ServiceDigital Twin Driven Product Design/Manufacturing/Service

Digital Twin, Smart Manufacturing, cyber-physical fusion, Industrial 4.0, Digital Twin Driven Product, Digital Twin Service

Qinglin Qi, received his Ph.D. degree from Beihang University. He is now working at Beihang University. He was selected into "Hong Kong Scholar" program and used to do research at The Hong Kong Polytechnic University. His research interests include Digital Twin, Smart Manufacturing, Cyber-physical fusion. He has published more than 20 articles in international journals (e.g., Nature, Engineering, Journal of Manufacturing Systems, etc.) on above-mentioned research fields, in which 7 papers are selected as ESI highly cited papers. The papers have been citied more than 6200 times in Google Scholar.He presided over 1 Youth Fund project of National Natural Science Foundation of China and participated in many other projects. He serves as Assistant Chief Advisor of the international journal named Digital Twin (https://digitaltwin1.org/), which is initiated by Beihang University in partnership with Taylor & Francis Group.

Workshop 8
Title: Multi-material Additive Manufacturing and Itelligent Robots

Multi-material additive manufacturing combined with intelligent robots plays an increasingly important role in industrial manufacturing. Unlike the more common single-material additive manufacturing, the multi-material additive manufacturing can produce complicated patterns of dielectrics, metals and even magnetic materials by combining multiple deposition heads within a single integrated system. This has inspired lots of interesting research work in recent years, e.g. metal additive manufacturing, robot motion control, visual detection of molten pool, deep neural networks and path planning of robots, etc. Moreover, extensive attentions are attracted on studies of molten pool feature extraction, application of intelligent robots, control system of additive manufacturing and laser welding methods.
Additive manufacturingmetal additive manufacturing, 3D Printing, Robot, Visual detection, Neural Networks, Path planning

Fei Xie was born in Jiangsu Province, China, in 1983. He received the B.S. and Ph.D. degrees from the College of Automation, Nanjing University of Aeronautics and Astronautics, Nanjing, China, in 2009 and 2014. He is now an Associate Prof in the College of Electrical and Automation Engineering, Nanjing Normal University, Nanjing, China. Fei Xie is the recipient of the excellent articles of JSEE journal in 2019 and science and technology awards of Jiangsu Province in 2020. His current research interests include metal additive manufacturing, computer vision, machine learning, multi-sensor integration and robot autonomous control technology. He has published more than 30 SCI papers as the first author and the corresponding author in recent five years. He is reviewers of SCI journals “Automatica”, “IEEE Transactions on Neural Networks and Learning Systems”, “IEEE Transactions on Vehicular Technology”, “Journal of Navigation”, ”IET Image Processing”, and conferences “International Federation of Automatic Control”, “Chinese Control Conference”, “IEEE/CSAA Guidance, Navigation and Control Conference”, etc.

Workshop 9
Title: The Role of Small Organic Molecule in Preparing Functional Materials for Supercapacitor

High performance energy storage devices are urgent needed for fully utilization of new and renewable energy. Supercapacitors are electrical energy storage system characterized by high power and long cycling life, which show great promising in recent years. To date, many functional materials have been demonstrated to be efficient supercapacitor electrodes, which include but not limited oxides, sulfides, nitrides as well as some heterostructures/composite. The processes used to synthesize these materials often utilize some organic reagents, such as solvent, surfactant, reducing agent. Combining our recent works, we will discuss the role of some small organic molecules, such as ethylene glycol, glycerol, glucose, and so on. The target materials involve oxide, sulfide, nitride as well as some heterostructures. The application of these materials in supercapacitors is also presented.
Metal oxide, metal sulfide, metal nitide, heterostructure, supercapacitor

Maiyong Zhu received his Ph.D from Yangzhou University (2011), China. After that, he joined Jiangsu University (China) as an assistant professor to conduct research work independently. In 2015, he was promoted to be an associate professor. During His research interest covers several subjects in the field of advanced functional nanomaterials varying from noble metals, metal oxides/sulfides, carbon, conducting polymers to metal organic frameworks, which emphasizes the relationship among synthesis, structure, and performance of functional materials. The application areas of his group developed materials include environmental treatment, chemical catalysis, and energy storage and conversion.

Workshop 10
Title: Reliability in Structural Design and Manufacturing

Uncertainty is vastly evitable in practice. Methods for uncertainty quantification are becoming widespread within the engineering community. In particular, reliability analysis and reliability-based design optimization have been widely applied in structural engineering and they are seen as the most suitable tools when various uncertainties must be explicitly considered.
The aim of this workshop is to bring together the research accomplishments provided by researchers from academia and the industry. It will focus on, but not be limited to, reliability modeling, assessment, and design of structures/manufacturing, especially those exposed to complex working environments, theoretical developments and engineering practices of uncertainty quantification methods for supporting the reliability design and manufacturing process. The other goal is to show the latest research results in the field of reliability in structural design and manufacturing. We encourage prospective authors to submit related distinguished research papers on the subject of both theoretical approaches and practical case reviews.
Reliability, reliability-based design optimization, uncertainty, modeling.

Xiukai Yuan, received a Ph.D. degree in Aircraft Design from Northwestern Polytechnical University. He worked as an Associate Professor at the School of Aerospace and Engineering, Xiamen University. His research interests include structural reliability analysis, reliability-based design optimization, uncertainty propagation and quantification and model validation and verification.
He participated in the National Natural Science Foundation, Aeronautical Science Foundation of China, etc. Based on these projects, he published more than 30 papers in Structural Safety, Reliability Engineering & System Safety, Mechanical Systems and Signal Processing, and other journals/conferences.

Dehui Wu, employed as a professor and doctoral supervisor at the School of Aerospace Engineering in Xiamen University, a key introduction talent of "Hundred Talents Program" in Fujian province, and served as the editorial board member of several professional journals. 
He completed his postdoctoral research in the Department of Electrical Engineering, Tsinghua University in 2009, and his research interests include nondestructive testing and reliability testing technology innovation. He has undertaken 6 national science and technology projects and 4 provincial science and technology projects, from which he has made a number of important research achievements. In the past five years, he has published a large of academic papers, 24 of which have been indexed in SCI database (6 papers appear in JCR Q1 and 5 papers appear in JCR Q2).