Haibin Zhu

Followers

Following

Co-authors

Public Views

Dr. Haibin Zhu is Full Professor and Coordinator of the Computer Science Program, Founding Director of Collaborative Systems Laboratory, member of Arts and Science Executive Committee, Nipissing University, Canada. He received B.S. degree in computer engineering from Institute of Engineering and Technology, China (1983), and M.S. (1988) and Ph.D. (1997) degrees in computer science from the National University of Defense Technology (NUDT), China. He was a visiting professor and a special lecturer in the College of Computing Sciences, New Jersey Institute of Technology, USA (1999-2002) and a lecturer, an associate professor and a full professor at NUDT (1988-2000). He has published 190 research papers, five books, four book chapters, and two conference proceedings. He is a senior member of IEEE and is serving as co-chair of the technical committee of Distributed Intelligent Systems of IEEE Systems, Man and Cybernetics (SMC) Society, member of the Conferences and Meetings Committee, and the Electronic Communications Subcommittee of IEEE SMC Society, Associate Editor (AE) of IEEE Transactions on SMC: Systems, IEEE Transactions on Computational Social Systems, IEEE SMC Magazine, and IEEE Canada Review. He has been an active organizer for the annual IEEE Int’l Conf. on SMC since 2003, as Special Session Chair, Tutorial Chair, Area Co-Chair, Social Media Co-Chair, Web Co-Chair, Poster Co-Chair, Session Chair, and Special Session Organizer. He is the Program Chair for 16th IEEE Int’l Conf. on Networking, Sensing and Control, Banff, AB, Canada, May 8-11, 2019. He was a PC Chair for 17th IEEE Int’l Conf. on Computer Supported Cooperative Work in Design, Whistler, BC, Canada, June 27- 29, 2013. He also served as PC members for 70 academic conferences. He is the founding researcher of Role-Based Collaboration and Adaptive Collaboration. His research has been being sponsored by NSERC, IBM, DRDC, and OPIC.He is the receipt of the meritorious service award from IEEE SMC Society (2018), the chancellor’s award for excellence in research (2011) and two research achievement awards from Nipissing University (2006, 2012), the IBM Eclipse Innovation Grant Awards(2004, 2005), the Best Paper Award from the 11th ISPE Int’l Conf. on Concurrent Engineering (ISPE/CE2004), the Educator’s Fellowship of OOPSLA’03, a 2nd class National Award for Education Achievement(1997), and three 1st Class Ministerial Research Achievement Awards from China (1997, 1994, and 1991). His research interests include Collaboration Theory, Technologies, Systems, and Applications, Human-Machine Systems, CSCW (Computer-Supported Cooperative Work), Multi-Agent Systems, Software Engineering, and Distributed Intelligent Systems.
Phone: +1 07054743450 ext. 4434
Address: Nipissing University
100 College Drive

less

Interests

Uploads

Papers by Haibin Zhu

Adaptive Collaboration Systems: Self-Sustaining Systems for Optimal Performance

IEEE Systems, Man, and Cybernetics Magazine, Oct 1, 2015

Adaptability is a common and typical property for natural systems in the real world. It is also a... more Adaptability is a common and typical property for natural systems in the real world. It is also an important and desirable property for computer supported artificial systems. An adaptive collaboration system (ACS) can be viewed as a set of interacting intelligent agents, real or abstract, forming an integrated system that can respond to internal and environmental changes. Feedback is a key feature of such systems because it enables appropriate responses to change. Artificial systems can be made adaptive by using feedback to sense new conditions in the environment and then adjusting accordingly. ACSs can find applications in almost all industrial sectors, particularly in aerospace, automotive, manufacturing, and management. Adaptive collaboration (AC) can be realized through the promising architecture and process of role-based collaboration (RBC) [21]. RBC is a computational methodology that uses roles [21] as primary underlying mechanisms to facilitate collaboration. RBC has been developed into a methodology of discovery in the research of collaboration systems, because it takes advantage of formalizations and abstractions of system components through mathematical expressions. Problem instances of such abstractions are easily found in real-world scenarios.

Role-Based Collaboration and E-CARGO: Revisiting the Developments of the Last Decade Role-based collaboration (RBC) is an emerging computational methodology that uses roles as the prim

IEEE Systems, Man, and Cybernetics Magazine, Jul 1, 2015

Role-based collaboration (RBC) is an emerging computational methodology that uses roles as the pr... more Role-based collaboration (RBC) is an emerging computational methodology that uses roles as the primary underlying mechanism to facilitate collaboration activities. It consists of a set of concepts, principles, models, and algorithms. RBC offers benefits and challenges that may not be revealed with the traditional methodologies and systems. Related research continues the process of improvement to the development, evaluation, management, and performance of computer-based systems. This article provides a concise introduction to RBC and its model, the Environments-Classes, Agents, Roles, Groups, and Objects (E-CARGO) model; reviews the related research achievements in RBC over the past decade; discusses the challenges requiring future research; presents fundamental methods for conducting related research; and analyzes the connections between RBC and other fields.

Role and Transition Mechanisms in Collaborative Systems

Computer Engineering, 2006

As a tool of expanding the human collaboration space,CSCW(computer supported cooperative work) sy... more As a tool of expanding the human collaboration space,CSCW(computer supported cooperative work) systems should not only provide virtual face-to-face collaborative environments but also improve face-to-face collaboration by providing more mechanisms to overcome the drawbacks of face-to-face collaboration.Roles are one of the effective ways of solving this problem,because roles can help users specify clearly their responsibilities and rights,dynamically change and transfer their positions to improve the efficiency of people’s collaboration.This paper introduces the basic concepts and principles of roles,discusses the architecture of role-based collaborative systems,and mainly demonstrates the implementation of the role transition in collaboration.

Encourage Participants’ Contributions by Roles

Teamwork requires every member to contribute to the team. Encouraging people to contribute in col... more Teamwork requires every member to contribute to the team. Encouraging people to contribute in collaboration is exciting and challenging. The model E-CARGO could support collaboration with human users, agents, roles and groups. By assigning roles and transferring roles, we can organize and encourage human users and agents to contribute in collaboration and make the teamwork more profitable. This paper analyses the behaviors of people in collaboration, proposes a methodology with roles to improve collaboration by assigning human users more roles, discusses the basic methods to evaluate and promote human users with roles and relevant properties and describes the implementation of the kernel mechanisms.

Download

Group role assignment

. The process can be divided into three steps, i.e., agent evaluation, group role assignment, and... more . The process can be divided into three steps, i.e., agent evaluation, group role assignment, and role transfer. This paper formally identifies various group role assignment problems under acceptable assumptions; proposes solutions based on exhaustivesearch; conducts experiments by randomly creating agent qualifications; analyzes the solutions' performance based on experimental results, and indicates future work activities.

Download

Effective Approaches to Adaptive Collaboration via Dynamic Role Assignment

IEEE transactions on systems, man, and cybernetics, 2016

Adaptive collaboration (AC) is essential for group performance optimization in collaborative syst... more Adaptive collaboration (AC) is essential for group performance optimization in collaborative systems. This paper begins by introducing AC within the context of solving a real-world problem. Next, AC problems are formalized based on the environment-class, agent, role, group, and object (E-CARGO) model. Three algorithms are proposed for solving AC problems. They are based on three different scenarios: 1) the current group state (GS); 2) the GS after a specific period; and 3) the GS throughout the collaboration. More complex AC problems and their solutions are then investigated. Derived from the above-mentioned algorithms, two additional algorithms are presented. They consider reassignment costs. Experiments are developed to analyze the performance of each proposed algorithm. Results indicate that the proposed algorithms perform better than static collaboration where there are no reassignment costs. If reassignment costs exist, we also provide a way of determining whether to adopt an AC approach. This paper provides insights into the AC process and its effectiveness in various scenarios.

Some issues of role-based collaboration

Roles are a powerful concept for facilitating distributed systems management. It has been accepte... more Roles are a powerful concept for facilitating distributed systems management. It has been accepted as a good solution for information sharing based on the research of RBAC (Role-Based Access Control). Although no explicit roles are declared in traditional CSCW (Computer-Supported-Cooperative Work) systems, there are implicit roles granted in the design. Consequently, we may infer that "without roles, there would be no collaboration". There is, however, a lack of specific, comprehensive research on building collaborative systems with role management and on role-based methods that have been successfully used in access control. This paper aims to clarify the basic problems related to the research of role-based collaboration and to propose a basic method to do that research.

Download

Adaptive Collaboration Based on the E-CARGO Model

International Journal of Agent Technologies and Systems, 2012

Download

Role mechanisms in collaborative systems

International Journal of Production Research, 2006

CSCW (Computer-Supported Cooperative Work) systems are computer-based tools that support collabor... more CSCW (Computer-Supported Cooperative Work) systems are computer-based tools that support collaborative activities. They should meet the requirements of normal collaborative efforts among people. They should not only support virtual face-to-face collaboration among people at a distance but also improve face-to-face collaboration by providing more mechanisms to overcome the drawbacks of face-to-face collaboration among people. Therefore, introducing roles into CSCW systems is extremely important. By roles, we can avoid users of CSCW systems being overwhelmed by too much irrelevant information. One of the major problems in current CSCW systems is determining how to define and specify roles clearly and rigorously, while maintaining the flexibility for collaboration. Many traditional CSCW systems based on roles have lost their flexibility after introducing roles because they can only provide static role mechanisms based on intuitive role concepts. There are no flexible mechanisms for role tuning, changing and transitions because there is no a special mechanism to express a role. This paper reviews the applications of roles in traditional collaborative systems, clarifies the general meanings of roles, discusses the functions of roles in collaboration, and suggests a role mechanism and a group of principles to support collaboration based on roles. At last, this paper concludes that roles need more comprehensive research and will be applied widely in different areas.

Download

Group Multi-Role Assignment with Coupled Roles

There are many different constraints when assigning agents to roles within a group. One such cons... more There are many different constraints when assigning agents to roles within a group. One such constraint is role coupling.. It is a complex problem that cannot be solved without appropriate modelling tools. The Role-Based Collaboration (RBC) and its Environments – Classes, Agents, Roles, Groups, and Objects (E-CARGO) model is such a tool. This paper proposes a solution to the role assignment problem in consideration of role coupling through the application of this tool. The problem can be described as a Group Multi-Role Assignment with Coupled Roles (GMRACR). It is considered as a multi-objective non-linear optimization problem. Useful solutions are implemented by using a Linear Programming (LP) solver, i.e., the IBM ILOG CPLEX optimization Platform (CPLEX). Experiments are then conducted to verify the proposed solutions. Contributions of this paper include formalization of the GMRACR problem. This provides the foundation for finding an objetive solution and advances the state of the art on the subject of assignment. The proposed solutions provide a solid foundation for decision making in dealing with similar issues.

Improvement to rated group role assignment algorithms

Role assignment is a critical task in Role-Based Collaboration (RBC). It can be divided into thre... more Role assignment is a critical task in Role-Based Collaboration (RBC). It can be divided into three steps, i.e., agent evaluation, group role assignment, and role transfer, where group role assignment is a timeconsuming process. This paper clarifies the problem of group role assignment; describes the general assignment problem; adapts the group role assignment problem to the general assignment problem; proposes an algorithm for group role assignment based on the Munkres algorithm; conducts an experiment by randomly creating agent qualifications, analyzes the solutions' performances, and points out the future work. The results show that the improved algorithm significantly improves the algorithm based on exhaustive search.

Download

Implementing Agent Evolution with Roles in Collaborative Systems

Computer-supported cooperative work (CSCW) systems could support people to accomplish common work... more Computer-supported cooperative work (CSCW) systems could support people to accomplish common work cooperatively with the help of computers. Members of a team take on corresponding tasks by playing particular roles during a collaborative activity. The team members are affected by the changing requirements, the environment and the advancement of personal ability. Hence, it leads to the continual transition between roles

Group role assignment based on multiple criteria in collaboration systems

In the real-world, there are many criteria to evaluate agents on roles, which are an important fa... more In the real-world, there are many criteria to evaluate agents on roles, which are an important factor affecting the result of the group role assignment (GRA). To obtain a satisfied assignment, we need to select an appropriate evaluation method. This paper points out the key issues of the related concepts, formalizes the problem of GRA based on multiple criteria (GRA-MC), investigates three algorithms of multi-criteria decision making, i.e., simple additive weighting (SAW), multiplication exponent weighting (MEW) and weighted distance (WD), briefs the procedure of GRA-MC, verifies the GRA-MA methods by simulations and a case study, and finally discusses the result of GRA-MC.

Support Collaboration with Roles

Collective group role assignment and its complexity

Role assignment is an important task in Role-Based Collaboration (RBC) and Adaptive Collaboration... more Role assignment is an important task in Role-Based Collaboration (RBC) and Adaptive Collaboration. There are many variations in the process of role assignment. An introduction of any new requirement leads to a significant change in the process and the complexity of the algorithm of role assignment. This paper formally identifies a group of problems in role assignment when multiple agents are involved; proposes initial solutions; conducts simulations and experiments to reveal the complexity of collective group role assignment, and indicates future work activities. The contributions of this paper include formal provision of taxonomy for collective group role assignment and indication of the complexities arising from of this type of problem through simulations and experiments.

WhiteCat: Making agent roles perceivable

ABSTRACT

The implementation of role specification mechanisms

Clear and exact role definition and specification are very important in collaborative systems. Th... more Clear and exact role definition and specification are very important in collaborative systems. The current situation is that there is no efficient mechanism to support role specification in collaboration. The paper describes how to implement and construct the fundamental mechanisms to specify role-based object technologies. These mechanisms can be used by a role facilitator who is in charge of collaboration.

A Role-Based Architecture for Intelligent Agent Systems

This paper explores the properties of intelligent agent systems, introduces the model of role-bas... more This paper explores the properties of intelligent agent systems, introduces the model of role-based collaboration E-CARGO, and proposes that roles can be taken as an underlying mechanism to build intelligent agent systems by describing the process of developing agent systems and the agent dynamics in role-based agent systems. Finally, it points out the research topics of role-based distributed intelligent systems.

Download

Role-Based Multi-Agent Systems

IGI Global eBooks, May 24, 2011

Agent system design is a complex task challenging designers to simulate intelligent collaborative... more Agent system design is a complex task challenging designers to simulate intelligent collaborative behavior. Roles can reduce the complexity of agent system design by categorizing the roles played by agents. The role concepts can also be used in agent systems to describe the collaboration among cooperative agents. In this chapter, we introduce roles as a means to support interaction and collaboration among agents in multi-agent systems. We review the application of roles in current agent systems at first, then describe the fundamental principles of role-based collaboration and propose the basic methodologies of how to apply roles into agent systems (i.e., the revised E-CARGO model). After that, we demonstrate a case study: a soccer robot team designed with role specifications. Finally, we present the potentiality to apply roles into information personalization.

Introduction to Special Session (R) on Role-Based Collaboration

ABSTRACT

Haibin Zhu

Uploads

Papers by Haibin Zhu

Log In