Search results

1 – 10 of over 70000
Article
Publication date: 1 February 2022

Ariel Rosenfeld and Nitzan Haimovich

In this work, the authors propose to harness the advantages of behavioral programming as a new technique for designing rule-based conversational agents.

Abstract

Purpose

In this work, the authors propose to harness the advantages of behavioral programming as a new technique for designing rule-based conversational agents.

Design/methodology/approach

To examine the study’s hypotheses, the authors perform a first-of-its-kind user study through which the authors examine how potential designers, both expert designers, computationally-oriented designers, and otherwise, leverage behavioral programming (BP) and dialog graphs for designing conversational agents (CAs). The authors also use two standard CA settings common in the literature: designing a CA representative for a user in an online dating service and a non-character player in a role-playing game (RPG).

Findings

The study’s results indicate that BP can be successfully utilized by computationally-oriented designers, with or without prior knowledge in CA design, and can facilitate the design of better CAs (i.e. more accurate and more robust). However, to capitalize on these potential advantages, designers may be required to devote more time to the design process and are likely to encounter higher temporal demand levels. These results suggest that BP, which was initially proposed and evaluated in the general context of software design, can constitute a valuable alternative to the classic rule-based CA design technique commonly practiced today.

Research limitations/implications

An important limitation of this study is the relatively small participant pool. While the authors do plan to extend this study in the future, the current coronavirus disease 2019 (COVID-19) situation makes it ever more complex to conduct formal user studies of this kind. It is, however, important to note that despite the low number of participants, many of the results are found to be statistically significant.

Practical implications

The authors plan to continue this line of work and conduct human studies for additional design techniques in other popular agent-based settings. Specifically, the authors seek to explore how people of different backgrounds should design agents for various tasks such as automated negotiation (e.g. how should a person design a representative agent to negotiate on her behalf?) and social choice (e.g. how should a person design a voting bot to represent her in online voting systems?).

Originality/value

People are increasingly interacting with conversational agents in various settings and for a variety of reasons, as the market size of those agents keeps on growing every year. Through a first-of-its-kind human study (N = 41), consisting of both expert designers, computationally-oriented designers, and otherwise, the authors demonstrate a few key advantages and limitations of BP in the realm of conversational agents and propose its consideration as an alternative to the classic dialog graph technique.

Details

EuroMed Journal of Business, vol. 18 no. 3
Type: Research Article
ISSN: 1450-2194

Keywords

Article
Publication date: 1 December 2001

C.J. Anumba, O.O. Ugwu, L. Newnham and A. Thorpe

Presents a multi‐agent system (MAS) for collaborative design in the construction sector. The system is intended to form a basis for integrating the often distributed…

1263

Abstract

Presents a multi‐agent system (MAS) for collaborative design in the construction sector. The system is intended to form a basis for integrating the often distributed cross‐functional activities that characterise collaborative design in construction. The MAS supports interaction and negotiation between the different agents that represent various participants that are usually engaged in a typical collaborative project design. The system is composed of different agents that provide services within the MAS environment. While some of the support services are provided by the agent platform, task agents that represent various functional disciplines undertake the real design activities. Describes details of the MAS, which simulates and demonstrates peer‐to‐peer interaction, communication and negotiation between the design agents in a collaborative design space. Also highlights important issues in MAS development and makes recommendations on how to improve collaborative design in construction using the MAS paradigm.

Details

Logistics Information Management, vol. 14 no. 5/6
Type: Research Article
ISSN: 0957-6053

Keywords

Article
Publication date: 27 July 2010

Nandish V. Patel, Tillal Eldabi and Tariq M. Khan

The purpose of this paper is to address the problem of designing artificial complex adaptive systems, like information systems and organisations, by developing a proof‐of‐concept…

1041

Abstract

Purpose

The purpose of this paper is to address the problem of designing artificial complex adaptive systems, like information systems and organisations, by developing a proof‐of‐concept conceptual proto‐agent model.

Design/methodology/approach

The paper develops an exploratory proto‐agent model and evaluates its suitability for implementation as agent‐based simulation.

Findings

The paper focuses on understanding the effect of emergence when designing artificial complex adaptive systems and produces a proto‐agent model that identified agents and their behavioural rules for modelling.

Practical implications

In deferred action, agents act in emergent organisation to achieve predetermined goals. Since emergence cannot be predicted, information systems and organisation design approaches that cater for emergent organisation are required.

Originality/value

The deferred action construct is a synthesis of planned approaches and contingency approaches to design information systems. It recognises the effect of emergence on information systems.

Details

Journal of Enterprise Information Management, vol. 23 no. 4
Type: Research Article
ISSN: 1741-0398

Keywords

Article
Publication date: 21 June 2013

Ewa Dostatni, Jacek Diakun, Adam Hamrol and Waldemar Mazur

The paper aims to describe ideas and implementation of the computer tool for computer‐aided and recycling‐oriented design. Currently, there is a strong tendency to take into…

Abstract

Purpose

The paper aims to describe ideas and implementation of the computer tool for computer‐aided and recycling‐oriented design. Currently, there is a strong tendency to take into account the impact of a product on the natural environment. The authors concentrated on the issue of the recycling process of the product, taking into account the phase of its design. The purpose, structure, technology and example results are presented in this paper.

Design/methodology/approach

It was assumed that analysis will be performed based on a set of measures of a product. These measures (developed by the authors), describing the product from the recycling point of view, are calculated automatically, according to the changes (variants) in the product's model. The presented tool is based on agent technology. The structure of the system – the agents, its roles and communication between them – has been described.

Findings

The main achievement of the work presented in this paper is the method supporting eco‐design based on agent technology. Based on the analysis of the process of recycling‐oriented eco‐design, the authors designed and then implemented the tool that aids designers' activities in the area of eco‐design. The drawn‐up method supports decision making concerning designing environmental‐friendly products. Thanks to agent technology, the design process can be conducted in the distributed design environment.

Research limitations/implications

The usage of the presented computer‐aided and recycling‐oriented system during the design process requires the duplication of some of the engineer's work. The analysis is performed within the presented tool, outside the typical contemporary design environment, such as CAD 3D systems. As a consequence, there is a need to enter the product structure into the described system, which can be inconvenient. The further work of the authors assumes implementation of this concept into a CAD 3D system.

Originality/value

There has been a limited amount of research work regarding application agent technology in the field of end‐of‐life oriented design. The structure of the system, the measurements and idea of extension of product structure are the original results of the work. The results could be implemented into commercial computer‐aided design systems, especially into its PLM (product lifecycle management) group, due to the weak representation of end‐of‐life phases in these tools.

Details

Industrial Management & Data Systems, vol. 113 no. 6
Type: Research Article
ISSN: 0263-5577

Keywords

Article
Publication date: 1 June 2006

Ching‐Jen Huang, Amy J.C. Trappey and Yin‐Ho Yao

The purpose of this research is to develop a prototype of agent‐based intelligent workflow system for product design collaboration in a distributed network environment.

2332

Abstract

Purpose

The purpose of this research is to develop a prototype of agent‐based intelligent workflow system for product design collaboration in a distributed network environment.

Design/methodology/approach

This research separates the collaborative workflow enactment mechanisms from the collaborative workflow building tools for flexible workflow management. Applying the XML/RDF (resource description framework) ontology schema, workflow logic is described in a standard representation. Lastly, a case study in collaborative system‐on‐chip (SoC) design is depicted to demonstrate the agent‐based workflow system for the design collaboration on the web.

Findings

Agent technology can overcome the difficulty of interoperability in cross‐platform, distributed environment with standard RDF data schema. Control and update of workflow functions become flexible and versatile by simply modifying agent reasoning and behaviors.

Research limitations/implications

When business partners want to collaborate, how to integrate agents in different workflows becomes a critical issues.

Practical implications

Agent technology can facilitate design cooperation and teamwork communication in a collaborative, transparent product development environment.

Originality/value

This research establishes generalized flow logic RDF models and an agent‐based intelligent workflow management system, called AWfMS, based on the RDF schema of workflow definition. AWfMS minimizes barriers in the distributed design process and hence increases design cooperations among partners.

Details

Industrial Management & Data Systems, vol. 106 no. 5
Type: Research Article
ISSN: 0263-5577

Keywords

Article
Publication date: 1 March 2001

O.O. UGWU, C.J. ANUMBA and A. THORPE

Domain ontologies facilitate sharing and re‐use of data and knowledge between distributed collaborating systems. A major problem in the design and application of intelligent…

Abstract

Domain ontologies facilitate sharing and re‐use of data and knowledge between distributed collaborating systems. A major problem in the design and application of intelligent systems is to capture and understand: the data and information model that describes the domain; the various levels of knowledge associated with problem solving; and the patterns of interaction, information and data flow in the problem solving space. This paper reports the development of an ontology for agent‐based collaborative design of portal structures, using knowledge acquisition techniques and tools. It illustrates the application of the ontology in the development of a prototype multi‐agent systems. The study shows that a common ontology facilitates interaction and negotiation between agents and other distributed systems. The paper discusses the findings from the knowledge acquisition, their implications in the design and implementation of multi‐agent systems, and gives recommendations on developing agent‐based systems for collaborative design and decision‐support in the construction sector.

Details

Engineering, Construction and Architectural Management, vol. 8 no. 3
Type: Research Article
ISSN: 0969-9988

Keywords

Article
Publication date: 5 August 2019

Juan Du, Hengqing Jing, Daniel Castro-Lacouture and Vijayan Sugumaran

The purpose of this paper is to develop a multi-agent-based model for quantitatively measuring how the design change management strategies improve project performance.

Abstract

Purpose

The purpose of this paper is to develop a multi-agent-based model for quantitatively measuring how the design change management strategies improve project performance.

Design/methodology/approach

Based on questionnaires and interviews, this paper investigates the coordination mechanism of risks due to design changes in prefabricated construction (PC) projects. Combined with all the variables related with design change risks, a multi-agent-based simulation model is proposed to evaluate the design change management effect.

Findings

The coordination mechanism between design change factors, design change events, risk consequence and management strategy in PC projects is described and then the simulation-based design change management mechanism in PC projects is used to assess the effect of management strategies under dynamic scenarios.

Originality/value

PC projects have rapidly increased in recent years due to the advantages of fast construction, high quality and labor savings. Different from traditional on-site construction, the impact and risk from design changes are likely to be greater due to the prefabricated project being multi-stage, highly interactive and complex. The simulations presented in this paper make it possible to test different design change management strategies in order to study their effectiveness and support managerial decision making.

Details

Engineering, Construction and Architectural Management, vol. 27 no. 1
Type: Research Article
ISSN: 0969-9988

Keywords

Article
Publication date: 19 October 2015

Kun Chen, Xin Li and Huaiqing Wang

Although big data analytics has reaped great business rewards, big data system design and integration still face challenges resulting from the demanding environment, including…

2713

Abstract

Purpose

Although big data analytics has reaped great business rewards, big data system design and integration still face challenges resulting from the demanding environment, including challenges involving variety, uncertainty, and complexity. These characteristics in big data systems demand flexible and agile integration architectures. Furthermore, a formal model is needed to support design and verification. The purpose of this paper is to resolve the two problems with a collective intelligence (CI) model.

Design/methodology/approach

In the conceptual CI framework as proposed by Schut (2010), a CI design should be comprised of a general model, which has formal form for verification and validation, and also a specific model, which is an implementable system architecture. After analyzing the requirements of system integration in big data environments, the authors apply the CI framework to resolve the integration problem. In the model instantiation, the authors use multi-agent paradigm as the specific model, and the hierarchical colored Petri Net (PN) as the general model.

Findings

First, multi-agent paradigm is a good implementation for reuse and integration of big data analytics modules in an agile and loosely coupled method. Second, the PN models provide effective simulation results in the system design period. It gives advice on business process design and workload balance control. Third, the CI framework provides an incrementally build and deployed method for system integration. It is especially suitable to the dynamic data analytics environment. These findings have both theoretical and managerial implications.

Originality/value

In this paper, the authors propose a CI framework, which includes both practical architectures and theoretical foundations, to solve the system integration problem in big data environment. It provides a new point of view to dynamically integrate large-scale modules in an organization. This paper also has practical suggestions for Chief Technical Officers, who want to employ big data technologies in their companies.

Details

Industrial Management & Data Systems, vol. 115 no. 9
Type: Research Article
ISSN: 0263-5577

Keywords

Article
Publication date: 8 October 2018

Faqihza Mukhlish, John Page and Michael Bain

The purpose of this paper is to review the current state of proceedings in the research area of automatic swarm design and discusses possible solutions to advance swarm robotics…

Abstract

Purpose

The purpose of this paper is to review the current state of proceedings in the research area of automatic swarm design and discusses possible solutions to advance swarm robotics research.

Design/methodology/approach

First, this paper begins by reviewing the current state of proceedings in the field of automatic swarm design to provide a basic understanding of the field. This should lead to the identification of which issues need to be resolved in order to move forward swarm robotics research. Then, some possible solutions to the challenges are discussed to identify future directions and how the proposed idea of incorporating learning mechanism could benefit swarm robotics design. Lastly, a novel evolutionary-learning framework for swarms based on epigenetic function is proposed with a discussion of its merits and suggestions for future research directions.

Findings

The discussion shows that main challenge which is needed to be resolved is the presence of dynamic environment which is mainly caused by agent-to-agent and agent-to-environment interactions. A possible solution to tackle the challenge is by incorporating learning capability to the swarm to tackle dynamic environment.

Originality/value

This paper gives a new perspective on how to improve automatic swarm design in order to move forward swarm robotics research. Along with the discussion, this paper also proposes a novel framework to incorporate learning mechanism into evolutionary swarm using epigenetic function.

Details

International Journal of Intelligent Unmanned Systems, vol. 6 no. 4
Type: Research Article
ISSN: 2049-6427

Keywords

Article
Publication date: 15 September 2023

Xiaohan Xu, Xudong Huang, Ke Zhang and Ming Zhou

In general, the existing compressor design methods require abundant knowledge and inspiration. The purpose of this study is to identify an intellectual design optimization method…

Abstract

Purpose

In general, the existing compressor design methods require abundant knowledge and inspiration. The purpose of this study is to identify an intellectual design optimization method that enables a machine to learn how to design it.

Design/methodology/approach

The airfoil design process was solved using the reinforcement learning (RL) method. An intellectual method based on a modified deep deterministic policy gradient (DDPG) algorithm was implemented. The new method was applied to agents to learn the design policy under dynamic constraints. The agents explored the design space with the help of a surrogate model and airfoil parameterization.

Findings

The agents successfully learned to design the airfoils. The loss coefficients of a controlled diffusion airfoil improved by 1.25% and 3.23% in the two- and four-dimensional design spaces, respectively. The agents successfully learned to design under various constraints. Additionally, the modified DDPG method was compared with a genetic algorithm optimizer, verifying that the former was one to two orders of magnitude faster in policy searching. The NACA65 airfoil was redesigned to verify the generalization.

Originality/value

It is feasible to consider the compressor design as an RL problem. Trained agents can determine and record the design policy and adapt it to different initiations and dynamic constraints. More intelligence is demonstrated than when traditional optimization methods are used. This methodology represents a new, small step toward the intelligent design of compressors.

Details

Engineering Computations, vol. 40 no. 9/10
Type: Research Article
ISSN: 0264-4401

Keywords

1 – 10 of over 70000