Fraudsters in the real world frequently add more legitimate links while concealing their direct ones with other fraudsters, leading to heterophily in fraud graphs, which is a problem that most GNN-based techniques are not built to solve. Several works have been proposed to tackle the issue from the spatial domain. However, researches on addressing the heterophily problem in the spectral domain are still limited due to a lack of understanding of spectral energy distribution in graphs with heterophily. In this paper, we analyze the spectral distribution with different heterophily degrees and observe that the heterophily of fraud nodes leads to the spectral energy moving from low-frequency to high-frequency. Further, we verify that splitting graphs using heterophilic and homophilic edges can obtain more significant expressions of signals in different frequency bands. The observation drives us to propose the spectral graph neural network, SplitGNN, to capture signals for fraud detection against heterophily. SplitGNN uses an edge classifier to split the original graph and adopts flexible band-pass graph filters to learn representations. Extensive experiments on real-world datasets demonstrate the effectiveness of our proposed method. The code and data are available at https://github.com/Split-GNN/SplitGNN.

Facial Expression Recognition (FER) for various low-resolution images is an important task and need in applications of analyzing crowd scenes (station, classroom, etc.). Due to the discriminative feature loss caused by reduced resolution, classifying various low-resolution facial images into the right category is still a challenging task. In this work, we proposed a novel generative adversarial network-based feature level super-resolution method for robust facial expression recognition (FSR-FER), which can reduce the chance of privacy leaking without restoring high-resolution facial images. In particular, a pre-trained FER model was employed as a feature extractor, and a generator network G and a discriminator network D are trained with features extracted from low-resolution and corresponding high-resolution images. Generator network G tries to transform features of low-resolution images to more discriminative ones by making them closer to the ones of corresponding high-resolution images. For better classification performance, we also proposed an effective classification-aware loss reweighting strategy based on the classification probability calculated by a fixed FER model to make our model focus more on samples that are prone to misclassification. Experimental results on the Real-World Affective Faces (RAF) Database and Static Facial Expressions in the Wild (SFEW) 2.0 dataset demonstrate that our method achieves satisfying results on various down-sample factors with a single model and has better performance on low-resolution images compared with methods using image super-resolution and expression recognition separately.

While recent research in music generation has mostly focused on encoder decoder architectures and self-attention mechanisms, prominent advancements regarding GANs have not yet been incorporated for the creation of music. These include solutions for major challenges when training GANs, most importantly training instability. In this work, we aim to apply this new knowledge to music generation, in order to make it more efficient and enable the automatic creation of music of higher quality. We utilize the progressive approach towards GANs, and implement it to train on symbolic music data. For best results, we process this data to obtain a new dataset, which matches the progressive approach. To achieve this, we propose a new way of downsampling fit for musical data. We furthermore conduct a user study to evaluate our results, and compute an FID score of 12.30 as objective metric.

The EU and other public organizations at different levels of national and local government across the world have funded and invested in numerous research and development projects on big data transport applications over last few years. The mid and long term effectiveness of these applications is very difficult to measure, and the benefits and usability of these applications are not easy to calculate. NOESIS, funded under EU H2020 program, aims to design a decision supported tool by gathering and analyzing these applications as use cases to formulate sufficient knowledge for policy makers to make informed decisions for their big data transport applications. The challenges in this work are associated with a small number of samples, with incomplete information, but having a good size of features that need to be analyzed to make a confident enough recommendation. This paper reports various statistical and machine learning approaches used to address these challenges and their results.

Process planning and scheduling are modeled sequentially in the traditional manufacturing system. However, because of their complementarity, the increasing need to integrate them has emerged to enhance the manufacturing productivity significantly. Therefore, the integrated process planning and scheduling (IPPS) is becoming a hotspot in providing a blueprint for efficient manufacturing system. This paper proposes a novel algorithm hybridizing the genetic algorithm with strong global searching ability and variable neighborhood search with strong local searching ability for the IPPS problem. To improve the searching ability, a novel procedure, encoding method, and local search method have been designed. Effective operators have been adopted. Three experiments with totally 37 well-known benchmark problems are employed to evaluate the performance of the proposed method. Based on the results, the proposed algorithm outperforms the state-of-the-art methods and finds the new solutions (the best solutions found so far) for some problems. The proposed method has also been applied on a real-world case from a nonstandard equipment production workshop for the packaging machine of a machine tool company in China. The solution demonstrates that it can solve real-world cases very well.

It is difficult for e-learners to make decisions on how to learn when they are facing with a large amount of learning resources, especially when they have to balance available limited learning time and multiple learning objectives in various learning scenarios. This research presented in this paper addresses this challenge by proposing a new multi-constraint learning path recommendation algorithm based on knowledge map . The main contributions of the paper are as follows. Firstly, two hypotheses on e-learners’ different learning path preferences for four different learning scenarios (initial learning, usual review, pre-exam learning and pre-exam review) are verified through questionnaire-based statistical analysis. Secondly, according to learning behavior characteristics of four types of the learning scenarios, a multi-constraint learning path recommendation model is proposed, in which the variables and their weighted coefficients considers different learning path preferences of the learners in different learning scenarios as well as learning resource organization and fragmented time. Thirdly, based on the proposed model and knowledge map , the design and implementation of a multi-constraint learning path recommendation algorithm is described. Finally, it is shown that the questionnaire results from over 110 e-learners verify the effectiveness of the proposed algorithm and show the similarity between the learners’ self-organized learning paths and the recommended learning paths.

The seven papers in this special section focus on the research and development of service-oriented collaborative computing technologies and their applications to the design of products, processes, systems and services in an industrial and social viewpoint.

There is evidence that an increasing number of enterprises plot together to evade tax in an unperceived way. At the same time, the taxation information related data is a classic kind of big data. These issues challenge the effectiveness of traditional data mining-based tax evasion detection methods. To address this problem, we first investigate the classic tax evasion cases, and employ a graph-based method to characterize their property that describes two suspicious relationship trails with a same antecedent node behind an Interest-Affiliated Transaction (IAT). Next, we propose a Colored Network-Based Model (CNBM) for characterizing economic behaviors, social relationships and the IATs between taxpayers, and generating a Taxpayer Interest Interacted Network (TPIIN). To accomplish the tax evasion detection task by discovering suspicious groups in a TPIIN, methods for building a patterns tree and matching component patterns are introduced and the completeness of the methods based on graph theory is presented. Then, we describe an experiment based on real data and a simulated network. The experimental results show that our proposed method greatly improves the efficiency of tax evasion detection, as well as provides a clear explanation of the tax evasion behaviors of taxpayer groups.

Ranking similar structure groups/subgraphs can contribute to importantly practical applications, such as finding the most suspicious tax evasion group within a heterogeneous information network. This problem, however lacks attentions in the current research community. Inspired by social network analysis, this paper coins a definition of a taxpayer interest interacted network (TPIIN), in which persons or companies act as nodes as well as the arcs act as the relationships between persons and/or companies, and the weight of an arc is equal to the interest affiliated degree (IAD) of a direct tie or link according to various economic behaviors between persons and/or companies. Moreover, we adopted four operations, Maximum, Minimum, Addition, and Multiply, to calculate the IAD of a trail, then propose a voting algorithm based on the four operations to compare the suspicion degrees of all groups containing the same trading relationship arc. Experiments are carried out and their results verify the proposed method.

There is evidence that an increasing number of enterprises plot together to evade tax in an unperceived way. At the same time, the taxation information related data is a classic kind of big data. These issues challenge the effectiveness of traditional data mining-based tax evasion detection methods. To address this problem, we first investigate the classic tax evasion cases, and employ a graph-based method to characterize their property that describes two suspicious relationship trails with a same antecedent node behind an Interest-Affiliated Transaction (IAT). Next, we propose a Colored Network-Based Model (CNBM) for characterizing economic behaviors, social relationships, and the IATs between taxpayers, and generating a Taxpayer Interest Interacted Network (TPIIN). To accomplish the tax evasion detection task by discovering suspicious groups in a TPIIN, methods for building a patterns tree and matching component patterns are introduced and the completeness of the methods based on graph theory is presented. Then, we describe an experiment based on real data and a simulated network. The experimental results show that our proposed method greatly improves the efficiency of tax evasion detection, as well as provides a clear explanation of the tax evasion behaviors of taxpayer groups.

In green management, the quality control performs a key factor for chain materials and products in chain productions. Selecting the correct control chart is essential to effectively monitoring process shifts. In particularly, a nonparametric control chart is recommended over a traditional control chart when the quality characteristics of a process are unknown. This paper designs an intelligent genetic algorithm (GA)-nonparametric EWMA sign chart for green chain management by an adaptive GA controller to upgrade green chains satisfactions. In this paper, we extend the nonparametric exponentially weighted moving average (EWMA) sign chart to a double EWMA (DEWMA) sign chart to improve the detection ability in small green process shifts. Simulation studies show that the nonparametric DEWMA sign chart performs better than the EWMA sign chart in detecting small process shifts, but that they perform similarly when detecting large shifts.

One of the key points to maintain and boost research and development in the area of smart wearable systems (SWS) is the development of integrated architectures for intelligent services, as well as wearable systems and devices for health and wellness management. This paper presents such a generic architecture for multiparametric, intelligent and ubiquitous wireless sensing platforms. It is a transparent, smartphone-based sensing framework with customizable wireless interfaces and plug'n'play capability to easily interconnect third party sensor devices. It caters to wireless body, personal, and near-me area networks. A pivotal part of the platform is the integrated inference engine/runtime environment that allows the mobile device to serve as a user-adaptable personal health assistant. The novelty of this system lays in a rapid visual development and remote deployment model. The complementary visual Inference Engine Editor that comes with the package enables artificial intelligence specialists, alongside with medical experts, to build data processing models by assembling different components and instantly deploying them (remotely) on patient mobile devices. In this paper, the new logic-centered software architecture for ubiquitous health monitoring applications is described, followed by a discussion as to how it helps to shift focus from software and hardware development, to medical and health process-centered design of new SWS applications.

Summary form only given. To enable a group of multiple disciplinary computer software systems to effectively and efficiently collaborate is an important task for applications such as cooperative designs, energy efficiency monitoring system, real-time collaborative mechatronic control systems, e-learning, and enterprise computing etc. With the cost reduction of the hardware for storing data and the need of maintaining the vast amount of data generated from simulation tools, social media and sensors for decision making, to retrieve the right information and to share appropriate knowledge at right time among the participants is a challenging task. On-line Analytical Processing, OLAP, is an effective tool to summarize vast structured data into concise data cubes with multiple dimensions for business intelligence and decision making. Semantic OLAP was developed in the research communities is to process the linked data which is a form of web data representation with semantics increasingly gaining its popularity over the Internet. The introduction of OLAP has increased the efficiency of data retrieval and data management, but it does not address the issues of information and knowledge sharing. In this talk, these issues will be reviewed with examples and a new OLAP framework which could bridge the gaps and increase the sharing among different OLAPs will be presented with a case study. This talk will also share delegates with recent research findings from some ongoing EU-funded projects.

This article proposes a tracking service to provide a facility to trace and compose the RFID-based services, and report the data and status of WEEE (Waste Electrical and Electronic Equipment) across their product lifecycle. Several issues of the tracking service are discussed and a CloudExplorer-based solution is designed to implement the WEEE tracking service. Among of them are (i) Techniques of the tracking service to discover, compose and process the RFID Web services; (ii)WEEE flow and RFID services identification; (iii) Architecture design of the tracking service; (iv) Functionality and system design; and (v)Software design and implementation.

This paper presents a Pulse Width Modulation (PWM) based method for Active Power (AP) and Reactive Power (RP) measurements in electric sinusoidal and Non-sinusoidal power systems. The method takes advantage of the fact that frequencies present in a power line are of a specific fundamental frequency range (a range centred around the 50Hz or 60Hz) and that in case of the presence of harmonics the frequencies of those dominating in the power line spectrum can be specified on the basis of the fundamental. In order to estimate the power components in a generalised power line, in the first stage the elimination of any harmonics present and the identification of the power line fundamental frequency are cascaded by the application, in the next step, of a PWM stage at which a Pulse Wave is generated based on the frequency of the fundamental. In the final stage of the method the power components are calculated. In the major advantages of the proposed method are included: a) in contrast to a number of existing methods a time delay or shifting of the input signal is not required, b) the method does not involve a time delay by ?/2 of the Current signal with respect to the Voltage signal, c) the fundamental frequency of the power line is considered as an unknown parameter, simultaneously estimated with the signal's spectrum using the Fast Fourier Technique (FFT) and so the method is insensitive to fundamental power line frequency changes, and d) complex computations that include multiplication of the Voltage and Current sample values by trigonometric functions are avoided.

Sustainability has become a critical driving force shaping the future of Waste Electrical and Electronic Equipment (WEEE) management. In this research, lifecycle information and flow management has been investigated to enable transition from the current “management authority-centric reporting model for WEEE” to a new “globally sustainable management model for WEEE”. In order to achieve the target, case studies on LCD TV WEEE have been conducted to understand supply chain information flows and recovery & remanufacturing processes. Based on that, information/flow framework design for WEEE management has been explored.

This paper discusses a group decision making approach which facilitates a multi-issue negotiation process between agents such as service providers and consumers in a fuzzy environment. The outcome of such encounters depends on two key aspects: the agenda (the set of issues associated with the service) and the negotiation process (how to settle the issues). In a multiple-issue negotiation process it is difficult to reach an optimal outcome when the two agents' preferences and the relative importance of the alternatives and their associated issues are not known to each other. A fuzzy group decision making process can be used to reach consensus and order the issues in the pre-negotiation stage to improve the efficiency of the outcome. We propose an approach where a fuzzy group decision making process is developed in an agenda based multi-issue negotiation environment.

Designing an effective and efficient intelligent interactive system for energy conservation in domestic environment requires considerable deliberations on tradeoffs of meeting the criteria derived from human-machine interaction and reasoning mechanism, so the system can provide the users with right information based on right decisions at right time. In this paper, we report a mixed initiative intelligent system that employs multi-modal sensor system, context awareness model, semantics, and service-oriented architecture to provide real-time energy consumption information and recommendations for positive behaviour change on households' energy consumption. The system adopts concept of On-Line Analytical Process (OLAP) to summarise large volume of data generated from energy consumption monitoring sensors into a set of meaningful information for the intelligent system to reason. Service-Oriented Architecture (SOA) is used to model hardware and software components, so they can be composed flexibly to meet the user and system requests. The system is currently deployed in around 250 households across Europe for evaluation. Initial households' feedbacks are encouraging.

This study develops a flexible remanufacturing design for green luggage chain to consider reuse and redesign by an adaptive inventory model. This research provides several novel design policies for their remanufacturing operations to increase chain response flexibility. This paper also presents a new methodology for improving the efficiency and generality of genetic algorithms in green design applications. The methodology provides the novel functions of adaptive parameter adjustment during each evolution generation of GAs. The contributions of this algorithm are essentially from the three features: (1) the crossover rate optimization; (2) the mutation rate optimization; (3) the new green design policies' optimization. The research was successfully applied for green luggage chains to produce optimal alternative solutions for chain designers.

A service-oriented travel portal with self-service package has been developed and put into practice for Yangtze River Delta and to serve the coming Shanghai World Expo. A technical issue is raised and become critical with more service providers join the portal. i.e., the portal is supposed to be capable of dynamically finding, reorganizing the services from different providers to get new service packages, and recommending to the tourists. Based on the ongoing project requirement and technical observation, this article proposes a semantic recommender for service discovery, package composition and recommendation. The solution is featured with business-oriented semantic discovery and personalized package composition and evaluation. The involved issues and techniques are common for all service-oriented applications. The recommender is being investigated and prototyped on the travel portal to be evaluated.

There is a growing interest in designing an interoperable smart home environment which involves heterogeneous appliance systems, as it aims to increase the system flexibility. With rapid growth in numbers of appliances, devices, and services, the task for integrating the systems become difficult. In addition, the diversity of these technologies involved in the environment poses tremendous challenges for implementation and development. The emergence of Service Component Architecture (SCA) also generates large interests, as they can exploit different aspects of information systems to enhance software engineering disciplines, facilitate hardware deployment, and improve quality of services. This paper presents a new approach to improve smart home design and configuration by introducing SCA to appliances and sensors networking. A prototype based on the proposed framework was developed to demonstrate its effectiveness.

Dynamic traffic signal control in Intelligent Transportation Systems (ITS) has been widely developed in major cities' urban areas around the world to provide more efficient way for solving traffic congestion problem. However, the problems in dynamic traffic signal control systems such as system flexibility, data standard common interface, transmission of required information, prediction performance, and real-time measurement data are all important issues. Therefore, in this paper, we proposed a new framework to integrate dynamic data driven application systems (DDDAS) with service-oriented architecture (SOA) and web services technology, for a decentralized traffic signal control system. An efficient and effective distributed data-driven optimization algorithm is designed in this framework to produce an optimal result and best strategy for signal control.

Appropriate use of group consensus on service consumers' QoS opinions can improve Web service discovery. For Web service participants with different backgrounds or preferences it may not be easy to reach a consensus on the Web service QoS opinions, so they should be treated as multi-groups. Also, to prevent possibly useful opinions from being omitted unintentionally, fuzzy clustering criteria for the "multi-groups" framework should be adopted. In this paper, we have proposed a FMGSAM (Fuzzy Multi-Groups based SAM) to improve the accuracy in group opinion similarity analysis and the efficiency in generating group consensus.

This article presents a collaborative travel portal with ecommerce and operation services based on multi-level authentication. The portal provides composite ecommerce service for tourists and distributed operation services for a virtual travel enterprise. The virtual enterprise is kind of dynamic coalition, and reorganized by tourism-related cross-regional business agencies. The portal has been developed based on two years of survey and interview with hundreds of prestigious travel agencies and practitioners. The portal-related issues have been addressed, e.g., ecommerce model, portal operation model, resource sharing and route scheduling, multi-level authorization and business collaboration, and financial balance between tourism businesses. The travel portal has been developed and operating with several members in Yangtze River Delta of China.

Inadequate selection of operators and parameters will produce premature convergence that will be avoided by adopting finer setting of parameters. This research was inspired by the concept of quality control utilizing as a control mechanism for process control in various GA searching processes. The process controllers attempt to apply these mechanisms to optimize the settings of the operators and parameters. In this study, we explored the function of the active setting is to adjust the trade-off between the exploration and exploitation by twelve's searching divisions. It applies evolution evidence to supervise the active setting of the GA parameters. Three different kinds of theoretical test-beds were carried out to validate this approach. The test results have been discovered that the active setting can make better the performance of genetic algorithm search. The test consequences also are showed that active is superior to static setting.

With the increasing popularity of deploying web services, quality of service (QoS) becomes a significant concern for service consumers and providers for service selection. However, representing and storing the values of QoS attributes are problematic, as the current universal description, discovery and integration (UDDI) was not designed to accommodate these emerging requirements. To solve the problems of storing QoS in UDDI and aggregating QoS values, three different approaches, namely type, keyword based and ontological approaches to model QoS tModel (technical model) have been proposed. The aim is to study these approaches and other existing QoS tModel representation for their efficiency and consistency in service selection. In this paper, we also report a number of experimental results based on an example in order to evaluate these approaches.

The proposed functional data service framework provides a way of making heterogeneous data sources more accessible to applications and manageable to developers by integrating a service-oriented architecture, a functional data model, the semantic Web, and other related technologies. With the supports of the proposed mechanism, different data sources with their supporting programming technologies are annotated with semantics to facilitate data advertisement and discovery. The data and their relationships in the proposed framework are modelled as a number of functions to form functional data models and these models are realised as web services, so the interfaces for accessing these data can be published. Semantic Web services and ontologies are used to describe the characteristics and facets of data sources. This paper describes the structure of the proposed framework and its advantages in integrating heterogeneous data sources. The paper includes an example to illustrate the main characteristics of the proposed framework.

It is very difficult to accurately predict Genetic Algorithm evolutions and estimate the effects of any change in the operator and parameter settings. So, the setting of the parameter values is guesswork largely. This research applied the concept of Orthogonal Arrays as a tool for identifying the optimal operator and parameter settings for a Genetic Algorithm. This approach was based on the method of a robust experimental design which is attributed by the Taguchi method. The proposed method used Orthogonal Arrays to design a series of experiments which allow the calculation of the optimal value for each of the related variables. The Taguchi method has been applied with a fair degree of success in many practical experiments. This research utilized the theoretical experiment testbeds designed by DeJong’s for different search environments in order to improve the efficiency for genetic algorithm operations.

Optimising variables in the quality control of production can be a complex issue, as it may involve many different constraints and expectations on the quality of products which are normally provided from different organisations to form a multiple supply chain. The challenge of measuring product interdependence across various supply chains and identifying a trade-off between quality and cost is not trivial. In this research, which applies dynamic genetic algorithms, we propose a new approach to representing the problem domain within the chromosome which takes advantage of schema evolution and domain knowledge to refine the chromosome structure. As a result, different weightings can be derived and applied to the genes in order to improve searching efficiency of the genetic algorithms (GA). An example of multiple supply chains has been used to evaluate the proposed approach. The results show that the proposed approach outperforms traditional GA approaches.

Abstract Mobile computing greatly facilitates the provision of mobile services using portable and handheld devices which are connected through wireless networks. A pre‐requisite for the provision of an effective service is to ensure quality of service (QoS) during the concurrent execution of requests and system or network failures. This paper presents a new transaction management approach for the provision of mobile services which is based on advanced transaction models and fuzzy selection criteria. It employs a novel QoS consensus moderation approach in order to select preferred mobile services from among various alternatives, thus providing multiple pathways to the completion of mobile service transactions. Unlike traditional transaction management schemes, the proposed approach takes into account QoS attributes in the commit process of mobile service transactions. The proposed approach is implemented as a prototype tool and evaluated through a number of experiments. Experimental results show that the proposed approach effectively selects mobile services and significantly increases the throughput (i.e. commit rate) of mobile service transactions. Copyright © 2007 John Wiley & Sons, Ltd.

Ensuring consensus on QoS attributes is imperative for the discovery of web services. Inconsistent views of service providers and consumers on QoS attributes could be problematic, even though they have consensus on characteristics. For instance, they may have distinct views of the QoS attribute of service reliability, wherein a consumer considers that a service is reliable if its success rate is 99.9% or 100%, while providers may consider its service as reliable if its success rate is higher than 90%. Different expectations in service discovery could hinder prevailing of the web services. This paper proposes a QoS Consensus Moderation Approach (QCMA) in order to perform QoS consensus and to alleviate the differences on QoS requirements in the web services discovery. The proposed approach is implemented and evaluated through an example of hotel booking web service.

Multi-agent systems (MAS) are one of the complex applications of distributed artificial intelligence. They are prone to different kinds of exception due to their characteristic of operating in a complex and dynamic environment. The dynamism and unpredictable nature of an open environment gives rise to unpredictable exceptions. It becomes essential to have some exception diagnosis mechanisms in place to be able to diagnose the cause of such exceptions and to execute proper recovery plans. These mechanisms do come with some overheads. In this paper, we present an empirical evaluation of our proposed sentinel based approach to exception diagnosis in an open MAS and also discuss the trade offs in using a sentinel based approach to exception diagnosis in an MAS.

Risk assessment for security management is a complex process which linked to substantial ambiguous. However, existing techniques of risk analysis determine the solution by the probability distribution junction of threats and its impact loss. In fact, it is difficult for users to collect precise and adequate events to estimate the probability of threats and impact losses. Consequently, a fuzzy risk analysis model is developed to prioritize the risk ranking of assets. The proposed model uses pseudo-order preference model (POPM) to represent the imprecise preference degree of decision maker and determine the ranking of alternative using fuzzy majority concept. It extends the traditional risk analysis using fuzzy multiple-person decision making (MPDM) theory and POPM to risk analysis in fuzzy environment. Finally, a real case of risk assessment for the internet data center (IDC) is given to illustrate our approach.

Transaction commit protocols have widely been used to ensure the correctness and reliability of distributed applications. This paper investigates into the performance of such protocols within the context of composite web services. It presents a new commit protocol which aims to improve the performance of composite web services transactions. The proposed protocol is tested through various analytical experiments. These experiments reveal that the proposed protocol significantly improves the performance in committing a composite web service transaction. The experiments also exhibit the processing overhead of the proposed protocol in the case of unsuccessful execution of a web service transaction

While we have seen a successful move towards a rapid proliferation of CSCW integration through Web technology including artificial intelligence techniques, still a significant work needs to be done in order to provide quality of service (QoS), particularly addressing the issues of QoS in terms of user requirements. In this paper, we present an approach based on ethnography and multi-agents systems to address these issues in an effective way by mapping a user mental model onto agents. We apply ethnographic approach in order to understand and explain the semantics, functionality and detailed user requirements of CSCW systems. Secondly, we employ artificial intelligent agents for communication and collaboration purposes based on user profile and preferences. In this paper, we also demonstrate the use/illness of this approach by presenting a real life case study of two CSCW (computer supported cooperative work) systems

Genetic algorithm (GA) technique is a promising approach to identify an optimum manufacturing cost by concurrently considering significant number of related variables. It is a superior technique for discovering optimal alternative solutions for multiple objective optimization problems. In GA, however, the setting of operators and the selections of their parameters could affect the output significantly, as they influence the processes of exploitation and exploration. The function of the dynamic setting is to adjust the trade-off between the exploration and exploitation of the search space. This research focuses on the application of evolution evidence to supervise the dynamic setting of the GA parameters. Theoretical test-beds were carried out to verify the theory. The practical experiments were conducted to solve the optimization problems in supply chain management. The experimental results have revealed that the dynamic setting improves the performance of supply chain management and the results also disclosed that dynamic is superior to static setting

Agent oriented architectures and service oriented architectures (SOA) have many features in common such as loose coupling and provision and consumption of services. Software agent systems have been used in many commercial applications due to their attractive attributes such as autonomy, flexibility and; a rich and complex set of interaction protocols. Agents in such systems provide and consume services on behalf of their owners. These systems are prone to various kinds of runtime exceptions due to the dynamic nature of open environments and the different programming models involved in the provision of a particular service. Diagnosis of underlying causes of these exceptions is critical for the successful and reliable operation of agent oriented services. This paper presents and discusses a sentinel agent based approach for diagnosing the underlying causes of runtime exception for agent-oriented services.

The advantages of service-oriented architecture for information systems development have increased its popularity and improved service availability over the Internet. In order to maintain its sustainability and prevent users from exploiting free services, a service-oriented market mechanism should be introduced to regulate the market. However, this issue has not been well addressed in the community. In this work, we propose core-based agents that can collect information from service-oriented markets to convince service providers and consumers to form a coalition based on the core concept solution from game theory. With the introduction of the agent to the service-oriented market, a number of multiple core markets can be merged into a virtual market with a unique core which satisfies the requirements of stability and efficiency. An example of a travel agent web service, which is a composite web service, will be used to illustrate the roles of the agents in this paper.

To fully realise the potential of Web services it is necessary to develop viable dynamic discovery and composition techniques. Matchmaking is considered as one of the crucial factors to ensure dynamic discovery and composition of Web services. Current matchmaking methods are inadequate given their inability to abstract and classify the underlying data of Web services. Instead, they classify Web services based on the capability of services, software signatures, and so on. This paper proposes a novel framework which exploits fuzzy logic in order to abstract and classify the underlying data of Web services as fuzzy terms and rules. The aim is to increase the efficiency of the discovery of Web services and to allow imprecise or vague terms in the search query.

Grid services are software components that provide seamless access to a variety of grid resources such as computational resources and data sources. We present a new multi-agent framework which aims to ensure effective mediation of grid services. The framework comprises different services including search and discovery, planning and coordination, and service reliability and security. The main objectives of the framework are to dynamically discover grid services, devise effective planning and coordination strategies for the discovered services, and securely and reliably utilise those services.

Open multi-agent systems (MAS) are decentralised and distributed systems that consist of large number of loosely coupled autonomous agents. Data and control in such systems is highly distributed. In the absence of centralised control they tend to be difficult to manage, especially in an open environment, which is a dynamic, complex, distributed and unpredictable. This dynamism and uncertainty of an open environment gives rise to unexpected plan failures. In this paper we focus on the process of diagnosing causes of exceptions in failed plan. We apply our proposed sentinel agent based architecture in order to diagnose a plan's actions failure interactively. Once an exception is detected the sentinel agents involve in a dialogue with associated agents using Agent Communication Language (ACL) messages in order to obtain relevant information. This information consists of abstract knowledge about the failed plan and knowledge about agents' mental attitudes regarding the failed plan. The sentinel agent then uses this abstract knowledge and agent's mental attitudes to diagnose the underlying cause of the plan failure. Agents voluntarily inform the sentinel about their mental state regarding the failed plan.

The open grid services infrastructure (OGSI) defines a distributed system framework by integrating grid and Web services technologies to facilitate resource sharing. In OGSI, Web services are supplemented with additional features in order to meet the requirements of grid computing. However, the issue of grid service composition is not well addressed in the OGSI framework. We apply BPEL4WS (business process execution language for Web services) as a business workflow description language for the composition of grid services. We provide an in depth analysis of BPEL4WS and OGSI in terms of their similarities and differences in areas such as life cycle management, Web service instantiation and instance group management. Based on our analysis we propose a high-level architecture to compliment OGSI with BPEL4WS for defining process workflow among grid services. We describe a prototype system which shows how the proposed architecture can be used in modelling or orchestrating grid services with BPEL4WS.

We present an active network-based approach in order to improve the performance of mobile transactions. This approach employs preemptive resume scheduling mechanism which reduces queuing delays involved in the processing of mobile transactions at each network node. Such reduction of queuing delay significantly improves performance of mobile transactions given the heavy network traffic and the lower network bandwidth. We have conducted several experiments using analytical modelling approach in order to determine the impact of priority scheduling mechanism on the performance of mobile transactions. Experiments show significant performance improvements of the proposed approach over existing approaches of mobile transactions. It has also been shown that the proposed approach is robust in that it can be applied to improve the performance of current mobile transaction approaches.

Transaction management is a major issue in Mobile Commerce (M-commerce). It enables people to order goods and access information in an anywhere and anytime fashion. Given the nature of mobile computing, there is a need for a generic approach that adapts to the needs of M-commerce applications. We propose a new multi-agent approach that dynamically manages mobile transactions which adapt to the processing environment of M-commerce. We also present techniques that deal with the issues of handoff, disconnection, or system failures. Potential advantages of the proposed approach include enhanced flexibility, improved performance and fault tolerance.

The leasing of idle computing resources over the net is one way to motivate more participants to join the grid computation initiative. Since the participating parties are independent bodies, negotiation activities are required. In this research, we propose a new automated negotiation mechanism that allows each party to reach an agreement. The mechanism includes two methods: a co-evolutionary method and a game theory based method that is a trusted third party mediated game to facilitate the automation of negotiation between two participants. This mechanism allows them to reach a state that exhibits Pareto efficiency and Nash Equilibrium without knowing each other's utility function.

In a complex engineering design, multiple engineering design agents are required to work cooperatively in order to design a product. Using a single system to model the problem is not natural and can be difficult, since multiple disciplinary teams in different departments, and multiple companies with different modelling methods and techniques are often involved Each design agent is only concerned with its design issues, having little or no knowledge about the concerns of other agents. A successful engineering design requires specialist knowledge and original ideas in order to produce a high-quality design. In this paper, we present a framework where agent technology is used to model interactions between design systems. We also introduce a multiple-evolutionary approach with an automated negotiation mechanism to enable agents to exchange design ideas and to reach an agreed optimised solution for a global design problem.

Exception handling in a multi-agent system (MAS) has not been well addressed compared to other software engineering paradigms. This results in part from the lack of a comprehensive classification of exceptions in MAS. The interaction between agents presents exceptions that cannot be addressed by the exception handling techniques used in traditional software engineering systems due to the introduction of the notions of sociability and autonomy. This paper attempts to provide an insight of agent exceptions by dividing them into three levels, namely environmental, knowledge and social level. The use of a temporal dimension in the form of explicit deadlines in communicative acts is presented as a means of clarifying and facilitating exception analysis at a social level. Comments are made on related work and areas for further work are identified.

Web-based engineering design activities require fault tolerance and concurrent access to shared resources such as databases and Web servers. Such activities are generally dynamic, cooperative, long-lived, interactive, and non-prescriptive. We propose a new multi-agent transaction model, which is based on extended transactions and multi-agent technologies. The novelty of this model is that it automatically customises transactions to the requirements of the design activities. In addition, this model is believed to improve concurrency and fault tolerance, facilitate interaction and co-operation of participating systems involved in design activities.

One feature of concurrent engineering is the notion of distributed design, and the ability to communicate changes to all participating disciplines. However, successful engineering design is constrained by the complexities of the design activity. The differences in system architectures or methodologies, the diverse knowledge and information generated by these distributed disciplines, all compounded by the problems of coordinating the communication process, reduce the reflectiveness of distributed design. Current thinking indicates that multi-agent systems (MASs) could alleviate this complex and large engineering design problem. A drawback of these approaches is the failure to recognise the significance of agent autonomy and proactiveness. In this paper, it is suggested that agent attributes such as proactiveness and autonomy are ideally suited to resolving these problems. They provide a more flexible and dynamic approach to multiple disciplines situated within distributed design environments, which can reduce the number of redundant design activities and thereby reduce the coordination management required and the number of design versions. It is proposed that an agent-based framework incorporating CORBA technology should be used to maximise the proactive nature of autonomous design agents.