Search

Collective adaptive systems (CAS) have been attracting increasing attention in the field of artificial intelligence (AI), in which collaboration of agents plays a key role. These systems aim to accomplish a certain goal though collaborating between a variety of agents with different tasks, which adapt to changes of environment to be of adaptability. To solve the issue of collaboration of agents in an uncertain and highly dynamic environment, our research team had proposed a Goal-Capability-Commitment (GCC) based mediation for multi-agent collaboration, which generates the collaboration planning driven by capability based on global context states in real-time dynamic environment. As a case study for the application of GCC model, this paper adopts GCC to model the RoboCup Rescue Simulation System (RCRSS). As the result of modelling, the GCC domain model is applied to RCRSS where an efficiently quantitative evaluation is provided.

The BDI model has solved the problem of reasoning and decision-making of agents in a particular environment by procedure reasoning. But in uncertain environment which the context is unknown the BDI model is not applicable, because in BDI model the context must be matched in plan library. To address this issue, in this paper we propose a method extending the BDI model with Q-learning which is one algorithm of reinforcement learning, and make an improvement to the decision-making mechanism on the ASL as a implement model of BDI. Finally we completed the simulation of maze on Jason simulation platform to verify the feasibility of the method.

With the rise of social media, much attention has been focused on it to collect the data from it, which gives us a novel scientific way to investigate some classic questions about individual and social aspects of our life. This paper researches on such a study based on the previous studies. We demonstrate that there is no relationship between movie box office revenue and social media data. This paper applies the second hottest social media application: Twitter, to analyze the relationship between movie box office revenue and Tweets through Pearson correlation coefficient.

For scalability, reliability and cost reduction, virtual environment has been evolved from the client-server model, peer-to-peer model, to the virtual node-based hybrid model. When objects are hosted by unreliable nodes, replication is applied for reliability. An important problem is to maintain replica consistency in interaction, while to minimize interaction latency in play. We propose a fast state machine replication model to address this issue. Besides correctness, our simulation shows the achievable high responsiveness. The work can also be applied in augmented and mixed reality systems, where hundreds of users interact with virtual elements on a common platform.

In e-business development, semantics-oriented document exchange is becoming important, because it can support cross-domain user connection, business transaction and collaboration. To provide this support, this paper proposes a DOC Mechanism to exchange semantically interoperable business documents between heterogeneous enterprise information systems. This mechanism is designed on a layered-sign network, which enables any exchanged e-business document to be independently interpretable without losing semantic consistency.

In e-business, creating a common concept set for business integration, interoperation and interaction has to consider the heterogeneity reality of different interpretations from multiple concept providers. Maintaining semantic consistency between multiple concept providers is a difficult problem. To solve this problem, this paper first reviewed the existing technologies of collaborative editing systems and consistency maintenance in the areas of both CSCW and e-business. Based on the discussion of existing technologies, it then proposes a novel CHCES approach, which divides a collaborative editing system into two layers in topology and introduces four strategies to edit common concepts between the two layers. A set of operations is designed, which demonstrates the solution.

In this paper, we provide a novel image annotation model by mining the Web. In our approach, the concepts or words appearing in the associated text are extracted and filtered as the semantic annotations for the corresponding Web images. In order to alleviate the influence caused by the noise images, for each semantic concept, we improve Web image-word relationships using Mixture Gaussian Distribution Model. By doing so, the concepts or words relevant to any image are re-weighed by both considering their relevance to the image in term of text and in term of visual feature. In fact, all the words associated to an image are not semantically independent. We use co-occurrences between two words to describe their semantic relevance. Thus, we further use a method, called Word Promotion, to co-enhance the weights of all the words associated to a given image based on their co-occurrences. Our experiments are conducted in several ways and the results show that our annotation method can achieve a satisfactory performance.

Establishing an open virtual money exchange regime is a novel idea but rarely discussed. This paper provides a pioneer research on virtual money exchange (VONEX) approach, aiming to facilitate the exchange of virtual currencies among a variety of heterogeneous virtual communities. It has defined the intrinsic value and exchangeable value of virtual currencies and suggested a redistribution strategy, constituting the theoretical foundation of the virtual exchange rate system, by which a novel VONEX exchange rate algorithm is derived. Further to the introduction of the algorithm, a proof is given to ensure its correctness.

In this paper, we studied the semantic consistency maintenance issue between heterogeneous contexts, that is, how a firm' business process of one e-marketplace can be transformed to another firm's business process of another e-marketplace in a semantically consistent way. The proposed solution of this paper uses XML Product Map (XPM) of collaborative concept to represent semantically consistent business processes, and adopts common action concept pool and XPM documents to design heterogeneous business processes that are suitable for heterogeneous business process transformation. We motivated the approach with a real-world PVC poncho trade problem and explained it in architecture of collaborative process design and automatic service provision. We reported the implementation specification within a hybrid human-agent framework, where four layers of system modules are specified. The approach is evaluated based on a new semantic impact chain method particularly for evaluating concept consistency in meaning representation between heterogeneous contexts of business processes.