Transactions on Computational Collective Intelligence II

The current challenge of the Semantic Web is the development of an expressive yet effective rule language. This paper presents an integration proposal for Description Logics (DL) and Attributive Logics (ALSV) is presented. These two formalisms stem from fields of Knowledge Representation and Artificial Intelligence. However, they are based on different design goals and therefore provide different description and reasoning capabilities. ALSV is the foundation of XTT2, an expressive language for rule-based systems. DL provide formulation for expressive ontology languages such as OWL2. An important research direction is the development of rule languages that can be integrated with ontologies. The contribution of the paper consists in introducing a possible transition from ALSV to DL. This opens up possibilities of using XTT2, a well-founded rule-based system modelling rule language, to improve the design of Semantic Web rules.

According to transaction cost economics, contracts are always incomplete and offer opportunities to defect. Some level of trust is a sine qua non for trade. If the seller is better informed about product quality than the buyer, the buyer has to rely on information the seller provides or has to check the information by testing the product or tracing the supply chain processes, thus incurring extra transaction cost. An opportunistic seller who assumes the buyer to trust, may deliver a lower quality product than agreed upon. In human decisions to deceive and to show trust or distrust, issues like mutual expectations, shame, self-esteem, personality, and reputation are involved. These factors depend in part on traders’ cultural background. This paper proposes an agent model of deceit and trust and describes a multi-agent simulation where trading agents are differentiated according to Hofstede’s dimensions of national culture. Simulations of USA and Dutch trading situations are compared.

The Web has been growing in size and with the proliferation of large-scale collaborative computing environments, Social Search has become increasingly important. This recent field focuses on assigning relevance to Web-pages by considering the reader’s perspective rather than Web-masters’ point of view. Current searching technologies of this form tend to rely on explicit human recommendations. In part because it is hard to obtain user feedback, these methods are hard to scale. The challenge is in producing implicit rankings, by reasoning over users’ Web-search activity, without recourse to explicit human intervention. This paper focuses on a novel Social Search model based on Information Foraging Theory, Effort and Computational Trust, showing a different way to implicitly judge Web-entities. The formalism has been divided in two sub-models. The first considers the effort expended by users, in viewing Web-sites, to assess their relevance to a given searching problem. The second enhances the first sub-model by considering only the most trustworthy users’ opinions, identified by Computational Trust techniques.

100 university students explicitly evaluated the usefulness of 12 thematic Web-sites and their browsing activity were gathered. Correlation indexes suggests the existence of a considerable relationship between explicit feedback and implicit computed judgements that were further compared to the ones, provided by the Google search engine. The proposed nature-inspired approach suggests that, by considering the same searching query, Social Search to be more effective than the Google Page-Rank Algorithm. The consideration of the only identified trustworthy students’ implicit feedback provides a way to increase the accuracy of the effort-based approach. This evidence supports the presentation of a schema for a Social Search engine that generates implicit rankings by considering the collective intelligence emerged from users on the Web.

Today, telecom operators face a threefold challenge: a social challenge dealing with the evolution of the consumer lifestyle, a technological challenge dealing with ever changing ICT trends and a business challenge dealing with the need for innovative business models. This paper introduces an idea of group-oriented services, a special type of personalized telecom services, as a possible solution for all three of these challenges. A proof-of-concept service, called Agent-Based Mobile Content Brokerage, is presented and elaborated with the aim to demonstrate a shift towards consumer-managed relationships, a novel provisioning paradigm within the telecom industry.

A semantically-linked web of electronic information – the Semantic Web – promises numerous benefits including increased precision in automated information sorting, searching, organizing and summarizing. Realizing this requires significantly more reliable meta-information than is readily available today. It also requires a better way to represent information that supports unified management of diverse data and diverse Manipulation methods: from basic keywords to various types of artificial intelligence, to the highest level of intelligent manipulation – the human mind. How this is best done is far from obvious. Relying solely on hand-crafted annotation and ontologies, or solely on artificial intelligence techniques, seems less likely for success than a combination of the two. In this paper describe an integrated, complete solution to these challenges that has already been implemented and tested with hundreds of thousands of users. It is based on an ontological representational level we call SemCards that combines ontological rigour with flexible user interface constructs. SemCards are machine- and human-readable digital entities that allow non-experts to create and use semantic content, while empowering machines to better assist and participate in the process. SemCards enable users to easily create semantically-grounded data that in turn acts as examples for automation processes, creating a positive iterative feedback loop of metadata creation and refinement between user and machine. They provide a holistic solution to the Semantic Web, supporting powerful management of the full lifecycle of data, including its creation, retrieval, classification, sorting and sharing. We have implemented the SemCard technology on the semantic Web site Twine.com, showing that the technology is indeed versatile and scalable. Here we present the key ideas behind SemCards and describe the initial implementation of the technology.

Education institutions such as universities have a lot of information including book information, equipment administrative information, student information, and several others. The institutions also have multiple information in time series. As collective intelligence in campus, integrating and reusing these preserved information regarding career and taking a class, university can effectively support students’ decision making of their getting jobs and subjects choice. Our purpose of support is to increase student’s motivation. In this paper, we focus on course record and job information included in students’ information, and propose the method to analyze correlation between a pattern of taking class and job lined up. Afterwards, we propose a support system regarding getting a job and taking class by using our proposed method. For a student who has his/her favorite job to get, the system supports his/her decision making of lecture choice by recommending a set of appropriate lecture groups. On another hand, for a student who does not have favorite job to get, the system supports his/her decision making of getting job by presenting appropriate job families related with lecture group in which he/she has ever taken. The contribution of this paper is showing a concrete method to reuse the campus collective information, implementing a system, and user perspectives.

This paper presents a new robust approach to the task assignment of unmanned aerial vehicles (UAVs) operating in uncertain environments whose the objective is maximizing the target score. The intrinsic uncertainty imbedded in military operations makes the problem more challenging. Scalability and robustness are recognized as two main issues. We deal with these issues by an approach based on DC (Difference of Convex functions) programming and DCA (DC Algorithm). The numerical results show that this approach is efficient.

New Internet applications and services as well as new user demands open many new issues concerning dynamic management of quality of service and price for received service, respectively. The main goals of Internet service providers are to maximize profit and maintain a negotiated quality of service. From the users’ perspective the main goal is to maximize ratio of received QoS and costs of service. However, achieving these objectives could become very complex if we know that Internet service users might during the session become highly dynamic and proactive. This connotes changes in user profile or network provider/s profile caused by high level of user mobility or variable level of user demands. This paper proposes a new agent based pricing architecture for serving the highly dynamic customers in context of dynamic user/network environment. The proposed architecture comprises main aspects and basic parameters that will enable objective and transparent assessment of the costs for the service those Internet users receive while dynamically change QoS demands and cost profile.

JABAT supports designing and implementing A-Team architectures for solving difficult optimization problems. This paper presents several applications of JABAT as a tool for solving such problems. List of implementations and extensions of JABAT shows how useful and flexible the system can be. The paper summarises experiences of authors gained while developing various A-Teams. Some conclusions concerning such details of the A-Team model like the composition of the team of agents, the choice of rules determining how the agents interact with the population of solutions, or how synchronisation or cooperation of agents influence the quality of results are offered.