An Introduction to MultiAgent Systems.

Due to increased competitive pressure, modern organizations tend to rely on knowledge and its exploitation to sustain a long-term advantage. This calls for a precise understanding of knowledge management (KM) processes and, specifically, how knowledge is created, shared/transferred, acquired, stored/retrieved, and applied throughout an organizational system. However, since the beginning of the new millennium, such KM processes have been deeply affected and molded by the advent of the fourth industrial revolution, also called Industry 4.0, which involves the interconnectedness of machines and their ability to learn and share data autonomously. For this reason, the present article investigates the intellectual structure and trends of KM in Industry 4.0. Bibliometric analysis and a systematic literature review are conducted on a total of 90 relevant articles. The results reveal six clusters of keywords, subsequently explored via a systematic literature review to identify potential stream of this emergent field and future research avenues capable of producing meaningful advances in managerial knowledge of Industry 4.0 and its consequences.

/pdf/knowledge-management-in-the-fourth-industrial-revolution-539tbwn12d.pdf

Knowledge Management in the Fourth Industrial Revolution: Mapping the Literature and Scoping Future Avenues

This chapter contains sections titled: 2.1 Introduction, 2.2 Agent Communications, 2.3 Agent Interaction Protocols, 2.4 Societies of Agents, 2.5 Conclusions, 2.6 Exercises, 2.7 References

Multiagent Systems and Societies of Agents

Today’s globalized and highly competitive world market has broadened the spectrum of requirements in all the sectors of the agri-food industry. This paper focuses on the dairy industry, on its need to adapt to the current market by becoming more resource efficient, environment-friendly, transparent and secure. The Internet of Things (IoT), Edge Computing (EC) and Distributed Ledger Technologies (DLT) are all crucial to the achievement of those improvements because they allow to digitize all parts of the value chain, providing detailed information to the consumer on the final product and ensuring its safety and quality. In Smart Farming environments, IoT and DLT enable resource monitoring and traceability in the value chain, allowing producers to optimize processes, provide the origin of the produce and guarantee its quality to consumers. In comparison to a centralized cloud, EC manages the Big Data generated by IoT devices by processing them at the network edge, allowing for the implementation of services with shorter response times, and a higher Quality of Service (QoS) and security. This work presents a platform oriented to the application of IoT, Edge Computing, Artificial Intelligence and Blockchain techniques in Smart Farming environments, by means of the novel Global Edge Computing Architecture, and designed to monitor the state of dairy cattle and feed grain in real time, as well as ensure the traceability and sustainability of the different processes involved in production. The platform is deployed and tested in a real scenario on a dairy farm, demonstrating that the implementation of EC contributes to a reduction in data traffic and an improvement in the reliability in communications between the IoT-Edge layers and the Cloud.

An intelligent Edge-IoT platform for monitoring livestock and crops in a dairy farming scenario

Classic multi-criteria group decision making models that have a high amount of alternatives are unmanageable for the experts. This is because they have to provide one value per each alternative and criteria. In this paper, we focus on solving this issue by carrying out multi-criteria group decision making methods using a different novel approach. Concretely, fuzzy ontologies reasoning procedures are used in order to automatically obtain the alternatives ranking classification. Thanks to our novel methodology, experts only need to provide the importance of a small set of criteria values making it possible for experts to perform multi-criteria group decision making procedures that have a high amount of alternatives without having to directly deal with them. Furthermore, in order to allow experts to provide their preferences in a comfortable way, multi-granular fuzzy linguistic modelling is used in order to allow each expert to choose the linguistic label set that better fits him/her.

Solving Multi-Criteria Group Decision Making Problems Under Environments with a High Number of Alternatives Using Fuzzy Ontologies and Multi-Granular Linguistic Modelling Methods

In an Industry 4.0 environment, the data generated by sensors networks requires machine learning and data analysis techniques. Thus, organizations face both new opportunities and challenges, one of them is predictive analysis using computer tools capable of detecting patterns in the analyzed data from the same rules that can be used to formulate predictions. The Heating, Ventilation and Air Conditioning Systems (HVAC) control in an important number of industries: indoor climate, air’s temperature, humidity and pressure, creating an optimal production environment. In accordance, a case study is presented, in it a HVAC dataset was used to test the performance of the equipment and observe whether it maintains temperatures in an optimal range. The aim of this paper is making use of machine learning algorithms for the design of predictive models in the Industry 4.0 environment, using the previously mentioned dataset.

Machine Learning Predictive Model for Industry 4.0

Learning management systems are used as a support tool in the process of knowledge sharing Teachers add the material related to the domain of knowledge and also elaborate pedagogical mediation activities for the students This process, in general, results in a learning environment that presents the same content for all participants, not taking into account the differences that exist between each of them, both in performance and behavior in the environment The purpose of this work is to show an adaptive, agent-based environment model to enable the teacher to use some tools to create an adaptive class In this model, resources and activities are made available to the participants in an individualized and adaptive way according to a previous configuration made by the teacher on the learning environment The system was developed using Moodle to be used as a test bed case study and a basic calculus course was created to perform a practical evaluation test of the proposed model with real students as participants

Adaptive Agent-Based Environment Model to Enable the Teacher to Create an Adaptive Class

The distribution of services on multi-agent systems allows it to reduce to the agents their computational load. The functionality of the system does not reside in the agents themselves, however it is ubiquitously distributed so that allows you to perform tasks in parallel avoiding an additional computational cost to the elements in the system. The distribution of services that offers SCODA (Distributed and Specialized Agent Communities) allows an intelligent management of these services provided by agents of the system and the parallel execution of threads that allow to respond to requests asynchronously, which implies an improvement in the performance of the system at both the computational level as the level of quality of service in the control of these services. The comparison carried out in the case of study that is presented in this paper demonstrates the existing improvement in the distribution of services on systems based on SCODA.

/pdf/improvement-in-the-distribution-of-services-in-multi-agent-1fu7yhl77i.pdf

Improvement in the distribution of services in multi-agent systems with SCODA

In the current educational context there has been a significant increase in learning object repositories (LOR), which are found in large databases available on the hidden web. All these information is described in any metadata labeling standard (LOM, Dublin Core, etc). It is necessary to work and develop solutions that provide efficiency in searching for heterogeneous content and finding distributed context. Distributed information retrieval, or federated search, attempts to respond to the problem of information retrieval in the hidden Web. Multi-agent systems are known for their ability to adapt quickly and effectively to changes in their environment. This study presents a model for the development of digital content retrieval based on the paradigm of virtual organizations of agents using a Service Oriented Architecture. The model allows the development of an open and flexible architecture that supports the services necessary to dynamically search for distributed digital content. A major challenge in searching and retrieving digital content is also to efficiently find the most suitable content for the users. This model proposes a new approach to filtering the educational content retrieved based on Case-Based Reasoning (CBR). It is based on the model AIREH (Architecture for Intelligent Recovery of Educational content in Heterogeneous Environments), a multi-agent architecture that can search and integrate heterogeneous educational content through a recovery model that uses a federated search. The model and the technologies presented in this research exemplify the potential for developing personalized recovery systems for digital content based on the paradigm of virtual organizations of agents. The advantages of the proposed architecture, as outlined in this article, are its flexibility, customization, integrative solution and efficiency.

/pdf/personalization-on-e-content-retrieval-based-on-semantic-web-1hu5mwyr10.pdf

Personalization on E-Content Retrieval Based on Semantic Web Services

Information fusion in a context-aware system is understood as a process that assembles assessments of the environment based on its goals. Advantages of intelligent approaches such as Multi-Agent Systems (MAS) and the use of Wireless Sensor Networks (WSN) within the information fusion process are emerging, especially in context-aware scenarios. However, it has become critical to propose improved and efficient ways to handle the enormous quantity of data provided by these approaches. Agents are a suitable option because they can represent autonomous entities by modeling their capabilities, expertise and intentions. In this sense, virtual organizations of agents are an interesting option/possibility because they can provide the necessary capacity to handle open and heterogeneous systems such as those normally found in the information fusion process. This paper presents a new framework that defines a method for creating a virtual organization of software and hardware agents. This approach facilitates the inclusion of context-aware capabilities when developing intelligent and adaptable systems, where functionalities can communicate in a distributed and collaborative way. Several tests have been performed to evaluate this framework and preliminary results and conclusions are presented.

/pdf/organizations-of-agents-in-information-fusion-environments-13969k2nhn.pdf

Sara Rodríguez González

Papers

Machine Learning Predictive Model for Industry 4.0

Adaptive Agent-Based Environment Model to Enable the Teacher to Create an Adaptive Class

Improvement in the distribution of services in multi-agent systems with SCODA

Personalization on E-Content Retrieval Based on Semantic Web Services

Organizations of agents in information fusion environments