Context-aware Agents Research Articles

Learning and adaptation of strategies in automated negotiations between context-aware agents

This work presents the hypothesis that guided the research efforts and a summary of the contributions of the doctoral thesis '`Aprendizaje y adaptación de estrategias para negociación automatizada entre agentes conscientes del contexto'. Succinctly, the thesis focuses on agents for automated bilateral negotiations that make use of the context as a key source of information to learn and adapt negotiation strategies in two levels of temporal abstraction. At the highest level, agents employ reinforcement learning to select strategies according to contextual circumstances. At the lowest level, agents use Gaussian Processes and artificial Theory of Mind to model their opponents and adapt their strategies. Agents are then tested in two Peer-to-Peer markets comprising an Eco-Industrial Park and a Smart Grid. The results highlight the significance for the automation of bilateral negotiations of incorporating the context as an informative source.

Cyber Physical System and Internet of Things on Upgrading Software Agents

Using the Jason framework and the CArtAgO platform, this study introduces a fresh paradigm for upgrading software agents in Cyber-Physical Systems (CPS) and the Internet of Things (IoT). We integrate Fuzzy Inference Systems (FIS) into the agents' decision-making processes using Fuzzy Logic Controllers (FLCs) within the JaCa environment. This collaboration seeks to resolve uncertainty in real-world CPS and IoT contexts, allowing agents to make context-aware and adaptable judgements. Our method improves agent adaptation by allowing for more nuanced responses to changing situations. The efficacy of this integration is demonstrated experimentally, with enhanced interoperability and responsiveness. This study advances intelligent agent systems by presenting a possible path for generating more context-aware agents in the dynamic landscape of CPS and IoT, encouraging efficient and adaptive autonomous systems.

Modelling and Verification of Context-Aware Intelligent Assistive Formalism

Recent years have witnessed the expeditious evolution of intelligent smart devices and autonomous software technologies with the expanded domains of computing from workplaces to smart computing in everyday routine life activities. This trend has been rapidly advancing towards the new generation of systems where smart devices play vital roles in acting intelligently on behalf of the users. Context-awareness has emerged from the pervasive computing paradigm. Context-aware systems have the ability to acquire contextual information from the surrounding environment autonomously, perform reasoning on it, and then adapt their behaviors accordingly. With the proliferation of context-aware systems and smart sensors, real-time monitoring of environmental situations (context) has become quite trivial. However, it is often challenging because the imperfect nature of context can cause the inconsistent behavior of the system. In this paper, we propose a context-aware intelligent decision support formalism to assist cognitively impaired people in managing their routine life activities. For this, we present a semantic knowledge-based framework to contextualize the information from the environment using the protégé ontology editor and Semantic Web Rule Language (SWRL) rules. The set of contextualized information and the set of rules acquired from the ontology can be used to model Context-aware Multi-Agent Systems (CMAS) in order to autonomously plan all activities of the users and notify users to act accordingly. To illustrate the use of the proposed formalism, we model a case study of Mild Cognitive Impaired (MCI) patients using Colored Petri Nets (CPN) to show the reasoning process on how the context-aware agents collaboratively plan activities on the user's behalf and validate the correctness properties of the system.

A context-aware approach to automated negotiation using reinforcement learning

Agents negotiate depending on individual perceptions of facts, events, trends and special circumstances that define the negotiation context. The negotiation context affects in different ways each agent’s preferences, bargaining strategies and resulting benefits, given the possible negotiation outcomes. Despite the relevance of the context, the existing literature on automated negotiation is scarce about how to account for it in learning and adapting negotiation strategies. In this paper, a novel contextual representation of the negotiation setting is proposed, where an agent resorts to private and public data to negotiate using an individual perception of its necessity and risk. A context-aware negotiation agent that learns through Self-Play and Reinforcement Learning (RL) how to use key contextual information to gain a competitive edge over its opponents is discussed in two levels of temporal abstraction. Learning to negotiate in an Eco-Industrial Park (EIP) is presented as a case study. In the Peer-to-Peer (P2P) market of an EIP, two instances of context-aware agents, in the roles of a buyer and a seller, are set to bilaterally negotiate exchanges of electrical energy surpluses over a discrete timeline to demonstrate that they can profit from learning to choose a negotiation strategy while selfishly accounting for contextual information under different circumstances in a data-driven way. Furthermore, several negotiation episodes are conducted in the proposed EIP between a context-aware agent and other types of agents proposed in the existing literature. Results obtained highlight that context-aware agents do not only reap selfishly higher benefits, but also promote social welfare as they resort to contextual information while learning to negotiate.

QoS Routing in Internet of Things (IoT) by Context Aware Agent priority by Meta Computational Intelligence for Evidence-based E-Health Services

Internet of Things (IoT) having taken giant leaps has emerged as one of the most promising fields with a plethora of E- Health applications. Due to burgeoning demands in data rates and Internet-enabled services, an evidence-based e-health is required in network traffic .Sudden and unforeseeable large-scale anomalies cause packet collisions and constant or sporadic interferences between multiple transmitters. Developing a ‘‘One-Queue-fits-all’’ solution is a great challenge. However, priority analysis for data services bolsters QoS. The proposed Context Aware Agent priority by Meta computational intelligence in IoT for evidence-based E- Health data service (CAAM -EH) aims to assign priority for packets from diverse networks based on their criticality levels. Data are estimated using attributes such as task, temporal, spatial and customized estimation. A Quad Tree structure is employed to organize the estimated data into various levels and priority is eventually set for transmission to the IoT. The Computational intelligence used to support event, time as well as query-based E health data from IoT.

The importance of context-dependent learning in negotiation agents

Automated negotiation between artificial agents is essential to deploy Cognitive Computing and Internet of Things. The behavior of a negotiation agent depends significantly on the influence of environmental conditions or contextual variables, since they affect not only a given agent preferences and strategies, but also those of other agents. Despite this, the existing literature on automated negotiation is scarce about how to properly account for the effect of context-relevant variables in learning and evolving strategies. In this paper, a novel context-driven representation for automated negotiation is introduced. Also, a simple negotiation agent that queries available information from its environment, internally models contextual variables, and learns how to take advantage of this knowledge by playing against himself using reinforcement learning is proposed. Through a set of episodes against other negotiation agents in the existing literature, it is shown using our context-aware agent that it makes no sense to negotiate without taking context-relevant variables into account. Our context-aware negotiation agent has been implemented in the GENIUS environment, and results obtained are significant and quite revealing.

Modeling and Reasoning about Preference-Based Context-Aware Agents over Heterogeneous Knowledge Sources

This paper presents a conceptual framework and multi-agent model for context-aware decision support in dynamic smart environments based on heterogeneous knowledge sources. A Protégé plug-in for rules extraction from distributed ontologies has been developed, which allows us to model context-aware agents using the notion of multi-context systems. Extracted rules can be annotated to match the users’ needs and to develop a preference model to support their preferences so as to provide a user with a more personalized services. The use of the proposed framework is illustrated using a simple fact-based preference model developed from ontologies considering two different smart environment domains.

A Framework for Implementing Formally Verified Resource-Bounded Smart Space Systems

Context-aware computing is a mobile computing paradigm that helps designing and implementing next generation smart applications, where personalized devices interact with users in smart environments. Development of such applications is inherently complex due to these applications adapt to changing contextual information and they often run on resource-bounded devices. Most of the existing context-aware development frameworks are centralized, adopt client---server architecture, and do not consider resource limitations of context-aware devices. This paper presents a systematic framework to modelling and implementation of resource-bounded multi-agent context-aware systems on Android devices. The proposed framework makes use of semantic technologies for context modelling and reasoning about resource-bounded context-aware agents, Android powered smartphones as development platform, a suitable communication model and declarative rule-based programming as a preferred development language.

A Logical Framework for the Representation and Verification of Context-aware Agents

We propose a logical framework for modelling and verifying context-aware multi-agent systems. We extend CTL? with belief and communication modalities, and the resulting logic ??OCRS allows us to describe a set of rule-based reasoning agents with bound on time, memory and communication. The set of rules which are used to model a desired systems is derived from OWL 2 RL ontologies. We provide an axiomatization of the logic and prove it is sound and complete. We show how Maude rewriting system can be used to encode and verify interesting properties of ??OCRS models using existing model checking techniques.

A Layered Context-Aware Agent for Mobile Applications Based on Users Needs Hierarchy

In order to improve the user’s experience in using mobile applications, a layered context-aware agent for mobile applications was proposed based on user’s needs hierarchy. In the proposed model, the layers were employed to distinguish different types of needs in the hierarchy and the priority of different layers was used to determine the time for showing the recommendation information. At first, the agent framework was proposed. And then, based on the proposed framework, the layered context-aware agent was developed based on the Maslow’s theory. At last, an experiment was conducted on the comparison between two methods of the random model and the proposed layered model for sending recommendation messages. And the result verified that the proposed agent was effective.

Context Aware Multisensor Image Fusion for Military Sensor Networks using Multi-Agent system

This paper proposes a Context Aware Agent based Military Sensor Network (CAMSN) to form an improved infrastructure for multi-sensor image fusion. It considers contexts driven by a node and sink. The contexts such as general and critical object detection are node driven where as sensing time (such as day or night) is sink driven. The agencies used in the scheme are categorized as node and sink agency. Each agency employs a set of static and mobile agents to perform dedicated tasks. Node agency performs context sensing and context interpretation based on the sensed image and sensing time. Node agency comprises of node manager agent, context agent and node blackboard (NBB). Context agent gathers the context from the target and updates the NBB, Node manager agent interprets the context and passes the context information to sink node by using flooding mechanism. Sink agency mainly comprises of sink manager agent, fusing agent, and sink black board. A context at the sensor node triggers the fusion process at the sink. Based on the context, sink manager agent triggers the fusing agent. Fusing agent roams around the network, visits active sensor node, fuses the relevant images and sends the fused image to sink. The fusing agent uses wavelet transform for fusion. The scheme is simulated for testing its operation effectiveness in terms of fusion time, mean square error, throughput, dropping rate, bandwidth requirement, node battery usage and agent overhead.

An autonomous service-platform to support distributed ontology-based context-aware agents

The use of semantic technology has recently witnessed a huge increase. One of the areas in which this technology is being used increasingly more often is that of context-aware agents. However, the use of ontologies in general and reasoning in particular can rapidly become resource intensive. Certainly if the data set, called the A-Box, used by these agents grows considerably over time. Moreover, in order to create context-aware applications, taking into account a wide range of different data sets and context parameters, agents have to be provided to expose that data. The collaboration between the agents in the system is necessary to correlate the information and augment the intelligence and added value of the context-aware agents. Therefore, there is a need to have a distributed approach by means of a service-platform, where the different agents in a context-aware environment can collaborate. The main focus of this article is on the research on the design of a service-platform for semantic ontology-based context-aware collaboration. The platform architecture to allow the collaboration and scheduling, together with the associated algorithms, will be presented. The engineering and implementation details will be highlighted. By means of detailed UML sequence diagrams, we will present the workflow and collaboration between the different modules in the platform. Additionally, supporting developments, such as the meta-ontology and our ontology generator, OTAGen, will be presented. Furthermore, we will detail how the platform can operate in an autonomous way, taking into account the changing context of the agents in the platform.

Providing home care using context-aware agents

This paper presents an ambient intelligence based architecture model that defines intelligent hybrid agents. These agents have the ability to obtain automatic and real-time information about the context using a set of technologies, such as radio frequency identification, wireless networks and wireless control devices. The architecture can be implemented on a wide diversity of dynamic environments, especially for providing home care to elderly and dependent people.

Context-aware agents in cooperative design environment

This paper presents a context-aware multi-agent cooperative design system framework. It analyses the related work of multi-agent cooperative design system and context-awareness computing first. Then, it presents the architecture of a multi-agent cooperative design system and the structure of a design agent in cooperative environment. Subsequently, it introduces the XML-based context modelling, capturing and processing in the environment. Finally, the design process is illustrated by a gear reducer design instance. The purpose of the paper is to bridge pervasive computing with agents through context-awareness and apply it in cooperative design.

Context-aware agents for user-oriented web services discovery and execution

Service-oriented computing (SOC) suggests that the Internet will be an open repository of many modular capabilities realized as web services. Organizations may be able to leverage this SOC paradigm if their employees are able to ubiquitously incorporate such capabilities and their resulting information into their daily practices. It is impractical to assume that human users will be able to manually search vast distributed repositories at real-time. This paper presents an architecture, Software Agent-Based Groupware using E-services (SAGE), that incorporates the use of intelligent agents to integrate human users with web services. SAGE provides background search and discovery approaches, thus enabling human users to exploit service-based capabilities that were previously too time-consuming to locate and integrate. We present a multi-agent system where each agent learns the rule-based preferences of a human user with regards to their current operational "context" and manages the incorporation of relevant web services.

Software Engineering for Large-Scale Multi-Agent Systems - SELMAS 2005

This paper is intended to sum up the results of the 4th International Workshop on Software Engineering for Large-Scale Multi-Agent Systems (SELMAS 2005) held in St. Louis, Missouri, USA, May 15--16, 2005, as part of the 27 th International Conference on Software Engineering (ICSE'05). The main purpose of this workshop was to share and pool together the collective experience of people, both academics and practitioners, who are actively working on software engineering for large-scale multi-agent systems. A selected set of expanded workshop papers and invited papers will appear in the 4 th edition of the book Software Engineering for Multi-Agent Systems (LNCS, Springer, 2006). The theme of this workshop edition was "Software Everywhere - Context-Aware Agents". The workshop consisted of an opening presentation, several paper presentations organized into three technical sessions, two keynotes, one panel, and two discussion groups. During the workshop we informally reviewed ongoing and previous work and debated a number of important issues. The SELMAS 2005 Web site, including the electronic version of this report, can be found at <www.teccomm.les.inf.pucrio.br/selmas2005>. We begin by presenting an overview of our goals and the workshop structure, and then focus on the workshop technical program and results.

Software engineering for large-scale multi-agent systems - SELMAS'05

Software is becoming present in every aspect of our lives, pushing us inevitably towards a world of distributed, context-aware computing systems. SELMAS'05, "Software Everywhere - Context-Aware Agents", was built on the success of precedent SELMAS workshops, but with a special emphasis on the impact of the agent technology in the development of large context-aware systems. SELMAS has a track record of bringing together researchers and practitioners with a variety of perspectives in order to engage in lively discussion and debate. A particular interest of this workshop was to understand those issues in the agent technology that make it difficult and/or improve the production of context-aware systems.

Research and implementation of the context-aware middleware for controlling home appliances

Smart homes integrated with sensors, actuators, wireless networks and context-aware middleware soon becomes part of our daily life. This paper describes a context-aware middleware providing an automatic home service based on a user's preference inside a smart home. The context-aware middleware includes an appliance controller, a context-aware agent and a scalable browser. The appliance controller takes charge of communication between appliances in the context-aware middleware. The context-aware middleware use OSGi (open service gateway initial) as the framework of the home network. The scalable browser recognizes the properties of all the rendering device, and it figures out their screen size. We use UlML (user interface markup language) as multiple rendering device. The context-aware agent utilizes 6 basic data values for learning and predicting the user's preference for the home appliances: the pulse, the body temperature, the facial expression, the room temperature, the time, and the location. The six data sets construct the context model and are used by the context manager module. The user profile manager maintains the history information for home appliances chosen by the user. The user-pattern learning and predicting module is based on a neural network, which predicts the proper home service for the user. The test results show that the pattern of an individual's preference can be effectively evaluated.

Context-aware privacy and security agents for distance education

Although distance education applications have been widely deployed, not many of them provide privacy and security for their users. Most of them only provide access control by requesting a user id and password. In a recent paper for AINA (Lin et al., 2004), we conveyed the importance of privacy and security for distance education and showed how they can be provided. In this paper, we present an extension of that work for the use of context-aware agents that can provide privacy and security for distance education applications in an intelligent manner based on the user's interaction context. Our agents are based on an agent framework adapted from IEEE P1484.1/D9: the Learning Technology Systems Architecture (LTSA) (IEEE, 2004).

Context‐aware agent platform in ubiquitous environments and its verification tests

AbstractThis paper deals with the “ubiquitous personal agent,” which distinctively provides information services to the individual user depending on his/her personal contexts. This is made possible by recognition of user contexts in ubiquitous environments through an agent technology used to realize context‐aware intelligent environments.This agent technology consists of a “context reasoning agent” and a “lightweight intelligent mobile agent.” The former is used for automatic recognition of various kinds of data and events which can be collected through realization of ubiquitous environments and of user “contexts.” The latter executes appropriate decentralization of a large variety of personalization‐related processing activities between various devices and server systems existing in the ubiquitous environments. In this paper, the details of the agent technology used are discussed and its effectiveness is confirmed by evaluation in tests of agent service using home information appliances already available on the domestic market. © 2004 Wiley Periodicals, Inc. Syst Comp Jpn, 35(7): 13–23, 2004; Published online in Wiley InterScience (www.interscience.wiley.com). DOI 10.1002/scj.10655