Machine diagnosis based on artificial immune systems

Nowadays, many of the manufactory and industrial system has a diagnosis system on top of it, responsible for ensuring the lifetime of the system itself. It achieves this by performing both diagnosis and error recovery procedures in real production time, on each of the individual parts of the system. There are many paradigms currently being used for diagnosis. However, they still fail to answer all the requirements imposed by the enterprises making it necessary for a different approach to take place. This happens mostly on the error recovery paradigms since the great diversity that is nowadays present in the industrial environment makes it highly unlikely for every single error to be fixed under a real time, no production stop, perspective. This work proposes a still relatively unknown paradigm to manufactory. The Artificial Immune Systems (AIS), which relies on bio-inspired algorithms, comes as a valid alternative to the ones currently being used. The proposed work is a multi-agent architecture that establishes the Artificial Immune Systems, based on bio-inspired algorithms. The main goal of this architecture is to solve for a resolution to the error currently detected by the system. The proposed architecture was tested using two different simulation environment, each meant to prove different points of views, using different tests. These tests will determine if, as the research suggests, this paradigm is a promising alternative for the industrial environment. It will also define what should be done to improve the current architecture and if it should be applied in a decentralised system.

Studies about the atomic capabilities concept for linear control systems in physical multi-agent environments

This paper shows the impact of the atomic capabilities concept to include control-oriented knowledge of linear control systems in the decisions making structure of physical agents. These agents operate in a real environment managing physical objects (e.g. their physical bodies) in coordinated tasks. This approach is presented using an introspective reasoning approach and control theory based on the specific tasks of passing a ball and executing the offside manoeuvre between physical agents in the robotic soccer testbed. Experimental results and conclusions are presented, emphasising the advantages of our approach that improve the multi-agent performance in cooperative systems

Studies about the atomic capabilities concept for linear control systems in physical multi-agent environments

This paper shows the impact of the atomic capabilities concept to include control-oriented knowledge of linear control systems in the decisions making structure of physical agents. These agents operate in a real environment managing physical objects (e.g. their physical bodies) in coordinated tasks. This approach is presented using an introspective reasoning approach and control theory based on the specific tasks of passing a ball and executing the offside manoeuvre between physical agents in the robotic soccer testbed. Experimental results and conclusions are presented, emphasising the advantages of our approach that improve the multi-agent performance in cooperative systems

A multi-agent architect for CSCW systems: from organisational semiotics perspective

This paper describes a multi-agent architecture to support CSCW systems modelling. Since CSCW involves different organizations, it can be seen as a social model. From this point of view, we investigate the possibility of modelling CSCW by agent technology, and then based on organizational semiotics method a multi-agent architecture is proposed via using EDA agent model. We explain the components of this multi-agent architecture and design process. It is argued that this approach provides a new perspective for modelling CSCW systems.

Intelligent agents for fault tolerance: from multi-agent simulation to cluster-based implementation

Recent research in multi-agent systems incorporate fault tolerance concepts, but does not explore the extension and implementation of such ideas for large scale parallel computing systems. The work reported in this paper investigates a swarm array computing approach, namely 'Intelligent Agents'. A task to be executed on a parallel computing system is decomposed to sub-tasks and mapped onto agents that traverse an abstracted hardware layer. The agents intercommunicate across processors to share information during the event of a predicted core/processor failure and for successfully completing the task. The feasibility of the approach is validated by simulations on an FPGA using a multi-agent simulator, and implementation of a parallel reduction algorithm on a computer cluster using the Message Passing Interface.

Queue-based agent architecture for multimodal interfaces

This paper presents a queue-based agent architecture for multimodal interfaces. Using a novel approach to intelligently organise both agents and input data, this system has the potential to outperform current state-of-the-art multimodal systems, while at the same time allowing greater levels of interaction and flexibility. This assertion is supported by simulation test results showing that significant improvements can be obtained over normal sequential agent scheduling architectures. For real usage, this translates into faster, more comprehensive systems, without the limited application domain that restricts current implementations.

Queue-based agent communication architecture for intelligent human-like computer interfaces

Human-like computer interaction systems requires far more than just simple speech input/output. Such a system should communicate with the user verbally, using a conversational style language. It should be aware of its surroundings and use this context for any decisions it makes. As a synthetic character, it should have a computer generated human-like appearance. This, in turn, should be used to convey emotions, expressions and gestures. Finally, and perhaps most important of all, the system should interact with the user in real time, in a fluent and believable manner.

A normative approach to multi-agent systems for intelligent buildings

Building Management Systems (BMS) are widely adopted in modern buildings around the world in order to provide high-quality building services, and reduce the running cost of the building. However, most BMS are functionality-oriented and do not consider user personalization. The aim of this research is to capture and represent building management rules using organizational semiotics methods. We implement Semantic Analysis, which determines semantic units in building management and their relationship patterns of behaviour, and Norm Analysis, which extracts and specifies the norms that establish how and when these management actions occur. Finally, we propose a multi-agent framework for norm based building management. This framework contributes to the design domain of intelligent building management system by defining a set of behaviour patterns, and the norms that govern the real-time behaviour in a building.

A logic-based agent that plans for extended reachability goals

Planning to reach a goal is an essential capability for rational agents. In general, a goal specifies a condition to be achieved at the end of the plan execution. In this article, we introduce nondeterministic planning for extended reachability goals (i.e., goals that also specify a condition to be preserved during the plan execution). We show that, when this kind of goal is considered, the temporal logic CTL turns out to be inadequate to formalize plan synthesis and plan validation algorithms. This is mainly due to the fact that the CTL`s semantics cannot discern among the various actions that produce state transitions. To overcome this limitation, we propose a new temporal logic called alpha-CTL. Then, based on this new logic, we implement a planner capable of synthesizing reliable plans for extended reachability goals, as a side effect of model checking.

Influence of voids in the hybrid layer based on self-etching adhesive systems: a 3-D FE analysis

The presence of porosities at the dentin/adhesive interface has been observed with the use of new generation dentin bonding systems. These porosities tend to contradict the concept that etching and hybridization processes occur equally and simultaneously. Therefore, the aim of this study was to evaluate the micromechanical behavior of the hybrid layer (HL) with voids based on a self-etching adhesive system using 3-D finite element (FE) analysis. Three FE models (Mr) were built: Mr, dentin specimen (41x41x82 μm) with a regular and perfect (i.e. pore-free) HL based on a self-etching adhesive system, restored with composite resin; Mp, similar to M, but containing 25% (v/v) voids in the HL; Mpp, similar to Mr, but containing 50% (v/v) voids in the HL. A tensile load (0.03N) was applied on top of the composite resin. The stress field was obtained by using Ansys Workbench 10.0. The nodes of the base of the specimen were constrained in the x, y and z axes. The maximum principal stress (σmax) was obtained for all structures at the dentin/adhesive interface. The Mpp showed the highest peak of σmax in the HL (32.2 MPa), followed by Mp (30 MPa) and Mr (28.4 MPa). The stress concentration in the peritubular dentin was high in all models (120 MPa). All other structures positioned far from voids showed similar increase of stress. Voids incorporated into the HL raised the σmax in this region by 13.5%. This behavior might be responsible for lower bond strengths of self-etching and single-bottle adhesives, as reported in the literature.

A Model-Based Monitoring Architecture for Heterogeneous Enterprise Services and Information Systems

Runtime management of distributed information systems is a complex and costly activity. One of the main challenges that must be addressed is obtaining a complete and updated view of all the managed runtime resources. This article presents a monitoring architecture for heterogeneous and distributed information systems. It is composed of two elements: an information model and an agent infrastructure. The model negates the complexity and variability of these systems and enables the abstraction over non-relevant details. The infrastructure uses this information model to monitor and manage the modeled environment, performing and detecting changes in execution time. The agents infrastructure is further detailed and its components and the relationships between them are explained. Moreover, the proposal is validated through a set of agents that instrument the JEE Glassfish application server, paying special attention to support distributed configuration scenarios.

Engineering Agent Systems for Decision Support

This paper discusses how agent technology can be applied to the design of advanced Information Systems for Decision Support. In particular, it describes the different steps and models that are necessary to engineer Decision Support Systems based on a multiagent architecture. The approach is illustrated by a case study in the traffic management domain.

A Satisfaction-based Model for Affect Recognition from Conversational Features in Spoken Dialog Systems

Detecting user affect automatically during real-time conversation is the main challenge towards our greater aim of infusing social intelligence into a natural-language mixed-initiative High-Fidelity (Hi-Fi) audio control spoken dialog agent. In recent years, studies on affect detection from voice have moved on to using realistic, non-acted data, which is subtler. However, it is more challenging to perceive subtler emotions and this is demonstrated in tasks such as labelling and machine prediction. This paper attempts to address part of this challenge by considering the role of user satisfaction ratings and also conversational/dialog features in discriminating contentment and frustration, two types of emotions that are known to be prevalent within spoken human-computer interaction. However, given the laboratory constraints, users might be positively biased when rating the system, indirectly making the reliability of the satisfaction data questionable. Machine learning experiments were conducted on two datasets, users and annotators, which were then compared in order to assess the reliability of these datasets. Our results indicated that standard classifiers were significantly more successful in discriminating the abovementioned emotions and their intensities (reflected by user satisfaction ratings) from annotator data than from user data. These results corroborated that: first, satisfaction data could be used directly as an alternative target variable to model affect, and that they could be predicted exclusively by dialog features. Second, these were only true when trying to predict the abovementioned emotions using annotator?s data, suggesting that user bias does exist in a laboratory-led evaluation.