Exploiting Learning Technologies for World Wide Web Agents

Postprint

Learning Mechanisms for Information Filtering Agents

Postprint

Nego : a virtual negociation market

Mémoire numérisé par la Direction des bibliothèques de l'Université de Montréal.

The framework of the virtual laser tracker - A systematic approach to the assessment of error sources and uncertainty in laser tracker measurement

Laser trackers have been widely used in many industries to meet increasingly high accuracy requirements. In laser tracker measurement, it is complex and difficult to perform an accurate error analysis and uncertainty evaluation. This paper firstly reviews the working principle of single beam laser trackers and state-of- The- Art of key technologies from both industrial and academic efforts, followed by a comprehensive analysis of uncertainty sources. A generic laser tracker modelling method is formulated and the framework of the virtual tracker is proposed. The VLS can be used for measurement planning, measurement accuracy optimization and uncertainty evaluation. The completed virtual laser tracking system should take all the uncertainty sources affecting coordinate measurement into consideration and establish an uncertainty model which will behave in an identical way to the real system. © Springer-Verlag Berlin Heidelberg 2010.

Nego : a virtual negociation market

Mémoire numérisé par la Direction des bibliothèques de l'Université de Montréal.

Cyber Enigmas? Passive Detection and Pedagogical Agents: Can Students Spot the fake?

This paper presents a study that was undertaken to examine human interaction with a pedagogical agent and the passive and active detection of such agents within a synchronous, online environment. A pedagogical agent is a software application which can provide a human like interaction using a natural language interface. These may be familiar from the smartphone interfaces such as ‘Siri’ or ‘Cortana’, or the virtual online assistants found on some websites, such as ‘Anna’ on the Ikea website. Pedagogical agents are characters on the computer screen with embodied life-like behaviours such as speech, emotions, locomotion, gestures, and movements of the head, the eye, or other parts of the body. The passive detection test is where participants are not primed to the potential presence of a pedagogical agent within the online environment. The active detection test is where participants are primed to the potential presence of a pedagogical agent. The purpose of the study was to examine how people passively detected pedagogical agents that were presenting themselves as humans in an online environment. In order to locate the pedagogical agent in a realistic higher education online environment, problem-based learning online was used. Problem-based learning online provides a focus for discussions and participation, without creating too much artificiality. The findings indicated that the ways in which students positioned the agent tended to influence the interaction between them. One of the key findings was that since the agent was focussed mainly on the pedagogical task this may have hampered interaction with the students, however some of its non-task dialogue did improve students' perceptions of the autonomous agents’ ability to interact with them. It is suggested that future studies explore the differences between the relationships and interactions of learner and pedagogical agent within authentic situations, in order to understand if students' interactions are different between real and virtual mentors in an online setting.

Intelligent pipeline control - a simulation study in the automotive sector

Automotive producers are aiming to make their order fulfilment processes more flexible. Opening the pipeline of planned products for dynamic allocation to dealers/ customers is a significant step to be more flexible but the behaviour of such Virtual-Build-To-Order systems are complex to predict and their performance varies significantly as product variety levels change. This study investigates the potential for intelligent control of the pipeline feed, taking into account the current status of inventory (level and mix) and of the volume and mix of unsold products in the planning pipeline, as well as the demand profile. Five ‘intelligent’ methods for selecting the next product to be planned into the production pipeline are analysed using a discrete event simulation model and compared to the unintelligent random feed. The methods are tested under two conditions, firstly when customers must be fulfilled with the exact product they request, and secondly when customers trade-off a shorter waiting time for compromise in specification. The two forms of customer behaviour have a substantial impact on the performance of the methods and there are also significant differences between the methods themselves. When the producer has an accurate model of customer demand, methods that attempt to harmonise the mix in the system to the demand distribution are superior.

Using SPL to Develop AAL Systems Based on Self-adaptive Agents

Abstract One of the most important challenges of this decade is the Internet of Things (IoT) that pursues the integration of real-world objects in Internet. One of the key areas of the IoT is the Ambient Assisted Living (AAL) systems, which should be able to react to variable and continuous changes while ensuring their acceptance and adoption by users. This means that AAL systems need to work as self-adaptive systems. The autonomy property inherent to software agents, makes them a suitable choice for developing self-adaptive systems. However, agents lack the mechanisms to deal with the variability present in the IoT domain with regard to devices and network technologies. To overcome this limitation we have already proposed a Software Product Line (SPL) process for the development of self-adaptive agents in the IoT. Here we analyze the challenges that poses the development of self-adaptive AAL systems based on agents. To do so, we focus on the domain and application engineering of the self-adaptation concern of our SPL process. In addition, we provide a validation of our development process for AAL systems.

A Metamodel for Collaboration Formalization

Part 11: Reference and Conceptual Models

A Framework for Energy-Efficiency in Smart Home Environments

Part 7: Cyber-Physical Systems

Behavioral Norms in Virtual Organizations

Part 2: Behaviour and Coordination

Collaborative Systems for Smart Environments: Trends and Challenges

Part 1: Introduction

DATA DRIVEN INTELLIGENT AGENT NETWORKS FOR ADAPTIVE MONITORING AND CONTROL

To analyze the characteristics and predict the dynamic behaviors of complex systems over time, comprehensive research to enable the development of systems that can intelligently adapt to the evolving conditions and infer new knowledge with algorithms that are not predesigned is crucially needed. This dissertation research studies the integration of the techniques and methodologies resulted from the fields of pattern recognition, intelligent agents, artificial immune systems, and distributed computing platforms, to create technologies that can more accurately describe and control the dynamics of real-world complex systems. The need for such technologies is emerging in manufacturing, transportation, hazard mitigation, weather and climate prediction, homeland security, and emergency response. Motivated by the ability of mobile agents to dynamically incorporate additional computational and control algorithms into executing applications, mobile agent technology is employed in this research for the adaptive sensing and monitoring in a wireless sensor network. Mobile agents are software components that can travel from one computing platform to another in a network and carry programs and data states that are needed for performing the assigned tasks. To support the generation, migration, communication, and management of mobile monitoring agents, an embeddable mobile agent system (Mobile-C) is integrated with sensor nodes. Mobile monitoring agents visit distributed sensor nodes, read real-time sensor data, and perform anomaly detection using the equipped pattern recognition algorithms. The optimal control of agents is achieved by mimicking the adaptive immune response and the application of multi-objective optimization algorithms. The mobile agent approach provides potential to reduce the communication load and energy consumption in monitoring networks. The major research work of this dissertation project includes: (1) studying effective feature extraction methods for time series measurement data; (2) investigating the impact of the feature extraction methods and dissimilarity measures on the performance of pattern recognition; (3) researching the effects of environmental factors on the performance of pattern recognition; (4) integrating an embeddable mobile agent system with wireless sensor nodes; (5) optimizing agent generation and distribution using artificial immune system concept and multi-objective algorithms; (6) applying mobile agent technology and pattern recognition algorithms for adaptive structural health monitoring and driving cycle pattern recognition; (7) developing a web-based monitoring network to enable the visualization and analysis of real-time sensor data remotely. Techniques and algorithms developed in this dissertation project will contribute to research advances in networked distributed systems operating under changing environments.

An investigation of two real time machine learning techniques that could enhance the adaptability of game AI agents

Developers strive to create innovative Artificial Intelligence (AI) behaviour in their games as a key selling point. Machine Learning is an area of AI that looks at how applications and agents can be programmed to learn their own behaviour without the need to manually design and implement each aspect of it. Machine learning methods have been utilised infrequently within games and are usually trained to learn offline before the game is released to the players. In order to investigate new ways AI could be applied innovatively to games it is wise to explore how machine learning methods could be utilised in real-time as the game is played, so as to allow AI agents to learn directly from the player or their environment. Two machine learning methods were implemented into a simple 2D Fighter test game to allow the agents to fully showcase their learned behaviour as the game is played. The methods chosen were: Q-Learning and an NGram based system. It was found that N-Grams and QLearning could significantly benefit game developers as they facilitate fast, realistic learning at run-time.

Revêtement intelligent à base des silices mésoporeuses fonctionnalisées pour le relargage stimulé d’agents antimicrobiens

Les biofilms bactériens sont composés d’organismes unicellulaires vivants au sein d’une matrice protectrice, formée de macromolécules naturelles. Des biofilms non désirés peuvent avoir un certain nombre de conséquences néfastes, par exemple la diminution du transfert de chaleur dans les échangeurs de chaleurs, l’obstruction de membranes poreuses, la contamination des surfaces coques de navires, etc. Par ailleurs, les bactéries pathogènes qui prolifèrent dans un biofilm posent également un danger pour la santé s’ils croissent sur des surfaces médicales synthétiques comme des implants biomédicaux, cathéters ou des lentilles de vue. De plus, la croissance sur le tissu naturel par certaines souches des bactéries peut être fatale, comme Pseudomonas aeruginosa dans les poumons. Cependant, la présence de biofilms reste difficile à traiter, car les bactéries sont protégées par une matrice extracellulaire. Pour tenter de remédier à ces problèmes, nous proposons de développer une surface antisalissure (antifouling) qui libère sur demande des agents antimicrobiens. La proximité et la disposition du système de relargage placé sous le biofilm, assureront une utilisation plus efficace des molécules antimicrobiennes et minimiseront les effets secondaires de ces dernières. Pour ce faire, nous envisageons l’utilisation d’une couche de particules de silice mésoporeuses comme agents de livraison d’agents antimicrobiens. Les nanoparticules de silice mésoporeuses (MSNs) ont démontré un fort potentiel pour la livraison ciblée d’agents thérapeutiques et bioactifs. Leur utilisation en nano médecine découle de leurs propriétés de porosité intéressantes, de la taille et de la forme ajustable de ces particules, de la chimie de leur surface et leur biocompatibilité. Ces propriétés offrent une flexibilité pour diverses applications. De plus, il est possible de les charger avec différentes molécules ou biomolécules (de tailles variées, allant de l’ibuprofène à l’ARN) et d’exercer un contrôle précis des paramètres d’adsorption et des cinétiques de relargage (désorption). Mots Clés : biofilms, nanoparticules de silice mésoporeuses, microfluidique, surface antisalissure.