Victor Callaghan

Creating an ambient-intelligence environment using embedded agents

The Essex intelligent dormitory, iDorm, uses embedded agents to create an ambient-intelligence environment. In a five-and-a-half-day experiment, a user occupied the iDorm, testing its ability to learn user behavior and adapt to user needs. The embedded agent discreetly controls the iDorm according to user preferences. Our work focuses on developing learning and adaptation techniques for embedded agents. We seek to provide online, lifelong, personalized learning of anticipatory adaptive control to realize the ambient-intelligence vision in ubiquitous-computing environments. We developed the Essex intelligent dormitory, or iDorm, as a test bed for this work and an exemplar of this approach.

A fuzzy embedded agent-based approach for realizing ambient intelligence in intelligent inhabited environments

We describe a novel life-long learning approach for intelligent agents that are embedded in intelligent environments. The agents aim to realize the vision of ambient intelligence in intelligent inhabited environments (IIE) by providing ubiquitous computing intelligence in the environment supporting the activities of the user. An unsupervised, data-driven, fuzzy technique is proposed for extracting fuzzy membership functions and rules that represent the users particularized behaviors in the environment. The users learned behaviors can then be adapted online in a life-long mode to satisfy the different user and system objectives. We have performed unique experiments in which the intelligent agent has learned and adapted to the users behavior, during a stay of five consecutive days in the intelligent dormitory (iDorm), which is a real ubiquitous computing environment test bed. Both offline and online experimental results are presented comparing the performance of our technique with other approaches. The results show that our proposed system has outperformed the other approaches, while operating online in a life-long mode to realize the ambient intelligence vision.

An experimental comparison of physical mobile interaction techniques: touching, pointing and scanning

This paper presents an analysis, implementation and evaluation of the physical mobile interaction techniques touching, pointing and scanning. Based on this we have formulated guidelines that show in which context which interaction technique is preferred by the user. Our main goal was to identify typical situations and scenarios in which the different techniques might be useful or not. In support of these aims we have developed and evaluated, within a user study, a low-fidelity and a high-fidelity prototype to assess scanning, pointing and touching interaction techniques within different contexts. Other work has shown that mobile devices can act as universal remote controls for interaction with smart objects but, to date, there has been no research which has analyzed when a given mobile interaction technique should be used. In this research we analyze the appropriateness of three interaction techniques as selection techniques in smart environments.

An Incremental Adaptive Life Long Learning Approach for Type-2 Fuzzy Embedded Agents in Ambient Intelligent Environments

In this paper, we present a novel type-2 fuzzy systems based adaptive architecture for agents embedded in ambient intelligent environments (AIEs). Type-2 fuzzy systems are able to handle the different sources of uncertainty and imprecision encountered in AIEs to give a very good response. The presented agent architecture uses a one pass method to learn in a nonintrusive manner the users particular behaviors and preferences for controlling the AIE. The agent learns the users behavior by learning his particular rules and interval type-2 Membership Functions (MFs), these rules and MFs can then be adapted online incrementally in a lifelong learning mode to suit the changing environmental conditions and user preferences. We will show that the type-2 agents generated by our one pass learning technique outperforms those generated by genetic algorithms (GAs). We will present unique experiments carried out by different users over the course of the year in the Essex Intelligent Dormitory (iDorm), which is a real AIE test bed. We will show how the type-2 agents learnt and adapted to the occupants behavior whilst handling the encountered short term and long term uncertainties to give a very good performance that outperformed the type-1 agents while using smaller rule bases

A user-independent real-time emotion recognition system for software agents in domestic environments

The mystery surrounding emotions, how they work and how they affect our lives has not yet been unravelled. Scientists still debate the real nature of emotions, whether they are evolutionary, physiological or cognitive are just a few of the different approaches used to explain affective states. Regardless of the various emotional paradigms, neurologists have made progress in demonstrating that emotion is as, or more, important than reason in the process of making decisions and deciding actions. The significance of these findings should not be overlooked in a world that is increasingly reliant on computers to accommodate to user needs. In this paper, a novel approach for recognizing and classifying positive and negative emotional changes in real time using physiological signals is presented. Based on sequential analysis and autoassociative networks, the emotion detection system outlined here is potentially capable of operating on any individual regardless of their physical state and emotional intensity without requiring an arduous adaptation or pre-analysis phase. Results from applying this methodology on real-time data collected from a single subject demonstrated a recognition level of 71.4% which is comparable to the best results achieved by others through off-line analysis. It is suggested that the detection mechanism outlined in this paper has all the characteristics needed to perform emotion recognition in pervasive computing.

Embedded Type-2 FLC for Real-Time Speed Control of Marine and Traction Diesel Engines

Marine propulsion and traction diesel engines operate in highly dynamic and uncertain environments. The current speed controllers for marine/traction diesel engines are based on PID and type-1 fuzzy logic controllers (FLCs) which cannot fully handle the uncertainties associated with such dynamic environments. Type-2 FLCs can handle such uncertainties to produce a better control performance. However, type-2 FLCs have a computational overhead associated with the iterative type-reduction process which can reduce the FLC real-time performance, especially when operating on industrial embedded controllers which have limited computational and memory capabilities. In this paper, we introduce a real-time type-2 FLC that is suited for embedded controllers operating in marine/traction diesel engines. We have conducted numerous experiments where the embedded type-2 FLCs dealt with the uncertainties in real-time and displayed a robust control response that outperformed the PID and type-1 FLCs whilst using smaller rule bases

Evolving spiking neural network controllers for autonomous robots

In this paper we introduce a novel mechanism for controlling autonomous mobile robots that is based on using spiking neural networks (SNNs). The SNNs are inspired by biological neurons that communicate using pulses or spikes. As SNNs have shown to be excellent control systems for biological organisms, they have the potential to produce good control systems for autonomous robots. In this paper we present the use and benefits of SNNs for mobile robot control. We also present an adaptive genetic algorithm (GA) to evolve the weights of the SNNs online using real robots. The adaptive GA using adaptive crossover and mutation converge in a small number of generations to solutions that allow the robots to complete the desired tasks. We have performed many experiments using real mobile robots to test the evolved SNNs in which the SNNs provided a good response.

Using Uncertainty Bounds in the Design of an Embedded Real-Time Type-2 Neuro-Fuzzy Speed Controller for Marine Diesel Engines

Marine diesel engines operate in highly dynamic and uncertain environments, hence they require robust and accurate speed controllers that can handle the encountered uncertainties. Type-2 Fuzzy Logic Controllers (FLCs) can handle such uncertainties; however they have a computational overhead associated with the iterative type-reduction process which can diminish the FLC real-time performance. Furthermore, manually designing a type-2 FLC is a difficult task particularly as the number of membership function parameters and rules increase. In this paper, we will introduce an embedded Real-Time Type-2 Neuro-Fuzzy Controller (RT2NFC) which overcomes the iterative type-reduction overhead and learns the parameters of interval type-2 FLC for marine engines. We have performed numerous experiments on a real diesel engine testing platform in which we compared our RT2NFC to a T2NFC based on the iterative type reduction procedure. Both T2NFCs were embedded on an industrial microcontroller platform where they handled the uncertainties to produce accurate and robust speed controllers that outperformed the currently used commercial engine controller. The RT2NFC gave approximately the same control response as the T2NFC, whilst the RT2NFC avoided the type-reduction overhead thus giving a faster real-time response.

A hierarchical fuzzy-genetic multi-agent architecture for intelligent buildings online learning, adaptation and control

In this paper, we describe a new application domain for intelligent autonomous systems--intelligent buildings (IB). In doing so we present a novel approach to the implementation of IB agents based on a hierarchical fuzzy genetic multi-embedded-agent architecture comprising a low-level behaviour based reactive layer whose outputs are co-ordinated in a fuzzy way according to deliberative plans. The fuzzy rules related to the room resident comfort are learnt and adapted online using our patented fuzzy-genetic techniques (British patent 99-10539.7). The learnt rule base is updated and adapted via an iterative machine-user dialogue. This learning starts from the best stored rule set in the agent memory (Experience Bank) thereby decreasing the learning time and creating an intelligent agent with memory. We discuss the role of learning in building control systems, and we explain the importance of acquiring information from sensors, rather than relying on pre-programmed models, to determine user needs. We describe how our architecture, consisting of distributed embedded agents, utilises sensory information to learn to perform tasks related to user comfort, energy conservation, and safety. We show how these agents, employing a behaviour-based approach derived from robotics research, are able to continuously learn and adapt to individuals within a building, whilst always providing a fast, safe response to any situation. In addition we show that our system learns similar rules to other offline supervised methods but that our system has the additional capability to rapidly learn and optimise the learnt rule base. Applications of this system include personal support (e.g. increasing independence and quality of life for older people), energy efficiency in commercial buildings or living-area control systems for space vehicles and planetary habitation modules.

A type-2 fuzzy embedded agent to realise ambient intelligence in ubiquitous computing environments

In this paper, we present a novel approach for realising the vision of ambient intelligence in ubiquitous computing environments (UCEs). This approach is based on embedding intelligent agents in UCEs. These agents use type-2 fuzzy systems which are able to handle the different sources of uncertainty and imprecision in UCEs to give a good response. We have developed a novel system for learning and adapting the type- 2 fuzzy agents so that they can realise the vision of ambient intelligence by providing a seamless, unobtrusive, adaptive and responsive intelligence in the environment that supports the activities of the user. The users behaviours and preferences for controlling the UCE are learnt online in a non-intrusive and life long learning mode so as to control the UCE on the users behalf. We have performed unique experiments in which the type-2 intelligent agent has learnt and adapted online to the users behaviour during a stay of five days in the intelligent Dormitory (iDorm) which is a real UCE test bed. We will show how our type-2 agents can deal with the uncertainty and imprecision present in UCEs to give a very good response that outperforms the type-1 fuzzy agents while using smaller rule bases.