2nd IET International Conference on Intelligent Environments (IE 06)
Buy conference proceeding
- Location: Athens, Greece
- Conference date: 5-6 July 2006
- ISBN: 0 86341 663 2
- Conference number: CP518
- The following topics are dealt with: ambient intelligence; smart home environments; interactive installations; space conception; agent systems; intelligent environments; multimedia processing; user-friendly multimodal spoken language dialogue systems; intelligent sensing systems; hybrid ubiquitous computing environments and ambient networks
1 - 20 of 100 items found
-
Preface
- + Show details - Hide details
-
p.
v1:1
(1)
(2 pages)
-
Employing neural networks to assist negotiating intelligent agents
- Author(s):
- + Show details - Hide details
-
p.
v1:101
(1)
Artificial intelligence is one of the various disciplines that need to be employed towards the vision of ambient intelligence. Mobile intelligent agents introduce a powerful technology that may assist the market penetration of services and products offered online in intelligent environments. Such agents have the potential to improve the efficiency, proactive behaviour and performance of computing and communication systems in such domains. In this framework, the design and evaluation of agents responsible for handling automated negotiations on behalf of their human or corporate owners is a challenging research field. In this paper these agents are enhanced with learning techniques, in order to better simulate the human intelligence and increase the profits of their owners. As mobile agents have reduced processing capabilities and may need to migrate to foreign network nodes, the learning mechanisms they employ should require minimal resources and be computationally efficient. The proposed learning technique is based on a specially designed neural network (NN), is quite lightweight, and is appropriate for agents that represent clients in automated negotiations in intelligent environments. Exploited by agents that use a fair relative tit-for-tat negotiation strategy, it aims to increase the ratio of successful negotiations and maximize the utility of the client. The designed NN-assisted negotiation strategy has been empirically evaluated via numerous experiments under various conditions. (10 pages)
-
Applying psychoanalytic and neuro-scientific models to automation
- Author(s):
- + Show details - Hide details
-
p.
v1:111
(1)
Project ARS (artificial recognition system) researches the future possibilities for building automation using bionic approaches. It focuses on the combination of bottom-up data processing systems with decision making inspired by modern psychoanalysis. We define a model based on a symbol processing unit and a decision unit implementing Sigmund Freud's ego-superego-id personality model, emotions and drives. This paper describes the basic principles of decision making and the complete connection down to sensors level, it shows some of the challenges in the process and first steps of implementing a prototype system. (8 pages)
-
Towards the detection of temporal behavioural patterns in intelligent environments
- Author(s):
- + Show details - Hide details
-
p.
v1:119
(1)
Ubiquitous computing applications propose new and creative solutions to every day needs. This paper addresses the issue of recognition of every day activities inside pervasive domestic environments in order to identify patterns of behaviour that can be later used to support care systems by detecting changes to those patterns. Our system uses a temporal neural-network-driven embedded agent able to work with online, real-time data from unobtrusive low-level sensors and actuators. We present experimental results that show that our agent is able to detect temporal patterns along with spatial similarity associations found in human behaviours and activities, in everyday living environments. (7 pages)
-
Intelligent virtual environments: operating conditioning and observational learning in agents using neural networks
- Author(s):
- + Show details - Hide details
-
p.
v1:127
(1)
Virtual environments are frequently used for simulation where situations with many agents interact among them with or without user interaction. In many cases, intelligence is required to the agents, meaning not only ability to sense the environment, make decisions and as a result act, but also including learning ability. On the other hand, in psychology field, several studies have been made - including both human observation and animal experimentation - and as a result, many different theories about learning have been formulated, such as classing conditioning, operating conditioning, cognitive learning and observational learning. This paper has as the objective of applying some of these psychology concepts to intelligent virtual agents field. With this purpose we developed a virtual environment where the agent's interaction takes place. Learning abilities are also incorporated to them using neural networks. Finally, results are presented and conclusions extracted. (7 pages)
-
The architecture of intelligent cities: integrating human, collective and artificial intelligence to enhance knowledge and innovation
- Author(s):
- + Show details - Hide details
-
p.
v1:13
(1)
Intelligent communities and cities (IC) belong to an emerging movement targeting the creation of environments that improve cognitive skills and abilities to learn and innovate. They represent environments that enable superior cognitive capabilities and creativity to be collectively constructed from combinations of individual cognitive skills and information systems that operate in the physical, institutional, and digital spaces of cities. Two academic traditions have been feeding the discussion concerning intelligent communities and cities: the literature on innovative environments and the planning of digital cities. Following an introduction on the meaning of ICs, we discuss the structuring of innovative environments such as clusters, technology districts and territorial systems of innovation, which rely on different architectures of knowledge networks enhancing product, process, and organizational innovation. Then we turn to digital cities and examine their concept, architecture, and constituent elements. In the final section of the paper we describe intelligent cities as overlapping of innovative clusters and digital cities. Intelligent cities integrate knowledge-intensive activities and clusters; embedded routines of social cooperation enabling knowledge sharing and innovation; advanced communication infrastructure and digital spaces for knowledge and innovation management; and proven ability to innovate and resolve problems that appear for the first time, since the capacity to innovate and manage uncertainty are critical factors in characterizing intelligence. (8 pages)
-
Rapid prototyping of context-aware games
- Author(s):
- + Show details - Hide details
-
p.
v1:135
(1)
This paper presents an evaluation of a context-aware game design and implementation process. The importance of gathering and disseminating context data for context-aware applications is widely recognised. However, developing context-aware applications is a demanding task without proper architecture. The architecture for context-aware applications should also support the development process. In this paper we review rapid context-aware application prototyping through the use of MUPE platform. (8 pages)
-
Design issues in personalizing intelligent buildings
- Author(s):
- + Show details - Hide details
-
p.
v1:143
(1)
This paper concerns the personalization of intelligent buildings, where intelligence of a building is considered in a broad sense, not confined to the computational aspects. Personalization is desired in order to give the individual greater representation in the building and for energy consumption/well-being balance in the context of measuring building intelligent quotient. The paper examines problems of programming in pervasive space, and current systems for personalization. It discusses design issues relating to human representation in the building, active and passive human participation, the nature of the personal agent, ownership and location, transparency, and norm-based agency. A design based upon active involvement of the occupant is presented. (7 pages)
-
Gesture synthesis from sign language notation using MPEG-4 humanoid animation parameters and inverse kinematics
- Author(s):
- + Show details - Hide details
-
p.
v1:151
(1)
This paper presents a novel approach for generating VRML animation sequences from sign language notation, based on MPEG-4 face and body animation. Sign language notation, in the well-known sign writing system, is provided as input and is initially converted to SWML (Sign Writing Markup Language), an XML-based format that has recently been developed for the storage, indexing and processing of sign writing notation. Each basic sign, namely signbox, is then converted to a sequence of body animation parameters (BAPs) of the MPEG-4 standard, corresponding to the represented gesture. Inverse Kinematics are also employed for synthesizing complex animation sequences (e.g. contacts). In addition, if a sign contains facial expressions, these are converted to a sequence of MPEG-4 facial animation parameters (FAPs), while exact synchronization between facial and body movements is guaranteed. These sequences, which can also be coded and/or reproduced by MPEG-4 BAP and FAP players, are then used to animate H-anim compliant VRML avatars, reproducing the exact gestures represented in the sign language notation. Envisaged applications include interactive information systems for the persons with hearing disabilities (Web, E-mail, info-kiosks) and automatic translation of written texts to sign language (e.g. for TV newscasts). (10 pages)
-
Tracking based face identification: a way to manage occlusions, and illumination, posture and expression changes
- Author(s):
- + Show details - Hide details
-
p.
v1:161
(1)
This paper presents a method for face identification using an eigenfaces approach. Our technique is suitable for use within ambient security environments and is robust across variations in pose, expression and illuminations conditions. To account for these variations, we use a face template matching algorithm based on a 3D head model. Thanks to our tracking-based approach our algorithm is able to extract simultaneously all parameters related to the face expression and to the 3D posture. With these estimates, we are able to reconstruct a frontal, neutral and normalized image on which an eigenface classification for identification is performed. (6 pages)
-
Root cepstral filtering for improved system identification
- Author(s):
- + Show details - Hide details
-
p.
v1:167
(1)
Phase information is seen to be important and decisive for the performance of a variety of signal processing tasks, including biometric data processing and robotics/navigational applications which require correct localization of objects or events. Existing approaches to system identification ignore phase information, under the minimum-phase assumption; yet, it is argued that improved performance can be obtained if phase information is retained. Modelling the impulse response of an unknown system from the observed output signal comprised of periodic input excitations, has traditionally been undertaken in the time domain. A novel method for system identification is proposed here, by undertaking the analysis in the frequency domain and utilizing the properties of the root cepstrum, which is a phase-retaining coefficient. We are able to demonstrate, that by warping the z-plane, the system impulse response will be separated from the problematic excitation. Hence, by moving the excitation zeros 'away' from the unit circle, the system impulse response may be extracted and modelled. Potential applications of our method include processing of biometric signals, where improved speaker identification/verification depends critically on an accurate vocal tract model of the speaker, as well as robotic/autonomous navigation applications, where correct automatic localization of items and/or events depends on the signal or system phase information. (5 pages)
-
Automated production of personalized video content for visitors of thematic parks
- Author(s):
- + Show details - Hide details
-
p.
v1:173
(1)
The proposed platform aims to develop an intelligent cross-media platform for personalised leisure and entertainment in thematic parks or venues. The system we develop allows the visitor to be the real protagonist in the venue. The platform caters for a great variety of media needs of the visitors: from recording their visit to provide a high-quality, customised souvenir, to embedding personalised electronic content into their activities in real time. The platform incorporates new and innovative solutions that cover and improve digital content acquisition and creation, management and processing, access, retrieval, manipulation and delivery of digital content. The platform is equipped with innovative imaging technologies for real time detection, localisation and tracking of "human content", i.e., the human visitor within the recoding being made in real-time by the system. No constraints are imposed on the variation of the environment. (9 pages)
-
Real-time perceptual navigation experiments in existing and virtual architectural space
- Author(s):
- + Show details - Hide details
-
p.
v1:183
(1)
This paper presents ongoing research on an experiment that concerns the spatial perception and cognition in real and virtual architectural environments and is part of a series of experiments that took place in the same field. The differences in perception and cognition of a real building and its virtual counterpart are studied through the processes of navigation and representation. Intelligent features, such as actors and interactive objects are used to determine their influence in the perception and cognition of virtual architectural space. For these reasons a computer gaming engine is used, which can provide a fully interactive intelligent virtual environment that is used to enhance the above factors. Preliminary results confirm earlier findings from previous similar experiments. It was found that there was a statistically significant tendency of the students towards larger scatter in more luminous virtual space as well as a tendency to visit the lit part of virtual space. Visitors of the photorealistic spaces also seem to have better knowledge of the depth of space in comparison to those navigating in the non photorealistic space. (5 pages)
-
Visual feedback information for virtual lifting tasks
- Author(s):
- + Show details - Hide details
-
p.
v1:189
(1)
This paper investigates the effect of visual feedback techniques to enhance user performance in virtual environments (VE) while carrying out manual lifting tasks. The aim of this study was to reduce lower back pain by enabling users to monitor their lower back condition in terms of lifting index (LI) values, whilst moving an object from one location to another. Several experiments were conducted to explore and evaluate the effectiveness of neutral, visual and combined visual feedback on lifting performance. An analysis of task completion time, percentage of harmful lifts and response time to feedback were analysed and used to identify the appropriateness of each visual feedback technique. The results showed that the addition of visual feedback did introduce an improvement in manual lifting tasks. The results also reveal that the combined visual feedback techniques performed better than singular feedback techniques. (8 pages)
-
Integrating emotion recognition into an adaptive spoken language dialogue system
- Author(s):
- + Show details - Hide details
-
p.
v1:197
(1)
In order to add adaptability and user-friendliness to human computer interfaces, the classification and recognition of a user's emotional state has evolved to a significant topic of interest within the research on natural spoken dialogue systems. In this article we pick up the idea of using hidden Markov models (HMMs) to recognize emotions from speech signals and we integrate these recognition results in adaptive dialogue management. At first we give an overlook on different characteristics of selected emotions with respect to the features extracted from the speech signal and we describe the emotion recognizer. Then we highlight our approaches to improve the quality of the recognizer models and we show how the recognizer's results are used to adapt a dialogue system's behavior to the user's emotional state. (6 pages)
-
Natural language processor for user driven free speech voice interaction in multimodal smart environments
- Author(s):
- + Show details - Hide details
-
p.
v1:203
(1)
The aim of the paper is to introduce a natural language processor enabling mobile multimodal interfaces to receive user driven free speech in order to enable more natural voice interaction with mobile applications and services to control devices in smart environments. Free speech of users is continuously analysed and matched against semantically defined device service commands. The concept and requirements of the language processor and the semantic description for application commands will be explained. Further the paper elaborates on how this concept was fitted into the general concept of a mobile multimodal interface and elaborates on implementation aspects of the language processor. The feasibility of the approach has been shown in a prototypical implementation. The work has been carried out as part of the research on mobile multimodal interfaces within the IST-FP6 MobiLife project. First order or main headings should commence at the left hand margin of each column, and should be in capitals and can be in bold. Except at the top of a new column the first order heading should be preceded by two lines of space and followed by two lines of space. (9 pages)
-
Seamless integration of output devices in intelligent environments: infrastructure, strategies and implementation
- Author(s):
- + Show details - Hide details
-
p.
v1:21
(1)
We present a novel software infrastructure for the seamless integration of heterogeneous output devices into intelligent environments. It dynamically coordinates the output devices to enable adaptive, multimedia presentations by taking the availability of resources and the context of the presentation into account. In this paper we focus on three topics. We present our connecting middleware which supports ad-hoc spontaneous interactions between heterogeneous devices connected by different types of networks. We focus on the multimedia output (MMO) channel which is situated atop this middleware and which is responsible for coordinating output devices according to their self-descriptions. Then we give details about the AI planner which is used by the MMO channel to compute a solution to the presentation problem given by the presentation context. Finally, we outline our implementations for an intelligent living room scenario and point out related work. (10 pages)
-
Next-generation human-computer interfaces - towards intelligent, adaptive and proactive spoken language dialogue systems
- Author(s):
- + Show details - Hide details
-
p.
v1:213
(1)
In this paper, we present an overview of some current research topics which we consider essential for the advanced development of spoken language dialogue systems. In particular, we argue that dialogue systems have to become more flexible at integrating information from different sources and more proactive if their information processing yields relevant inferences. In addition, emotion recognition and adaptive dialogue management are discussed. (7 pages)
-
An architecture for multimodal applications over wireless data networks
- Author(s):
- + Show details - Hide details
-
p.
v1:221
(1)
As speech is a natural way of interaction between humans and machines, more and more applications will arise that exploit the specific feature. Multimodality comes as the next step in order to offer even more natural, friendlier and personalized interfaces. In this work, we present the architecture of a distributed system that utilizes the data channel (GPRS or 3G), in order to accommodate multimodal applications on a mobile device. Within the context of our work we also introduce a generic framework for creating applications of this kind. Finally, we integrate the proposed system in order to demonstrate a sample application. (7 pages)
-
Cluster-based approaches to the statistical modelling of dialogue data in the British National Corpus
- Author(s):
- + Show details - Hide details
-
p.
v1:229
(1)
Spoken language dialogue systems (SLDSs) are becoming more and more widespread as interfaces between human users and automated systems. The speech recogniser is a key component of an SLDS, and a statistical language model is at the core of most successful recognisers. In this paper, we describe and compare several cluster-based strategies for modelling dialogue turns, applying them to pairs of successive short dialogue turns from the British National Corpus - the type of turn pairs likely to be common in the kind of highly interactive dialogues in which an SLDS would be expected to participate. (10 pages)
