Dissertations / Theses on the topic 'User modelling'
To see the other types of publications on this topic, follow the link: User modelling.
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 dissertations / theses for your research on the topic 'User modelling.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse dissertations / theses on a wide variety of disciplines and organise your bibliography correctly.
1
Biswas, P. "Inclusive user modelling." Thesis, University of Cambridge, 2010. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.596672.
Full textAbstract:
I have investigated how physical capabilities of users with a wide range of abilities are reflected in their interactions with digital devices. I have formulated a simulator that embodies both the internal state of a computer application and also the perceptual, cognitive and motor processes of its user. The simulator can predict the likely interaction patterns when undertaking a task using a variety of input devices, and estimate the time to complete the task in the presence of different disabilities and for different levels of skill. The simulator consists of a perception model, a cognitive model and a motor behaviour model. The preparation model simulates the phenomena of visual perception (like focussing and shifting attention) and can also simulate the effects of different visual impairments on interaction. It has predicted the visual search time and eye gaze pattern of able-bodied people and a few types of visually impaired users with statistically significant accuracy. The cognitive model simulates expert performance by using CPM-GOMS model. It can also simulate performance of novices by using a dual-space model. The motor-behaviour model is based on statistical analysis of cursor traces from motor-impaired users. As part of the model, I have also developed a new scale of characterizing the extent of disability of users by measuring their grip strength. I have evaluated the simulator through an icon searching task undertaken by visually and motor impaired people and also used the simulator to develop a new assistive interaction technique. My studies have already been used to design an accessible game and the University has been awarded EU funding for a project that will build on results from my PhD research.
2
Adikari, Sisira. "Usability modelling for requirements engineering /." Canberra, 2008. http://erl.canberra.edu.au/public/adt-AUC20081204.145827/index.html.
Full text
3
Nadee, Wanvimol. "Modelling user profiles for recommender systems." Thesis, Queensland University of Technology, 2016. https://eprints.qut.edu.au/93723/1/Wanvimol_Nadee_Thesis.pdf.
Full textAbstract:
Recommender systems assist users in finding what they want. The challenging issue is how to efficiently acquire user preferences or user information needs for building personalized recommender systems. This research explores the acquisition of user preferences using data taxonomy information to enhance personalized recommendations for alleviating cold-start problem. A concept hierarchy model is proposed, which provides a two-dimensional hierarchy for acquiring user preferences. The language model is also extended for the proposed hierarchy in order to generate an effective recommender algorithm. Both Amazon.com book and music datasets are used to evaluate the proposed approach, and the experimental results show that the proposed approach is promising.
4
Adikari, Sisira, and n/a. "Usability Modelling For Requirements Engineering." University of Canberra. Information Sciences & Engineering, 2008. http://erl.canberra.edu.au./public/adt-AUC20081204.145827.
Full textAbstract:
For over two decades user-centric methods and techniques have been proposed to assist the
production of usable, useful, and desirable software products. Despite these approaches,
usability problems are still identified in finished software products creating problems at
systems acceptance, rework and impacting end user experience. Part of the reason for these
continuing problems is that user-centric approaches are not part of the traditional software
engineering process. The literature review shows that software engineering and human-computer
interaction are largely different communities.
The aim of this thesis is to investigate whether the incorporation of user modelling and
usability modelling into software requirements specifications would improve design quality
and usability of software products. This research study used a Design Science dominant
mixed research methodology consisting of case study and action research for creating,
analysing and evaluating artefacts for improving the effectiveness of user-centred design and
usability of software artefacts. Using the functional specification of an existing system in a
government agency, ten designers created screen and interaction designs. The specification
was then enhanced with usability specifications and the designers redeveloped their designs
in the light of the enhanced specification. Both designs were subject to pre-defined usability
tests and designers described their design experience as they worked.
The results of the research demonstrated that enhancing traditional software requirements
specifications with additional specifications of user modelling and usability modelling made
a positive difference to both designer perception as well as design quality of user interface
artefacts. The theoretical and practical values of these findings are explored.
5
Despotakis, Dimoklis. "Modelling viewpoints in user generated content." Thesis, University of Leeds, 2013. http://etheses.whiterose.ac.uk/5754/.
Full textAbstract:
The Web 2.0 infrastructure allowed for a tremendous technological growth in the ways that information is distributed and exchanged among individuals. Web sites transformed to hosts of an abundance of user generated content in various domains comprising thereafter social media platforms. This evolution heralded the beginning of a new era for user modelling. Several types of applications have gained benefit from harvesting social media content for either populating or enriching user models by identifying, extracting and analysing digital user traces aiming at improving system responses for adaptation and personalisation. However, different user experiences and backgrounds determine different user viewpoints, and it is evident that the next generation of user modelling approaches should cater for viewpoints diversity. This can enable better understanding of the users' conceptualisations, their exposure to diverse interpretations overcoming thus the 'filter bubble' effect and enriching their perspective. How can we represent user viewpoints? How can we capture user-viewpoints from user generated content? How can we enable intelligent analysis of user viewpoints to explore diversity? This research complements notable efforts for viewpoints modelling by addressing three main challenges: (i) enable better understanding of users by capturing the semantics of user viewpoints; (ii) formally represent user viewpoints by capturing the viewpoint focus, and identify the projection of user models on the domain of interest; and, (iii) enable exploration of diversity by providing intelligent methods for analysis and comparison of viewpoints. The proposed approach is wrapped within a framework for representing, capturing and analysing user viewpoint semantics, called ViewS. ViewS defines a semantic augmentation pipeline for processing textual user generated content. The semantic output is then used as input together with the annotating ontologies in a component for capturing viewpoint focus which exploits Formal Concept Analysis. The viewpoint focus model is used then to analyse and compare user viewpoints and explore diversity. ViewS has been deployed and evaluated for user viewpoints on social signals in interpersonal communication, including emotion and body language, where diverse interpretations can be obtained by different individuals and groups.
6
Strachan, Linda Noreen. "Pragmatic user modelling for complex commercial systems." Thesis, National Library of Canada = Bibliothèque nationale du Canada, 1999. http://hdl.handle.net/1993/1579.
Full textAbstract:
While user modelling has become a mature field, with demonstrable research systems of great power, comparatively little progress has been made in the development of user modelling components for commercial software systems. The development of minimalist user modelling components, which are simplified to provide "just enough" assistance to a user through a pragmatic adaptive user interface, is seen by many as an important step toward this goal. This thesis describes the development, implementation, and empirical evaluation of a minimalist user modelling component for the Tax and Investment Management Strategizer (TIMS), a complex commercial software system for financial management. The experimental results demonstrate that a minimalist user modelling component improves the subjective measure of user satisfaction. Important issues and considerations for the development of user modelling components for commercial software systems are also discussed.
7
Lin, Jian. "General-purpose user-defined modelling system (GPMS)." Thesis, Lancaster University, 1993. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.335145.
Full text
8
Cocea, Mihaela. "User modelling and adaptation in exploratory learning." Thesis, Birkbeck (University of London), 2011. http://eprints.port.ac.uk/12174/.
Full textAbstract:
User modelling in Exploratory Learning Environments (ELEs) is an emerging field with several challenges to be addressed. Due to the freedom given to learners, the amount of information generated is very large, making the modelling process very challenging. Consequently, only relevant information should be used in the user modelling process. This, however, leads to other challenges such as identification of relevant information, finding an optimal knowledge representation and defining an inference mechanism by which this knowledge is used in diagnosing the learner. This thesis addresses the challenges of user modelling in ELEs by monitoring learners' behaviour and taking into account only relevant actions in the context of an ELE for the domain of mathematical generalisation. An iterative approach was used, in line with the iterative design of the ELE. The modelling mechanism employed a modified version of Case-based Reasoning (CBR) and was evaluated using pedagogical scenarios and data from simulated and real students. This approach has the advantage of storing only relevant information and allows learner diagnosis during as well as at the end of a task. The user model was further exploited to support learning related activities, such as prioritising feedback and grouping for collaboration. For feedback prioritisation, a mechanism based on Multi-criteria Decision Making was developed and tested with the help of educational experts. The grouping for collaboration approach was inspired from Group Technology, a method from cellular manufacturing systems, and its testing showed it produces meaningful groups. Both the feedback prioritisation and the grouping for collaboration mechanisms propose solutions that are particularly relevant for ELEs by considering pertinent criteria for this type of learning. To ensure optimal coverage of the knowledge base, the user modelling approach was enhanced with adaptive mechanisms for expanding the knowledge base, which was tested on real and simulated data. This approach ensures that learner diagnostic is possible when the initial knowledge base is small and/or new behaviours are encountered over time.
9
Ennis, Mark. "Modelling the IR task : supporting the user." Thesis, City University London, 1998. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.287670.
Full text
10
Ultes, Stefan [Verfasser]. "User-centred adaptive spoken dialogue modelling / Stefan Ultes." Ulm : Universität Ulm, 2015. http://d-nb.info/1122195621/34.
Full text
11
Springett, Mark Vincent. "User modelling for evaluation of direct manipulation interfaces." Thesis, City University London, 1995. http://openaccess.city.ac.uk/7776/.
Full textAbstract:
This thesis applies models of user action to usability evaluation of direct manipulation interfaces. In particular, the utility of a Model of Action for assisting novice evaluators in usability tests is investigated. An initial model of user action is proposed, based on the theory of action proposed by Norman (1986). This model includes a description of knowledge sources used in interaction, error types and user responses to errors. The model is used to interpret data on user behaviour and errors in an empirical study of MacDraw I. This study used the Protocol Analysis technique proposed by Ericsson and Simon (1984). Protocol evidence shows that the search and specification stages of user action could usefully be treated as separate in terms of user knowledge recruitment and the nature of system support. The Model of Action is then expanded and modified to account for the empirical findings. The new model distinguishes knowledge-based, rule-based and skill-based processing in Direct Manipulation (DM) interaction, using the distinction drawn by Rasmussen (1986). These processing levels are explicitly linked to types of presentation technique and categories of user error. This is developed into a technique for determining system causes of usability problems. A set of mental dialogue tokens (roles) are developed to assist novice evaluators in the interpretation of error causes. Roles are linked to types of user error in the cycle of action in a diagnostic model. This model forms the basis of a budget method for use by novice evaluators, named Model Mismatch Analysis (MMA). These developments are tested by a two-tier study of user performance on Microsoft Word. The empirical evidence validated the taxonomy of errors, and tests the utility of five retrospective data analysis techniques. A study of novice evaluator performance is reported, comparing the MMA method to the Usability Checklist proposed by Ravden and Johnson (1989). The MMA method is shown to be the more efficient approach. To summarise, models of Direct Manipulation action are shown to assist novice evaluators both in the diagnosis of usability problems, and the selection of remedies.
12
Yang, Baoguo. "User information modelling in social communities and networks." Thesis, University of York, 2015. http://etheses.whiterose.ac.uk/18567/.
Full textAbstract:
User modelling is the basis for social network analysis, such as community detection, expert finding, etc. The aim of this research is to model user information including user-generated content and social ties. There have been many algorithms for community detection. However, the existing algorithms consider little about the rich hidden knowledge within communities of social networks. In this research, we propose to simultaneously discover communities and the hidden/latent knowledge within them. We focus on jointly modelling communities, user sentiment topics, and the social links. We also learn to recommend experts to the askers based on the newly posted questions in online question answering communities. Specifically, we first propose a new probabilistic model to depict users' expertise based on answers and their descriptive ability based on questions. To exploit social information in community question answering (CQA), the link analysis is also considered. We also propose a user expertise model under tags rather than the general topics. In CQA sites, it is very common that some users share the same user names. Once an ambiguous user name is recommended, it is difficult for the asker to find out the target user directly from the large scale CQA site. We propose a simple but effective method to disambiguate user names by ranking their tag-based relevance to a query question. We evaluate the proposed models and methods on real world datasets. For community discovery, our models can not only identify communities with different topic-sentiment distributions, but also achieve comparable performance. With respect to the expert recommendation in CQA, the unified modelling of user topics/tags and abilities are capable of improving the recommendation performance. Moreover, as for the user name disambiguation in CQA, the proposed method can help question askers match the ambiguous user names with the right people with high accuracy.
13
Finlay, Janet Elizabeth. "Modelling users by classification : an example-based approach." Thesis, University of York, 1990. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.276497.
Full text
14
Vythoulkas, Petros C. "Modelling dynamic stochastic user equilibrium for urban road networks." Thesis, Cranfield University, 1991. http://hdl.handle.net/1826/3937.
Full textAbstract:
In this study a dynamic assignment model is developed which estimates travellers' route
and departure time choices and the resulting time varying traffic patterns during the
morning peak. The distinctive feature of the model is that it does not restrict the
geometry of the network to specific forms.
The proposed framework of analysis consists of a travel time model, a demand model
and a demand adjustment mechanism. Two travel time models are proposed. The first
is based on elementary relationships from traffic flow theory and provides the
framework for a macroscopic simulation model which calculates the time varying flow
patterns and link travel times given the time dependent departure rate distributions; the
second is based on queueing theory and models roads as bottlenecks through which
traffic flow is either uncongested or fixed at a capacity independent of traffic density.
The demand model is based on the utility maximisation decision rule and defines the
time dependent departure rates associated with each reasonable route connecting, the
O-D pairs of the network, given the total utility associated with each combination of
departure time and route. Travellers' choices are assumed to result from the trade-off
between travel time and schedule delay and each individual is assumed to first choose a
departure time t, and then select a reasonable route, conditional on the choice of t. The
demand model has therefore the form of a nested logit. The demand adjustment
mechanism is derived from a Markovian model, and describes the day-to-day evolution
of the departure rate distributions. Travellers are assumed to modify their trip choice
decisions based on the information they acquire from recent trips. The demand
adjustment mechanism is used in order to find the equilibrium state of the system,
defined as the state at which travellers believe that they cannot increase their utility of
travel by unilaterally changing route or departure time.
The model outputs exhibit the characteristics of real world traffic patterns observed
during the peak, i. e., time varying flow patterns and travel times which result from
time varying departure rates from the origins. It is shown that increasing the work start
time flexibility results in a spread of the departure rate distributions over a longer
period and therefore reduces the level of congestion in the network. Furthermore, it
was shown that increasing the total demand using the road network results in higher
levels of congestion and that travellers tend to depart earlier in an attempt to
compensate for the increase in travel times. Moreover, experiments using the queueing
theory based travel time model have shown that increasing the capacity of a bottleneck
may cause congestion to develop downstream, which in turn may result in an increase
of the average travel time for certain O-D pairs. The dynamic assignment model is also
applied to estimate the effects that different road pricing policies may have on trip
choices and the level of congestion; the model is used to demonstrate the development
of the shifting peak phenomenon. Furthermore, the effect of information availability
on the traffic patterns is investigated through a number of experiments using the
developed dynamic assignment model and assuming that guided drivers form a class of
users characterised by lower variability of preferences with respect to route choice.
15
Hawalah, Ahmad. "Modelling dynamic and contextual user profiles for personalized services." Thesis, University of Essex, 2012. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.573021.
Full textAbstract:
During the last few years the Internet and the WWW have become a major source of information as well as an essential platform for mass media, communication, e-commerce and entertainment. This expansion has led to information overload so finding or searching for relevant information has become more and more challenging. Personalization and recommender systems have been widely used during the past few years to overcome this information overload problem. The main objective of these systems is to learn user interests and then provide a personalized experience to each user accordingly. However; as information on the WWVV increases, so do users' demands: web personalization systems need to provide users not only with recommendations for relevant information, but also provide these recommendations in the right situation. However, when examining the current works in the personalization field, we can see that there is a limitation in providing a generic personalization system that can model dynamic and contextual profiles to provide more intelligent personalized services. Most of the current systems are not able to adapt to user frequent changing behaviours, and ignore the fact that users might have different preferences in different situations and contexts. Aiming to address these limitations in current personalization systems, this thesis focuses on the aspects of modelling conceptual user profiles that are dynamic and contextual in a content-based platform. The novelty is in the way that these profiles are learnt, adapted, exploited and integrated to infer not just highly relevant items, but also provide such items in the right situation.
16
Caregnato, Sonia Elisa. "Modelling the user education domain : a grounded theory approach." Thesis, University of Sheffield, 2000. http://etheses.whiterose.ac.uk/3060/.
Full textAbstract:
This thesis reports a research work whose objective was to derive a grounded model of the user education domain, which was identified as pertaining to subject librarians' expertise, using a knowledge elicitation approach in the field of agricultural sciences. The knowledge elicitation framework adopted was that which sees knowledge acquisition as a process of modelling expertise, and the models derived as qualitative in nature. Accordingly, the main methodological approach involved was based on qualitative research and use of grounded theory methods. The research design was divided into three studies, all based on interview data. The research started by studying the role of subject librarians in academic libraries in the UK (Study One), which identified the area of user education for further study. Study Two proceeded to elicit information seeking practices and user education processes from academics and librarians. Finally, Study Three elicited information seeking practices of students who were engaged in library research. A model of the user education domain in the field of agricultural sciences in a Brazilian university was derived from the combination of the analysis of Study Two and Three. The model describes the library research process of individuals as happening in discipline specific contexts, influenced by the world at large. The process takes place through a series of information-seeking tasks and task-related strategies, which are employed to search external knowledge sources and satisfy an information need. During this interaction, internal knowledge sources are used and modified according to the tasks and strategies being carried out. If these internal knowledge sources are deficient for effective use of external knowledge sources, mediation strategies by an expert can help readjust the information-seeking process and alter the state of related internal knowledge sources The model proposed is used to derive recommendations for the design of user education programmes, subject librarians' work, and domain modelling using grounded theory.
17
Schatzmann, Jost. "Statistical user and error modelling for spoken dialogue systems." Thesis, University of Cambridge, 2008. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.612439.
Full text
18
Lewis, John Michael. "A user modelling approach to computer based advice generation." Thesis, University of Edinburgh, 1990. http://hdl.handle.net/1842/19053.
Full textAbstract:
The need for Intelligent advice, help and tutoring, generated automatically by computers is widely accepted. Recently, efforts to achieve these requirements have focused upon research into user models and improved user-machine interaction. This thesis develops a mechanism for detecting when an individual has a problem with the computer system, and identifies the nature of his problem. The method uses Plan Recognition to suggest plans that a user may be following. A Chart Parser is used to achieve this plan recognition task. This technique is capable of detecting multiple, interleaved and incomplete plans, without prior knowledge of the user's intended goals. A model of the user's beliefs is developed for the UNIX operating system. This model is capable of representing misconceptions that users possess about the domain. The combination of these techniques and heuristics to suggest when the user is experiencing difficulty, enables the computer to initiate the advice process and determine the basis for the advice.
19
Georgiou, Theodosis. "User modelling for adaptive training in high performance driving." Thesis, Imperial College London, 2016. http://hdl.handle.net/10044/1/43533.
Full textAbstract:
User model creation is a fundamental component for the development of intelligent personalised systems. This thesis proposes an adaptive user modelling framework that uses a combination of unobtrusive task-related and physiological data with the aim of identifying strengths and weaknesses in user performance in the defined task. The research is focused on utilising the framework to provide personalised content adaptation in car racing games. Our system adopts concepts from the Trace Theory (TT) framework, and uses machine learning techniques to extract specific features from the user and the game. These metrics are then transformed and evaluated into higher level abstractions such as experience, exploration and physiological attention by utilising the educational theoretical frameworks of Flow and Zone Theory. The end result is to provide new game paths utilising the user’s model. We demonstrate that this procedural generation of user-tailored content drives the self-motivating behaviour of players to immerse and engage themselves in the game’s virtual world. Collection of data and feedback from multiple users (52) allowed us to associate the model’s outcomes to the user responses, as well as device multiple trial scenarios to verify their training and engagement. We have also evaluated the algorithms for the generation of new tracks for their suitability on the skill’s profile of 41 of our subjects and race track diversity among the evolved paths. We have also designed a method for predicting the states of the user-controlled system by combining information from both sources – vehicle and user – via Gaussian Processes (GPs). In the context of high speed car racing we showed that the forthcoming position and speed of the car can be predicted with high accuracy by our trained user models. This opens up future possibilities of generating better personalised tracks for individuals or even real-time share-control of the car to optimally assist the users in dangerous situations.
20
Kim, Sanghee. "User modelling for knowledge sharing in e-mail communication." Thesis, University of Southampton, 2002. https://eprints.soton.ac.uk/45959/.
Full textAbstract:
This thesis addresses the problem of sharing and transferring knowledge within knowledge-intensive organisations from a user modelling perspective with the purpose of improving individual and group performance. It explores the idea of creating organisational environments from which any of the users involved can benefit by being aware of each other such that sharing expertise between those who are knowledge providers and those who are knowledge seekers can be maximised. In order to encourage individuals to share such valuable expertise, it also explores the idea of keeping a balance between ensuring the availability of information and the increase in user workloads due to the need to handle unwanted information. In an attempt to demonstrate the ideas mentioned above, this research examines the application of user modelling techniques to the development of communication-based task learning systems based on e-mail communication. The design rationale for using e-mail is that personally held expertise is often explicated through e-mail exchanges since it provides a good source for extracting user knowledge. The provision of an automatic message categorisation system that combines knowledge acquired from both statistical and symbolic text learning techniques is one of the three themes of this work. The creation of a new user model that captures the different levels of expertise reflected in exchanged e-mail messages, and makes use of them in linking knowledge providers and knowledge seekers is the second. The design of a new information distribution method to reduce both information overload and underload is the third.
21
Kim, Changkyun. "Application of user equilibrium traffic assignment in evacuation modelling." Thesis, Virginia Tech, 1991. http://hdl.handle.net/10919/41496.
Full textAbstract:
The Mass Evacuation (MASSVAC) model was originally developed for analysis and evaluation of evacuation plan in a specific area facing natural disasters. It was later applied to deal with the problems of evacuation around nuclear power stations (MASSVAC 3.0). The purpose of this model is to simulate the network clearance time and evacuation routes. In the process, it employs the Dial's or the all-or-nothing method to assign the traffic on to the network.
The major effort in this research is to include the user equilibrium assignment method to reduce the evacuation times and to improve highway network performance. Evacuation routes, number of links used, and evacuation times etc. are found to be influenced by the user equilibrium assignment method. Transportation System Management (TSM) strategies have also been incorporated in this enhanced model (MASSVAC 4.0) to improve the network performance during evacuation. The trip distribution process and the shortest path algorithm has been modified appropriately to suit the user equilibrium assignment.
Master of Science
22
Ionascu, Beatrice. "Modelling user interaction at scale with deep generative methods." Thesis, KTH, Skolan för elektroteknik och datavetenskap (EECS), 2018. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-239333.
Full textAbstract:
Understanding how users interact with a company's service is essential for data-driven businesses that want to better cater to their users and improve their offering. By using a generative machine learning approach it is possible to model user behaviour and generate new data to simulate or recognize and explain typical usage patterns. In this work we introduce an approach for modelling users' interaction behaviour at scale in a client-service model. We propose a novel representation of multivariate time-series data as time pictures that express temporal correlations through spatial organization. This representation shares two key properties that convolutional networks have been built to exploit and allows us to develop an approach based on deep generative models that use convolutional networks as backbone. In introducing this approach of feature learning for time-series data, we expand the application of convolutional neural networks in the multivariate time-series domain, and specifically user interaction data. We adopt a variational approach inspired by the β-VAE framework in order to learn hidden factors that define different user behaviour patterns. We explore different values for the regularization parameter β and show that it is possible to construct a model that learns a latent representation of identifiable and different user behaviours. We show on real-world data that the model generates realistic samples, that capture the true population-level statistics of the interaction behaviour data, learns different user behaviours, and provides accurate imputations of missing data.Förståelse för hur användare interagerar med ett företags tjänst är essentiell för data-drivna affärsverksamheter med ambitioner om att bättre tillgodose dess användare och att förbättra deras utbud. Generativ maskininlärning möjliggör modellering av användarbeteende och genererande av ny data i syfte att simulera eller identifiera och förklara typiska användarmönster. I detta arbete introducerar vi ett tillvägagångssätt för storskalig modellering av användarinteraktion i en klientservice-modell. Vi föreslår en ny representation av multivariat tidsseriedata i form av tidsbilder vilka representerar temporala korrelationer via spatial organisering. Denna representation delar två nyckelegenskaper som faltningsnätverk har utvecklats för att exploatera, vilket tillåter oss att utveckla ett tillvägagångssätt baserat på på djupa generativa modeller som bygger på faltningsnätverk. Genom att introducera detta tillvägagångssätt för tidsseriedata expanderar vi applicering av faltningsnätverk inom domänen för multivariat tidsserie, specifikt för användarinteraktionsdata. Vi använder ett tillvägagångssätt inspirerat av ramverket β-VAE i syfte att lära modellen gömda faktorer som definierar olika användarmönster. Vi utforskar olika värden för regulariseringsparametern β och visar att det är möjligt att konstruera en modell som lär sig en latent representation av identifierbara och multipla användarbeteenden. Vi visar med verklig data att modellen genererar realistiska exempel vilka i sin tur fångar statistiken på populationsnivå hos användarinteraktionsdatan, samt lär olika användarbeteenden och bidrar med precisa imputationer av saknad data.
23
Hale, P. "User driven modelling : visualisation and systematic interaction for end-user programming with tree-based structures." Thesis, University of the West of England, Bristol, 2012. http://eprints.uwe.ac.uk/17918/.
Full textAbstract:
This thesis addresses certain problems encountered by teams of engineers when modelling complex structures and processes subject to cost and other resource constraints. The cost of a structure or process may be ‘read off’ its specifying model, but the language in which the model is expressed (e.g. CAD) and the language in which resources may be modelled (e.g. spreadsheets) are not naturally compatible. This thesis demonstrates that a number of intermediate steps may be introduced which enable both meaningful translation from one conceptual view to another as well as meaningful collaboration between team members. The work adopts a diagrammatic modelling approach as a natural one in an engineering context when seeking to establish a shared understanding of problems. Thus, the research question to be answered in this thesis is: ‘To what extent is it possible to improve user-driven software development through interaction with diagrams and without requiring users to learn particular computer languages?’ The goal of the research is to improve collaborative software development through interaction with diagrams, thereby minimising the need for end-users to code directly. To achieve this aim a combination of the paradigms of End-User Programming, Process and Product Modelling and Decision Support, and Semantic Web are exploited and a methodology of User Driven Modelling and Programming (UDM/P) is developed, implemented, and tested as a means of demonstrating the efficacy of diagrammatic modelling. In greater detail, the research seeks to show that diagrammatic modelling eases problems of maintenance, extensibility, ease of use, and sharing of information. The methodology presented here to achieve this involves a three step translation from a visualised ontology, through a modelling tool, to output to interactive visualisations. An analysis of users groups them into categories of system creator, model builder, and model user. This categorisation corresponds well with the three-step translation process where users develop the ontology, modelling tool, and visualisations for their problem. This research establishes and exemplifies a novel paradigm of collaborative end-user programming by domain experts. The end-user programmers can use a visual interface where the visualisation of the software exactly matches the structure of the software itself, making translation between user and computer, and vice versa, much more direct and practical. The visualisation is based on an ontology that provides a representation of the software as a tree. The solution is based on translation from a source tree to a result tree, and visualisation of both. The result tree shows a structured representation of the model with a full visualisation of all parts that leads to the computed result. In conclusion, it is claimed that this direct representation of the structure enables an understanding of the program as an ontology and model that is then visualised, resulting in a more transparent shared understanding by all users. It is further argued that our diagrammatic modelling paradigm consequently eases problems of maintenance, extensibility, ease of use, and sharing of information. This method is applicable to any problem that lends itself to representation as a tree. This is considered a limitation of the method to be addressed in a future project.
24
Sutton, T. P. "Integrated species distribution modelling system : a user friendly front end to the GARP modelling toolkit." Thesis, Stellenbosch : Stellenbosch University, 2004. http://hdl.handle.net/10019.1/53748.
Full textAbstract:
Thesis (MA)--Stellenbosch University, 2004.ENGLISH ABSTRACT: At a social, ecological and biological level it is important tha t we gain a better understanding of species distribution and the constraints to species distribution. Various modelling tools and approaches are available to provide this type of functionality. The GARP (Genetic Algorithm for Rule set Production) Modelling System (GMS) was selected because of its strong predictive modelling abilities and its ability to represent the results of model iterations in both a tabular and cartographic manner. A shortcoming in this system was identified in tha t it requires strong information technology skills in order to carry out the modelling process. This can be attributed to the lack of a user-friendly interface to the system. In order to address this a loosely coupled system was developed that provides an easy to use web-based front end to the GMS. This Integrated Modelling System extends the core functionality of the GMS by providing a system that provides detailed history for each analysis, allows fine tuning of the modelling process, integrates directly with a biodiversity database containing specimen observations, and provides a simple ‘wizard’ interface to the modelling process.
AFRIKAANSE OPSOMMING: Van ’n sosiale, ekologiese en biologiese standpunt is dit belangrik dat ons spesies verspreiding en die beperkings daarvan verstaan. ’n Verskeidenheid sagteware pakkette en metodologiee is beskikbaar om spesies verspreiding te modelleer. Die GARP (Genetic Algorithm for Rule set Production) sagteware was gebruik vir sy sterk voorspellingsvermoe, en sy kapasiteit vir kartografiese en tubulere tentoonstelling van model resultate. ’n Tekortkoming met hierdie stelsel was gei'dentifiseer - dit is nie gebruikersvriendelik nie en gebruikers het sterk informasie tegnologie vermoens nodig. Om hierdie tekortkominge aan te spreek was ’n sagteware program ontwerp wat van GARP gebruik maak deur middel van ’n webblaaier. Hierdie ge'integreerde stelsel bou op die basiese funksionaliteit van GARP om ’n werk omgewing te skep wat ’n gedetailleerde geskiedenis van elke model stoor, fyn beheer oor die model toelaat, direk met ’n bio diver siteits databasis koppel, en van ’n eenvoudige ’wizard’ stelsel gebruik maak om gebruikers opsies te bepaal.
25
Song, Wei. "User-driven quality of experience modelling for mobile video optimisation." Thesis, Queensland University of Technology, 2012. https://eprints.qut.edu.au/59518/1/Wei_Song_Thesis.pdf.
Full textAbstract:
The increasing demand for mobile video has attracted much attention from both industry and researchers. To satisfy users and to facilitate the usage of mobile video, providing optimal quality to the users is necessary. As a result, quality of experience (QoE) becomes an important focus in measuring the overall quality perceived by the end-users, from the aspects of both objective system performance and subjective experience. However, due to the complexity of user experience and diversity of resources (such as videos, networks and mobile devices), it is still challenging to develop QoE models for mobile video that can represent how user-perceived value varies with changing conditions. Previous QoE modelling research has two main limitations: aspects influencing QoE are insufficiently considered; and acceptability as the user value is seldom studied. Focusing on the QoE modelling issues, two aims are defined in this thesis: (i) investigating the key influencing factors of mobile video QoE; and (ii) establishing QoE prediction models based on the relationships between user acceptability and the influencing factors, in order to help provide optimal mobile video quality.
To achieve the first goal, a comprehensive user study was conducted. It investigated the main impacts on user acceptance: video encoding parameters such as quantization parameter, spatial resolution, frame rate, and encoding bitrate; video content type; mobile device display resolution; and user profiles including gender, preference for video content, and prior viewing experience. Results from both quantitative and qualitative analysis revealed the significance of these factors, as well as how and why they influenced user acceptance of mobile video quality.
Based on the results of the user study, statistical techniques were used to generate a set of QoE models that predict the subjective acceptability of mobile video quality by using a group of the measurable influencing factors, including encoding parameters and bitrate, content type, and mobile device display resolution. Applying the proposed QoE models into a mobile video delivery system, optimal decisions can be made for determining proper video coding parameters and for delivering most suitable quality to users. This would lead to consistent user experience on different mobile video content and efficient resource allocation.
The findings in this research enhance the understanding of user experience in the field of mobile video, which will benefit mobile video design and research. This thesis presents a way of modelling QoE by emphasising user acceptability of mobile video quality, which provides a strong connection between technical parameters and user-desired quality. Managing QoE based on acceptability promises the potential for adapting to the resource limitations and achieving an optimal QoE in the provision of mobile video content.
26
Tzanavari, Aimilia. "User modeling for intelligent human-computer interaction." Thesis, University of Bristol, 2001. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.364961.
Full text
27
Cunningham, James Alexander. "Modelling knowledge through user focused design in knowledge management applications." Thesis, University of Salford, 2009. http://usir.salford.ac.uk/26630/.
Full textAbstract:
Knowledge management, as an organisational management technique, aims to capture the knowledge of the members of an organisation and to distribute it among those members in a way which encourages new knowledge to emerge. Software, explicitly designed to aid these goals, is seen as a useful tool for knowledge management. The core focus in the design of such software is in creating structures which allow the knowledge being captured to be represented in the software. However this ability to represent knowledge, on its own, will only serve to make explicit what is already there and will not provide the ability to capture new knowledge in different forms to the knowledge already represented. This thesis examines the question of how best to resolve this apparent conflict through the construction of an argument that rethinks the role of the end user and their relationship to software design in knowledge management, along with the development of a knowledge management-specific software development methodology. Through an in-depth analysis of the 'eCognos' project, which aimed to provide knowledge management software for the construction domain, the notion that a key aspect of knowledge management software design must be the realisation that modelling specifically against a single domain will lead to the development of software artefacts which fundamentally constrain their goal of enabling knowledge management is explored.
28
Vrhovski, DrazÌŒen. "Simulation modelling of satellite positioning for urban road user charging." Thesis, University of Nottingham, 2005. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.420392.
Full text
29
Pedley, A. G. "User defined feature modelling : representing extrinsic form, dimensions and tolerances." Thesis, University of Edinburgh, 1997. http://hdl.handle.net/1842/15622.
Full textAbstract:
The aim of the work is to provide better computer aided support for design and manufacturing in order to enhance process integration, reduce product development cycles, increase quality and lower costs, thereby raising commercial competitiveness. Feature Modelling is accepted as an aid to process integration and simultaneous engineering strategies. However, there are a number of problems restricting the impact of feature modelling technology in Computer Aided Design and Manufacturing. There is a considerable legacy of purely volume based models. Libraries of predefined features are too restrictive. There are no standards for the exchange of user defined feature models. Engineering drawings are provided in 2D representations separate from the feature model. Tolerances and dimensions are generally applied to engineering drawings, hence are not homogeneous with the three-dimensional (3D) shape model which precludes the development of variational models and enhanced design and manufacturing analysis. User defined feature functionally has been neglected. The following objectives have been undertaken in this work in order to address the above problems: Development of methods to model user defined features with extrinsically defined form; Implementation of a 3D dimension and tolerance system associated with solid and features models; Establishment of techniques to control a feature's parameters through the use of dimensions; Investigation of structures for the exchange of user defined feature models. Extrinsic form features have been developed that allow the integration of objects from many different sources within the feature model that can be swept to create free form geometry. Any solid or feature model may have associative dimensions and tolerances applied which are visualised as part of the 3D model. The template definition of a feature has been extended to enable dimensions representing a features size parameters to be described; these dimensions can be used to control the model. The dimensions and geometric tolerances have been implemented as features belonging to separate workpieces creating a hyper feature model. Dimensional tolerances have been implemented as attributes of the dimensions. Parallel geometric tolerances have been found to behave as 3D constraints. The feature and accuracy model has been output to manufacturing software applications.
30
Sarabia, Del Castillo Miguel. "User modelling for robotic companions using stochastic context-free grammars." Thesis, Imperial College London, 2015. http://hdl.handle.net/10044/1/29421.
Full textAbstract:
Creating models about others is a sophisticated human ability that robotic companions need to develop in order to have successful interactions. This thesis proposes user modelling frameworks to personalise the interaction between a robot and its user and devises novel scenarios where robotic companions may apply these user modelling techniques. We tackle the creation of user models in a hierarchical manner, using a streamlined version of the Hierarchical Attentive Multiple-Models for Execution and Recognition (HAMMER) architecture to detect low-level user actions and taking advantage of Stochastic Context-Free Grammars (SCFGs) to instantiate higher-level models which recognise uncertain and recursive sequences of low-level actions. We discuss a couple of distinct scenarios for robotic companions: a humanoid sidekick for power-wheelchair users and a companion of hospital patients. Next, we address the limitations of the previous scenarios by applying our user modelling techniques and designing two further scenarios that fully take advantage of the user model. These scenarios are: a wheelchair driving tutor which models the user abilities, and the musical collaborator which learns the preferences of its users. The methodology produced interesting results in all scenarios: users preferred the actual robot over a simulator as a wheelchair sidekick. Hospital patients rated positively their interactions with the companion independently of their age. Moreover, most users agreed that the music collaborator had become a better accompanist with our framework. Finally, we observed that users' driving performance improved when the robotic tutor instructed them to repeat a task. As our workforce ages and the care requirements in our society grow, robots will need to play a role in helping us lead better lives. This thesis shows that, through the use of SCFGs, adaptive user models may be generated which then can be used by robots to assist their users.
31
Mohamed, Soha. "Spatiotemporal user and place modelling on the geo-social web." Thesis, Cardiff University, 2017. http://orca.cf.ac.uk/98190/.
Full textAbstract:
Users of Location-Based Social Networks (LBSN) are giving away information about their whereabouts, and their interactions in the geographic space. In comparison to other types of personal data, location data are sensitive and can reveal user’s daily routines, activities, experiences and interests in the physical world. As a result, the user is facing an information overload that overburdens him to make a satisfied decision on where to go or what to do in a place. Thus, finding the matching places, users and content is one of the key challenges in LSBNs. This thesis investigates the different dimensions of data collected on LBSNs and proposes a user and place modelling framework. In particular, this thesis proposes a novel approach for the construction of different views of personal user profiles that reflect their interest in geographic places, and how they interact with geographic places. Three novel modelling frameworks are proposed, the static user model, the dynamic user model and the semantic place model. The static user model is a basic model that is used to represent the overall user interactions towards places. On the other hand, the dynamic user model captures the change of the user’s preferences over time. The semantic place model identifies user activities in places and models the relationships between places, users, implicit place types, and implicit activities. The proposed models demonstrate how geographic place characteristics as well as implicit user interactions in the physical space can further enrich the user profiles. The enrichment method proposed is a novel method that combines the semantic and the spatial influences into user profiles. Evaluation of the proposed methods is carried out using realistic data sets collected from the Foursquare LBSN. A new Location and content recommendation methods are designed and implemented to enhance existing location recommendation methods and results showed the usefulness of considering place semantics and the time dimension when the proposed user profiles in recommending locations and content. The thesis considers two further related problems; namely, the construction of dynamic place profiles and computing the similarity between users on LBSN. Dynamic place profiles are representations of geographic places through users’ interaction with the places. In comparison to static place models represented in gazetteers and map databases, these place profiles provide a dynamic view of how the places are used by actual people visiting and interacting with places on the LBSN. The different views of personal user profiles constructed within our framework are used for computing the similarity between users on the LBSN. Temporal user similarities on both the semantic and spatial levels are proposed and evaluated. Results of this work show the challenges and potential of the user data collected on LBSN.
32
Ingmarsson, Magnus. "Modelling User Tasks and Intentions for Service Discovery in Ubiquitous Computing." Licentiate thesis, Linköping University, Linköping University, MDA - Human Computer Interfaces, 2007. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-8319.
Full textAbstract:
Ubiquitous computing (Ubicomp) increases in proliferation. Multiple and ever growing in numbers, computational devices are now at the users' disposal throughout the physical environment, while simultaneously being effectively invisible. Consequently, a significant challenge is service discovery. Services may for instance be physical, such as printing a document, or virtual, such as communicating information. The existing solutions, such as Bluetooth and UPnP, address part of the issue, specifically low-level physical interconnectivity. Still absent are solutions for high-level challenges, such as connecting users with appropriate services. In order to provide appropriate service offerings, service discovery in Ubicomp must take the users' context, tasks, goals, intentions, and available resources into consideration. It is possible to divide the high-level service-discovery issue into two parts; inadequate service models, and insufficient common-sense models of human activities.
This thesis contributes to service discovery in Ubicomp, by arguing that in order to meet these high-level challenges, a new layer is required. Furthermore, the thesis presents a prototype implementation of this new service-discovery architecture and model. The architecture consists of hardware, ontology-layer, and common-sense-layer. This work addresses the ontology and common-sense layers. Subsequently, implementation is divided into two parts; Oden and Magubi. Oden addresses the issue of inadequate service models through a combination of service-ontologies in concert with logical reasoning engines, and Magubi addresses the issue of insufficient common-sense models of human activities, by using common sense models in combination with rule engines. The synthesis of these two stages enables the system to reason about services, devices, and user expectations, as well as to make suitable connections to satisfy the users' overall goal.
Designing common-sense models and service ontologies for a Ubicomp environment is a non-trivial task. Despite this, we believe that if correctly done, it might be possible to reuse at least part of the knowledge in different situations. With the ability to reason about services and human activities it is possible to decide if, how, and where to present the services to the users. The solution is intended to off-load users in diverse Ubicomp environments as well as provide a more relevant service discovery.
Report code: LiU-Tek-Lic-2007:14.
33
Sule, Mary-Jane. "Trusted cloud computing modelling with distributed end-user attestable multilayer security." Thesis, Brunel University, 2016. http://bura.brunel.ac.uk/handle/2438/12893.
Full textAbstract:
As cloud computing continues to gain popularity and its economies of scale continue to improve, stakeholders want to minimise the security risk, protect their data and other resources while maximising the gains of using any cloud resources and its application. It is predicted that by the end of 2017, bulk of spending on any IT infrastructure would be on cloud infrastructure and services as many critical applications – power, medical, finance among others continue to be migrated onto cloud platforms. For these sectors, the security challenges of cloud adoption continue to be of a great concern even with its benefits. The ability to trust and measure security levels of any cloud platform is paramount in the complete adoption and use of cloud computing in many mission critical sectors. In-depth study and analysis of the trustworthiness of various cloud based platforms/systems are often limited by the complex and dynamic nature of cloud and often do not correctly foresee or practically determine the varying trust relationship between and across the cloud layers, components (schedulers), algorithms and applications especially at a large scale. Tradition security and privacy controls continue to be implemented on cloud but due to its fluid and dynamic nature, research work in the area of end-user attestable trust evaluation of the cloud platform is limited. Most of the current simulation tools do not cater for modelling of Trust on scalable multi-layer cloud deployments (including workflow and infrastructure).Even as these tools continue to be implemented none has been used to cater for all the layers of the cloud platform. This research presents a deployment of trusted computing applied in cloud computing suited for mission critical applications. It attempts to simplify the integration of trusted platform module based integrity measurement into cloud infrastructure. Using Eucalyptus cloud software on server-grade hardware, a trusted community cloud platform was deployed on the Brunel Network as presented in Chapter 3. Security is enhanced by the integration of an end-user accessible TPM integrity measurement and verification process; this guarantees trusted ownership and integrity of the uploaded data and provides additional level of trust for the cloud platform. This research further presents a technique which allows data owners to first secure their data offline by inserting colour drops into the data using steganography. The colour drops are used to detect unauthorised modifications, verify data owner in the event the copyright of the data is in dispute and identify the path through which it was tampered with. This process ensures integrity and confidentiality of the resources. This thesis also presents a trust model using fuzzy logic which was simulated using Simulink in Matlab and subsequently evaluated on an experimental platform deployed on the Brunel network. Using this model, end-users can determine the trust values for a cloud platform or service, as well as, classify and compare various cloud platforms. The results obtained suggest that the outputs of this research work can improve end-user confidence when selecting or consuming cloud resources with enhanced data integrity and protection.
34
Idaewor, Patricia Fatima Renua. "Transport user satisfaction modelling : application to the brokerage vehicle selection process." Thesis, University College London (University of London), 2005. http://discovery.ucl.ac.uk/1444425/.
Full textAbstract:
General customer satisfaction studies link use and reuse of a commodity or service to the extent to which customers are satisfied. There is currently great interest in increasing transport accessibility, which in this context consists of the ease of reaching and using transport, and thus means are being devised to increase both the use and reuse of transport. This thesis investigates the use of customer satisfaction models in relation to the use and reuse of transport services. Much of the transport for people with restricted mobility is provided by the Community Transport sector where the criteria for vehicle selection in relation to a particular person's proposed journey are currently vehicle availability, costs and time constraints, and the matching of passenger disability and vehicle capability. Beyond requirements related to the barriers to access found in the transport system, transport users do have other needs and preferences, such as safety, comfort, convenience, friendly crew, reliability, etc., that can affect their satisfaction with the service provided. Unfortunately, such a multi-criteria decision process makes it difficult for community transport managers and operators to take these preferences into consideration systematically when allocating transport to individuals. This thesis develops a predictive model of transport satisfaction that can be used in such transport provision decision-making. A comprehensive list of travel attributes affecting transport-user satisfaction has been derived from the literature and confirmed through group interviews. For each of these attributes, a predictive model of satisfaction based on the level of service of the attribute, the user's prior transport experience and socio-demographic characteristics, has been derived. An overall transport satisfaction model has been developed from a combination of the individual attribute satisfactions. The model was validated by comparing its output to an independent dataset and a high level of similarity was observed. In addition, a framework for such a decision-making process for a community transport brokerage has been designed.
35
Dungs, Sebastian Verfasser], and Norbert [Akademischer Betreuer] [Fuhr. "Modelling temporal patterns in user behaviour / Sebastian Dungs ; Betreuer: Norbert Fuhr." Duisburg, 2019. http://d-nb.info/1191693384/34.
Full text
36
Hauthal, Eva. "Detection, Modelling and Visualisation of Georeferenced Emotions from User-Generated Content." Doctoral thesis, Saechsische Landesbibliothek- Staats- und Universitaetsbibliothek Dresden, 2015. http://nbn-resolving.de/urn:nbn:de:bsz:14-qucosa-163847.
Full textAbstract:
In recent years emotion-related applications like smartphone apps that document and analyse the emotions of the user, have become very popular. But research also can deal with human emotions in a very technology-driven approach. Thus space-related emotions are of interest as well which can be visualised cartographically and can be captured in different ways. The research project of this dissertation deals with the extraction of georeferenced emotions from the written language in the metadata of Flickr and Panoramio photos, thus from user-generated content, as well as with their modelling and visualisation. Motivation is the integration of an emotional component into location-based services for tourism since only factual information is considered thus far although places have an emotional impact. The metadata of those user-generated photos contain descriptions of the place that is depicted within the respective picture. The words used have affective connotations which are determined with the help of emotional word lists. The emotion that is associated with the particular word in the word list is described on the basis of the two dimensions ‘valence’ and ‘arousal’. Together with the coordinates of the respective photo, the extracted emotion forms a georeferenced emotion. The algorithm that was developed for the extraction of these emotions applies different approaches from the field of computer linguistics and considers grammatical special cases like the amplification or negation of words. The algorithm was applied to a dataset of Flickr and Panoramio photos of Dresden (Germany). The results are an emotional characterisation of space which makes it possible to assess and investigate specific features of georeferenced emotions. These features are especially related to the temporal dependence and the temporal reference of emotions on one hand; on the other hand collectively and individually perceived emotions have to be distinguished. As a consequence, a place does not necessarily have to be connected with merely one emotion but possibly also with several. The analysis was carried out with the help of different cartographic visualisations. The temporal occurrence of georeferenced emotions was examined detailed. Hence the dissertation focuses on fundamental research into the extraction of space-related emotions from georeferenced user-generated content as well as their visualisation. However as an outlook, further research questions and core themes are identified which arose during the investigations. This shows that this subject is far from being exhaustedIn den letzten Jahren sind emotionsbezogene Anwendungen, wie Apps, die die Emotionen des Nutzers dokumentieren und analysieren, sehr populär geworden. Ebenfalls in der Forschung sind Emotionen in einem sehr technologiegetriebenen Ansatz ein Thema. So auch ortsbezogene Emotionen, die sich somit kartographisch darstellen lassen und auf verschiedene Art und Weisen gewonnen werden können. Das Forschungsvorhaben der Dissertation befasst sich mit der Extraktion von georeferenzierten Emotionen aus geschriebener Sprache unter Verwendung von Metadaten verorteter Flickr- und Panoramio-Fotos, d.h. aus nutzergenerierten Inhalten, sowie deren Modellierung und Visualisierung. Motivation hierfür ist die Einbindung einer emotionalen Komponente in ortsbasierte touristische Dienste, da diese bisher nur faktische Informationen berücksichtigen, obwohl Orte durchaus eine emotionale Wirkung haben. Die Metadaten dieser nutzergenerierten Inhalte stellen Beschreibungen des auf dem Foto festgehaltenen Ortes dar. Die dafür verwendeten Wörter besitzen affektive Konnotationen, welche mit Hilfe emotionaler Wortlisten ermittelt werden. Die Emotion, die mit dem jeweiligen Wort in der Wortliste assoziiert wird, wird anhand der zwei Dimensionen Valenz und Erregung beschrieben. Die extrahierten Emotionen bilden zusammen mit der geographischen Koordinate des jeweiligen Fotos eine georeferenzierte Emotion. Der zur Extraktion dieser Emotionen entwickelte Algorithmus bringt verschiedene Ansätze aus dem Bereich der Computerlinguistik zum Einsatz und berücksichtigt ebenso grammatikalische Sonderfälle, wie Intensivierung oder Negation von Wörtern. Der Algorithmus wurde auf einen Datensatz von Flickr- und Panoramio-Fotos von Dresden angewendet. Die Ergebnisse stellen eine emotionale Raumcharakterisierung dar und ermöglichen es, spezifische Eigenschaften verorteter Emotionen festzustellen und zu untersuchen. Diese Eigenschaften beziehen sich sowohl auf die zeitliche Abhängigkeit und den zeitlichen Bezug von Emotionen, als auch darauf, dass zwischen kollektiv und individuell wahrgenommenen Emotionen unterschieden werden muss. Das bedeutet, dass ein Ort nicht nur mit einer Emotion verbunden sein muss, sondern möglicherweise auch mit mehreren. Die Auswertung erfolgte mithilfe verschiedener kartographischer Visualisierungen. Eingehender wurde das zeitliche Auftreten der ortsbezogenen Emotionen untersucht. Der Fokus der Dissertation liegt somit auf der Grundlagenforschung zur Extraktion verorteter Emotionen aus georeferenzierten nutzergenerierten Inhalten sowie deren Visualisierung. Im Ausblick werden jedoch weitere Fragestellungen und Schwerpunkte genannt, die sich im Laufe der Untersuchungen ergeben haben, womit gezeigt wird, dass dieses Forschungsgebiet bei Weitem noch nicht ausgeschöpft ist
37
Fang, Anjie. "Analysing political events on Twitter : topic modelling and user community classification." Thesis, University of Glasgow, 2019. http://theses.gla.ac.uk/41135/.
Full textAbstract:
Recently, political events, such as elections or referenda, have raised a lot of discussions on social media networks, in particular, Twitter. This brings new opportunities for social scientists to address social science tasks, such as understanding what communities said, identify- ing whether a community has an influence on another or analysing how these communities respond to political events online. However, identifying these communities and extracting what they said from social media data are challenging and non-trivial tasks. In this thesis, we aim to make progress towards understanding 'who' (i.e. communities) said 'what' (i.e. discussed topics) and 'when' (i.e. time) during political events on Twitter. While identifying the 'who' can benefit from Twitter user community classification approaches, 'what' they said and 'when' can be effectively addressed on Twitter by extracting their discussed topics using topic modelling approaches that also account for the importance of time on Twitter. To evaluate the quality of these topics, it is necessary to investigate how coherent these topics are to humans. Accordingly, we propose a series of approaches in this thesis. First, we investigate how to effectively evaluate the coherence of the topics generated using a topic modelling approach. The topic coherence metric evaluates the topical coherence by examining the semantic similarity among words in a topic. We argue that the semantic similarity of words in tweets can be effectively captured by using word embeddings trained using a Twitter background dataset. Through a user study, we demonstrate that our proposed word embedding-based topic coherence metric can assess the coherence of topics like humans. In addition, inspired by the precision at k information retrieval metric, we propose to evaluate the coherence of a topic model (containing many topics) by averaging the top-ranked topics within the topic model. Our proposed metrics can not only evaluate the coherence of topics and topic models, but also can help users to choose the most coherent topics. Second, we aim to extract topics with a high coherence from Twitter data. Such topics can be easily interpreted by humans and they can assist to examine 'what' has been discussed on Twitter and 'when'. Indeed, we argue that topics can be discussed in different time periods and therefore can be effectively identified and distinguished by considering their time periods. Hence, we propose an effective time-sensitive topic modelling approach by integrating the time dimension of tweets (i.e. 'when'). We show that the time dimension helps to generate topics with a high coherence. Hence, we argue that 'what' has been discussed and 'when' can be effectively addressed by our proposed time-sensitive topic modelling approach. Next, to identify 'who' participated in the topic discussions, we propose approaches to identify the community affiliations of Twitter users, including automatic ground-truth generation approaches and a user community classification approach. To generate ground-truth data for training a user community classifier, we show that the mentioned hashtags and entities in the users' tweets can indicate which community a Twitter user belongs to. Hence, we argue that they can be used to generate the ground-truth data for classifying users into communities. On the other hand, we argue that different communities favour different topic discussions and their community affiliations can be identified by leveraging the discussed topics. Accordingly, we propose a Topic-Based Naive Bayes (TBNB) classification approach to classify Twitter users based on their words and discussed topics. We demonstrate that our TBNB classifier together with the ground-truth generation approaches can effectively identify the community affiliations of Twitter users. Finally, to show the generalisation of our approaches, we apply our approaches to analyse 3.6 million tweets related to US Election 2016 on Twitter. We show that our TBNB approach can effectively identify the 'who', i.e. classify Twitter users into communities by using hashtags and the discussed topics. To investigate 'what' these communities have discussed, we apply our time-sensitive topic modelling approach to extract coherent topics. We finally analyse the community-related topics evaluated and selected using our proposed topic coherence metrics. Overall, we contribute to provide effective approaches to assist social scientists towards analysing political events on Twitter. These approaches include topic coherence metrics, a time-sensitive topic modelling approach and approaches for classifying the community affiliations of Twitter users. Together they make progress to study and understand the connections and dynamics among communities on Twitter.
38
Al, Alshaikh Modhi. "Dynamic multi-concept user profile modelling in research paper recommender systems." Thesis, University of Brighton, 2018. https://research.brighton.ac.uk/en/studentTheses/8860a703-0d0b-49ef-aa00-ecece40d21d8.
Full textAbstract:
The internet and the digital libraries are major sources of information for researchers, and there is an enormous growth of information on these sources. A large number of research papers are available which leads to the information overload problem and hence finding research papers that are related to users’ interests become difficult and time consuming. The field of recommender systems aims to solve the information overload problem by filtering information and providing users with relevant results. Although the current recommender systems provide recommendation services to users, different limitations and challenges have not been adequately addressed in the research paper domain. The work presented in this thesis contributes to the development of models and algorithms to the recommender systems in the research paper domain. The main aim of this thesis is to develop a dynamic multiconcept system that is able to recommend research papers of interest at appropriate times. The first contribution of this thesis is modelling dynamic user profiles that are able to adapt to the changes in multiple user interests and to be compatible with the requirements of advanced ontologies. The second contribution is analysing users’ reading behaviour with research papers to develop novel short-term and long-term models that are able to adapt dynamically according to a user’s changing behaviour during his/her short and long term goals. These models can effectively learn different users’ reading behaviours implicitly without the need for any intervention from the user. The third contribution is predicting user’s future interests using a novel collaborative filtering approach without the need for the user ratings. All our proposed models are evaluated using offline evaluations with the BibSonomy dataset that contains actual users’ records. Our results show that our models outperform the baselines used for comparisons. Finally, we integrated our models to one unified dynamic hybrid system in order to provide recommendations which most closely represent the users’ research interests at particular times. The evaluation results indicate that the dynamic hybrid system that models and integrates multiple user interests and concepts can bring substantial benefits to a recommender system in the research paper domain.
39
Dungs, Sebastian [Verfasser], and Norbert [Akademischer Betreuer] Fuhr. "Modelling temporal patterns in user behaviour / Sebastian Dungs ; Betreuer: Norbert Fuhr." Duisburg, 2019. http://d-nb.info/1191693384/34.
Full text
40
Rawat, Rakesh. "User behaviour modelling in a multi-dimensional environment for personalization and recommendation." Thesis, Queensland University of Technology, 2010. https://eprints.qut.edu.au/48135/1/Rakesh_Rawat_Thesis.pdf.
Full textAbstract:
Handling information overload online, from the user's point of view is a big challenge, especially when the number of websites is growing rapidly due to growth in e-commerce and other related activities. Personalization based on user needs is the key to solving the problem of information overload. Personalization methods help in identifying relevant information, which may be liked by a user. User profile and object profile are the important elements of a personalization system. When creating user and object profiles, most of the existing methods adopt two-dimensional similarity methods based on vector or matrix models in order to find inter-user and inter-object similarity. Moreover, for recommending similar objects to users, personalization systems use the users-users, items-items and users-items similarity measures. In most cases similarity measures such as Euclidian, Manhattan, cosine and many others based on vector or matrix methods are used to find the similarities. Web logs are high-dimensional datasets, consisting of multiple users, multiple searches with many attributes to each. Two-dimensional data analysis methods may often overlook latent relationships that may exist between users and items. In contrast to other studies, this thesis utilises tensors, the high-dimensional data models, to build user and object profiles and to find the inter-relationships between users-users and users-items. To create an improved personalized Web system, this thesis proposes to build three types of profiles: individual user, group users and object profiles utilising decomposition factors of tensor data models. A hybrid recommendation approach utilising group profiles (forming the basis of a collaborative filtering method) and object profiles (forming the basis of a content-based method) in conjunction with individual user profiles (forming the basis of a model based approach) is proposed for making effective recommendations. A tensor-based clustering method is proposed that utilises the outcomes of popular tensor decomposition techniques such as PARAFAC, Tucker and HOSVD to group similar instances. An individual user profile, showing the user's highest interest, is represented by the top dimension values, extracted from the component matrix obtained after tensor decomposition. A group profile, showing similar users and their highest interest, is built by clustering similar users based on tensor decomposed values. A group profile is represented by the top association rules (containing various unique object combinations) that are derived from the searches made by the users of the cluster. An object profile is created to represent similar objects clustered on the basis of their similarity of features. Depending on the category of a user (known, anonymous or frequent visitor to the website), any of the profiles or their combinations is used for making personalized recommendations. A ranking algorithm is also proposed that utilizes the personalized information to order and rank the recommendations. The proposed methodology is evaluated on data collected from a real life car website. Empirical analysis confirms the effectiveness of recommendations made by the proposed approach over other collaborative filtering and content-based recommendation approaches based on two-dimensional data analysis methods.
41
Abbas, Ayman. "A modelling approach to individualised computer aided learning for geometric design." Thesis, University of Strathclyde, 1997. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.324096.
Full text
42
Mooney, Gabrielle Joanne. "Intelligent information retrieval from the World Wide Web using fuzzy user modelling." Thesis, De Montfort University, 1999. http://hdl.handle.net/2086/10685.
Full textAbstract:
This thesis investigates the application. of fuzzy logic techniques and user modelling to the process of information retrieval (IR) from the World Wide Web (WWW). The research issue is whether this process can be improved through such an application. The exponential rise of information itself as an invaluable global commodity, coupled with .acceierating development in. computing and telecommunications, and boosted by networked information sources such as the WWW, has led to the development of tools, such as search engines, to facilitate information search and retrieval. However, despite their sophistication, they are unable effectively to. address users' information. needs. Also, as the-WWW can be seen as a dynamic, continuously changing global information corpus, these tools suffer from the problems of irrelevancy and redundancy. Therefore, in order to overcome these problems and remain effective, IR systems need to become 'intelligent' in some way. It is from this premise that the focus of this research has developed. Initially, theoretical and investigative research into the areas ofIR from electronic sources and the nature of the Internet (including the WWW) revealed that highly sophisticated systems are being developed and there is a drive towards the integration of, for example, electronic libraries, COROM networks, and the WWW. Research into intelligent IR, the use of AI techniques to improve the IR process, informed an evaluation of various approaches. This revealed that a munber of techniques, for example, expert systems, neural networks and semantic networks, have been employed, with limited success. Owing to the nature of the WWW, though, many of the previous AI approaches are inapplicable as they rely too much on extensive knowledge of the retrieval corpus. However, the evaluation suggested that fuzzy logic, with its inherent ability to capture partial knowledge within fuzzy sets, is a valid approach. User modelling research indicated that adaptive user stereotypes are a fruitful way to represent different types of user and their information need. Here, these stereotypes are represented as fuzzy sets, ensuring flexibility and adaptivity. The goal of the reported research. then, was not to. develop an 'intelligent agent' but to apply fuzzy logic techniques and user modelling to the process of user query formulation, in order to test the research issue. This issue was whether the application of these techniques could improve the IR process. A prototype system, the Fuzzy Modelling Query Assistant (FMQA), was developed that attempts intelligently to assist the user in capturing their information need. The concept was to refine the user's query before submitting it to an existing search engine, in order to improve upon the IR results of using the search tool alone. To address the research issue, a user study of the FMQA was performed. The design and conduct is reported in depth. The study results were analysed and the findings are given. The results indicate that,. for certain types of user especially, the FMQA does provide improvement in the IR process, in terms of the results. There is a critical review of the research aims in the light of the results, conclusions are drawn and recommendations for future research given.
43
McIntyre-Bahatty, Yasen Timothy. "Neural network modelling, evaluation and end-user orientation in the financial markets." Thesis, University of Bristol, 1997. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.389130.
Full text
44
Kyriacou, Demetris. "Enriching lifelong user modelling in a social networking and e-commerce era." Thesis, University of Southampton, 2010. https://eprints.soton.ac.uk/141608/.
Full textAbstract:
Lifelong User Modelling is an area that aims at harvesting the massive volume of web-based user information, so that it can be used for educational long-term services. Although an amount of research has addressed this issue from an educational angle, by finding ways for educational peer systems to exchange data sets among them, little has been done to investigate the potential of the social networking and e-commerce domains in the Lifelong User Modelling vision to enable Lifelong Learning services to be used. This thesis presents a Scrutable User Modelling Infrastructure (SUMI) that can accommodate current social networking and e-commerce services for allowing the exchange of user data among these services and educational systems, for potentially improved personalisation services. Special focus has been given to three user modelling aspects: interoperability, scrutability and privacy. The suitability of SUMI regarding these aspects is tested by developing and evaluating a prototype service. The prototype SUMI service focuses on making the infrastructure scrutable, in terms of allowing users to have control of their imported models in SUMI, while also offering various controls for safeguarding the privacy of their information in SUMI. To assess our interoperability design decisions, four successful simulation tests have been conducted. To evaluate the proposed scrutability and privacy user privileges, two user-based evaluations have been carried out. For each evaluation, the method and results are described. Overall results have revealed that participants have expressed their general acceptance of having available such an infrastructure and service, while favouring a more holistic approach when exposed to such an environment.
45
Baslyman, Malak. "Activity-based Process Integration Framework to Improve User Satisfaction and Decision Support in Healthcare." Thesis, Université d'Ottawa / University of Ottawa, 2018. http://hdl.handle.net/10393/38104.
Full textAbstract:
Requirements Engineering (RE) approaches are widely used in several domains such as telecommunications systems, information systems, and even regulatory compliance. However, they are rarely applied in healthcare beyond requirements elicitation. Healthcare is a multidisciplinary environment in which clinical processes are often performed across multiple units. Introducing a new Information Technology (IT) system or a new process in such an environment is a very challenging task, especially in the absence of recognized RE practices. Currently, many IT systems are not welcomed by caregivers and are considered to be failures because they change what caregivers are familiar with and bring new tasks that often consume additional time.
This thesis introduces a new RE-based approach aiming to evaluate and estimate the potential impact of new system integrations on current practices, organizational goals,and user satisfaction using goal modelling and process modelling techniques. This approach is validated with two case studies conducted in real hospitals and a usability study involving healthcare practitioners. The contributions of the thesis are:
• Major: a novel Activity-based Process Integration (AbPI) framework that enables the integration of a new process into existing practices incrementally, in a way that permits continuous analysis and evaluation. AbPI also provides several alternatives to a given integration to ensure effective flowing and minimal disturbance to current practices. AbPI has a Goal Integration Method to integrate new goals, an Integration Method to integrate new processes, and an Alternative Evaluation Method exploiting multi-criteria decision-making algorithms to select among strategies.
The modelling concepts of AbPI are supported by a profile of the User Requirements Notation augmented with a new distance-based goal-oriented approach to alternative selection and a new data-quality-driven algorithm for the propagation of confidence levels in goal models.
• Minor: a usability study of AbPI to investigate the usefulness of the framework in a healthcare context. This usability study is part of the validation and is also a minor contribution due to: 1) the lack of usability studies when proposing requirements engineering frameworks, and 2) an intent to discover the potential usefulness of the framework in a context where recognized RE practices are seldom used.
46
Kinley, Khamsum. "Towards modelling web search behaviour : integrating users’ cognitive styles." Thesis, Queensland University of Technology, 2013. https://eprints.qut.edu.au/63804/1/Kinley_Kinley_Thesis.pdf.
Full textAbstract:
With the rapid growth of information on the Web, the study of information searching has let to an increased interest. Information behaviour (IB) researchers and information systems (IS) developers are continuously exploring user - Web search interactions to understand and to help users to provide assistance with their information searching. In attempting to develop models of IB, several studies have identified various factors that govern user's information searching and information retrieval (IR), such as age, gender, prior knowledge and task complexity. However, how users' contextual factors, such as cognitive styles, affect Web search interactions has not been clearly explained by the current models of Web Searching and IR.
This study explores the influence of users' cognitive styles on their Web search behaviour. The main goal of the study is to enhance Web search models with a better understanding of how these cognitive styles affect Web searching. Modelling Web search behaviour with a greater understanding of user's cognitive styles can help information science researchers and IS designers to bridge the semantic gap between the user and the IS. To achieve the aims of the study, a user study with 50 participants was conducted. The study adopted a mixed method approach incorporating several data collection strategies to gather a range of qualitative and quantitative data. The study utilised pre-search and post-search questionnaires to collect the participants' demographic information and their level of satisfaction about the search interactions. Riding's (1991) Cognitive Style Analysis (CSA) test was used to assess the participants' cognitive styles. Participants completed three predesigned search tasks and the whole user - web search interactions, including thinkaloud, were captured using a monitoring program. Data analysis involved several qualitative and quantitative techniques: the quantitative data gave raise to detailed findings about users' Web searching and cognitive styles, the qualitative data enriched the findings with illustrative examples.
The study results provide valuable insights into Web searching behaviour among different cognitive style users. The findings of the study extend our understanding of Web search behaviour and how users search information on the Web. Three key study findings emerged: • Users' Web search behaviour was demonstrated through information searching strategies, Web navigation styles, query reformulation behaviour and information processing approaches while performing Web searches. The manner in which these Web search patterns were demonstrated varied among the users with different cognitive style groups.
• Users' cognitive styles influenced their information searching strategies, query reformulation behaviour, Web navigational styles and information processing approaches. Users with particular cognitive styles followed certain Web search patterns.
• Fundamental relationships were evident between users' cognitive styles and their Web search behaviours; and these relationships can be illustrated through modelling Web search behaviour. Two models that depict the associations between Web search interactions, user characteristics and users' cognitive styles were developed. These models provide a greater understanding of Web search behaviour from the user perspective, particularly how users' cognitive styles influence their Web search behaviour.
The significance of this research is twofold: it will provide insights for information science researchers, information system designers, academics, educators, trainers and librarians who want to better understand how users with different cognitive styles perform information searching on the Web; at the same time, it will provide assistance and support to the users. The major outcomes of this study are 1) a comprehensive analysis of how users search the Web; 2) extensive discussion on the implications of the models developed in this study for future work; and 3) a theoretical framework to bridge high-level search models and cognitive models.
47
Clark, Graham Adrian. "An intelligent modelling interface for process simulators in process industries." Thesis, Loughborough University, 2001. https://dspace.lboro.ac.uk/2134/7562.
Full textAbstract:
Over the past three decades, modelling packages for chemical processes have become more advanced and widely used. For example, equation-oriented dynamic simulators, such as gPROMS are useful for simulating plantwide processes as well as unit operations, and are widely used by process engineers. Whereas, other types of simulator (e.g. Simulink) are often used by control engineers to solve complex control problems. However, both these types of simulator rely on the user being proficient in modelling and familiar with their syntax beforehand. A useful development would be the integration of some knowledge into the formation of the process models and automatic syntax code generation. This would lead to the design engineers having a library of knowledge to check on first, much as an expert engineer uses their past experiences to help guide them through a design. If this could be incorporated into a modelling interface this would greatly help the design engineer, especially when tackling problems in areas that they have little, or no experience. The thesis addresses this problem and describes the design of an intelligent modelling interface that incorporates a knowledge base using some form of a priori case library and recall facility. The interface also incorporates an automatic input file generation stage. At present, the user can: specify a single unit operation problem to search for, retrieve similar cases from the database, specify their solution in the database based on past cases and experience, and then automatically generate an input file for either gPROMS or Simulink. These features are demonstrated through four case studies.
48
Titidezh, Omid. "Assessing transport accessibility for healthcare facility reconfiguration using GIS and multilevel modelling." Thesis, Loughborough University, 2012. https://dspace.lboro.ac.uk/2134/12355.
Full textAbstract:
Transport accessibility to healthcare facilities is a major issue in the United Kingdom, as recently demonstrated by the shift away from providing healthcare in acute hospitals to care closer to home . Common measures of accessibility focus on the creation of distance or travel time contours around a destination and devote less attention to individual differences such as user perceptions, their transport usage, and area-wide factors including income deprivation, safety and security. Failure to account for such factors may result in imperfect decision making in terms of healthcare relocation and reconfiguration. This thesis therefore aims to develop a user-based accessibility model by focusing on both individual socio-economic (e.g. age, gender, access to transport modes) and area-wide characteristics (e.g. income deprivation, public transport provision, safety and security). In order to identify important factors that affect accessibility and to develop the user-based accessibility model, two revealed preference questionnaire surveys were undertaken at Loughborough and Hinckley. The purpose of the first questionnaire was to understand underlying factors affecting accessibility to a healthcare facility. The results revealed that both individual and area-wide factors affect transport accessibility to a healthcare facility. The purpose of the second questionnaire was conducted to capture data relating to users perception of accessibility and their socio-economic factors so as to develop a user-perception based accessibility model. Network-based travel time and travel distance as well as public transport provision data from a respondent home to a healthcare facility were generated using a GIS technique. Individual-level questionnaire data were then integrated with the other secondary datasets (e.g. Census, Index of Multiple Deprivation, Accidents) using postcodes of survey respondents. Both single-level and multilevel mixed-effects linear regression models were employed to develop a relationship between user-perceptions relating to accessibility and the factors influencing accessibility. Multilevel models that can control data from the two levels (i.e. individuals nested within local areas) provided better goodness-of-fit statistics compared with those of single-level regression models. The results indicate that travel distance by car, number of available direct bus services, age, and destination choices affect user-perceptions of accessibility to a healthcare facility. For instance, if travel distance by car increases by one mile then the perception of accessibility to a healthcare facility decreases by four units (on a scale of 0-100). Surprisingly, many area-wide factors such as security and safety, income deprivation were found to be statistically insignificant. In order to see which healthcare facility is more accessible, calibrated multilevel models along with number of people within the catchment area were then employed to predict the overall accessibility score related to a healthcare facility. This is important for policy makers in healthcare facility relocation and reconfiguration with respect to user perception of transport accessibility. Also it would be valuable to organisations that need to make decisions based on their users perceptions who are the real decision makers as to whether to use a facility or not.
49
Tsagkarakis, George. "Domestic demand and network management in a user-inclusive electrical load modelling framework." Thesis, University of Edinburgh, 2015. http://hdl.handle.net/1842/16207.
Full textAbstract:
Interest has been growing in the interaction of various power demand transformations, such as demand side management (DSM) and voltage control, with the power demand. Initial studies have highlighted the need for a better understanding of the power demand of low voltage (LV) residential networks. Furthermore, it is expected that future alteration of the residential appliance mixture, because of the advances in technology, will have an impact on both the demand curve as well as the electrical characteristics. This thesis presents a study of the impact of current and future household load on the power demand curve and the network operation. In order to achieve this, a bottom-up load modelling tool was developed to create LV detailed demand profiles that include not only the active and reactive power demand, but their electrical characteristics as well. The methodology uses a Markov chain Monte Carlo approach to generate residential LV demand profiles taking into account the user activity and behaviour to represent UK population. An appliance database has also been created which corresponds to the UK residential appliance mixture in order to calculate more accurately the power demand. The main advantages of the approach presented here are the flexibility in altering the type and number of the appliances that populate a household and how easily it can be adapted to a different population, location and climate. The tool is used to investigate the impact of scenarios that simulate future load replacement and the network behaviour under certain methods of demand control, implementation of DSM and control of voltage on the secondary of the LV transformer. The algorithm that was developed to apply the DSM actions on the power demand focused on the management of individual loads. The drivers used in this approach were the financial and environmental benefit of customers and the increase in the quality of the network operation. The control of the voltage as a method for power reduction takes into account the voltage dependence of the demand. The primary target is to quantify the benefits of this strategy either in combination with DSM for higher power reduction during the peak hours or on the current network as a quicker, easier and less expensive alternative to DSM. The study shows that there is a significant power reduction in both cases which is dependent on the time of day and not constant as expected from the literature. The results show that there are significant differences between current and future load demand characteristics that would be very difficult to acquire without the modelling technique presented. The alternative solution would require extensive local load and network modifications and a long period of expensive tests and measurements in the field.
50
Janarthanam, Srinivasan Chandrasekaran. "Learning user modelling strategies for adaptive referring expression generation in spoken dialogue systems." Thesis, University of Edinburgh, 2011. http://hdl.handle.net/1842/5033.
Full textAbstract:
We address the problem of dynamic user modelling for referring expression generation in spoken dialogue systems, i.e how a spoken dialogue system should choose referring expressions to refer to domain entities to users with different levels of domain expertise, whose domain knowledge is initially unknown to the system. We approach this problem using a statistical planning framework: Reinforcement Learning techniques in Markov Decision Processes (MDP). We present a new reinforcement learning framework to learn user modelling strategies for adaptive referring expression generation (REG) in resource scarce domains (i.e. where no large corpus exists for learning). As a part of the framework, we present novel user simulation models that are sensitive to the referring expressions used by the system and are able to simulate users with different levels of domain knowledge. Such models are shown to simulate real user behaviour more closely than baseline user simulation models. In contrast to previous approaches to user adaptive systems, we do not assume that the user’s domain knowledge is available to the system before the conversation starts. We show that using a small corpus of non-adaptive dialogues it is possible to learn an adaptive user modelling policy in resource scarce domains using our framework. We also show that the learned user modelling strategies performed better in terms of adaptation than hand-coded baselines policies on both simulated and real users. With real users, the learned policy produced around 20% increase in adaptation in comparison to the best performing hand-coded adaptive baseline. We also show that adaptation to user’s domain knowledge results in improving task success (99.47% for learned policy vs 84.7% for hand-coded baseline) and reducing dialogue time of the conversation (11% relative difference). This is because users found it easier to identify domain objects when the system used adaptive referring expressions during the conversations.