Browsing by Author "Nugent, Chris"

Now showing 1 - 20 of 64
  • No Thumbnail Available
    ItemMetadata only
    Activity Recognition in Pervasive Intelligent Environments
    (Atlantis Press, 2011) Chen, Liming; Nugent, Chris; Biswas, J.; Hoey, J.
    This book consists of a number of chapters addressing different aspects of activity recognition, roughly in three main categories of topics. The first topic will be focused on activity modeling, representation and reasoning using mathematical models, knowledge representation formalisms and AI techniques. The second topic will concentrate on activity recognition methods and algorithms. Apart from traditional methods based on data mining and machine learning, we are particularly interested in novel approaches, such as the ontology-based approach, that facilitate data integration, sharing and automatic/automated processing. In the third topic we intend to cover novel architectures and frameworks for activity recognition, which are scalable and applicable to large scale distributed dynamic environments. In addition, this topic will also include the underpinning technological infrastructure, i.e. tools and APIs, that supports function/capability sharing and reuse, and rapid development and deployment of technological solutions. The fourth category of topic will be dedicated to representative applications of activity recognition in intelligent environments, which address the life cycle of activity recognition and their use for novel functions of the end-user systems with comprehensive implementation, prototyping and evaluation. This will include a wide range of application scenarios, such as smart homes, intelligent conference venues and cars.
  • No Thumbnail Available
    ItemMetadata only
    Ambient Assisted Living and Daily Activities
    (Springer, 2014-12) Pecchia, Leandro; Chen, Liming; Nugent, Chris; Bravo, Jose
    This book constitutes the refereed proceedings of the 6th International Workshop on Ambient Assisted Living, IWAAL 2014, held in Belfast, UK, in December 2014. The 42 full papers presented with 12 papers of the workshop WAGER 2014 and 10 papers of a special session HTA were carefully reviewed and selected from numerous submissions. The focus of the papers is on following topics: ADL detection, recognition, classification; behavioural changes, coaching and education; AAL design and technical evaluation; expression, mood and speech recognition; health monitoring, risk prediction and assessment; localization; and user preferences, usability, AAL acceptance and adoption.
  • Thumbnail Image
    ItemEmbargo
    An approach to provide dynamic, illustrative, video-based guidance within a goal-driven smart home
    (Springer, 2016-10-27) Rafferty, Joseph; Nugent, Chris; Liu, Jun; Chen, Liming
    The global population is aging in a never-before seen way, introducing an increasing ageing-related cognitive ailments, such as dementia. This aging is coupled with a reduction in the global support ratio, reducing the availability of formal and informal support and therefore capacity to care for those suffering these aging related ailments. Assistive Smart Homes (SH) are a promising form of technology enabling assistance with activities of daily living, providing support of suffers of cognitive ailments and increasing their independence and quality of life. Traditional SH systems have deficiencies that have been partially addressed by through goal-driven SH systems. Goal-driven SHs incorporate flexible activity models, goals, which partially address some of these issues. Goals may be combined to provide assistance with dynamic and variable activities. This paradigm-shift, however, introduces the need to provide dynamic assistance within such SHs. This study presents a novel approach to achieve this through video based content analysis and a mechanism to facilitate matching analysed videos to dynamic activities/goals. The mechanism behind this approach is detailed and followed by the presentation of an evaluation where showing promising results were shown.
  • No Thumbnail Available
    ItemMetadata only
    Assessment and Visualization of Parkinson's Disease Tremor
    (IEEE, 2011-01-17) Synnott, J.; Chen, Liming; Nugent, Chris; Moore, G.
    Current clinical methods of Parkinson's disease assessment are known to be subjective and potentially error prone. This paper presents a preliminary investigation into the development of a novel approach for the assessment of Parkinsonian tremor. The approach is based on a computer vision technique with the aim of providing a more objective, frequent, yet unobtrusive means of assessment. A method of tremor amplitude quantification is proposed, and 3D visualization techniques are exploited to provide an intuitive tool for the monitoring and assessment of Parkinson's disease. The approach developed has the potential to address the limitations and patient privacy concerns associated with video-based monitoring technology. Initial results following evaluation have demonstrated the viability and benefits of the approach, including objectiveness, repeatability and clarity of activity performance results.
  • Thumbnail Image
    ItemOpen Access
    Automatic Metadata Generation Through Analysis of Narration Within Instructional Videos
    (Springer US, 2015-08-08) Rafferty, Joseph; Nugent, Chris; Liu, Jun; Chen, Liming
    Current activity recognition based assistive living solutions have adopted relatively rigid models of inhabitant activities. These solutions have some deficiencies associated with the use of these models. To address this, a goal-oriented solution has been proposed. In a goal-oriented solution, goal models offer a method of flexibly modelling inhabitant activity. The flexibility of these goal models can dynamically produce a large number of varying action plans that may be used to guide inhabitants. In order to provide illustrative, video-based, instruction for these numerous actions plans, a number of video clips would need to be associated with each variation. To address this, rich metadata may be used to automatically match appropriate video clips from a video repository to each specific, dynamically generated, activity plan. This study introduces a mechanism of automatically generating suitable rich metadata representing actions depicted within video clips to facilitate such video matching. This performance of this mechanism was evaluated using eighteen video files; during this evaluation metadata was automatically generated with a high level of accuracy.
  • Thumbnail Image
    ItemEmbargo
    Automatic Summarization of Activities Depicted in Instructional Videos by Use of Speech Analysis
    (Springer, 2014-12) Rafferty, Joseph; Nugent, Chris; Liu, Jun; Chen, Liming
    Existing activity recognition based assistive living solutions have adopted a relatively rigid approach to modelling activities. To address the deficiencies of such approaches, a goal-oriented solution has been proposed that will offer a method of flexibly modelling activities. This approach does, however, have a disadvantage in that the performance of goals may vary hence requiring differing video clips to be associated with these variations. In order to address this shortcoming, the use of rich metadata to facilitate automatic sequencing and matching of appropriate video clips is necessary. This paper introduces a mechanism of automatically generating rich metadata which details the actions depicted in video files to facilitate matching and sequencing. This mechanism was evaluated with 14 video files, producing annotations with a high degree of accuracy.
  • No Thumbnail Available
    ItemMetadata only
    Chapter 24: Smart Home Research: Projects and Issues
    (IGI Global, 2011-05) Poland, M.P.; Nugent, Chris; Wang, H.; Chen, Liming
    Smart Homes are environments facilitated with technology that act in a protective and proactive function to assist an inhabitant in managing their daily lives specific to their individual needs. A typical Smart Home implementation would include sensors and actuators to detect changes in status and to initiate beneficial interventions. This paper aims to introduce the diversity of recent Smart Home research and to present the challenges that are faced not only by engineers and potential inhabitants, but also by policy makers and healthcare professionals
  • Thumbnail Image
    ItemOpen Access
    Comparing CNN and Human Crafted Features for Human Activity Recognition
    (IEEE, 2019-08) Cruciani, Federico; Vafeiadis, Anastasios; Nugent, Chris; Cleland, Ian; McCullagh, Paul; Votis, Konstantinos; Giakoumis, Dimitrios; Tzovaras, Dimitrios; Chen, Liming; Hamzaoui, Raouf
    Deep learning techniques such as Convolutional Neural Networks (CNNs) have shown good results in activity recognition. One of the advantages of using these methods resides in their ability to generate features automatically. This ability greatly simplifies the task of feature extraction that usually requires domain specific knowledge, especially when using big data where data driven approaches can lead to anti-patterns. Despite the advantage of this approach, very little work has been undertaken on analyzing the quality of extracted features, and more specifically on how model architecture and parameters affect the ability of those features to separate activity classes in the final feature space. This work focuses on identifying the optimal parameters for recognition of simple activities applying this approach on both signals from inertial and audio sensors. The paper provides the following contributions: (i) a comparison of automatically extracted CNN features with gold standard Human Crafted Features (HCF) is given, (ii) a comprehensive analysis on how architecture and model parameters affect separation of target classes in the feature space. Results are evaluated using publicly available datasets. In particular, we achieved a 93.38% F-Score on the UCI-HAR dataset, using 1D CNNs with 3 convolutional layers and 32 kernel size, and a 90.5% F-Score on the DCASE 2017 development dataset, simplified for three classes (indoor, outdoor and vehicle), using 2D CNNs with 2 convolutional layers and a 2x2 kernel size.
  • No Thumbnail Available
    ItemMetadata only
    Comparison of Fusion Methods Based on DST and DBN in Human Activity Recognition
    (Springer, 2011-03-10) Tolstikov, A.; Hong, X.; Biswas, J.; Nugent, Chris; Chen, Liming; Parente, G.
    Ambient assistive living environments require sophisticated information fusion and reasoning techniques to accurately identify activities of a person under care. In this paper, we explain, compare and discuss the application of two powerful fusion methods, namely dynamic Bayesian networks (DBN) and Dempster-Shafer theory (DST), for human activity recognition. Both methods are described, the implementation of activity recognition based on these methods is explained, and model acquisition and composition are suggested. We also provide functional comparison of both methods as well as performance comparison based on the publicly available activity dataset. Our findings show that in performance and applicability, both DST and DBN are very similar; however, significant differences exist in the ways the models are obtained. DST being top-down and knowledge-based, differs significantly in qualitative terms, when compared with DBN, which is data-driven. These qualitative differences between DST and DBN should therefore dictate the selection of the appropriate model to use, given a particular activity recognition application.
  • No Thumbnail Available
    ItemMetadata only
    A Conceptual Framework for Supporting Adaptive Personalized Help-on-Demand Services
    (Springer, 2012-11) Burns, William; Chen, Liming; Nugent, Chris; Donnelly, Mark P.; Skillen, Kerry-Louise; Solheim, Ivar
    Mobile applications that encompass personalization and context-aware components are increasingly becoming more prevalent. The ability to offer personalized content and User Interfaces to the users of these applications, however, has still not been fully addressed. In this paper we describe a conceptual framework that establishes a User Profile and aims to monitor the usage patterns of users of a mobile application and, based on these patterns, provide both personalized, context aware content and user interfaces. The framework consists of four components that together contribute towards an overall Help on Demand service that is targeted at older age Smartphone users. A usage scenario is presented to describe the typical usage of the help on demand service.
  • No Thumbnail Available
    ItemMetadata only
    The creation of simulated activity datasets using a graphical intelligent environment simulation tool
    (IEEE, 2014-11-06) Synnott, J.; Chen, Liming; Nugent, Chris; Moore, G.
    The availability of datasets capturing the performance of activities of daily living is limited by difficulties associated with the collection of such data. Software solutions can mitigate these limitations, providing researchers with the ability to rapidly generate simulated data. This paper describes the use of IE Sim to create a simulated intelligent environment within which activities of daily living can be performed using a virtual avatar. IE Sim has been demonstrated to facilitate the generation of datasets capturing normal activity performance in addition to overlapping activities and abnormal activities such as hazardous scenarios.
  • No Thumbnail Available
    ItemMetadata only
    Development of a Smart Home Simulator for use as a Heuristic Tool for Management of Sensor Distribution
    (IOS Press, 2009-07-23) Chen, Liming; Wang, H.; Nugent, Chris; Poland, M.P.
    Smart Homes offer potential solutions for various forms of independent living for the elderly. The assistive and protective environment afforded by smart homes offer a safe, relatively inexpensive, dependable and viable alternative to vulnerable inhabitants. Nevertheless, the success of a smart home rests upon the quality of information its decision support system receives and this in turn places great importance on the issue of correct sensor deployment. In this article we present a software tool that has been developed to address the elusive issue of sensor distribution within smart homes. Details of the tool will be presented and it will be shown how it can be used to emulate any real world environment whereby virtual sensor distributions can be rapidly implemented and assessed without the requirement for physical deployment for evaluation. As such, this approach offers the potential of tailoring sensor distributions to the specific needs of a patient in a non-evasive manner. The heuristics based tool presented here has been developed as the first part of a three stage project.
  • No Thumbnail Available
    ItemMetadata only
    A dynamic annotation tool to support in-home autism intervention
    (2012) Donnelly, Mark P.; Cruciani, F.; Galway, L.; Nugent, Chris; Paggetti, C.; McCullogh, P.; Tamburini, E.; Chen, Liming
    The Congress sets out to be an international forum for the exchange of ideas and opinions in which different parties (people with autism, families, professionals of the intervention, investigators and developers) are able to debate on the subject of applied technologies in the world of autism.
  • No Thumbnail Available
    ItemMetadata only
    Editorial: Knowledge-Driven Activity Recognition in Intelligent Environments
    (Elsevier, 2011-06) Chen, Liming; Nugent, Chris; Cook, Diane J.; Yu, Z.
    This is an editorial.
  • No Thumbnail Available
    ItemMetadata only
    Engineering Knowledge for Assistive Living
    (Springer-Verlag, 2010-09-01) Chen, Liming; Nugent, Chris
    This paper introduces a knowledge based approach to assistive living in smart homes. It proposes a system architecture that makes use of knowledge in the lifecycle of assistive living. The paper describes ontology based knowledge engineering practices and discusses mechanisms for exploiting knowledge for activity recognition and assistance. It presents system implementation and experiments, and discusses initial results.
  • Thumbnail Image
    ItemEmbargo
    Evaluation Of MediaPlace: a geospatial semantic enrichment system for photographs
    (ACM, 2015-12-11) Ennis, A.; Nugent, Chris; Morrow, P.; Chen, Liming; Ioannidis, George; Stan, Alexandru
    In today's world of internet connected devices and smart phones, it has become effortless to create and consume vast amounts of information. This is particularly the case with photographs, with vast amounts being created and shared online every day. Never-the-less, it still remains a challenge to discover the "right" information for the appropriate purpose. This paper describes and discusses the testing and evaluation of the MediaPlace system with the well-known dataset YFCC-100M, which contains 48 million geospatial geotagged photographs, from Flickr produced by Yahoo. MediaPlace is a system which we have developed to automatically enrich geotagged photographs with semantic geospatial information derived from several online geospatial datasets.
  • No Thumbnail Available
    ItemMetadata only
    Feature learning for human activity recognition using convolutional neural networks: A case study for inertial measurement unit and audio data
    (Springer, 2020-01-24) Cruciani, Federico; Vafeiadis, Anastasios; Nugent, Chris; Cleland, Ian; McCullagh, Paul; Votis, Konstantinos; Giakoumis, Dimitrios; Tzovaras, Dimitrios; Chen, Liming; Hamzaoui, Raouf
    The use of Convolutional Neural Networks (CNNs) as a feature learning method for Human Activity Recognition (HAR) is becoming more and more common. Unlike conventional machine learning methods, which require domain-specific expertise, CNNs can extract features automatically. On the other hand, CNNs require a training phase, making them prone to the cold-start problem. In this work, a case study is presented where the use of a pre-trained CNN feature extractor is evaluated under realistic conditions. The case study consists of two main steps: (1) different topologies and parameters are assessed to identify the best candidate models for HAR, thus obtaining a pre-trained CNN model. The pre-trained model (2) is then employed as feature extractor evaluating its use with a large scale real-world dataset. Two CNN applications were considered: Inertial Measurement Unit (IMU) and audio based HAR. For the IMU data, balanced accuracy was 91.98% on the UCI-HAR dataset, and 67.51% on the real-world Extrasensory dataset. For the audio data, the balanced accuracy was 92.30% on the DCASE 2017 dataset, and 35.24% on the Extrasensory dataset.
  • No Thumbnail Available
    ItemMetadata only
    Flexible and Customizable Visualization of Data Generated within Intelligent Environments
    (IEEE, 2012-09) Synnott, J.; Chen, Liming; Nugent, Chris; Moore, G.
    This paper outlines a tool for the visualization of data generated within Intelligent Environments. This tool has been designed with a focus on flexibility and customizability hence facilitating application to a range of areas including institutionalized or home-based healthcare monitoring. Through the use of an object toolbox, non-technical users can rapidly re-create a visual representation (aka a "Scene") of an intelligent environment and connect this scene to an active data repository. Data generated within the environment can be visualized in real-time, or summarized using a density ring visualization format that can be customized based on user defined rules to highlight events of particular interest. The tool was tested within a smart lab used as an active research environment. Collection of data over a one week period resulted in 3840 sensor activations. Visualization of this dataset illustrates the potential of the tool to highlight normal and abnormal activity trends within the environment.
  • No Thumbnail Available
    ItemMetadata only
    Formal Modeling Techniques for Ambient Assisted Living
    (Springer, 2010-11-23) Parente, G.; Nugent, Chris; Hong, X.; Donnelly, Mark P.; Chen, Liming; Vicario, E.
    In the development of systems of ambient assisted living (AAL), formalized models and analysis techniques can provide a ground that makes development amenable to a systematic approach. We consider the following formal modeling tools and techniques: fault trees, evidential reasoning, evidential ontology networks, temporal logic, hidden Markov models and partially observable Markov models. We review them in the perspective of their potential in the realm of AAL, recalling the general traits and potential of each of them, and highlighting how this can be concretely deployed within the AAL realm. To this end, we present a number of scenarios providing insight on how each technique can match the needs of different types of problem in the application domain.
  • Thumbnail Image
    ItemOpen Access
    From Activity Recognition to Intention Recognition for Assisted Living Within Smart Homes
    (IEEE Transactions on Human-Machine Systems, 2017-01-05) Rafferty, Joseph; Nugent, Chris; Liu, Jun; Chen, Liming
    The global population is aging; projections show that by 2050, more than 20% of the population will be aged over 64. This will lead to an increase in aging related illness, a decrease in informal support, and ultimately issues with providing care for these individuals. Assistive smart homes provide a promising solution to some of these issues. Nevertheless, they currently have issues hindering their adoption. To help address some of these issues, this study introduces a novel approach to implementing assistive smart homes. The devised approach is based upon an intention recognition mechanism incorporated into an intelligent agent architecture. This approach is detailed and evaluated. Evaluation was performed across three scenarios. Scenario 1 involved a web interface, focusing on testing the intention recognition mechanism. Scenarios 2 and 3 involved retrofitting a home with sensors and providing assistance with activities over a period of 3 months. The average accuracy for these three scenarios was 100%, 64.4%, and 83.3%, respectively. Future will extend and further evaluate this approach by implementing advanced sensor-filtering rules and evaluating more complex activities.