Philip Moore

A Survey of Context Modeling for Pervasive Cooperative Learning

Context represents a fundamental issue in research into pervasive and cooperative computing applications. This paper presents a survey on context modelling issues, together with a discussion on approaches to context modelling in intelligent context-aware pervasive systems. There is a parametric evaluation of the approaches considered, the conclusion drawn being that ontology-based modelling approach represents the optimal approach. The paper concludes with potential directions for future work.

Smart-Context

This paper addresses context in intelligent context-aware systems to support personalised service provision and cooperative computing. Context processing, context modelling, ontology, and OWL are introduced and a context reasoning ontology presented. Context implementation reduces to a decision problem which is characterised as one of selecting from a number of potential options based on the relationship between the values that describe the input and the solution, the modelling school of decision analysis attempts to construct an explicit model of such relationships, usually in the form of decision trees. An overview of decision trees with parametric design considerations is presented. Comparisons with related research are drawn and an evaluation and simulation of Smart-Context is presented. RDF/S with OWL and Jena provide an effective basis for autonomous decision making using processing rules, and the issue is one of implementation in adaptable and tractable solutions. A conclusion with open research questions is presented with consideration of potential directions for future research.

Ontology driven decision support for the diagnosis of mild cognitive impairment

In recent years, mild cognitive impairment (MCI) has attracted significant attention as an indicator of high risk for Alzheimers disease (AD), and the diagnosis of MCI can alert patient to carry out appropriate strategies to prevent AD. To avoid subjectivity in diagnosis, we propose an ontology driven decision support method which is an automated procedure for diagnosing MCI through magnetic resonance imaging (MRI). In this approach, we encode specialized MRI knowledge into an ontology and construct a rule set using machine learning algorithms. Then we apply these two parts in conjunction with reasoning engine to automatically distinguish MCI patients from normal controls (NC). The rule set is trained by MRI data of 187 MCI patients and 177 normal controls selected from Alzheimers Disease Neuroimaging Initiative (ADNI) using C4.5 algorithm. By using a 10-fold cross validation, we prove that the performance of C4.5 with 80.2% sensitivity is better than other algorithms, such as support vector machine (SVM), Bayesian network (BN) and back propagation (BP) neural networks, and C4.5 is suitable for the construction of reasoning rules. Meanwhile, the evaluation results suggest that our approach would be useful to assist physicians efficiently in real clinical diagnosis for the disease of MCI.

Detection of the onset of agitation in patients with dementia: real-time monitoring and the application of big-data solutions

The changing demographic profile of the population has potentially challenging consequences resulting in a rapidly growing elderly population with healthcare implications including Alzheimer type conditions (a leading cause of dementia). Dementia requires long term care to manage the negative behavioural symptoms which are primarily exhibited in terms of agitation and aggression. This article considers dementia with a discussion around independent assisted living (IAL). We discuss the behavioural and psychological symptoms of dementia (BPSD) and the factors (precursors) to the onset of agitation and aggression. Context and data processing is introduced and the nature of knowledge considered. Next generation context-aware systems are considered with the focus on health monitoring. We postulate that the challenges lie in the effective realisation of IAL; achieving this however remains an objective of intensive multi-disciplinary research involving both clinicians and computer science in the development of software and non-invasive sensor technologies implemented in mobile systems.

Automatic Identification and Removal of Ocular Artifacts in EEG—Improved Adaptive Predictor Filtering for Portable Applications

Electroencephalogram (EEG) signals have a long history of use as a noninvasive approach to measure brain function. An essential component in EEG-based applications is the removal of Ocular Artifacts (OA) from the EEG signals. In this paper we propose a hybrid de-noising method combining Discrete Wavelet Transformation (DWT) and an Adaptive Predictor Filter (APF). A particularly novel feature of the proposed method is the use of the APF based on an adaptive autoregressive model for prediction of the waveform of signals in the ocular artifact zones. In our test, based on simulated data, the accuracy of noise removal in the proposed model was significantly increased when compared to existing methods including: Wavelet Packet Transform (WPT) and Independent Component Analysis (ICA), Discrete Wavelet Transform (DWT) and Adaptive Noise Cancellation (ANC). The results demonstrate that the proposed method achieved a lower mean square error and higher correlation between the original and corrected EEG. The proposed method has also been evaluated using data from calibration trials for the Online Predictive Tools for Intervention in Mental Illness (OPTIMI) project. The results of this evaluation indicate an improvement in performance in terms of the recovery of true EEG signals with EEG tracking and computational speed in the analysis. The proposed method is well suited to applications in portable environments where the constraints with respect to acceptable wearable sensor attachments usually dictate single channel devices.

Smart care spaces: needs for intelligent at-home care

Pressures on the availability of healthcare spaces, the high costs of institutional care, and the desires of those being cared for, cause a current move toward care either at home or within low-supervision environments. This brings about an important question: how can smart care spaces be created that intelligently link the home care environment to the needs of the cared-for? To a significant degree this involves development of sensored spaces connected to intelligent computer-systems. However, that intelligence requires an understanding of how sensors can provide more than just environmental variables, instead making systems aware of symptoms, comfort and potential needs for intervention. Therefore, this paper discusses the current need for development of smart care spaces, provides an introduction to some of the cost-effective sensors available, and reviews links between sensor data and medical conditions. It will conclude that there is a growing need for smart care spaces that allow effective monitorin...

Monitoring and Detection of Agitation in Dementia: Towards Real-Time and Big-Data Solutions

The changing demographic profile of the population has potentially challenging social, geopolitical, and financial consequences for individuals, families, the wider society, and governments globally. The demographic change will result in a rapidly growing elderly population with healthcare implications which importantly include Alzheimer type conditions (a leading cause of dementia). Dementia requires long term care to manage the negative behavioral symptoms which are primarily exhibited in terms of agitation and aggression as the condition develops. This paper considers the nature of dementia along with the issues and challenges implicit in its management. The Behavioral and Psychological Symptoms of Dementia (BPSD) are introduced with factors (precursors) to the onset of agitation and aggression. Independent living is considered, health monitoring and implementation in context-aware decision-support systems is discussed with consideration of data analytics. Implicit in health monitoring are technical and ethical constraints, we briefly consider these constraints with the ability to generalize to a range of medical conditions. We postulate that health monitoring offers exciting potential opportunities however the challenges lie in the effective realization of independent assisted living while meeting the ethical challenges, achieving this remains an open research question remains.

An Intelligent Mobile Advertising System (iMAS): Location-Based Advertising to Individuals and Business

Rapid expansion of wireless technologies has provided a platform to support intelligent systems in the domain of mobile marketing. Utilizing Location Based Services (LBS) and Global Navigational Satellite Systems (GNSS) infrastructure provides the transport of real-time, scheduled, location-based advertising to individuals and business. In this paper a distributed synchronous platform is proposed called iMAS. iMAS proposes to use an open source platform independent approach to provide the services and interaction with the iMAS system. Intelligent advertising services (IAS) is an integral component of the system and uses a global positioning system (GPS) to enable information to be received depending on the longitude and latitude coordinates of the iMAS device. This allows for contextual information to be used as a means to provide intelligent context-aware location-centric targeted marketing advertisements to the general public. At this stage iMAS is a proof of concept and subsequent research is already under way to test the device in a controlled environment.

Fuzzy ECA Rules for Pervasive Decision-Centric Personalised Mobile Learning

This chapter addresses personalisation in intelligent context-aware information systems. A personalized mobile learning system can be viewed as an information system related to the domain of education. Personalization requires the identification and selection of individuals; this can be achieved using an individual’s profile (termed context). A context is inherently complex, its effective use representing a challenge that has to date not been adequately addressed. This chapter considers this challenge, identifies context-aware systems as intrinsically decision-centric, and introduces Fuzzy Event:Condition:Action (FEAC) rules as an effective approach to enable deterministic computational intelligence to be applied in intelligent context-aware personalised mobile learning systems. The FECA rules algorithm is presented with example implementations, an evaluation, and proof-of-concept. The chapter closes with a discussion, conclusions, open research questions, and consideration of future directions for future work.

The Complexity of Context in Mobile Information Systems

This paper considers the complexity of context in mobile Information systems. Personalization is considered with context, context-awareness, mobile systems, and related research including adaptation. The principal design issues are introduced with consideration of proposed solutions and open research questions. This paper posits that the current predominance of location-based context-aware applications and systems fails to leverage the inherent richness and complexity of available contextual information and intelligent context-aware systems are required to effectively realize personalized service provision in mobile information systems.