Search

Recent years have seen an influx of medical technologies capable of remotely monitoring the health and behaviours of individuals to detect, manage and prevent health problems. Known collectively as personal health monitoring (PHM), these systems are intended to supplement medical care with health monitoring outside traditional care environments such as hospitals, ranging in complexity from mobile devices to complex networks of sensors measuring physiological parameters and behaviours. This research project assesses the potential ethical implications of PHM as an emerging medical technology, amenable to anticipatory action intended to prevent or mitigate problematic ethical issues in the future. PHM fundamentally changes how medical care can be delivered: patients can be monitored and consulted at a distance, eliminating opportunities for face-to-face actions and potentially undermining the importance of social, emotional and psychological aspects of medical care. The norms evident in this movement may clash with existing standards of 'good' medical practice from the perspective of patients, clinicians and institutions. By relating utilitarianism, virtue ethics and theories of surveillance to Habermas' concept of colonisation of the lifeworld, a conceptual framework is created which can explain how PHM may be allowed to change medicine as a practice in an ethically problematic way. The framework relates the inhibition of virtuous behaviour among practitioners of medicine, understood as a moral practice, to the movement in medicine towards remote monitoring. To assess the explanatory power of the conceptual framework and expand its borders, a qualitative interview empirical study with potential users of PHM in England is carried out. Recognising that the inherent uncertainty of the future undermines the validity of empirical research, a novel epistemological framework based in Habermas' discourse ethics is created to justify the empirical study. By developing Habermas' concept of translation into a procedure for assessing the credibility of uncertain normative claims about the future, a novel methodology for empirical ethical assessment of emerging technologies is created and tested. Various methods of analysis are employed, including review of academic discourses, empirical and theoretical analyses of the moral potential of PHM. Recommendations are made concerning ethical issues in the deployment and design of PHM systems, analysis and application of PHM data, and the shortcomings of existing research and protection mechanisms in responding to potential ethical implications of the technology.

In partnership with iMonSys - an emerging company in the passive care field - a new system, 'Verity', is being developed to fulfil the role of a passive behaviour monitoring and alert detection device, providing an unobtrusive level of care and assessing an individual's changing behaviour and health status whilst still allowing for independence of its elderly user. In this research, a Hidden Markov Model incorporating Fuzzy Logic-based sensor fusion is created for the behaviour detection within Verity, with a method of Fuzzy-Rule induction designed for the system's adaptation to a user during operation. A dimension reduction and classification scheme utilising Curvilinear Distance Analysis is further developed to deal with the recognition task presented by increasingly nonlinear and high dimension sensor readings, and anomaly detection methods situated within the Hidden Markov Model provide possible solutions to identification of health concerns arising from independent living. Real-time implementation is proposed through development of an Instance Based Learning approach in combination with a Bloom Filter, speeding up the classification operation and reducing the storage requirements for the considerable amount of observation data obtained during operation. Finally, evaluation of all algorithms is completed using a simulation of the Verity system with which the behaviour monitoring task is to be achieved.

The constantly increasing global elderly population is associated with a wide range of needs due to the varying degrees of decline in behavioral, social, emotional, mental, psychological, and motor abilities. Falls, highly common in the elderly, on account of such declining abilities and environmental factors, can limit their abilities to perform Activities of Daily Living (ADLs), as well as cause multiple health related complications including death. Therefore, it is essential that the future of intelligent living spaces, such as Smart Homes, are equipped with adaptable, pervasive, and ubiquitous systems that can anticipate and respond to these diverse needs of the elderly, while being able to track their dynamic indoor location, to provide solutions as and where such needs arise. The interdisciplinary work presented in this dissertation, aims to address these challenges and makes ten scientific contributions to these fields. First, it presents a methodology that investigates the many modalities of user interactions to deduce a user's indoor location in a particular "activity-based zone" during ADLs. Next, it presents a context-independent solution to determine the "zone-based" indoor position of a user in any indoor environment. These two approaches achieved performance accuracies of 81.36% and 81.13%, respectively, when tested on a dataset. Third, it presents a methodology for detecting a user's location in an indoor environment in terms of the X and Y coordinate information. This methodology outperformed all prior works in this field when evaluated using the Root Mean Squared Error (RMSE)-based performance evaluation metrics as per ISO/IEC18305:2016—an international standard for testing Localization and Tracking Systems. Fourth, it presents the findings from a comparison study of multiple learning approaches that were developed, implemented, and evaluated to address the challenge of determining the best machine learning method for Indoor Localization. The findings show that the Random Forest-based learning approach outperformed all the other learning approaches. Fifth, it proposes a novel methodology that can identify falls and fall-like movements during ADLs. Sixth, it presents a comparison study that involved implementation and testing of 19 machine learning algorithms to develop systems for fall detection. The study was performed on two datasets and the findings show that the k-NN classifier outperformed all the other machine learning approaches. Seventh, it introduces a novel boosting approach to improve the performance accuracy of such systems. This methodology achieved performance accuracies of 99.87% and 99.66%, respectively, when evaluated on two datasets. Eighth, it presents a methodology for detection of the floor and regions in an indoor environment to provide semantic context to indoor localization while modeling each user in a user-specific manner. The methodology was tested on a dataset of 18 different users who navigated in 3 buildings consisting of 5 floors and 254 indoor spatial regions. Ninth, it presents a system to detect stair navigations as such movements are associated with falls in the elderly. Finally, it outlines the approach for the development of an ADL-based Big Data collection and analysis system that can be used for development of these approaches in the real-world.

Abstract: The Smart-Condo™ is a comprehensive platform that aims to provide a variety of services, based on information gleaned from sensors deployed in an apartment, that can potentially improve healthcare delivery. One of our main objectives has been to develop an accurate non-invasive occupant-localization method using passive infrared sensors. In this thesis, we present a simulation framework with which we investigate tradeoffs between the number of sensors and the localization accuracy of our platform. We compare the results of simulations and real-world trials and conclude that our simulation framework is a reliable estimator of the localization accuracy of a particular sensor configuration. We then propose a methodology for planning new deployments that takes into account geometric properties of the new space and the context of occupant's activities. More specifically, we describe a model with the potential to capture typical indoor mobility patterns and formulate a sensor placement optimization problem based on this model. We propose a placement algorithm with near-optimality guarantee. Through simulation-enabled evaluation, we demonstrate that this algorithm generates sensor configurations with localization accuracy superior to that achievable with the same number of sensors placed manually or randomly in the same environment.