The purpose of this research was to develop a theoretical understanding of the influences on participation for individuals with spinal cord injury (SCI) from a self-perceived perspective, with particular focus on the role of assistive technology (AT) in self-perceived participation. The theoretical underpinning, symbolic interactionism, was used to gain an understanding of the ways that adults with SCI ascribe meaning to the interaction between themselves and their unique environments in a process of participation. A grounded theory study of 19 adults with SCI was conducted. Participants engaged in individual in-depth interviews, used photovoice as a framework for taking photographs of aspects of their environment that promoted and restricted participation, and engaged in focus groups. The constructed grounded theory is summarized as follows: Negotiating the Body-environment Interface is a continuous process for those living with a SCI. Despite the relative stability of their changed body, they Live in a Changed World, one perceived differently after SCI. Four sets of strategies are used by individuals to interact within their unique environments: creating an accessible proximal environment; using AT and adaptations; advocating and educating; and gaining information and knowledge. Strategies were selected to engage in a Process of Participation, a process that consisted of a sense of inclusion, autonomy, accomplishment, and reciprocity. Intervening conditions were the physical (architectural, natural), socio-cultural (social supports, societal attitudes), and institutional (services, policies) environmental aspects that served as barriers or facilitators to the process of participation. The study has added to the growing body of literature on self-perceived participation that forefronts the sense of connectivity and engagement people feel within their environment. The findings highlighted how AT holds unique meaning, and how decisions around use of technology for participation is influenced by personal factors, and physical, socio-cultural, and institutional environments. A new definition of AT was constructed that acknowledges the environmental influences and importance of self-perceived participation as an outcome of AT use. This research highlights the instrumental role of the environment in supporting self-perceived participation of adults with SCI. Further research on developing ways to create inclusive and supportive environments for assistive technology users is warranted.

The purpose of this research was to develop a theoretical understanding of the influences on participation for individuals with spinal cord injury (SCI) from a self-perceived perspective, with particular focus on the role of assistive technology (AT) in self-perceived participation. The theoretical underpinning, symbolic interactionism, was used to gain an understanding of the ways that adults with SCI ascribe meaning to the interaction between themselves and their unique environments in a process of participation. A grounded theory study of 19 adults with SCI was conducted. Participants engaged in individual in-depth interviews, used photovoice as a framework for taking photographs of aspects of their environment that promoted and restricted participation, and engaged in focus groups. The constructed grounded theory is summarized as follows: Negotiating the Body-environment Interface is a continuous process for those living with a SCI. Despite the relative stability of their changed body, they Live in a Changed World, one perceived differently after SCI. Four sets of strategies are used by individuals to interact within their unique environments: creating an accessible proximal environment; using AT and adaptations; advocating and educating; and gaining information and knowledge. Strategies were selected to engage in a Process of Participation, a process that consisted of a sense of inclusion, autonomy, accomplishment, and reciprocity. Intervening conditions were the physical (architectural, natural), socio-cultural (social supports, societal attitudes), and institutional (services, policies) environmental aspects that served as barriers or facilitators to the process of participation. The study has added to the growing body of literature on self-perceived participation that forefronts the sense of connectivity and engagement people feel within their environment. The findings highlighted how AT holds unique meaning, and how decisions around use of technology for participation is influenced by personal factors, and physical, socio-cultural, and institutional environments. A new definition of AT was constructed that acknowledges the environmental influences and importance of self-perceived participation as an outcome of AT use. This research highlights the instrumental role of the environment in supporting self-perceived participation of adults with SCI. Further research on developing ways to create inclusive and supportive environments for assistive technology users is warranted.

The work described in this thesis falls under the umbrella of the Aurora project (Aurora 2000). Aurora is a long-term research project which, through diverse studies, investigates the potential enhancement of the everyday lives of children with autism through the use of robots, and other interactive systems, in playful contexts. Autism is a lifelong pervasive disability which affects social interaction and communication. Importantly for this thesis, children with autism exhibit a deficit in narrative comprehension which adversely impacts their social world. The research agenda addressed by this thesis was to develop an interactive software system which promotes an understanding of narrative structure (and thus the social world) while addressing the needs of individual children. The conceptual approach developed was to break down narrative into proto-narrative components and address these components individually through the introduction of simple game-like tasks, called t-stories, presented in a human-computer interaction context. The overarching hypothesis addressed was that it is possible to help children with autism to improve their narrative skills by addressing proto-narrative components independently. An interactive software system called TouchStory was developed to present t-stories to children with autism. Following knowledge of the characteristics and preferences of this group of learners TouchStory maintained strong analogies with the concrete, physical world. The design approach was to keep things simple, introducing features only if necessary to provide a focussed and enjoyable game. TouchStory uses a touch-sensitive screen as the interaction device as it affords immediate direct manipulation of the t-story components. Socially mediated methods of requirements elicitation and software evaluation (such as focus groups, thinking aloud protocols, or intergenerational design teams) are not appropriate for use with children with autism who are not socially oriented and, in the case of children with ‗lower functioning‘ autism, may have very few words or no productive language. Therefore a new strategy was developed to achieve an inclusive, child-centred design; this was to interleave prototype development with evaluation over several long-term trials. The trials were carried out in the participants‘ own school environments to provide an ecologically valid contextual enquiry. In the first trial 18 participants were each seen individually once. The second and third trials were extended studies of 12 and 20 school visits with 12 and 6 participants respectively; each participant was seen individually on each school visit, provided that the participant was at school on the day of the visit. Evaluation was carried out on the basis of video recordings of the sessions and software logs of the on-screen interactions. Individual learning needs were addressed by adapting the set of t-stories presented to the participant on the basis of success during recent sessions. No ordering of difficulty among the proto-narrative categories could be known a priori for any individual child, and may vary from child to child. Therefore the intention was to gradually, over multiple sessions, increase the proportion of t-stories from proto-narrative categories which the individual participant found challenging, while retaining sufficient scope for the expression of skills already mastered for the session to be enjoyable and rewarding. The adaptation of the software was achieved by introducing a simple adaptive formula, evaluating it over successive long terms trials, and increasing the complexity of the formula only where necessary. Results indicate that individual participants found the interactive presentation of the simple game-like tasks engaging, even after repeated exposures on as many as 20 occasions. The adaptive formula developed in this study did, for engaged participants, focus on the proto-narrative categories which the participant needed to practice but was likely to succeed; that is it did target an effective learning zone. While little evidence was seen of learning with respect to the fully developed narratives encountered in everyday life, results strongly suggest that some participants were actively engaged in self-directed, curiosity-driven activity that functioned as learning in that they were able to transfer knowledge about the appropriateness of particular responses to previously unseen t-stories. This thesis was driven by the needs of children with autism; contributions are made in a number of cognate areas. A conceptual contribution was made by the introduction of the proto-narrative concept which was shown to identify narrative deficits in children with autism and to form a basis for learning. A contribution was made to computational adaptation by the development of a novel adaptive formula which was shown to present a challenging experience while maintaining sufficient predictability and opportunities for the expression of skills already mastered to provide a comfortable experience for children with autism. A contribution was made to software development by showing that children with autism may be included in the design process through iterative development combined with long term trials. A contribution was made to assistive technology by demonstrating that simplicity together with evaluation over long term trials engages children with autism and is a route to inclusion. We cannot expect any magic fixes for children with autism, progress will be made by small steps; this thesis forms a small but significant contribution.

The levels of income and employment rates of people with disabilities are often lower than those without them. An effective way to free disabled people from these circumstances would be to design proper job accommodation for them. Ordinarily, physical conditions severely restrict their ability to carry out their work efficiently unless they have are provided with appropriately designed assistive technology (AT). However, due to the physical conditions unique to each disabled person, understanding the requirements of a disabled person is often a challenge to an AT designer. The aims of this research were to develop a design model for an empathy tool that would assist in the process of designing AT for job accommodation, and to explore the relationship between the use of empathy tools and the improvement of design elements in job accommodation AT. The design models employed were developed by analysing interviews with AT users and examining the results of observations and a literature review. The model was then used to build an empathy tool to be used in designing job accommodation AT for a selected subject; the empathy tools were used in a series of assessments of designer users. The results show that, when compared with tools used in traditional design briefs, empathy tools can successfully help designers to improve design elements in terms, respectively, of their understanding of users' physical abilities (22 per cent), work requirements (26.6 per cent), ergonomic requirements (22.8 per cent), and environment characteristics (21.4 per cent). Meanwhile, it is difficult for the tool to improve upon other design elements, about which one must learn by gaining design experience.

En años recientes, el uso de tabletas y teléfonos o dispositivos inteligentes ha incrementado continuamente gracias a la facilidad y disponibilidad de acceso a la información, entretenimiento y comunicación que ofrecen con su creciente variedad de aplicativos y especialmente su acceso a internet. A diferencia de computadoras o notebooks, estos dispositivos tienen tecnologías para mejorar la usabilidad para personas con dificultades visuales que también pueden ser utilizadas para crear nuevos aplicativos de asistencia sin la necesidad de aparatos externos. Esto genera oportunidades para un desarrollo inclusivo que mantiene la misma portabilidad. Sin embargo, estos dispositivos principalmente usan una pantalla táctil y aún entre sus tecnologías incorporadas, no tienen medios para ingresar datos que sean permitan que personas con ceguera ingresen información por otros medios que no sean su voz o un complejo teclado QWERTY. En este artículo, proponemos el uso de una solución adaptativa que permite al usuario usar la misma pantalla táctil como una alternativa para ingresar datos al simular un teclado Braille y demostramos su uso, además de tecnologías de lector de texto, con una aplicación que permite que una persona ciega chatee mediante mensajes instantáneos.

The Web has been a blessing for visually impaired users as with the help of assistive technologies such as screen readers, they can access previously inaccessible information independently. However, for screen reader users, web-based information seeking can still be challenging as web pages are mainly designed for visual interaction. This affects visually impaired users’ perception of theWeb as an information space as well as their experience of search interfaces. The aim of this thesis is therefore to consider visually impaired users’ information seeking behaviour, abilities and interactions via screen readers in the design of a search interface to support complex information seeking. We first conduct a review of how visually impaired users navigate the Web using screen readers. We highlight the strategies employed, the challenges encountered and the solutions to enhance web navigation through screen readers. We then investigate the information seeking behaviour of visually impaired users on the Web through an observational study and we compare this behaviour to that of sighted users to examine the impact of screen reader interaction on the information seeking process. To engage visually impaired users in the design process, we propose and evaluate a novel participatory approach based on a narrative scenario and a dialogue-led interaction to verify user requirements and to brainstorm design ideas. The development of the search interface is informed by the requirements gathered from the observational study and is supported through the inclusion of visually impaired users in the design process. We implement and evaluate the proposed search interface with novel features to support visually impaired users for complex information seeking. This thesis shows that considerations for information seeking behaviour and users’ abilities and mode of interaction contribute significantly to the design of search user interfaces to ensure that interface components are accessible as well as usable.

Braille, as a special written method of communication for the blind, has been globally accepted for years. It gives blind people another chance to learn and communicate more efficiently with the rest of the world. It also makes possible the translation of printed languages into a written language which is recognisable for blind people. Recently, Braille is experiencing a decreasing popularity due to the use of alternative technologies, like speech synthesis. However, as a form of literacy, Braille is still playing a significant role in the education of people with visual impairments. With the development of electronic technology, Braille turned out to be well suited to computer-aided production because of its coded forms. Software based text-to-Braille translation has been proved to be a successful solution in Assistive Technology (AT). However, the feasibility and advantages of the algorithm reconfiguration based on hardware implementation have rarely been substantially discussed. A hardware-based translation system with algorithm reconfiguration is able to supply greater throughput than a software-based system. Further, it is also expected as a single component integrated in a multi-functional Braille system on a chip. / Therefore, this thesis presents the development of a system for text-to-Braille translation implemented in hardware. Differing from most commercial methods, this translator is able to carry out the translation in hardware instead of using software. To find a particular translation algorithm which is suitable for a hardware-based solution, the history of, and previous contributions to Braille translation are introduced and discussed. It is concluded that Markov systems, a formal language theory, were highly suitable for application to hardware based Braille translation. Furthermore, the text-to-Braille algorithm is reconfigured to achieve parallel processing to accelerate the translation speed. Characteristics and advantages of Field Programmable Gate Arrays (FPGAs), and application of Very High Speed Integrated Circuit Hardware Description Language (VHDL) are introduced to explain how the translating algorithm can be transformed to hardware. Using a Xilinx hardware development platform, the algorithm for text-to-Braille translation is implemented and the structure of the translator is described hierarchically.

The number of elderly people around the world is growing rapidly. This has led to an increase in the number of people who are seeking assistance and adequate service either at home or in long-term- care institutions to successfully accomplish their daily activities. Responding to these needs has been a burden to the health care system in terms of labour and associated costs and has motivated research in developing alternative services using new technologies. Various intelligent, and non-intelligent, machines and robots have been developed to meet the needs of elderly and people with upper limb disabilities or dysfunctions in gaining independence in eating, which is one of the most frequent and time-consuming everyday tasks. However, in almost all cases, the proposed systems are designed only for the personal use of one individual and little effort to design a multiple-user feeding robot has been previously made. The feeding requirements of elderly in environments such as senior homes, where many elderly residents dine together at least three times per day, have not been extensively researched before. The aim of this research was to develop a machine to feed multiple elderly people based on their characteristics and feeding needs, as determined through observations at a nursing home. Observations of the elderly during meal times have revealed that almost 40% of the population was totally dependent on nurses or caregivers to be fed. Most of those remaining, suffered from hand tremors, joint pain or lack of hand muscle strength, which made utensil manipulation and coordination very difficult and the eating process both messy and lengthy. In addition, more than 43% of the elderly were very slow in eating because of chewing and swallowing problems and most of the rest were slow in scooping and directing utensils toward their mouths. Consequently, one nurse could only respond to a maximum of two diners simultaneously. In order to manage the needs of all elderly diners, they required the assistance of additional staff members. The limited time allocated for each meal and the daily progression of the seniors’ disabilities also made mealtime very challenging. Based on the caregivers’ opinion, many of the elderly in such environments can benefit from a machine capable of feeding multiple users simultaneously. Since eating is a slow procedure, the idle state of the robot during one user’s chewing and swallowing time can be allotted for feeding another person who is sitting at the same table. The observations and studies have resulted in the design of a food tray, and selection of an appropriate robot and applicable user interface. The proposed system uses a 6-DOF serial articulated robot in the center of a four-seat table along with a specifically designed food tray to feed one to four people. It employs a vision interface for food detection and recognition. Building the dynamic equations of the robotic system and simulation of the system were used to verify its dynamic behaviour before any prototyping and real-time testing.

This thesis describes the research, design, and development of a mid-drive wheelchair for use by the elders living independently, in assisted living facilities, and in nursing homes created by a design team at Georgia Tech's Center for Assistive Technology and Environmental Access (CATEA). This wheelchair stands to significantly improve the mobility of elders through better drive wheel placement and design features that could stand to improve their quality of life.

Advances in machine learning are having a profound impact on disciplines spanning the sciences. Assistive technology and health informatics are fields for which minor improvements achieved through leveraging more advanced machine learning algorithms can translate to major real world impact. However, successful application of machine learning currently requires broad domain knowledge to determine which model is appropriate for a given task, and model specific expertise to configure a model to a problem of interest. A major motivation for this thesis was: How can we make machine learning more accessible to assistive technology and health informatics researchers? Naturally, a complementary goal is to make machine learning more accessible in general. Specifically, in this thesis we explore how to automate the role of a machine learning expert through automatically adapting models and adjusting parameters to a given task of interest. This thesis consists of a number of contributions towards solving this challenging open problem in machine learning and these are empirically validated on four real-world applications. Through an interesting theoretical link between two seemingly disparate latent variable models, we create a hybrid model that allows one to flexibly interpolate over a parametric unsupervised neural network, a classification neural network and a non-parametric Gaussian process. We demonstrate empirically that this non-parametrically guided autoencoder allows one to learn a latent representation that is more useful for a given task of interest. We establish methods for automatically configuring machine learning model hyperparameters using Bayesian optimization. We develop Bayesian methods for integrating over parameters, explore the use of different priors over functions, and develop methods to run experiments in parallel. We demonstrate empirically that these methods find better hyperparameters on recent benchmark problems spanning machine learning in significantly less experiments than the methods employed by the problems' authors. We further establish methods for incorporating parameter dependent variable cost in the optimization procedure. These methods find better hyperparameters in less cost, such as time, or within bounded cost, such as before a deadline. Additionally, we develop a constrained Bayesian optimization variant and demonstrate its superiority over the standard procedure in the presence of unknown constraints.