Autism Spectrum Disorders I am currently involved in a project that investigates the nature of anxiety in children with autism spectrum disorders (ASD). These disorders are neurodevelopmental disorders characterized by a triad of core features: impairments in social interaction, impairments in communication, and presence of restrictive repetitive and stereotypical behaviours, interests, or activities. The prevalence of ASD is estimated to be in the range of 80-240 in 10,000, more than three times higher than that of childhood cancer and juvenile diabetes The high prevalence of anxiety in children with ASD and its profound impact on social and emotional development strongly motivate development of effective assessment and intervention techniques. Without early intervention, symptoms of anxiety may become more severe and continue into adulthood. Moreover, assessment of anxiety is often based on clinical interviews and standard anxiety scales. As a result of the above challenges, individuals with ASD are often excluded from the diagnosis process, and assessment is done based on input from parents and care-givers. This project investigates the development of objective, physiology driven measures of anxiety in children with ASD. Access Innovations for Children with Disabilities An estimated 4.5 million individuals in Canada, USA and Europe are candidates for augmentative and alternative communication (AAC) technologies that augment or replace speech-based communication. One third of this population has no means of communication due to complete loss of speech or functional movements caused by degenerative motor neuron disease, cerebral palsy, brain stem stroke, or traumatic brain injuries. In many cases, non-verbal persons have an intact mind and the potential to attain a higher level of independence, participate in educational opportunities, and pursue meaningful employment. Yet, the majority of these individuals do not have access to AAC technologies that enable them to realize this potential. One of the main barriers hindering access to AAC technologies is operational difficulties resulting from physical impairments such as muscle weakness and spasticity. To overcome this barrier, the goal of my research at the PRISM Lab is to create novel assistive communication technologies that harness whatever physical or physiological functions the individual possesses to offer a personalized AAC solution. More specifically, the focus of this research is wearable body-machine interfaces for children with severe physical disabilities. These interfaces translate physical and physiological activity into computer control signals for external devices, allowing non-verbal individuals to communicate their preferences and intentions with others and the environment through changes in physiological body signals. I am currently involved in an interdisciplinary project that examines factors affecting social inclusion of children with severe disabilities. These children are often socially marginalized and isolated due to physical barriers, inaccessible environments, and social arrangements that do not support their unique needs. Despite the profound impact of social inclusion on children’s psychosocial development, very little is known about the environmental qualities that promote experiences of participation and inclusion in children with severe disabilities. To address this gap, our project describes experiences of these children in various activity settings and examines associations among these experiences and environmental qualities. Description of these experiences, however, is not trivial as children with severe disabilities often have limited or no speech. The goal of my work is to develop alternative means of communication for these children based on novel pattern discovery techniques. These tools rely on physiological signals, such as heart rate and respiration patterns, to decode emotional experiences of non-verbal children. WLAN Positioning Advances in wireless communication have enabled mobility of personal computing devices equipped with sensing and computing capabilities. This has motivated the development of location-based services (LBS) that are implemented on top of existing communication infrastructures to cater to changing user contexts. To enable and support the delivery of LBS, accurate, reliable, and realtime user location information is needed. My PhD thesis introduces a cognitive dynamic system for tracking the position of mobile users using received signal strength (RSS) in Wireless Local Area Networks (WLAN). The main challenge in WLAN positioning is the unpredictable nature of the RSS-position relationship. Existing system rely on a set of training samples collected at a set of anchor points with known positions in the environment to characterize this relationship. The first contribution of my thesis is the use of nonparametric kernel density estimation for minimum mean square error positioning using the RSS training data. This formulation enables the rigorous study of state-space filtering in the context of WLAN positioning. The outcome is the Nonparametric Information (NI) filter, a novel recursive position estimator that incorporates both RSS measurements and a dynamic model of pedestrian motion during estimation. In contrast to traditional Kalman filtering approaches, the NI filter does not require the explicit knowledge of RSS-position relationship and is therefore well-suited for the WLAN positioning problem. The use of the dynamic motion model by the NI filter leads to the design of a cognitive dynamic tracking system. This design harnesses the benefits of feedback and position predictions from the filter to guide the selection of anchor points and radio sensors used during estimation. Experimental results using real measurement from an office environment demonstrate the effectiveness of proactive determination of sensing and estimation parameters in mitigating difficulties that arise due to the unpredictable nature of the indoor radio environment. In particular, the results indicate that the proposed cognitive design achieves an improvement of 3.19m (56%) in positioning error relative to memoryless positioning alone. Multimedia Retrieval My Master's research focuses on investigating the application of information fusion techniques in the context of content-based image retrieval. In the recent years, the amount of digital multimedia information has grown tremendously. This information can be easily be shared and accessed through medium such as the Internet among businesses and people. In order for this data to be useful, an effective tool for searching and retrieving relevant information is needed. We use a technique known as content-based image retrieval for retrieving images similar to a given user query. The retrieval is done by comparing the visual features of images such as color, shape, and texture. In order to find images similar to the user query, a similarity measure between images is required. This measure is usually a function of the similarities between the visual features of images (e.g. color, shape, and texture). I investigate different techniques for combining the low level features in order to calculate the similarity between two images. |