Mobile service provisioning is intended to serve interoperable functionality from mobile devices over the network. The mobile service paradigm shifts the role of mobile devices from consumers to providers, opening up new opportunities for a multitude of collaborative services and applications ranging from sharing personal information to collaborative participatory sensing. Although many basic principles of the standard Web service approach continue to apply, the inherent limitations of mobile devices and broadband wireless access render the deployment of standard architectures in mobile environments inefficient. This research introduces two concepts that revolutionize mobile service provisioning: personal and cloud-assisted service provisioning. Personal services are intended to offer a range of user-centric data services to a limited set of consumers that are explicitly authorized by the user providing the service. Personal services facilitate prevailing trends such as social networking and mobile healthcare services, without compromising personal privacy. Cloud-assisted service provisioning bridges the gap between limited resources of mobile devices and increasing resource demands of mobile applications. This approach provides reliable and efficient mobile services, while alleviating the burden on limited mobile resources. Both approaches take advantage of the device's mobility and real time access to various context information. Experimental results reveal that personal services offer personalization based on the user's context and preferences, while cloud-assisted service provisioning, in addition to optimizing the consumption of mobile scarce resources, offers significant improvement to the reliability and availability of mobile services. / Thesis (Ph.D, Computing) -- Queen's University, 2013-09-03 10:28:42.795

It is well known that home exercise is as good as rehab center. Unfortunately, passive devices such as dumbbells, elastic bands, stress balls and tubing that have been widely used for home-based arm rehabilitation do not provide therapists with the information needed to monitor the patient’s progress, identify any impairment, and suggest treatments. Moreover, the lack of interactivity of these devices turns the rehabilitation exercises into a boring, unpleasant task. In this thesis, we introduce a family of home-based post-stroke rehabilitation systems aimed at solving the aforementioned problems. We call such applications: “Shared Haptic Environment on the Cloud for Arm Rehabilitation Exercises (SHECARE)”. The systems combine recent rehabilitation approaches with efficient, yet affordable skeleton tracking input technologies, and multimodal interactive computer environment. In addition, the systems provide a real-time feedback to the stroke patients, summarize the feedback after each session, and predict the overall recovery progress. Moreover, these systems show a new style of home-based rehabilitation approach that motivate the patients by engaging the whole family and friends in the rehabilitation process and allow the therapists to remotely assess the progress of the patients and adjust the training strategy accordingly. Two mathematical models have been presented in this thesis. The first model is developed to find the relationship between upper extremity kinematics and the associated forces/strength. The second model is used to evaluate the medical condition of the stroke patients and predict their recovery progress depending on their performance history. The objective assessments, clinical tests, and the subjective assessments, usability studies have shown the feasibility of the proposed systems for rehabilitation in stroke patients with upper limb motor dysfunction.