Assessing the Oral Health Needs of Public Housing Residents

Objectives: “Tooth Smart Healthy Start” is a randomized clinical trial which aims to reduce the incidence of early childhood caries (ECC) in Boston public housing residents as part of the NIH funded Northeast Center for Research to Evaluate and Eliminate Dental Disparities. The purpose of this project was to assess public housing stakeholders' perception of the oral health needs of public housing residents and their interest in replicating “Tooth Smart Healthy Start” in other public housing sites across the nation. Methods: The target population was the 180 attendees of the 2010 meeting of the Health Care for Residents of Public Housing National Conference. A ten question survey which assessed conference attendees' beliefs about oral health and its importance to public housing residents was distributed. Data was analyzed using SAS 9.1. Descriptive statistics were calculated for each variable and results were stratified by participants' roles. Results: Thirty percent of conference attendees completed the survey. The participants consisted of residents, agency representatives, and housing authority personnel. When asked to rank health issues facing public housing residents, oral health was rated as most important (42%) or top three (16%) by residents. The agency representatives and housing authority personnel rated oral health among the top three (33% and 58% respectively) and top five (36% and 25% respectively). When participants ranked the three greatest resident health needs out of eight choices, oral health was the most common response. Majority of the participants expressed interest in replicating the “Tooth Smart Healthy Start” program at their sites. Conclusion: All stakeholder groups identified oral health as one of the greatest health needs of residents in public housing. Furthermore, if shown to reduce ECC, there is significant interest in implementing the program amongst key public housing stakeholders across the nation.

Articulated Pose Estimation in a Learned Smooth Space of Feasible Solutions

A learning based framework is proposed for estimating human body pose from a single image. Given a differentiable function that maps from pose space to image feature space, the goal is to invert the process: estimate the pose given only image features. The inversion is an ill-posed problem as the inverse mapping is a one to many process. Hence multiple solutions exist, and it is desirable to restrict the solution space to a smaller subset of feasible solutions. For example, not all human body poses are feasible due to anthropometric constraints. Since the space of feasible solutions may not admit a closed form description, the proposed framework seeks to exploit machine learning techniques to learn an approximation that is smoothly parameterized over such a space. One such technique is Gaussian Process Latent Variable Modelling. Scaled conjugate gradient is then used find the best matching pose in the space of feasible solutions when given an input image. The formulation allows easy incorporation of various constraints, e.g. temporal consistency and anthropometric constraints. The performance of the proposed approach is evaluated in the task of upper-body pose estimation from silhouettes and compared with the Specialized Mapping Architecture. The estimation accuracy of the Specialized Mapping Architecture is at least one standard deviation worse than the proposed approach in the experiments with synthetic data. In experiments with real video of humans performing gestures, the proposed approach produces qualitatively better estimation results.