Regularized Online Mixture of Gaussians for Background Subtraction

Mixture of Gaussians (MoG) modelling [13] is a popular approach to background subtraction in video sequences. Although the algorithm shows good empirical performance, it lacks theoretical justification. In this paper, we give a justification for it from an online stochastic expectation maximization (EM) viewpoint and extend it to a general framework of regularized online classification EM for MoG with guaranteed convergence. By choosing a special regularization function, l1 norm, we derived a new set of updating equations for l1 regularized online MoG. It is shown empirically that l1 regularized online MoG converge faster than the original online MoG .

The Stormont Papers: 50 years of Northern Ireland Debates Online

This website offers access to the Parliamentary Debates of the devolved government of Northern Ireland from June 7 1921 to the dissolution of Parliament in March 28 1972.

These papers cast a unique and valuable light on the development of the Province. The 92,000 printed pages of Parliamentary Debates are held by few institutions and they have no comprehensive subject index. Hence they have been inaccessible and difficult to use. This project, with the support of academics, archivists and politicians, has taken the Papers and fully digitised them. The resource has been available online since October 2006.

Visitors to the site can search either the full text or specific keywords (for example Prisons, Westminster or Drunkenness), or they can browse particular debates according to the combined subject index, or they can simply view the volumes.

Online Multiperson Tracking With Occlusion Reasoning and Unsupervised Track Motion Model

We address the problem of multi-target tracking in realistic crowded conditions by introducing a novel dual-stage online tracking algorithm. The problem of data-association between tracks and detections, based on appearance, is often complicated by partial occlusion. In the first stage, we address the issue of occlusion with a novel method of robust data-association, that can be used to compute the appearance similarity between tracks and detections without the need for explicit knowledge of the occluded regions. In the second stage, broken tracks are linked based on motion and appearance, using an online-learned linking model. The online-learned motion-model for track linking uses the confident tracks from the first stage tracker as training examples. The new approach has been tested on the town centre dataset and has performance comparable with the present state-of-the-art

A systematic review protocol on the use of online learning and blended learning for teaching clinical skills to undergraduate health professional students

Aim: This paper is a review protocol that will be used to identify, critically appraise and synthesize the best current evidence relating to the use of online learning and blended learning approaches in teaching clinical skills in undergraduate nursing.

Background: Although previous systematic reviews on online learning versus face to face learning have been undertaken (Cavanaugh et al. 2010, Cook et al. 2010), a systematic review on the impact of online learning and blended learning for teaching clinical skills has yet to be considered in undergraduate nursing. By reviewing nursing students’ online learning experiences, systems can potentially be designed to ensure all students’ are supported appropriately to meet their learning needs.

Methods/Design: The key objectives of the review are to evaluate how online-learning teaching strategies assist nursing students learn; to evaluate the students satisfaction with this form of teaching; to explore the variety of online-learning strategies used; to determine what online-learning strategies are more effective and to determine if supplementary face to face instruction enhances learning. A search of the following databases will be made MEDLINE, CINAHL, BREI, ERIC and AUEI. This review will follow the Joanna Briggs Institute guidance for systematic reviews of quantitative and qualitative research.

Conclusion: This review intends to report on a combination of student experience and learning outcomes therefore increasing its utility for educators and curriculum developers involved in healthcare education.

Taiwanese Learners’ Motivation and Attitude Towards Completing an Online Distance Education Course During a One Year Industrial Placement

This mixed methods study investigated language learning motivation in an one-year e-learning course for technological university students to bridge the geographical divide between students on industrial placements when studying graded readers using an e-learning course to improve their English competence and to pass the General English Proficiency Test. Data was collected through questionnaires and course feedback. The results of this study extend Gardner’s socio-educational model in an e-learning environment by adding the new category, Computer Attitudes, which was proven to be highly correlated with Motivation. Although the low proficiency English students had good computer skills, their habits of using the computer for entertainment and their lack of the skill of “technological communication efficacy” caused increased anxiety when using computers and thus provided them with a lower computer confidence over time. Consequently, it is recommended that sound e-learning training should be provided to all of the students prior to embarking on an e-leaning course so that these learners can benefit from online language learning in the future.