Paul D. Kelly

Queen's University Belfast, Béal Feirste, N Ireland, United Kingdom

Are you Paul D. Kelly?

Claim your profile

Publications (3)2.08 Total impact

  • [Show abstract] [Hide abstract]
    ABSTRACT: The HaptiMap toolkit is an open-source library enabling location-based mobile application developers to include features advancing accessibility in their applications. This paper presents the structure of the geospatial data access of the HaptiMap toolkit. In addition, an evaluation is carried out on the processing performance of the toolkit. The operation performances are compared with the corresponding operations of a leading open-source library, which supports computational geometry calculations. The results indicate that implementing custom-optimized algorithms for the toolkit’s data model is a feasible approach when the algorithms are specific or simple enough, while complex algorithms should be accessed through wrapped functions. KeywordsGeographic information–computational geometry–accessibility–opensource–audio–tactile
    12/2011: pages 149-163;
  • Source
    Jian Xun Peng · Stuart Ferguson · Karen Rafferty · Paul D. Kelly ·
    [Show abstract] [Hide abstract]
    ABSTRACT: This paper presents a feature selection method for data classification, which combines a model-based variable selection technique and a fast two-stage subset selection algorithm. The relationship between a specified (and complete) set of candidate features and the class label is modeled using a non-linear full regression model which is linear-in-the-parameters. The performance of a sub-model measured by the sum of the squared-errors (SSE) is used to score the informativeness of the subset of features involved in the sub-model. The two-stage subset selection algorithm approaches a solution sub-model with the SSE being locally minimized. The features involved in the solution sub-model are selected as inputs to support vector machines (SVMs) for classification. The memory requirement of this algorithm is independent of the number of training patterns. This property makes this method suitable for applications executed in mobile devices where physical RAM memory is very limited.An application was developed for activity recognition, which implements the proposed feature selection algorithm and an SVM training procedure. Experiments are carried out with the application running on a PDA for human activity recognition using accelerometer data. A comparison with an information gain-based feature selection method demonstrates the effectiveness and efficiency of the proposed algorithm.
    Neurocomputing 10/2011; 74(17):3543-3552. DOI:10.1016/j.neucom.2011.06.023 · 2.08 Impact Factor
  • Source
    Paul D. Kelly · M. Eng ·

Publication Stats

11 Citations
2.08 Total Impact Points

Top Journals


  • 2011
    • Queen's University Belfast
      • School of Electronics, Electrical Engineering and Computer Science
      Béal Feirste, N Ireland, United Kingdom