Biomedical subjects

Mark L Nagurka

Publications and source records attributed to Mark L Nagurka.

2 recordsLinked to original sources

PubMed2006

Effect of keyswitch design of desktop and notebook keyboards related to key stiffness and typing force.

This study aimed to compare and analyse rubber-dome desktop, spring-column desktop and notebook keyboards in terms of key stiffness and fingertip typing force. The spring-column keyboard resulted in the highest mean peak contact force (0.86N), followed by the rubber dome desktop (0.68N) and the notebook (0.59N). All these differences were statistically significant. Likewise, the spring-column keyboard registered the highest fingertip typing force and the notebook keyboard the lowest. A comparison of forces showed the notebook (rubber dome) keyboard had the highest fingertip-to-peak contact force ratio (overstrike force), and the spring-column generated the least excess force (as a ratio of peak contact force). The results of this study could aid in optimizing computer key design that could possibly reduce subject discomfort and fatigue.

Adult↗

PubMed2006

One-class-at-a-time removal sequence planning method for multiclass classification problems.

Using dynamic programming, this work develops a one-class-at-a-time removal sequence planning method to decompose a multiclass classification problem into a series of two-class problems. Compared with previous decomposition methods, the approach has the following distinct features. First, under the one-class-at-a-time framework, the approach guarantees the optimality of the decomposition. Second, for a K-class problem, the number of binary classifiers required by the method is only K-1. Third, to achieve higher classification accuracy, the approach can easily be adapted to form a committee machine. A drawback of the approach is that its computational burden increases rapidly with the number of classes. To resolve this difficulty, a partial decomposition technique is introduced that reduces the computational cost by generating a suboptimal solution. Experimental results demonstrate that the proposed approach consistently outperforms two conventional decomposition methods.

Algorithms↗