This method ranks the documents using the Okapi BM25 (Robertson et al., 1999) ranking function, which is often used as a baseline for ranking in keyword-matching-based search systems.
We used the US National Library of Medicine (NLM)'s Medical Subject Headings (MeSH) ontology to expand the baseline ranked queries.
A conventional IR system (Lucene) is used to provide a baseline document ranking from which a classification can be derived by selection of a threshold.
In addition to the "ontology-centred" mechanisms provided for matchmaking and semi-automatic annotation of web services, the system provides a ranking mechanism to support the selection of markets and services that, in contrast to baseline ranking approaches, is based on agents' preferences and satisfaction as well as on the workload.
Information derived from the OntoGene pipeline, and from the ranking process described in the previous section, is then added as additional features in order to improve the baseline ranking generated by the IR system [the integration of the various components is performed using mainly JRuby (http://jruby.org/), through which the Lucene API is accessed].
The determinants of the LTL ranking at the follow-up examination were evaluated in a model that included baseline LTL ranking, age, sex, smoking (yes/no), and BMI.
Figure 2 shows the baseline risk ranking using OEHHA unit risks or cancer potency factors, along with the median risk calculated using the U.S. EPA potency factors.
The determinants of the LTL ranking at the follow-up examination were assessed using multiple regression analysis, including in the model the baseline LTL ranking, age, sex, present smoking (yes/no), and BMI.
This method is used as a baseline for the performance of document ranking.
To distinguish the pattern from clustering produced simply by ranking the serotypes, a baseline distribution is shown.
