Limits...
Using Open Geographic Data to Generate Natural Language Descriptions for Hydrological Sensor Networks.

Molina M, Sanchez-Soriano J, Corcho O - Sensors (Basel) (2015)

Bottom Line: In this paper, we discuss the feasibility of using geographic knowledge from public databases available on the Web (such as OpenStreetMap, Geonames, or DBpedia) to automatically construct such descriptions.We present a general method that uses such information to generate sensor descriptions in natural language.The results of the evaluation of our method in a hydrologic national sensor network showed that this approach is feasible and capable of generating adequate sensor descriptions with a lower development effort compared to other approaches.

View Article: PubMed Central - PubMed

Affiliation: Department of Artificial Intelligence, Technical University of Madrid, Campus de Montegancedo S/N, 28660 Boadilla del Monte, Madrid, Spain. martin.molina@upm.es.

ABSTRACT
Providing descriptions of isolated sensors and sensor networks in natural language, understandable by the general public, is useful to help users find relevant sensors and analyze sensor data. In this paper, we discuss the feasibility of using geographic knowledge from public databases available on the Web (such as OpenStreetMap, Geonames, or DBpedia) to automatically construct such descriptions. We present a general method that uses such information to generate sensor descriptions in natural language. The results of the evaluation of our method in a hydrologic national sensor network showed that this approach is feasible and capable of generating adequate sensor descriptions with a lower development effort compared to other approaches. In the paper we also analyze certain problems that we found in public databases (e.g., heterogeneity, non-standard use of labels, or rigid search methods) and their impact in the generation of sensor descriptions.

No MeSH data available.


Related in: MedlinePlus

Evaluation results for geographic areas. The graphic shows the values obtained for the baseline accuracy (orange) and for our method’s accuracy (blue).
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC4541865&req=5

sensors-15-16009-f006: Evaluation results for geographic areas. The graphic shows the values obtained for the baseline accuracy (orange) and for our method’s accuracy (blue).

Mentions: As a result of this evaluation process, we obtained a 73% improvement in accuracy with respect to the baseline. The method obtained an average accuracy of 0.52 of correct names for the complete set of sensors. There are significant differences among geographic areas corresponding to different basins (Figure 6). The best values are for the following areas: Jucar basin (0.66), Guadiana basin (0.63), and Catalonian basin (0.63). The worst value (0.37) corresponds to the Tajo basin. This low value can be justified (as it is argued later) because domain experts in this area created the descriptions following different naming strategies compared to the rest of the areas.


Using Open Geographic Data to Generate Natural Language Descriptions for Hydrological Sensor Networks.

Molina M, Sanchez-Soriano J, Corcho O - Sensors (Basel) (2015)

Evaluation results for geographic areas. The graphic shows the values obtained for the baseline accuracy (orange) and for our method’s accuracy (blue).
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC4541865&req=5

sensors-15-16009-f006: Evaluation results for geographic areas. The graphic shows the values obtained for the baseline accuracy (orange) and for our method’s accuracy (blue).
Mentions: As a result of this evaluation process, we obtained a 73% improvement in accuracy with respect to the baseline. The method obtained an average accuracy of 0.52 of correct names for the complete set of sensors. There are significant differences among geographic areas corresponding to different basins (Figure 6). The best values are for the following areas: Jucar basin (0.66), Guadiana basin (0.63), and Catalonian basin (0.63). The worst value (0.37) corresponds to the Tajo basin. This low value can be justified (as it is argued later) because domain experts in this area created the descriptions following different naming strategies compared to the rest of the areas.

Bottom Line: In this paper, we discuss the feasibility of using geographic knowledge from public databases available on the Web (such as OpenStreetMap, Geonames, or DBpedia) to automatically construct such descriptions.We present a general method that uses such information to generate sensor descriptions in natural language.The results of the evaluation of our method in a hydrologic national sensor network showed that this approach is feasible and capable of generating adequate sensor descriptions with a lower development effort compared to other approaches.

View Article: PubMed Central - PubMed

Affiliation: Department of Artificial Intelligence, Technical University of Madrid, Campus de Montegancedo S/N, 28660 Boadilla del Monte, Madrid, Spain. martin.molina@upm.es.

ABSTRACT
Providing descriptions of isolated sensors and sensor networks in natural language, understandable by the general public, is useful to help users find relevant sensors and analyze sensor data. In this paper, we discuss the feasibility of using geographic knowledge from public databases available on the Web (such as OpenStreetMap, Geonames, or DBpedia) to automatically construct such descriptions. We present a general method that uses such information to generate sensor descriptions in natural language. The results of the evaluation of our method in a hydrologic national sensor network showed that this approach is feasible and capable of generating adequate sensor descriptions with a lower development effort compared to other approaches. In the paper we also analyze certain problems that we found in public databases (e.g., heterogeneity, non-standard use of labels, or rigid search methods) and their impact in the generation of sensor descriptions.

No MeSH data available.


Related in: MedlinePlus