
doi: 10.21138/gf.591
Las matrices de confusion son la forma mas usual y estandar de informar sobre la exactitud tematica de productos derivados de la clasificacion de datos procedentes de imagenes. En este marco, son ampliamente utilizados dos indices: el porcentaje de acuerdo y el indice Kappa. Ambos son indices globales y no permiten un control categoria por categoria y, aun menos, establecer dentro de una categoria condiciones especificas. En este trabajo se propone un metodo novedoso basado en la distribucion multinomial y en un test estadistico exacto. De esta forma, se pueden establecer las preferencias de exactitud para cada categoria y tambien establecer cierto grado de mala clasificacion entre distintas categorias.
| selected citations These citations are derived from selected sources. This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | 2 | |
| popularity This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network. | Average | |
| influence This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically). | Average | |
| impulse This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network. | Average |
