In order to meet the multifarious needs for drug information and to cope with the post-marketing surveillance of drugs adequately, an on-line drug information network, which is composed of two data bases, clinical case record data base and literature data base, has been developed. Primary considerations in designing these systems were input of clean data, accurate input, insuring that no ADRs are overlooked, accumulation of the latest data, saving manpower required for processing, and processing large quantities of data. This system is also designed to input and to output in Japanese character.
A robust method for coarse classifier construction from a large number of basic recognizers for on-line handwritten Chinese/Japanese character recognition