| Nome: | Descrição: | Tamanho: | Formato: | |
|---|---|---|---|---|
| 1.03 MB | Adobe PDF |
Orientador(es)
Resumo(s)
Mass drug administration is the process of distributing medication to people who are in areas with risk of neglected tropical diseases. The monitoring of this process is supported by the application of forms in the communities, which are then sent to the headquarters, where they are manually entered into governmental health information systems. This paper aims at finding a solution for automating the process, making it more efficient, reliable and scalable.
The proposed solution involves the usage of Optical Character Recognition (OCR) to extract the data, and is composed of a Backend, an Android Application and a Backoffice. It was evaluated using several metrics, achieving mean values of 0.8% Character Error Rate (CER), 2.5% Word Error Rate (WER), 3.7% Field Error Rate (FER) and 96.2% Precision, Recall and F1 score. Forms filled in English and forms filled using print handwriting style had significantly better results than forms
filled in Portuguese and forms filled using cursive style, respectively. The application was used by two testers from the Nongovernmental Organization (NGO), resulting in positive feedback, with some improvements being suggested.
Descrição
Palavras-chave
Optical Character Recognition Text extraction Mass drug administration Web Information System Android development
Contexto Educativo
Citação
Ribeiro, R., Teixeira, C., Vicente, P. & Sousa, P. B. (2025, dezembro 9). Development of a mass drug administration monitoring system for a humanitarian NGO. In Sá, C., Oliveira, C., Silva, E., Cardoso, M., Morgado, N., Proença, P., Carvalho, P., Vieira, R., Meireles, R., & Moreira, S. (Eds.). Simpósio de Engenharia Informática 2025. Instituto Superior de Engenharia do Porto ISEP – P.Porto
Editora
Instituto Superior de Engenharia do Porto (ISEP) – P.Porto
