A Fully Automated Intelligent Medicine Dispensary System Based on AIoT

Juihung Chang, Hoeyuan Ong, Tihao Wang, Hsiao Hwa Chen

Research output: Contribution to journalArticlepeer-review

2 Citations (Scopus)


The COVID-19 pandemic has caused a high rate of infection, and thus effective epidemic prevention measures of avoiding the second spread of COVID-19 in hospitals are major challenges for healthcare workers. Hospitals, where medicines are collected, are vulnerable to the rapid spread of COVID-19. Using the remote health monitoring technology of the Internet of Things (IoT) to automatically monitor and record the basic medical information of patients, reduce the workload of healthcare workers, and avoid direct contact with healthcare workers to cause secondary infections is an important research topic. This research proposes a new artificial intelligence solution based on the IoT, replacing existing medicine stations and recognizing medicine bags through the state-of-the-art optical character recognition (OCR) model and PP-OCR v2. The use of OCR in identification of medicine bags can replace healthcare workers in data recording. In addition, this research proposes an administrator management and monitoring system to monitor the equipment and provide a mobile application for patients to check the latest status of medicine bags in real time, and record their medication times. The results of the experiments indicate that the recognition model works very well in different conditions (up to 80.76% in PP-OCR v2 and 94.22% in PGNet), which supports both Chinese and English languages.

Original languageEnglish
Pages (from-to)23954-23966
Number of pages13
JournalIEEE Internet of Things Journal
Issue number23
Publication statusPublished - 2022 Dec 1

All Science Journal Classification (ASJC) codes

  • Signal Processing
  • Information Systems
  • Hardware and Architecture
  • Computer Science Applications
  • Computer Networks and Communications


Dive into the research topics of 'A Fully Automated Intelligent Medicine Dispensary System Based on AIoT'. Together they form a unique fingerprint.

Cite this