Thông tin chung
  English
  Đề tài NC khoa học
  Bài báo, báo cáo khoa học
  Hướng dẫn Sau đại học
  Sách và giáo trình
  Các học phần và môn giảng dạy
  Giải thưởng khoa học, Phát minh, sáng chế
  Khen thưởng
  Thông tin khác
  Tài liệu tham khảo
  Hiệu chỉnh
 
Số người truy cập: 107,100,658

 Improvement of Machine Learning Method by Combining Flow Text and Layout Text in Extracting Information from Scanned Healthcare Documents
Tác giả hoặc Nhóm tác giả: Van-Minh Le, Thi Thanh Ha Hoang
Nơi đăng: Frontiers in Intelligent Computing: Theory and Applications; Số: 1;Từ->đến trang: 265-274;Năm: 2020
Lĩnh vực: Công nghệ thông tin; Loại: Bài báo khoa học; Thể loại: Quốc tế
TÓM TẮT
Electronic Health Records system plays a very important part of hospitals and also clinical units. The basic problem of this kind of system is how to migrate data from traditional system which contains typical documents to new one. The main solution of this paper is to extract data from scanned healthcare documents (.pdf file) and insert them into database. Normally, a .pdf file can be converted into text files with two formats: flow text and keep layout text. While flow text shows recognized words one by one, line by line, keep layout text presents these words column by column. Some columns represent data and others represent description of data. In this paper, we propose a method to take advantages of description of data to improve the accuracy of data extraction. This method combines flow text format and keep layout to make feature of words for the machine learning approach to extract data.
ABSTRACT
Electronic Health Records system plays a very important part of hospitals and also clinical units. The basic problem of this kind of system is how to migrate data from traditional system which contains typical documents to new one. The main solution of this paper is to extract data from scanned healthcare documents (.pdf file) and insert them into database. Normally, a .pdf file can be converted into text files with two formats: flow text and keep layout text. While flow text shows recognized words one by one, line by line, keep layout text presents these words column by column. Some columns represent data and others represent description of data. In this paper, we propose a method to take advantages of description of data to improve the accuracy of data extraction. This method combines flow text format and keep layout to make feature of words for the machine learning approach to extract data.
© Đại học Đà Nẵng
 
 
Địa chỉ: 41 Lê Duẩn Thành phố Đà Nẵng
Điện thoại: (84) 0236 3822 041 ; Email: dhdn@ac.udn.vn