[Tao Weiye] College of Medical Information Engineering, Guangdong Pharmaceutical University, Guangzhou, China;[Zeng Jieqiong] Electrical Engineering, Guangzhou Senior Light Industry Technical School, Guangzhou, China
The key characteristic of Riemannian geometry is Riemannian metric. The most important work for the discretion of Riemannian geometry is to seek a discret representation of Riemannian metric, which fo
[Wang, Ruoyu] Information Network Engineering and Research Center, South China University of Technology, Guangzhou, China;[Tang, Deyu; Liu, Zhen; Li, Jincheng] College of Medical Information Engineering, Guangdong Pharmaceutical University, Guangzhou, China
Boosting - Class imbalance - Class imbalance problems - Classification accuracy - ELM (extreme learning machine) - Misclassification costs - Mutual informations - Performance balance
Journal of Computational Information Systems,2013年9(2):493-501 ISSN：1553-9105
[Tang, Deyu; Cai, Yongming] College of Medical Information and Engineering, GuangDong Pharmaceutical University, Guangdong 510006, China;[Cai, Xianfa] College of Computer Science and Engineering, South China University of Technology, Guangdong 510006, China
[Zhou, Huaying; Xue, Yonggang; Zhang, Qirui] Guangdong Pharmaceut Univ, Coll Med Informat Engn, Guangzhou, Guangdong, Peoples R China.
medical information;document categorization;information entropy;document indexing;Naive Bayes;Rocchio
Medical document categorization is the process of automatically assigning one or more predefined category labels to medical documents. Document indexing plays a very important role in the process of classification. This paper proposes an improved method of computing term weights which is called tfidfie (term frequency, inverted document tfidf frequency and inverted entropy). In comparison with the I h (term frequency and inverted document frequency) function, the tfidfie function adds an information entropy factor, H, which represents the distribution of documents in the training set in which the term occurs. Then, we discuss the effects of training set in medical document categorization. An imbalanced training set decreases the performance of classifier. Considering the characteristics of medical documents, the medical classifiers are constructed by the methods of Naive Bayes and Rocchio respectively. The experiment results show that tfidfie improves the classification performance and Naive Bayes outperforms Rocchio.
Liu, Hua;Chen, Xiaofeng;Zhou, Changren;Li, Hong
[Li, Hong; Zhou, Changren] Department of Materials Science and Engineering, Jinan University, Guangzhou 510632, China;[Liu, Hua] College of Medical Information Engineering, Guangdong Pharmaceutical University, Guangzhou 510006, China;[Liu, Hua; Chen, Xiaofeng] College of Materials Science and Engineering, South China University of Technology, Guangzhou 510640, China
[Cai, Yongming; Luo, Man; Tang, Deyu; Yi, Faling] Department of Medical Information Engineering GuangDong Pharmaceutical University, Guangzhou, China
Gas law - Healthy humans - Ideal gas law - Lung simulators - PID controllers - Recoil pressure - Transmural pressure - Ventilation mode
The aim of this paper is to present a mechanical lung to simulate human normal breathing. It is based on gas laws and pulmonary compliance theories to establish mathematical model of the lung respiration. The ventilation mode algorithm and the PID controller are fulfilled. The dependency of airway resistance on lung recoil pressure and transmural pressure of the airways are simulated. The result shows that the method is reasonable.