Weijia Lu
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Weijia Lu has a total of 9 co-authors. Here are the top co-authors by number of shared publications:
Zhuangzhi Yan
School of Communication and Information Engineering, Shanghai University, Shanghai, China
3 shared publicationsChen Hao
Department of Informatics , Affiliated Hospital of Nantong University , Nantong , Jiangsu 226001, China
1 shared publicationDengfu Yao
1 shared publicationHaijiao Lu
1 shared publication- Hao Chen
Information Department, Affiliated Hospital of Nantong University, Nantong, Jiangsu, 226001, China
1 shared publication - Liang Ma
Information Center, Affiliated Hospital of Nantong University, Nantong, China
1 shared publication
Latest Publications
- Open Access
- 24 July 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 136014-136023
A Clinical Prediction Model in Health Time Series Data Based on Long Short-Term Memory Network Optimized by Fruit Fly Optimization Algorithm
Aiming the problems that the clinical data of different patients is difficult for reasonable representation and the time interval between medical events is different, which lead to the difficulty of clinical prediction, a clinical prediction model based on the long short-term memory (LSTM) network optimized by fruit fly optimization algorithm in health time series data is proposed. First, FastText method is used to represent the interpretable vector of medical events, which can extract the concept relationship rich in medical information more effectively. Then, considering the strong dependence of clinical data on time stamp, LSTM network is used to model clinical events for better extraction of long-term and shortterm information, so as to improve the prediction performance of the model. Finally, the fruit fly optimization algorithm is used to find the optimal super parameters of LSTM network, which can improve the training efficiency and prediction precision of the network. Experimental results on MIMIC datasets show that the prediction precision, Recall@k and MAP@k of the proposed model are better than those of other models. The validity of the model is proved.
- 24 July 2020
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 8, 136014-136023
Open AccessA Clinical Prediction Model in Health Time Series Data Based on Long Short-Term Memory Network Optimized by Fruit Fly Optimization Algorithm
Aiming the problems that the clinical data of different patients is difficult for reasonable representation and the time interval between medical events is different, which lead to the difficulty of clinical prediction, a clinical prediction model based on the long short-term memory (LSTM) network optimized by fruit fly optimization algorithm in health time series data is proposed. First, FastText method is used to represent the interpretable vector of medical events, which can extract the concept relationship rich in medical information more effectively. Then, considering the strong dependence of clinical data on time stamp, LSTM network is used to model clinical events for better extraction of long-term and shortterm information, so as to improve the prediction performance of the model. Finally, the fruit fly optimization algorithm is used to find the optimal super parameters of LSTM network, which can improve the training efficiency and prediction precision of the network. Experimental results on MIMIC datasets show that the prediction precision, Recall@k and MAP@k of the proposed model are better than those of other models. The validity of the model is proved.
- Open Access
- 11 May 2016
- Published by Walter de Gruyter GmbH in Journal of Intelligent Systems
- Vol. 26 (3) , 573-583
Particle Swarm Optimisation-Support Vector Machine Optimised by Association Rules for Detecting Factors Inducing Heart Diseases
Existing systems for diagnosing heart diseases are time consuming, expensive, and error prone. Aiming at this, a detection algorithm for factors inducing heart diseases based on a particle swarm optimisation-support vector machine (PSO-SVM) optimised by association rules (ARs) was proposed. Firstly, AR was used to select features from a disease data set so as to train feature sets. Then, PSO-SVM was used to classify training and testing sets, and then the factors inducing heart diseases were analysed. Finally, the effectiveness and reliability of the proposed algorithm was verified by experiments on the UCI Cleveland data set with confidence as the index. The experimental results showed that females have less risk of having a heart attack than males. Irrespective of gender, once diagnosed with chest pain without symptoms and angina caused by exercise, people are more likely to suffer from heart disease. Moreover, compared with another two advanced classification algorithms, the proposed algorithm showed better classification performance and therefore can be used as a powerful tool to help doctors diagnose and treat heart diseases.
- 11 May 2016
- Published by Walter de Gruyter GmbH in Journal of Intelligent Systems
- Vol. 26 (3) , 573-583
Open AccessParticle Swarm Optimisation-Support Vector Machine Optimised by Association Rules for Detecting Factors Inducing Heart Diseases
Existing systems for diagnosing heart diseases are time consuming, expensive, and error prone. Aiming at this, a detection algorithm for factors inducing heart diseases based on a particle swarm optimisation-support vector machine (PSO-SVM) optimised by association rules (ARs) was proposed. Firstly, AR was used to select features from a disease data set so as to train feature sets. Then, PSO-SVM was used to classify training and testing sets, and then the factors inducing heart diseases were analysed. Finally, the effectiveness and reliability of the proposed algorithm was verified by experiments on the UCI Cleveland data set with confidence as the index. The experimental results showed that females have less risk of having a heart attack than males. Irrespective of gender, once diagnosed with chest pain without symptoms and angina caused by exercise, people are more likely to suffer from heart disease. Moreover, compared with another two advanced classification algorithms, the proposed algorithm showed better classification performance and therefore can be used as a powerful tool to help doctors diagnose and treat heart diseases.
- 27 October 2015
- Published by SAGE Publications in Technology and Health Care
- Vol. 23 (6) , 699-713
An improved fuzzy C-means clustering algorithm for assisted therapy of chronic bronchitis
BACKGROUND: Bronchitis is considered a non-specific inflammation in the peripheral tissues of the trachea and bronchus. Many therapeutic schemes for chronic bronchitis have been reported in existing research. METHODS: This work attempted to conduct
- 27 October 2015
- Published by SAGE Publications in Technology and Health Care
- Vol. 23 (6) , 699-713
An improved fuzzy C-means clustering algorithm for assisted therapy of chronic bronchitis
BACKGROUND: Bronchitis is considered a non-specific inflammation in the peripheral tissues of the trachea and bronchus. Many therapeutic schemes for chronic bronchitis have been reported in existing research. METHODS: This work attempted to conduct
- 1 November 2011
- Vol. 35 (6) , 437-41
[Design and implementation of EMR information system in hospitals].
With the electronic medical records information system as the core of hospital information platform design, this paper introduces the design of the system which is structured for electronic medical records, and the advantage and effectiveness is also introduced. From the aspects of the concept, system framework, data integration, right frame and safety control, identity index and a clinical pathway, etc, the paper introduces the basic idea and process of the hospital information platform design, with the hospital recording electronic medical records as the core.
- 1 November 2011
- Vol. 35 (6) , 437-41
[Design and implementation of EMR information system in hospitals].
With the electronic medical records information system as the core of hospital information platform design, this paper introduces the design of the system which is structured for electronic medical records, and the advantage and effectiveness is also introduced. From the aspects of the concept, system framework, data integration, right frame and safety control, identity index and a clinical pathway, etc, the paper introduces the basic idea and process of the hospital information platform design, with the hospital recording electronic medical records as the core.
- 1 May 2011
- Vol. 35 (3) , 169-73
[A noninvasive and continuous method for blood pressure measurement using pulse wave].
This paper presents a method of noninvasive and continuous measurement of blood pressure by pulse wave. The method is realized by extracting the characteristic parameters of human brachial artery pulse wave and developing the stepwise regression equation. The experiment results showed that blood pressure measured by this method was well correlated with which measured by mercury sphygmomanometer. The mean difference of blood pressure was smaller than 3 mmHg, and the standard deviation was smaller than 5 mmHg.
- 1 May 2011
- Vol. 35 (3) , 169-73
[A noninvasive and continuous method for blood pressure measurement using pulse wave].
This paper presents a method of noninvasive and continuous measurement of blood pressure by pulse wave. The method is realized by extracting the characteristic parameters of human brachial artery pulse wave and developing the stepwise regression equation. The experiment results showed that blood pressure measured by this method was well correlated with which measured by mercury sphygmomanometer. The mean difference of blood pressure was smaller than 3 mmHg, and the standard deviation was smaller than 5 mmHg.