Improving Accuracy of Imbalanced Clinical Data Classification Using Synthetic Minority Over-Sampling Technique

2019 ◽  
pp. 99-110 ◽  
Author(s):  
Fatihah Mohd ◽  
Masita Abdul Jalil ◽  
Noor Maizura Mohamad Noora ◽  
Suryani Ismail ◽  
Wan Fatin Fatihah Yahya ◽  
...  
Keyword(s):  
Clinical Data ◽  
Data Classification ◽  
Sampling Technique ◽  
Improving Accuracy

Efficient Probabilistic Analysis and Design Optimization Using Data Classification Decision Boundaries

2010 ◽  
Author(s):  
Liping Wang ◽  
Arun K. Subramaniyan ◽  
Don Beeson
Keyword(s):  
Probabilistic Analysis ◽  
Adaptive Sampling ◽  
Optimization Design ◽  
Data Classification ◽  
Sampling Technique ◽  
Support Vector ◽  
Classification Methods ◽  
Analysis And Design ◽  
Using Data ◽  
Decision Boundaries

A new technique for performing probabilistic analysis and optimization design using data classification methods is investigated. The approach is based on nonlinear decision boundaries constructed from data classification methods. A statistical learning tool known as support vector machine (SVM) is used to construct the boundaries. An adaptive sampling technique is used to generate samples and update the approximated decision function. The proposed approach is demonstrated with several benchmark and engineering problems.

scholarly journals Medical Data Classification Based on SMOTE and Recurrent Neural Network

2020 ◽  
Vol 9 (3) ◽  
pp. 2560-2565
Keyword(s):  
Neural Network ◽  
Recurrent Neural Network ◽  
Nearest Neighbor ◽  
Data Classification ◽  
Sampling Technique ◽  
Medical Data ◽  
K Nearest Neighbor ◽  
Data Imbalance ◽  
Imbalance Problem ◽  
Medical Data Classification

Medical data classification analysis the medical data of the patients to predict the diseases risk. Data mining techniques were highly used in the medical data classification and predicted the diseases. Many existing methods were use the various classifier and feature selection to improve the performance of the classification. Although data imbalance problem is need to be solved for increases the performance. In this research, Synthetic Minority Over-sampling TEchnique (SMOTE) techniques is used for solving the data imbalance problem and Recurrent Neural Network (RNN) was used for the classification. The SMOTE method based on the k Nearest Neighbor (kNN) for the over-sample and under-sample the attributes. The RNN process the instance independent of the previous instance for the classification. Four medical datasets of University of California, Irvine (UCI) were used to evaluate the effectiveness of the proposed SMOTE-RNN method. The proposed SMOTE-RNN method has the accuracy of 85 % while existing method has 82 % accuracy.

scholarly journals A Study to Assess the Stress among Antenatal Women Admitted for Safe Confinement at a Tertiary Level Hospital, Thiruvananthapuram, Kerala

2021 ◽  
Vol 8 (7) ◽  
pp. 391-396
Author(s):  
Gayathri Krishna ◽  
Aswathy S R ◽  
Arathy Lal S
Keyword(s):  
Clinical Data ◽  
Stress Level ◽  
Sampling Technique ◽  
Research Approach ◽  
Mild Stress ◽  
Severe Stress ◽  
Cross Sectional Survey ◽  
Related Factors ◽  
Cross Sectional ◽  
Moderate Stress

Aim: To assess stress among antenatal women admitted for safe confinement and to find stress level and related factors for stress. Identifying the level of stress will help to develop interventions to reduce the stress. Objectives: i) To find out the level of stress experienced by antenatal women. ii) To find out the association between level of stress and selected socio-demographic and clinical data of antenatal women. Method: A quantitative research approach-descriptive cross-sectional survey design was adopted. 60 samples were selected for the study by using purposive sampling technique. Results: It is identified that 1% of selected antenatal women had no stress, 73% had mild stress, 25% had moderate stress and 1% had severe stress. After calculation of chi square values, it is identified that there is association between stress level and selected sociodemographic variables (occupation) and also there is significant association between stress level and clinical data (parity). Conclusion: Majority of women in their antenatal period experience varying stress. 73.33% of them had mild stress where as 26.66% experienced moderate stress. Extreme levels of stress including no stress and severe stress were very rare ie, 1%. Multiple factors have association with their stress level. Present study documented significant association with parity and occupational status of women. Keywords: stress, antenatal women, safe confinement.

Sign in / Sign up

Export Citation Format

Share Document