Corpus ID: 212600786

Gaussian Distributive Stochastic Neighbor Embedding Based Feature Extraction for Medical Data Diagnosis

@inproceedings{Nithya2018GaussianDS,
  title={Gaussian Distributive Stochastic Neighbor Embedding Based Feature Extraction for Medical Data Diagnosis},
  author={Nithya},
  year={2018}
}
-Feature extraction is a key process to reduce the dimensionality of medical dataset for efficient disease prediction. The feature extraction technique removes irrelevant features to acquire higher prediction accuracy during disease diagnosis. Few research works are developed to extract the relevant features from dataset using different data mining techniques. But, performance of conventional feature extraction technique was not efficient which reduces the accuracy of disease prediction and… Expand

Figures and Tables from this paper

References

SHOWING 1-10 OF 23 REFERENCES
Feature selection method based on mutual information and class separability for dimension reduction in multidimensional time series for clinical data
TLDR
The improved method can effectively reduce the dimensions of multidimensional time series for clinical data through the combination of the Kozachenko–Leonenko (K–L) information entropy estimation method for feature extraction based on mutual information and the feature selection algorithm based on class separability. Expand
Survival analysis for high-dimensional, heterogeneous medical data: Exploring feature extraction as an alternative to feature selection
TLDR
It is proposed to use random survival forests to accurately determine local neighborhood relations from right censored survival data and consider multiview spectral embedding algorithms, which specifically have been developed for these situations. Expand
On Orthogonal Feature Extraction Model with Applications in Medical Prognosis
TLDR
An Orthogonal Feature Extraction (OFE) model based on feature ranking techniques is proposed, which aims at improving cancer prediction accuracy andumerical results indicated that OFE method can efficiently construct combinations of significant variables enabling computational complexity reduction and also provide recognizable better performance. Expand
A novel feature extraction approach based on ensemble feature selection and modified discriminant independent component analysis for microarray data classification
Abstract Microarray data play critical role in cancer classification. However, with respect to the samples scarcity compared to intrinsic high dimensionality, most approaches fail to classify smallExpand
Breast cancer discriminant feature analysis for diagnosis via jointly sparse learning
TLDR
Experimental results on breast cancer datasets indicate that JSDA outperforms some well-known subspace learning algorithms in prediction accuracy, not matter they are non-sparse or sparse, particularly in the cases of small sample sizes. Expand
Selecting and Extracting Effective Features for Automated Diagnosis of Alzheimer's Disease
TLDR
The results show that the highest classification performance is obtained using the proposed model, and this is very promising compared to Principle Component Analysis (PCA) and Linear Discriminate Analysis (LDA). Expand
A framework for feature extraction from hospital medical data with applications in risk prediction
TLDR
For unplanned readmissions, auto-extracted standard features from complex medical records, outperformed baselines derived from the socio-demographic information and Elixhauser comorbidities, over 20 settings (5 prediction horizons over 4 diseases). Expand
Diabetes Disease Diagnosis Method based on Feature Extraction using K-SVM
TLDR
This study proposed an integration approach between the SVM technique and K-means clustering algorithms to diagnose diabetes disease and achieved high accuracy for differentiating the hidden patterns of the Diabetic and Non-diabetic patients compared with the modern diagnosis methods. Expand
Supervised Feature Selection for Diagnosis of Coronary Artery Disease Based on Genetic Algorithm
TLDR
This paper presents a new method for the diagnosis of Coronary Artery Diseases founded on Genetic Algorithm (GA) wrapped Bayes Naive (BN) based FS and results have shown very promising outcomes. Expand
Hybrid Feature Selection Based Weighted Least Squares Twin Support Vector Machine Approach for Diagnosing Breast Cancer, Hepatitis, and Diabetes
TLDR
A hybrid feature selection (HFS) based efficient disease diagnostic model for Breast Cancer, Hepatitis, and Diabetes that combines the positive aspects of both Filter and Wrapper FS approaches is proposed. Expand
...
1
2
3
...