Designing Extreme Learning Machine Network Structure Based on Tolerance Rough Set

2017 ◽  
Vol 13 (4) ◽  
pp. 38-55 ◽  
Author(s):  
Han Ke
Keyword(s):  
Breast Cancer ◽  
Extreme Learning Machine ◽  
Rough Set ◽  
Network Structure ◽  
High Efficiency ◽  
Breast Cancer Dataset ◽  
Intelligent Technique ◽  
Tolerance Rough Set ◽  
Learning Machine

In this paper, we present a new extreme learning machine network structure on the basis of tolerance rough set. The purpose of this paper is to realize the high-efficiency and multi-dimensional ELM network structure. Various published algorithms have been applied to breast cancer datasets, but rough set is a fairly new intelligent technique that applies to predict breast cancer recurrence. We analyze Ljubljana Breast Cancer Dataset, firstly, obtain lower and upper approximations and calculate the accuracy and quality of the classification. The high values of the quality of classification and accuracy prove that the attributes selected can well approximate the classification. Rough sets approach is established to solve the prolem of tolerance.

Designing Extreme Learning Machine Network Structure Based on Tolerance Rough Set

2020 ◽  
pp. 263-282
Author(s):  
Han Ke
Keyword(s):  
Breast Cancer ◽  
Extreme Learning Machine ◽  
Rough Set ◽  
Network Structure ◽  
High Efficiency ◽  
Breast Cancer Dataset ◽  
Tolerance Rough Set ◽  
Learning Machine ◽  
Lower And Upper Approximations

In this paper, we present a new extreme learning machine network structure on the basis of tolerance rough set. The purpose of this paper is to realize the high-efficiency and multi-dimensional ELM network structure. Various published algorithms have been applied to breast cancer datasets, but rough set is a fairly new intelligent technique that applies to predict breast cancer recurrence. We analyze Ljubljana Breast Cancer Dataset, firstly, obtain lower and upper approximations and calculate the accuracy and quality of the classification. The high values of the quality of classification and accuracy prove that the attributes selected can well approximate the classification. Rough sets approach is established to solve the prolem of tolerance.

Comparison of Several Extreme Learning Machine Algorithm for Modeling Concrete Compressive Strength

2014 ◽  
Vol 548-549 ◽  
pp. 1735-1738 ◽  
Author(s):  
Jian Tang ◽  
Dong Yan ◽  
Li Jie Zhao
Keyword(s):  
Compressive Strength ◽  
Extreme Learning Machine ◽  
Prediction Accuracy ◽  
Partial Least Square ◽  
Least Square ◽  
Extreme Learning Machines ◽  
Concrete Compressive Strength ◽  
Learning Machines ◽  
Learning Machine

Modeling concrete compressive strength is useful to ensure quality of civil engineering. This paper aims to compare several Extreme learning machines (ELMs) based modeling approaches for predicting the concrete compressive strength. Normal ELM algorithm, Partial least square-based extreme learning machines (PLS-ELMs) algorithm and Kernel ELM (KELM) algorithm are used and evaluated. Results indicate that the normal ELMs algorithm has the highest modeling speed, and the KELM has the best prediction accuracy. Every method is validated for modeling concrete compressive strength. The appropriate modeling approach should be selected according different purposes.

scholarly journals Distance Based Multiple Kernel ELM: A Fast Multiple Kernel Learning Approach

2015 ◽  
Vol 2015 ◽  
pp. 1-9 ◽  
Author(s):  
Chengzhang Zhu ◽  
Xinwang Liu ◽  
Qiang Liu ◽  
Yuewei Ming ◽  
Jianping Yin
Keyword(s):  
Extreme Learning Machine ◽  
High Efficiency ◽  
Computational Cost ◽  
Multiple Kernel Learning ◽  
Superior Performance ◽  
Kernel Learning ◽  
Normal Vector ◽  
Learning Approach ◽  
Multiple Kernel ◽  
Learning Machine

We propose a distance based multiple kernel extreme learning machine (DBMK-ELM), which provides a two-stage multiple kernel learning approach with high efficiency. Specifically, DBMK-ELM first projects multiple kernels into a new space, in which new instances are reconstructed based on the distance of different sample labels. Subsequently, anl2-norm regularization least square, in which the normal vector corresponds to the kernel weights of a new kernel, is trained based on these new instances. After that, the new kernel is utilized to train and test extreme learning machine (ELM). Extensive experimental results demonstrate the superior performance of the proposed DBMK-ELM in terms of the accuracy and the computational cost.

scholarly journals Application of Rough Sets to Predict the Breast Cancer Risk Association with Routine Blood Analyses

2021 ◽  
Vol 10 (3) ◽  
pp. 67-72
Author(s):  
Amr H. AbdelHaliem ◽  
Mohammed A. Atiea ◽  
Mohammed E.Wahed ◽  
Mohammed S. Metwally
Keyword(s):  
Breast Cancer ◽  
Expert Systems ◽  
Rough Set ◽  
Prediction Models ◽  
Rule Induction ◽  
Breast Cancer Dataset ◽  
Operating Characteristics ◽  
Suggested Approach ◽  
Hybrid Prediction ◽  
Routine Blood

For women around the globe, breast cancer has been a significant cause of mortality. Around the same time, early diagnosis and high cancer prediction precision are critical to improving the quality of care and the recovery rate of the patient. Expert systems and machine learning techniques are gaining prominence in this area as a result of efficient classification and high diagnostic ability. This paper introduces a model of hybrid prediction (RS QA) based on a rough set theoryand a quasi-optimal (AQ) rule induction algorithm. To find a minimal set of attributes that completely define the results, a rough set tool is used. The selected characteristics were collected, ensuring the high standard of the classification. Then to produce the decision rules, we use the quasi-optimal (AQ) rule induction algorithm. These hybrid prediction models allow expert systems to be built based on the conceptual rules of the IF/THEN sort. The suggested experiment is performed using the Coimbra Breast Cancer Dataset (BCCD) based on sets of measures that can be obtained in routine blood tests. Using classification precision, sensitivity, specificity, and receiver operating characteristics (ROC) curves, the efficiency of our suggested approach was assessed. Experimental results indicate the highest classification accuracy (91.7 percent), sensitivity (83.3 percent), and precision (94.3) obtained by the proposed (RS_QA) model.

Sign in / Sign up

Export Citation Format

Share Document