Artificial bee colony optimization-based weighted extreme learning machine for imbalanced data learning

2018 ◽  
Vol 22 (S3) ◽  
pp. 6937-6952 ◽  
Author(s):  
Xiaofen Tang ◽  
Li Chen
Keyword(s):  
Extreme Learning Machine ◽  
Artificial Bee Colony ◽  
Imbalanced Data ◽  
Artificial Bee Colony Optimization ◽  
Bee Colony ◽  
Weighted Extreme Learning Machine ◽  
Bee Colony Optimization ◽  
Learning Machine ◽  
Imbalanced Data Learning

Mining of structural motifs in proteins using artificial bee colony optimization framework for druggability

2021 ◽  
Author(s):  
L. S. Suma ◽  
S. S. Vinod Chandra
Keyword(s):  
Artificial Bee Colony ◽  
Area Under The Curve ◽  
Docking Studies ◽  
Artificial Bee Colony Optimization ◽  
Optimization Framework ◽  
Bee Colony ◽  
Novel Variant ◽  
Bee Colony Optimization ◽  
Novel Strategy ◽  
Sensitivity Specificity

In this work, we have developed an optimization framework for digging out common structural patterns inherent in DNA binding proteins. A novel variant of the artificial bee colony optimization algorithm is proposed to improve the exploitation process. Experiments on four benchmark objective functions for different dimensions proved the speedier convergence of the algorithm. Also, it has generated optimum features of Helix Turn Helix structural pattern based on the objective function defined with occurrence count on secondary structure. The proposed algorithm outperformed the compared methods in convergence speed and the quality of generated motif features. The motif locations obtained using the derived common pattern are compared with the results of two other motif detection tools. 92% of tested proteins have produced matching locations with the results of the compared methods. The performance of the approach was analyzed with various measures and observed higher sensitivity, specificity and area under the curve values. A novel strategy for druggability finding by docking studies, targeting the motif locations is also discussed.

scholarly journals Pareto front feature selection based on artificial bee colony optimization

2018 ◽  
Vol 422 ◽  
pp. 462-479 ◽  
Author(s):  
Emrah Hancer ◽  
Bing Xue ◽  
Mengjie Zhang ◽  
Dervis Karaboga ◽  
Bahriye Akay
Keyword(s):  
Feature Selection ◽  
Pareto Front ◽  
Artificial Bee Colony ◽  
Artificial Bee Colony Optimization ◽  
Bee Colony ◽  
Bee Colony Optimization

Two-step fault diagnosis framework for rolling element bearings with imbalanced data based on GSA-WELM and GSA-ELM

2017 ◽  
Vol 232 (16) ◽  
pp. 2937-2947 ◽  
Author(s):  
Yuan Lan ◽  
Xiaohong Han ◽  
Weiwei Zong ◽  
Xiaojian Ding ◽  
Xiaoyan Xiong ◽  
...  
Keyword(s):  
Fault Diagnosis ◽  
Extreme Learning Machine ◽  
Gravitational Search Algorithm ◽  
Imbalanced Data ◽  
Rolling Element Bearing ◽  
Rolling Element Bearings ◽  
Misclassification Cost ◽  
Weighted Extreme Learning Machine ◽  
Rolling Element ◽  
Learning Machine

Rolling element bearings constitute the key parts on rotating machinery, and their fault diagnosis is of great importance. In many real bearing fault diagnosis applications, the number of fault data is much less than the number of normal data, i.e. the data are imbalanced. Many traditional diagnosis methods will get low accuracy because they have a natural tendency to favor the majority class by assuming balanced class distribution or equal misclassification cost. To deal with imbalanced data, in this article, a novel two-step fault diagnosis framework is proposed to diagnose the status of rolling element bearings. Our proposed framework consists of two steps for fault diagnosis, where Step 1 makes use of weighted extreme learning machine in an effort to classify the normal or abnormal categories, and Step 2 further diagnoses the underlying anomaly in detail by using preliminary extreme learning machine. In addition, gravitational search algorithm is applied to further extract the significant features and determine the optimal parameters of the weighted extreme learning machine and extreme learning machine classifiers. The effectiveness of our proposed approach is testified on the raw data collected from the rolling element bearing experiments conducted in our Institute, and the empirical results show that our approach is really fast and can achieve the diagnosis accuracies more than 96%.

Sign in / Sign up

Export Citation Format

Share Document