Kestrel-based Search Algorithm (KSA) and Long Short Term Memory (LSTM) Network for feature selection in classification of high-dimensional bioinformatics datasets
Journal Title: Annals of Computer Science and Information Systems - Year 2018, Vol 15, Issue
Abstract
Although deep learning methods have been applied to the selection of features in the classification problem, current methods of learning parameters to be used in the classification approach can vary in accuracy at each time interval, resulting in potentially inaccurate classification of features. To address this challenge, this study proposes an approach to learning these parameters by using two different aspects of Kestrel bird behavior to adjust the learning rate until the optimal value of the parameter is found: random encircling from a hovering position and learning through imitation from the well-adapted behaviour of other Kestrels. The proposed bio-inspired approach is integrated with deep learning method (that is, recurrent neural network with long short term memory network). A benchmark dataset (with continuous data attributes) was chosen to test the proposed search algorithm. The results showed that KSA is comparable to BAT, ACO and PSO as the test statistics (that is, Wilcoxon signed rank test) show no statistically significant differences between the mean of classification accuracy at level of significance of 0.05. However, KSA, when compared with WSA-MP, shows a statistically significant difference between the mean of classification accuracy
Authors and Affiliations
Israel Edem Agbehadji, Richard Millham, Simon James Fong, Hongji Yang
Keywords
Related Articles
- EP ID EP569778
- DOI 10.15439/2018F52
- Views 42
- Downloads 0
Dataset Enhancement in Hair Follicle Detection: ESENSEI Challenge
In this paper, a solution to ESENSEI data mining challenge concerning the analysis of microscopic hair images is described. The task of the challenge was to detect locations of hair follicles in closeup images of a human...
Financial Inclusion in India and PMJDY: A Critical Review
The recent developments in banking and insurance have transformed the financial system, however, it is restricted only to certain segments of the society, excluding others. i.e. ``financial exclusion''. People with low i...
Usability Of An E-Commerce Website Using Information Mining and Artificial Intelligence
Everyday a number of people are launching new websites of which many are e-Commerce websites. E-Commerce website means business and to have business they have to be useful to the customer. So, it is very important for th...
Detection of Malicious Executables Using Rule Based Classification Algorithms
Machine Learning class rule has varied packages together with classification, clustering, will understand association rules furthermore and is capable of the method an enormous set of the information set as measure super...
A Perspective Approach (OABC) Algorithm using Square Odd Routing for minimized Energy Consumption
ABC set of principles has been already proposed furthermore with some drove guidelines, yet the length of the work parameter has been spinning round detecting the hubs in static or dynamic way with no accentuation at the...