Optimization of Attribute Selection Model Using Bio-Inspired Algorithms

Abstract

Attribute selection which is also known as feature selection is an essential process that is relevant to predictive analysis. To date, various feature selection algorithms have been introduced, nevertheless they all work independently. Hence, reducing the consistency of the accuracy rate. The aim of this paper is to investigate the use of bio-inspired search algorithms in producing optimal attribute set. This is achieved in two stages; 1) create attribute selection models by combining search method and feature selection algorithms, and 2) determine an optimized attribute set by employing bio-inspired algorithms. Classification performance of the produced attribute set is analyzed based on accuracy and number of selected attributes. Experimental results conducted on six (6) public real datasets reveal that the feature selection model with the implementation of bio-inspired search algorithm consistently performs good classification (i.e higher accuracy with fewer numbers of attributes) on the selected data set. Such a finding indicates that bio-inspired algorithms can contribute in identifying the few most important features to be used in data mining model construction.

Recent Trends of Machine Learning Predictions Using Open Data: A Systematic Review

“…Moreover, the model's accuracy would improve if the data had more features (Rocca et al, 2016). Feature selection, which is also known as attribute selection, is an essential process to prediction analysis, especially in real OD that consists of a large number of attributes (Basir et al, 2018). This study showed significant results on the manipulation of a bioinspired algorithm to reduce feature sets.…”

“…Research shows that manipulating of the bio-inspired search algorithms can be considered in OD for future studies, as it can demonstrate the best setup for more promising results (Basir et al, 2018). Nevertheless, some researchers also showed that conventional ML models could work better than DL techniques over time.…”

Ant colony algorithm for text classification in multicore-multithread environment

“…The main task focused on supervised learning which requires the user to explicitly train the prototype in order to classify test documents after applying the pre-processing part. One of major problems occur in text classification challenge is curse of dimensionality that reduce the effectiveness of algorithm especially the non-statistical approaches when processing data in high-dimensional spaces [4]. Besides that, ambiguous meaning of a term that always happen in a document may abstain a classification model to strive hundred percent classification rates.…”