A New Discretization Approach of Bat and K-Means

Abstract

Bat algorithm is one of the optimization techniques that mimic the behavior of bat. Bat algorithm is a powerful algorithm in finding the optimum feature data collection. Classification is one of the data mining tasks that useful in knowledge representation. But, the high dimensional data become the issue in the classification that interrupt classification accuracy. From the literature, feature selection and discretization able to overcome the problem. Therefore, this study aims to show Bat algorithm is potential as a discretization approach and as a feature selection to improve classification accuracy. In this paper, a new hybrid Bat-K-Mean algorithm refer as hBA is proposed to convert continuous data into discrete data called as optimize discrete dataset. Then, Bat is used as feature selection to select the optimum feature from the optimized discrete dataset in order to reduce the dimension of data. The experiment is conducted by using k-Nearest Neighbor to evaluate the effectiveness of discretization and feature selection in classification by comparing with continuous dataset without feature selection, discrete dataset without feature selection, and continuous dataset without discretization and feature selection. Also, to show Bat is potential as a discretization approach and feature selection method. . The experiments were carried out using a number of benchmark datasets from the UCI machine learning repository. The results show the classification accuracy is improved with the Bat-K-Means optimized discretization and Bat optimized feature selection.

Logistic Model Tree Forest for Steel Plates Faults Prediction

“…(iv) In the experiments, the proposed LMT forest method with an accuracy of 86.655% outperformed the random forest method with an accuracy of 79.547% on the same dataset. (v) Our method achieved higher classification accuracy than the state-of-the-art methods [20][21][22][23][24][25][26][27][28][29][30][31][32] on the same steel plate fault dataset and demonstrated its superiority over its counterparts.…”

“…Therefore, it is essential to obtain hidden patterns in related data and consequently make an accurate prediction for steel plate faults. To achieve this objective, different machine learning techniques have been used in previous works, including support vector machines [20,25,29,30], neural networks [25,28,29], decision trees [20,21,24,26], naive Bayes [24,27], K-nearest neighbors [24,26,27], random forest [21,25,26,30,31], and AdaBoost [26,31,32]. In addition, deep learning approaches have been utilized, including long short-term memory [21] and convolutional neural networks [72].…”

An improve unsupervised discretization using optimization algorithms for classification problems

“…Interval for each bin is denoted as 𝑘 𝑛 (𝑛 = 1,2 ⋯ , 𝑛 − 1)). The interval for bin 1𝑠𝑡 is determined by (2), and the interval for bin 2𝑛𝑑 is determined by (3), and so forth for 𝑛𝑡ℎ as (4).…”

“…The relationship between discretization and the BA arises when dealing with optimization problems that involve continuous variables [4]. In some cases, the BA can be adapted to work with discrete variables by introducing a discretization process.…”

“…Mohamed and Azah [4], discretization processes conducted during the pre-processing phase can enhance classification performance. Discretization involves the process of converting continuous data into discrete intervals or categories, thereby simplifying the representation of complex numerical information.…”