Artificial Bee Colony Algorithm Based on K-Means Clustering for Droplet Property Optimization

Abstract

Abstract. The major challenge in printable electronics fabrication is to effectively and accurately control a drop-on-demand (DoD) inkjet printhead for high printing quality. In this paper, a prediction model based on Lumped Element Modeling (LEM) is proposed to search the parameters of driving waveform for obtaining the desired droplet properties. Although the evolution algorithms are helpful to solve this problem, the classical evolution algorithms may get trapped into local optimal due to the inefficiency of local search. To overcome it, we present an improved artificial bee colony algorithm based on K-means clustering (KCABC), which enhances the population diversity by dynamically clustering and increases the convergence rates by the modification of information communication in the employed bees' phase. Combined with KCABC, the prediction model is applied to optimize the droplet volume and velocity of nanosilver ink for high printing quality. Experimental results demonstrate the proposed prediction model with KCABC plays a good performance in terms of efficiency and accuracy of searching the appropriate combination of waveform parameters for printable electronics fabrication.

Automated Pricing and Replenishment Decisions for Vegetable Items

“…When analyzing the correlation between different categories, this paper adopts Spearman correlation coefficient analysis (Spearman), the correlation coefficient of the two two data is calculated, and the heat map is obtained to describe the correlation. Then consider the sales distribution pattern of different single products of vegetables, because there are more single product categories, this paper adopts the idea of dimensionality reduction, and carries out K-means mean clustering for them [2]. The single product will be classified according to spring, summer, autumn, winter to study, using the idea of cluster analysis to determine the correlation between them, so as to draw conclusions.…”

A survey on the studies employing machine learning (ML) for enhancing artificial bee colony (ABC) optimization algorithm

“…Moreover, the abandoned solution position is determined by Hooke and Jeeves-based direct search method. Sun et al (2015a) presented an improved ABC algorithm based on K-Means clustering, which improves the population diversity using dynamically clustering and enhances the convergence ability by a variation in the information sharing of the employed bees. Sun et al (2015b) proposed an improved multi-objective ABC algorithm based on K-Means clustering.…”