Recent research advances on fabric dyeing have focused on modeling the relationship between dye concentrations and the final color on fabrics. The emerging techniques in related studies have great potential to evolve the traditional dyeing industry to manufacture much more smartly. Given that dyeing is a complex process regulated by many factors, one of the challenging problems in the aforementioned techniques is to maintain the modeling accuracy at acceptable level. Other than developing high-performance algorithms and model architectures, it is also important to include effective data pre-processing techniques in modeling. In this paper, we show that conducting log-transform to the industrial dyeing data can greatly improve the performance of industrial dyeing recipe models. Such observations are confirmed on modeling tasks using different formats of color as input and different types of loss function in the model training. These findings may provide useful implications for related studies for the dyeing industry.

No abstract

Intelligent manufacturing for the fabric dyeing industry requires high-performance dyeing recipe recommendation systems. Nowadays, recommending dyeing recipes by mining dyeing manufacturing data has become a new direction for the development of recipe recommendation systems. As one of the indispensable parts in the system development, data pre-processing needs more than routine steps such as the removal of missing data and outliers. Considering that dyes can have very different coloration properties on different fabrics, dyeing manufacturing records for a given dye combination to different fabric types should be properly categorized before they are used for training regression models for dyeing recipe prediction. In this paper, we propose a simple but effective method for this categorization work. Our method uses conventional K-means clustering analysis to find fabric types that have similar coloration properties for a given dye combination. We have applied the method on a dye combination formed by Colvaceton reactive dye-navy blue CF (CRD-navy blue), Colvaceton reactive dye-bright red 3BSN150% (CRD-red) and Colvaceton reactive dye-yellow 3RS150% (CRD-yellow) on 28 different types of fabrics. We show that these 28 types of fabrics can be well categorized into 8 groups based on the coloration properties. Our proposed method can be listed as one of the standard data pre-processing steps in the development of data-mining based recipe recommendation systems.

Three-dimensional (3D) inter-site distance can be measured by single-molecule localization microscopy. Existing theories and analysis tools for 3D inter-site distance measurement only consider the simplest case where all measured distances are from an identical 3D Rician distribution. There are many problems where the 3D inter-site distance measurement result is made up of multiple components. For example, the measurement of intramolecular distances of deoxyribonucleic acid (DNA) with multiple possible conformations. In these cases, the overall distance distributions become finite mixtures of 3D Rician distributions (or 3D Rician mixtures). Here, we provide a numerical method using the 3D Rician mixture model (3D RMM) to resolve the finite 3D inter-site distance mixtures, which is based on the expectation-maximization (EM) algorithm. The proposed method has been tested on simulation data of finite 3D inter-site distance mixtures. The result using the Gaussian mixture model in the developed method is also discussed for comparison. Mini-abstract: In this paper, we provide a numerical method to resolve the finite 3D inter-site distance mixtures measured from 3D single-molecule localization microscopy. The paper contains 4 figures and 5 tables.