In this paper, white pixel percentage (WPP) value, as an overall measure of fold crack damages, has been analysed with respect to selected parameters of sample preparation and digitalization process, as well as the results of residual tensile strength. The WPP values were derived by an automated image processing algorithm, developed earlier, based on extensive comparative analysis of the existing computer-aided methods. Results indicate that WPP values correlate well with the extent of fold cracks on the coated samples, as far as the used parameters of sample preparation and digitalization are concerned. In the case of correlation with residual tensile strength, results for samples folded in cross direction revealed that the extent of the visually registered fold cracks agree well with the actual damage, while for samples folded in machine direction, the overall strength losses weren’t alarming, although the fold cracks were detected correctly. In addition, results pointed out that the simplest sample placement position (inner angle of 180°) is not applicable for realistic sample representation. Furthermore, scanners could provide a superior image quality in lab conditions, but for industry application, a camera-based solution would be more purposeful, while micrographs are more suitable for traditional visual analysis.

Starting from the assumption that wastewater treatments can have a significant impact on the interactions between microplastics (MPs) and various pollutants in different matrices, a focus must be directed on examination of classic and redesigned treatments to remove synthetic dyes in the presence of MPs from wastewater. This paper investigates the potential application of Fenton-like process for the removal of water-based printing dye (Cyan) from aqueous solution containing MPs in a form of granulated polyethylene (PEg). The influence of five quantitative parameters on decolorization efficiency was investigated: initial dye concentration (20-180 mgL-1), nano zero valent iron (nZVI) dosage (0.75-60 mgL-1), PEg concentration (1-10 gL-1), hydrogen-peroxide concentration (1-11 mM) and pH value (2-10). A novel statistical approach, definitive screening design, resulted with the optimization process which yielded highest removal efficiency of 92% under following conditions: initial dye concentration of 155 mgL-1, nZVI dosage of 55 mgL-1, PEg concentration of 2.35 gL-1, H2O2 concentration of 2 mM and pH value 2.5. Available data indicate that in the future, wastewater containing MPs will dictate ways to reuse this water in terms of closing the water material cycle and reducing environmental pollution. Therefore, the industrial wastewater reuse is an important component of sustainable wastewater management practices, namely, water resource augmentation and pollutant reduction.

Innovations in artificial intelligence (AI) are shaping the future of almost every industry, and the printing industry is no exception. Applications of AI in the printing industry can be found in prepress optimization, production automation, variable data printing, quality control, predictive maintenance, customer engagement, workflow improvement, and waste reduction. Prepress is the first, crucial and critical stage in the printing process where files are prepared for the actual printing process. It has always been adaptable to changes due to technological requirements and improvements. The introduction of AI in the production phase of prepress has already demonstrated numerous benefits, such as seamless file management, comprehensive preflight checks, advanced PDF editing and automation of repetitive and time-consuming tasks such as file conversion, layout adjustments, trapping and color correction. AI-powered color management systems, which are essential in prepress, are becoming more sophisticated and can predict and compensate for color differences between different substrates and devices. Although the benefits of AI in prepress are obvious, there are still certain challenges and considerations, including the initial investment, data security, complexity of integration and lack of expertise. This paper aims to explore the integration of AI elements in prepress applications and provide a comprehensive overview of the benefits, challenges and future prospects in this area.

In this study we have aimed to present statistical evaluation of changes in the surface roughness of the solid tone areas on CtP flexo printing plate in dependence of print run. Changes in flexo plate surface roughness is influenced by the plate-making process, printing pressure and speed, the interaction with the ink and printing substrate and by the wear of the printing plate due to long print-runs. Thus, the aim of this research was to evaluate the changes in the amplitude surface roughness parameters (Ra, Rp, Rv and Rz), between the printing plates used for different print runs. In the experiment, we have employed three sets of CtP flexo printing plates, for three colors-cyan, magenta and blue. The first set was not used for printing, the second was used to print 7 rolls of substrate and the third is used to print 11 rolls of printing substrate. The amplitude surface roughness parameters were compared by applying independentsamples t-test method using the software SPSS (Statistical Package for Social Science) with a 0.05 significance level. Statistical analysis revealed that the difference between the amplitude surface roughness parameters measured on CtP flexo printing plates are significant with a 95% confidence level, whereas the statistical significance pointed out that with the longer print runs, the difference will be strongly expressed.

The paper presents a comparative pilot analysis of an AI-based visual attention prediction system with the traditional eye-tracking method in the context of UI/UX design. The study assesses the accuracy and reliability of AI-generated attention heatmaps compared to empirical eye-tracking data. The results indicate that AI systems show a strong ability to approximate human attention, achieving ROC-AUC values between 0.75 and 0.84. The study highlights AI's potential in early-stage design iterations, offering a suitable alternative to time-consuming eye-tracking testing sessions, but recommends combining AI tools with traditional methods for critical design decisions.