prošireni sažetak izlaganja sa skupa
The graphic industry, including printing, packaging, bookbinding, and digital media, faces sustainability challenges due to high levels of waste, inefficient resource management, and excessive energy consumption. Key Performance Indicators (KPIs) enable the monitoring and optimization of production processes with the aim of reducing the environmental footprint and increasing operational efficiency. However, the lack of precise industrial data often limits quality analysis and data-driven decision-making. Artificial intelligence (AI) provides a solution to this problem through predictive analytics and process automation, enabling smarter resource management and waste reduction.
This paper explores the application of the Extreme Gradient Boosting (XGBoost) model for the analysis and optimization of key KPI indicators in the graphic industry, with a focus on sustainability and resource efficiency. The model includes relevant indicators, such as percentage of material waste, energy efficiency, number of defective prints, machine efficiency, and equipment downtime. Given the limited availability of real industry data, this research employs simulated datasets based on industry standards to evaluate the accuracy of AI-based predictions and the potential for process optimization through AI technologies.
The methodological approach involves the generation of synthetic KPI data and the application of the XGBoost algorithm, which outperforms traditional machine learning methods due to its ability to analyze large datasets faster, detect complex patterns, and provide more accurate predictions for variations in production processes. Additionally, XGBoost enables the simultaneous optimization of multiple variables, improving decision-making in dynamic production systems. The model evaluation is conducted using metrics such as mean absolute error (MAE), mean squared error (MSE), and coefficient of determination (R²). The expected results demonstrate how AI can significantly enhance resource efficiency, reduce waste, and optimize production parameters.
Beyond waste prediction, AI allows for the identification of patterns that contribute to waste and automatically suggests adjustments to the production process. By implementing machine learning and analyzing data from various sources, XGBoost models can continuously refine their accuracy and adapt to changes in the production environment. Furthermore, the integration of AI systems with Industry 4.0 enables the connection of data from sensor systems and production management software, allowing for real-time decision-making and improved operational flexibility.
Moreover, the implementation of AI technologies in the graphic industry can introduce a system for automatically adjusting KPI thresholds, allowing for proactive optimization of production processes. This approach contributes not only to cost reduction but also to achieving industry ESG goals, such as carbon footprint reduction and more efficient resource management. The research findings are expected to provide the foundation for the broader integration of AI tools into sustainable production, along with guidelines for the further development of smart KPI management systems.
This paper contributes to the development of an AI-supported system for managing sustainable KPI indicators in the graphic industry, facilitating more precise production planning, material utilization optimization, and environmental footprint reduction. The results obtained can serve as a basis for further research and industrial application of AI technologies in the context of sustainable graphic production.
artificial intelligence; sustainable graphic arts production; key performance indicators (KPIs); process optimization; Industry 4.0; predictive analytics; XGBoost; ESG framework
Razvojem virtualizacijskih tehnologija raste kompleksnost IT sustava, dok korisnici istovremeno zahtijevaju brži pristup resursima, napredne integracije i jednostavnost korištenja. Jedno od ključnih rješenja za ove izazove primjena je…
Ovaj rad istražuje i uspoređuje mogućnosti prosljeđivanja grafičkih kartica na Hyper-V i KVM hipervizorima prema virtualnim strojevima, detaljno opisujući metode, postupke i razlike u arhitekturi koje utječu na…
The ever-growing usage and adaptation of HTTP/3 in web traffic leverages Quick UDP Internet Connections (QUIC) as a transport protocol. QUIC is widely recognized for reduced latency, enhanced…
