This article presents a comparative analysis of two prominent machine learning techniques for predicting electricity consumption in workplace lighting systems: polynomial regression analysis and artificial neural networks. The primary objective is to assess their suitability and applicability for developing an accurate predictive model. After a brief overview of the current state of energy-saving techniques, the article examines several established models for predicting energy consumption in buildings and systems. These models include artificial neural networks, regression analysis and support vector machines. It then focuses on a practical comparison between polynomial regression analysis and an artificial neural network-based model. The article then looks at the data preparation process, outlining how the data is used within each model to establish appropriate prediction functions. Finally, it describes the methods used to evaluate the accuracy of the developed prediction functions. These functions allow the prediction of lighting consumption based on external lighting intensity. The article evaluates the accuracy of the developed prediction functions using the root mean square error, correlation coefficient and coefficient of determination values. The article compares these values obtained for both models, allowing a conclusive assessment of which model provides superior accuracy in predicting lighting consumption based on external lighting intensity.

The COVID-19 pandemic has caused huge health and economic damages. Various protective face masks, such as single-use, cotton, and the most widespread FFP2 or KN95 masks, are used to prevent the spread of this virus. However, these face masks are usually packaged in plastic packaging, which increases the amount of plastic waste. Plastic gloves are also often used in the connection of the pandemic. All this leads to a large production of protective equipment, but their use contributes to the increase of this type of waste, which presents a new challenge in waste management. This article investigates a complete element analysis of these mentioned materials and observes potential harmful substances. Further, pellets, as a potential fuel for combustion or pyrolysis purposes, were produced with the content of 5% and 10% of face masks. FFP2 were firstly separated from ear straps and wires, then disintegrated, added to spruce sawdust, and compressed into pellets. A series of experiments were realized and aimed at elemental, thermogravimetric, and calorific value analyses of produced pellets. Based on the results, it can be concluded that the presence of face masks FFP2 in pellets increases the content of carbon, hydrogen, and nitrogen, volatile matter, and calorific values, but decreases the content of fixed carbon. According to elemental analysis of produced pellets, no significant amounts of harmful elements were found.

The quality of workplace lighting is of significant consequence to the well-being and productivity of employees. This study examines the influence of diverse lighting modalities on employee satisfaction and performance within an intelligent building. In building, three primary lighting modes are used: daylighting, constant illuminance, and power lighting. A survey was conducted with the objective of assessing the perceptions of the lighting conditions held by employees. The findings suggest that the majority of respondents expressed satisfaction with the overall lighting quality, particularly when natural light was integrated with artificial lighting. However, it is notable that there were variations in satisfaction levels, which serves to illustrate the importance of developing lighting solutions that are tailored to specific needs and preferences. The findings indicate that optimal lighting, characterized by appropriate illuminance levels, color temperature, and glare control, can positively impact employee mood, concentration, and overall job satisfaction.

At present, we are still feeling the effects of the COVID-19 pandemic in connection with the huge amount of waste generated. However, the reuse of the produced waste in other processes requires energy consumption. This article deals with the reuse of face masks FFP2, which were added as an admixture to spruce or beech sawdust and then processed into pellets. During the production process of the pellets, energy consumption was measured and further converted to one ton of pellets, and also the consumption was reflected in the price of electricity. After storage, the mechanical durability and dimensions of the individual pellets were measured, and their density was calculated. Based on the results, it can be concluded that spruce pellets with 10% face masks FFP2 (consumption 747.41 kWh; durability 97.53%) and beech pellets with 5% face masks FFP2 (consumption 721.27 kWh; durability 97.38%) achieved higher values of mechanical durability and also consumed more energy than the remaining samples with lower values of durability without considering the sample with spruce sawdust and 5% FFP2 face masks (consumption 872.63 kWh; durability 91.68%). The production of spruce pellets with 5% FFP2 face masks was affected mainly by cold outside weather.

In recent years, there has been a growing emphasis on the efficient utilization of natural resources across various facets of life. One such area of focus is transportation, particularly electric mobility in conjunction with the deployment of renewable energy sources. To fully realize this objective, it is crucial to quantify the probability of achieving the desired state—production exceeding consumption. This article deals with the computation of the probability that the energy required to charge an electric vehicle will originate from a renewable source at a specific time and for a predetermined charging duration. The base of the model lies in artificial neural networks, which serve as an ancillary tool for the actual probability assessment. Neural networks are used to forecast the values of energy production and consumption. Following the processing of these data, the probability of energy availability for a given day and month is determined. A total of seven scenarios are calculated, representing individual days of the week. These findings can help users in their decision-making process regarding when and for how long to connect their electric vehicle to a charging station to receive assured clean energy from a local photovoltaic source.