Air pollution has a major impact on human health, especially in cities, and elevated concentrations of PMx are responsible for a large number of premature deaths each year. Therefore, the amount of PM10 in the air is monitored and forecasts are made to predict the air quality. In Poland, mainly deterministic models are used to predict air pollution. Accordingly, research efforts are being made to develop other models to forecast the ambient PM10 levels. The aim of the study was to compare the machine learning models for predicting PM10 levels in the air in the city of Lublin. The following machine learning models were used: Linear regression (LR), K-Nearest Neighbors Regression (KNNR), Support Vector Machine (SVM), Regression Trees (RT), Gaussian Process Regression Models (GPR), Artificial Neural Network (ANN) and Long Short-Term Memory network (LSTM). The collected data for three consecutive years (January 2017 to December 2019) were used to develop the models. In total, 19 parameters, covering meteorological variables and concentrations of several chemical species, were explored as potential predictors of PM10. The data used to build the models did not take into account the seasons. The algorithms achieved the following R² values: 0.8 for LR, 0.79 for KNNR, 0.82 for SVM, 0.77 for RT, 0.89, 0.90 for ANN and 0.81 for LSTM. Research has shown that the selection of a machine learning model has a large impact on the quality of the results. In this research, the ANN model performed slightly better than other models. Then, an ANN was used to train a network with five output neurons to predict the approximate level of PM10 at different time points (PM level at a given time, after 1 h, after 6 h, after 12 h and after 24 h). The results showed that the developed and tuned ANN model is appropriate (R = 0.89). The model created in this way can be used to determine the risk of exceeding the PM10 alert level and to inform about the air quality in the region.

Modelling the time that the system remains in a given state using classical distributions is not always possible. In many cases, empirical distributions are multimodal due to the influence of external, hidden factors and the selection of the best classical distributions may lead to erroneous results. In the article the method of diagnosis of influence of hidden factors into sojourn time of semi-Markov models was presented. In order to capture hidden factors, the authors proposed to model the distributions of the sojourn time with a mixture of distributions, which is a significant novelty in relation to the studies presented in the literature. Hidden factors directly affect the reliability of technical systems. Detecting the existence of these factors enables more accurate modeling of system readiness. Paying attention to irregularities caused by hidden factors makes it possible to reduce system maintenance costs. Such a system model provides complete information and enables a reliable assessment of the system readiness and maintenance.

Mechanization of forestry work is crucial in forest management, and the specific nature of the tasks performed requires reliable machines with a high level of technical readiness. Therefore, models describing the exploitation process of multi-operational machines used to obtain wood raw materials, and especially assessing the level of their technical readiness, are extremely important. For multi-tasking objects performing random activities in given time intervals, calculating readiness measures is a complex issue. Forecasting subsequent operational states and their durations allows to predict the behavior of technical objects and schedule work. In addition to identifying the sequence of states, it is also important to identify the sojourn time in these states. This article presents a method for identifying the semi-Markov process and then assessing the technical readiness of a Harvester machine. This allowed for conclusions regarding the timely completion of assigned tasks, and also made it possible to adjust the activities carried out to the requirements of forest management.

Recently, biomass has become an increasingly widely used energy resource. The problem with the use of biomass is its variable composition. The most important property that determines the energy content and thus the performance of fuels such as biomass is the heating value (HHV). This paper focuses on selecting the optimal number of input variables using linear regression (LR) and the multivariate adaptive regression splines approach (MARS) to create an artificial neural network model for predicting the heating value of selected biomass. The MARS model selected the input data better than the LR model. The best modeling results were obtained for a network with three input neurons and nine neurons in the hidden layer. This was confirmed by a high correlation coefficient of 0.98. The obtained results show that artificial neural network (ANN) models are effective in predicting the calorific value of woody and field biomass, and can be considered a worthy simulation model for use in selecting biomass feedstocks and their blends for renewable fuel applications.

Artificial neural network models for the task of detection are used in many fields and find various applications. Models of this kind require adequate computational resources and thus require adequate energy expenditure. The increase in the number of parameters, the complexity of architectures, and the need to process large data sets significantly increase energy consumption, which is becoming a key sustainability challenge. Optimization of computing and the development of energy-efficient hardware technologies are essential to reduce the energy footprint of these models. This article examines the effect of the type of model, as well as its parameters, on energy consumption during inference. For this purpose, sensors built into the graphics card were used, and software was developed to measure the energy demand of the graphics card for different architectures of YOLO models (v8, v9, v10), as well as for different batch and model sizes. This study showed that the increase in energy demand is not linearly dependent on batch size. After a certain level of batch size, the energy demand begins to decrease. This dependence does not occur only for n/t size models. Optimum utilization of computing power due to the number of processed images for the studied models occurs at the maximum studied batch size. In addition, tests were conducted on an embedded device.

This paper presents an open architecture for a sensor platform for the processing, collection, and image reconstruction from measurement data. This paper focuses on ultrasound tomography in block-wise-transform-reduction image reconstruction. The advantage of the presented solution, which is part of the project “Next-generation industrial tomography platform for process diagnostics and control”, is the ability to analyze spatial data and process it quickly. The developed solution includes industrial tomography, big data, smart sensors, computational intelligence algorithms, and cloud computing. Along with the measurement platform, we validate the methods that incorporate image compression into the reconstruction process, speeding up computation and simplifying the regularisation of solving the inverse tomography problem. The algorithm is based on discrete transformation. This method uses compression on each block of the image separately. According to the experiments, this solution is much more efficient than deterministic methods. A feature of this method is that it can be directly incorporated into the compression process of the reconstructed image. Thus, the proposed solution allows tomographic sensor-based process control, multidimensional industrial process control, and big data analysis.