Background and objective: According to the World Health Organization (WHO), more than 100 million people have already recovered from SARS-CoV-2 infection. Therefore, it is imperative to understand the possible outcomes of COVID-19. The aim of our study was to evaluate pulmonary function, exercise capacity, residual radiological changes, and health-related quality of life (HRQoL) at follow-up in a cohort of SARS-CoV-2 pneumonia survivors. Materials and Methods: Patients with SARS-CoV-2 infection and radiologically confirmed lung injury, with no chronic lung disease prior to this infection, were included in the study. Patients’ evaluation 2 months after their discharge from hospital included spirometry (FVC, FEV1, FEV1/FVC), determination of lung volume (TLC, VC, RV) and diffusing capacity of lung for carbon monoxide (DLCO, adjusted for hemoglobin), 6-Minute Walk Test (6MWT), chest CT scan, and 36-Item Short Form General Health Survey (SF-36). Results: Fifty-one patients (25 men, 26 women) were included. The mean age was 56 years (SD-11,72). Eighteen patients (35.3%) had experienced moderate COVID-19, 21 (41.2%) severe COVID-19, and 12 (23.5%) were critically ill. The mean follow-up visit time after the discharge from hospital was 60 days (SD-17). Pulmonary function at follow-up was impaired in 24 (47.2%) patients. Reduced lung volume was observed in 15 (29.4%) patients, DLCO reduction in 15 (29.4%) patients, and only one patient displayed obstruction. Twelve patients out of 51 (12/51, 27.3%) showed reduced physical capacity in the 6 MWT, and 3/51 (9.1%) showed desaturation, with SO2 < 90%. Different levels of abnormality were found in 49/51 (96,1%) patients on follow-up chest CT; the median radiological score was 10.9 (SD ± 8.87, possible maximal score, 25). Ground-glass opacity was the most common radiological feature, found in 45 (88.2%) patients. The SF-36 scores demonstrated a reduction in health status across all domains, with the lowest scores for limitations in social activities because of physical problems, vitality, and general health. Conclusion: In the group of COVID-19 pneumonia survivors 2 months after hospital discharge, residual changes in the lungs on chest CT and in lung function and reduced physical and HRQoL status were found in a significant number of patients. To evaluate COVID-19 long-term consequences, a longer follow-up period is needed.

The reliability of internal combustion engines becomes an important aspect when traditional fuels with biofuels. Therefore, the development of prognostic models becomes very important for evaluating and predicting the replacement of traditional fuels with biofuels in internal combustion engines. The models have been made to model AVL 5402 engine emission, vibration, and sound pressure parameters using a three-stage statistical regression models. The fifteen parameters might be accurately predicted by a single statistic presented here. Both fuel type (diesel fuel and HVO) and engine parameters that can be adjusted were considered, since this analysis followed the symmetry of the methods. The data analysis process included three distinct steps and symmetric statistical regression testing was performed. The algorithm examined the effectiveness of various engine settings. Finally, the optimal fixed engine parameter and the optimal statistic were used to construct an ANCOVA model. The ANCOVA model improved the accuracy of prediction for all fifteen missing parameters.

In this paper, long short-term memory (LSTM) and Transformer neural network models were developed for classification of different conveyor belt conditions (loaded and unloaded). Comparative shallow models such as logistic regression, support vector machine and random forest were also developed and summarized. Six different-length belt pressure signals were analyzed: 0.2, 0.4, 0.8, 1.6, 3.2, and 5.0 s. Both LSTM and Transformer models achieved 100% accuracy using pressure raw signal. Furthermore, LSTM model reached the highest classification level with the shortest signals. Accuracy and F1-score of 98% and 100% were reached using only 0.8 and 1.6 s-length signals, respectively. Also, LSTM model performed training and testing procedures faster than Transformer. Random forest model demonstrated the best classification level using aggregated signal data with accuracy of 85% and F1-score for loaded and unloaded conditions of 85% and 69%, respectively. Loaded conveyor belt condition was significantly easier to classify than the unloaded one in all models. Only LSTM showed better classification recall for unloaded conveyor belt condition using short signal. Experimental research dataset CORBEL (Conveyor belt pressure signal dataset) and models are open-sourced and accessible on GitHub https://github.com/TadasZvirblis/CORBEL .

Statistical regression models have rarely been used for engine exhaust emission parameters. This paper presents a three-step statistical analysis algorithm, which shows increased prediction accuracy when using vibration and sound pressure data as a covariate variable in the exhaust emission prediction model. The first step evaluates the best time domain statistic and the point of collection of engine data. The univariate linear regression model revealed that non-negative time domain statistics are the best predictors. Also, only one statistic evaluated in this study was a statistically significant predictor for all 11 exhaust parameters. The ecological and energy parameters of the engine were analyzed by statistical analysis. The symmetry of the methods was applied in the analysis both in terms of fuel type and in terms of adjustable engine parameters. A three-step statistical analysis algorithm with symmetric statistical regression analysis was used. Fixed engine parameters were evaluated in the second algorithm step. ANOVA revealed that engine power was a strong predictor for fuel mass flow, CO, CO₂, NO_x, THC, CO_Sick, O₂, air mass flow, t_exhaust, whereas type of fuel was only a predictor of t_air and t_fuel. Injection timing did not allow predicting any exhaust parameters. In the third step, the best fixed engine parameter and the best time domain statistic was used as a model covariate in ANCOVA model. ANCOVA model showed increased prediction accuracy in all 11 exhausted emission parameters. Moreover, vibration covariate was found to increase model accuracy under higher engine power (12 kW and 20 kW) and using several types of fuels (HVO30, HVO50, SME30, and SME50). Vibration characteristics of diesel engines running on alternative fuels show reliable relationships with engine performance characteristics, including amounts and characteristics of exhaust emissions. Thus, the results received can be used to develop a reliable and inexpensive method to evaluate the impact of various alternative fuel blends on important parameters of diesel engines.

There are different deep neural network (DNN) architectures and methods for performing augmentation on time series data, but not all the methods can be adapted for specific datasets. This article explores the development of deep learning models for time series, applies data augmentation methods to conveyor belt (CB) tension signal data and investigates the influence of these methods on the accuracy of CB state classification. CB systems are one of the essential elements of production processes, enabling smooth transportation of various industrial items, therefore its analysis is highly important. For the purpose of this work, multi-domain tension data signals from five different CB load weight conditions (0.5 kg, 1 kg, 2 kg, 3 kg, 5 kg) and one damaged belt condition were collected and analysed. Four DNN models based on fully convolutional network (FCN), convolutional neural network combined with long short-term memory (CNN-LSTM) model, residual network (ResNet), and InceptionTime architectures were developed and applied to classification of CB states. Different time series augmentations, such as random Laplace noise, drifted Gaussian noise, uniform noise, and magnitude warping, were applied to collected data during the study. Furthermore, new CB tension signals were generated using a TimeVAE model. The study has shown that DNN models based on FCN, ResNet, and InceptionTime architectures are able to classify CB states accurately. The research has also shown that various data augmentation methods can improve the accuracy of the above-mentioned models, for example, the combined addition of random Laplace and drifted Gaussian noise improved FCN model’s baseline (without augmentation) classification accuracy with 2.0 s-length signals by 4.5% to 92.6% ± 1.54%. FCN model demonstrated the best accuracy and classification performance despite its lowest amount of trainable parameters, thus demonstrating the importance of selecting and optimizing the right architecture when developing models for specific tasks.