Nowadays, air pollution is an important problem with negative impacts on human health and on the environment. The air pollution forecast can provide important information to all affected sides, and allows appropriate measures to be taken. In order to address the problems of filling in the missing values in the time series used for air pollution forecasts, the automation of the allocation of optimal subset of input variables, the dependency of the air quality at a particular location on the conditions of the surrounding environment, as well as automation of the model’s optimization, this paper proposes a deep spatiotemporal model based on a 2D convolutional neural network and a long short-term memory network for predicting air pollution. The model utilizes the automatic selection of input variables and the optimization of hyperparameters by a genetic algorithm. A hybrid strategy for missing value imputation is used based on a combination of linear interpolation and a strategy of using the average between the previous value and the average value for the same time in other years. In order to determine the best architecture of the spatiotemporal model, the architecture hyperparameters are optimized by a genetic algorithm with a modified crossover operator for solutions with variable lengths. Additionally, the trained models are included in various ensembles in order to further improve the prediction performance—these include ensembles of models with the same architecture comprising the best architecture obtained by the evolutionary optimization, and ensembles of diverse models comprising the k best models of the evolutionary optimization. The experimental results for the Beijing Multi-Site Air-Quality Data Set show that the proposed spatiotemporal model for air pollution forecasting provides good and consistent prediction results. The comparison of the suggested model with other deep NN models shows satisfactory results, with the best performance according to MAE, based on the experimental results for the station at Wanliu (16.753 ± 0.384). Most of the model architectures obtained by the optimization of the model hyperparameters using the genetic algorithm have one convolutional layer with a small number of kernels and a small kernel size; the convolutional layers are followed by a max-pooling layer, and one or two LSTM layers are utilized with dropout regularization applied to the LSTM layer using small values of p (0.1, 0.2 and 0.3). The utilization of ensembles from the k best trained models further improves the prediction results and surpasses other deep learning models, according to MAE and RMSE metrics. The used hybrid strategy for missing value imputation enhances the results, especially for data with clear seasonality, and produces better MAE compared to the strategy using average values for the same hour of the same day and month in other years. The experimental results also reveal that random searching is a simple and effective strategy for selecting the input variables. Furthermore, the inclusion of spatial information in the model’s input data, based on the local neighborhood data, significantly improves the predictive results obtained with the model. The results obtained demonstrate the benefits of including spatial information from as many surrounding stations as possible, as well as using as much historical information as possible.

In view of Industry 4.0, data generation and analysis are challenges. For example, machine health monitoring and remaining useful life prediction use sensor signals, which are difficult to analyze using traditional methods and mathematical techniques. Machine and deep learning algorithms have been used extensively in Industry 4.0 to process sensor signals and improve the accuracy of predictions. Therefore, this paper proposes and validates the data-driven prediction model to analyze sensor data, including in the data transformation phase Principal Component Analysis tested by Fourier Transformation and Wavelet Transformation, and the modeling phase based on machine and deep learning algorithms. The machine learning algorithms used for tests in this research are Random Forest Regression (RFR), Multiple Linear Regression (MLR), and Decision Tree Regression (DTR). For the deep learning comparison, the algorithms are Deep Learning Regression and Convolutional network with LeNet-5 Architecture. The experimental results indicate that the models show promising results in predicting wear values and open the problem to further research, reaching peak values of 92.3% accuracy for the first dataset and 62.4% accuracy for the second dataset.

Earth Observation (EO) is used to monitor and assess the status of, and changes in, the natural and manmade environment via remote sensing technologies, usually involving satellites carrying imaging devices. EO applications provide important inputs to governments in planning, implementing, and monitoring the progress of the 2030 Agenda for Sustainable Development. Along with other countries, Bulgaria has committed to all 17 Sustainable Development Goals (SDGs) and reflected them in its strategic documents. EO is one of the priority technologies for the development of the Bulgarian space sector. This paper analyzes how EO data could significantly help Bulgarian authorities in achieving and monitoring the progress of the SDG targets based on three specific EO monitoring pilot projects’ results (showcases) focused more on the policy management approach than scientific achievement. The first project showed the opportunities of EO data for integration of a national (local) geospatial database with the existing international networks for monitoring natural disasters and accidents. The second demonstrated the time series usage of EO data for water quality monitoring. The third project integrated remote sensing data from EO and in situ measurements with ancillaries’ data to provide phenology status and crop production forecast in a common geospatial database with the aim to support the Bulgarian agriculture sector modernization.

With the growing implementation of artificial intelligence in products that are used in everyday life arises the threat of exploitation of vulnerabilities in them, which could lead to, sometimes, lasting damage to the system and the user. This article examines the possible connections, threats and implementations for artificial intelligence in cybersecurity. It represents a literature review of current trends of AI applications and problems in the field of cybersecurity for offensive and defensive use, with a focus on the technological as well as the ethical perspective.

WordPress is the world’s most popular content management system. In recent years, websites using WordPress have been a popular target for hackers due to the platform’s popularity. To solve these problems, users turn to security plugins to help them deal with security threats. However, there is no in-depth security analysis of the WordPress plugin system. In this regard, the paper aims to analyze the work of the main security plugins, including code analysis, testing with different types of threats, checking the data that they collect, and evaluating their strengths and weaknesses. The working principles and implementations of modern security plugins have been described and the criteria for selecting the studied plugins have been defined. The results have been summarized and the approaches used by the different plugins have been compared.