The purpose of this paper is to improve the accuracy of solving prediction tasks of the missing IoT data recovery. To achieve this, the authors have developed a new ensemble of neural network tools. It consists of two successive General Regression Neural Network (GRNN) networks and one neural-like structure of the Successive Geometric Transformation Model (SGTM). The principle of ensemble topology construction on two successively connected general regression neural networks, supplemented with an SGTM neural-like structure, is mathematically substantiated, which improves the accuracy of prediction results. The effectiveness of the method is based on the replacement of the summation of the results of the two GRNNs with a weighted summation, which improves the accuracy of the ensemble operation in general. A detailed algorithmic implementation of the ensemble method as well as a flowchart of its operation is presented. The parameters of the ensemble operation are determined by optimization using the brute-force method. Based on the developed ensemble method, the solution of the task of completing the partially missing values in the real monitoring dataset of the air environment collected by the IoT device is presented. By comparing the performance of the developed ensemble with the existing methods, the highest accuracy of its performance (by the parameters of Mean Absolute Percentage Error (MAPE) and Root Mean Squared Error (RMSE) accuracy) among the most similar in this class has been proved.

In today’s data-driven world, where information is one of the most valuable resources, forecasting the behavior of time series, collected by modern sensor networks and IoT systems, is crucial across various fields, including finance, climatology, and engineering. However, existing neural network models often struggle with time series forecasting collected by different sensors due to challenges such as large data volumes, long-term dependencies, noise, and anomalies, which can negatively impact predictive accuracy. This paper aims to enhance the accuracy of time series forecasting by proposing an adapted transformer architecture combined with an innovative data preprocessing method. The proposed preprocessing technique employs the fast Fourier transform (FFT) to transition from the time domain to the frequency domain, enriching the data with additional frequency-domain features. These features are represented as complex numbers, which improve the informational content of the data for subsequent analysis, thereby boosting forecasting performance. Furthermore, the paper introduces a modified transformer model specifically designed to address the identified challenges in time series prediction. The performance of the proposed model was evaluated using three diverse datasets collected by different sensors, each with varying measurement frequencies, data types, and application domains, providing a comprehensive comparison with state-of-the-art models such as LSTM, FFT-LSTM, DeepAR, Transformer, and FFT-Transformer. Extensive evaluation using five distinct performance metrics demonstrates that the proposed model consistently outperforms existing methods, achieving the highest accuracy across all datasets.

An effective solution of the prediction tasks requires the high accuracy of the result with minimal resource and time costs for the operation of the chosen algorithm. In cases when high accuracy of the received result has the first priority, it is expedient to use ensemble learning. This paper describes a prediction method using a new, stacking-based GRNN ensemble model. Each member of the developed ensemble processes its own dataset, where the vectors of the original set of data are randomly shifted relative to the current point. The authors chose SGTM neural-like structure as a meta-algorithm for the formation of the result of the ensemble. This choice is argued by the high accuracy and speed of its work. The results of a number of experimental studies on the optimal parameters selection of the developed ensemble are described. A comparison of the efficiency of its work with a number of known predictors was done. Prospects for further research are described.

This paper presents an analysis of digital skills and network infrastructure in the European Union (EU) countries based on data from the Digital Economy and Society Index (DESI) 2024. We analyze the current state of digital skills and network infrastructure in EU countries, which in the DESI framework is called digital infrastructure, identifying key trends and differences between EU member states. The analysis shows significant differences in the relative share of citizens with a certain level of digital skills across countries, both among ordinary users of digital services and among information and communication technology professionals. The analysis of digital infrastructure includes fixed broadband coverage, mobile broadband, and edge networks, the latter of which are expected to become an important component of future digital infrastructure. The results highlight the importance of harmonizing the development of digital skills and digital infrastructure to support the EU’s digital transformation. Significant attention is paid to 5G technology. The feasibility of including a new additional indicator in DESI for next-generation 5G technology in the frequency range of 24.25–52.6 GHz is shown. The value of this indicator can be used to assess the readiness of the EU economy for technological leaps that place extremely high demands on reliability and data transmission delays. The results of the current state and the analysis of digital skills and infrastructure contribute to understanding the potential for the future development of the EU digital economy.

The importance of enhancing the accuracy of time-series forecasting using artificial intelligence tools is increasingly critical in light of the rapid advancements in modern technologies, particularly deep learning and neural networks. These approaches have already shown considerable advantages over traditional methods, especially due to their capacity to efficiently process large datasets and detect complex patterns. A crucial step in the forecasting process is the preprocessing of time-series data, which can greatly improve the training quality of neural networks and the precision of their predictions. This paper introduces a novel preprocessing technique that integrates information from both the time and frequency domains. To achieve this, the authors developed a feature extraction–extension scheme, where the extraction component focuses on obtaining the phase and amplitude of complex numbers through fast Fourier transform (FFT) and the extension component expands the time intervals by enriching them with the corresponding frequency characteristics of each individual time point. Building upon this preprocessing method, the FFT-LSTM forecasting model, which combines the strengths of FFT and Long Short-Term Memory (LSTM) recurrent neural networks, was enhanced. The simulation of the improved FFT-LSTM model was carried out on two time series with distinct characteristics. The results revealed a substantial improvement in forecasting accuracy compared to established methods in this domain, with about a 5% improvement in MAE and RMSE, thereby validating the effectiveness of the proposed approach for forecasting applications across various fields.

Background: Today, IoT-based systems are widely used in various applications. Intellectual analysis of the data collected by IoT devices is an important task for the efficient and successful functioning of such systems. In particular, the reliability of such kind of analysis has greatly influenced the ability to partially or fully automate certain processes or subsystems. However, imperfect devices of data collection, transportation errors, etc. lead to gaps in the data. Such incompetency makes an effective intellectual data analysis for the specific tasks impossible. That is why there must be a scientific solution to this problem of effectively filling the gaps in the data collected by the IoT sensors. Methods: The authors propose a new prediction method for solving this problem based on the use of General Regression Neural Networks (GRNN). Results: The possibility of approximation and partial elimination of the error of this computational intelligence tool has been analytically proved. A prediction method based on the use of GRNN was developed. The optimal parameters of the developed method were selected. The simulation of its work was performed to solve the problem of recovery of missing sensor data in the air pollution monitoring dataset. Conclusion: The highest accuracy of the developed method in comparison with other methods of this class was experimentally established. All advantages and disadvantages are described. Perspectives of further research are outlined.