Over the last few years, human activity recognition (HAR) has drawn increasing interest from the scientific community. This attention is mainly attributable to the proliferation of wearable sensors and the expanding role of HAR in such fields as healthcare, sports, and human activity monitoring. Convolutional neural networks (CNN) are becoming a popular approach for addressing HAR problems. However, this method requires extensive training datasets to perform adequately on new data. This paper proposes a novel deep learning model pre-trained on scalograms generated using the continuous wavelet transform (CWT). Nine popular CNN architectures and different CWT configurations were considered to select the best performing combination, resulting in the training and evaluation of more than 300 deep learning models. On the source KU-HAR dataset, the selected model achieved classification accuracy and an F1 score of 97.48% and 97.52%, respectively, which outperformed contemporary state-of-the-art works where this dataset was employed. On the target UCI-HAPT dataset, the proposed model resulted in a maximum accuracy and F1-score increase of 0.21% and 0.33%, respectively, on the whole UCI-HAPT dataset and of 2.82% and 2.89%, respectively, on the UCI-HAPT subset. It was concluded that the usage of the proposed model, particularly with frozen layers, results in improved performance, faster training, and smoother gradient descent on small HAR datasets. However, the use of the pre-trained model on sufficiently large datasets may lead to negative transfer and accuracy degradation.

The paper describes a new non-iterative linear supervised learning predictor. It is based on the use of Ito decomposition and the neural-like structure of the successive geometric transformations model (SGTM). Ito decomposition (Kolmogorov–Gabor polynomial) is used to extend the inputs of the SGTM neural-like structure. This provides high approximation properties for solving various tasks. The search for the coefficients of this polynomial is carried out using the fast, non-iterative training algorithm of the SGTM linear neural-like structure. The developed method provides high speed and increased generalization properties. The simulation of the developed method’s work for solving the medical insurance costs prediction task showed a significant increase in accuracy compared with existing methods (common SGTM neural-like structure, multilayer perceptron, Support Vector Machine, adaptive boosting, linear regression). Given the above, the developed method can be used to process large amounts of data from a variety of industries (medicine, materials science, economics, etc.) to improve the accuracy and speed of their processing.

Presents the results of machine learning based on a non-iterative artificial neural network. Short-term, medium-term, and long-term forecasts of electric energy consumption for the “Lviv Regional Center of Emergency Medical and Disaster Medicine” were implemented. The informational and analytical system for forecasting the consumption of electric energy on the basis of non-iterative neural networks is developed.

AGVs are important elements of the Industry 4.0 automation process. The optimization of logistics transport in production environments depends on the economical use of battery power. In this study, we propose a novel deep neural network-based method and data mining for predicting segmented AGV battery voltage drop. The experiments were performed using data from the Formica 1 AGV of AIUT Ltd., Gliwice, Poland. The data were converted to a one-second resolution according to the OPCUA open standard. Pre-processing involved using an analysis of variance to detect any missing data. To do this, the standard deviation, variance, minimum and maximum values, range, linear deviation, and standard deviation were calculated for all of the permitted sigma values in one percent increments. Data with a sigma exceeding 1.5 were considered missing and replaced with a smoothed moving average. The correlation dependencies between the predicted signals were determined using the Pearson, Spearman, and Kendall correlation coefficients. Training, validation, and test sets were prepared by calculating additional parameters for each segment, including the count number, duration, delta voltage, quality, and initial segment voltage, which were classified into static and dynamic categories. The experiments were performed on the hidden layer using different numbers of neurons in order to select the best architecture. The length of the “time window” was also determined experimentally and was 12. The MAPE of the short-term forecast of seven segments and the medium-term forecast of nine segments were 0.09% and 0.18%, respectively. Each study duration was up to 1.96 min.

The use of machine learning tools in modern materials science can significantly reduce the duration and cost of developing new materials and improving the properties of existing ones. This is especially true in studying expensive and strategic importance materials like alloys of rare earth metals, which are used to manufacture high-energy permanent magnets. At the same time, single machine learning algorithms do not always provide the accuracy required to solve a particular applied task. Therefore, the current paper aimed to develop an ensemble model for predicting the magnetic properties of Sm-Co system alloys with high accuracy. Based on literature data, we have collected the dataset of the relationship between phase composition, sample state, crystallographic orientation, microstructure, and magnetic properties. We have compared different machine learning algorithms. A stacking ensemble model was designed based on high-precision machine learning algorithms: Neural Networks, AdaBoost, Gradient Boosting, and Random Forest algorithm. The proposed ensemble scheme showed a significant increase in the accuracy for predicting the magnetic properties of Sm-Co alloys on the example of coercivity.

Technical systems in the modern global world are rapidly evolving and improving. In most cases, these are large-scale multi-level systems and one of the problems that arises in the design process of such systems is to determine their reliability. Accordingly, in the paper, a mathematical model based on the Weibull distribution has been developed for determining a computer network reliability. In order to simplify calculating the reliability characteristics, the system is considered to be a hierarchical one, ramified to level 2, with bypass through the level. The developed model allows us to define the following parameters: the probability distribution of the count of working output elements, the availability function of the system, the duration of the system’s stay in each of its working states, and the duration of the system’s stay in the prescribed availability condition. The accuracy of the developed model is high. It can be used to determine the reliability parameters of the large, hierarchical, ramified systems. The research results of modelling a local area computer network are presented. In particular, we obtained the following best option for connecting workstations: 4 of them are connected to the main hub, and the rest (16) are connected to the second level hub, with a time to failure of 4818 h.