Irena Valova

Forecasting the energy consumption of different consumers became an important procedure with the creation of the European Electricity Market. This study presents a methodology for 24-hour ahead prediction of the energy consumption, which is suitable for application in animal husbandry facilities, such as pig farms. To achieve this, 24 individual models are trained using artificial neural networks that forecast the energy production 1 to 24 h ahead. The selected features include power consumption over the last 72 h, time-based data, average, minimum, and maximum daily temperatures, relative humidities, and wind speeds. The models’ Normalized mean absolute error (NMAE), Normalized root mean square error (NRMSE), and Mean absolute percentage error (MAPE) vary between 16.59% and 19.00%, 22.19% and 24.73%, and 9.49% and 11.49%, respectively. Furthermore, the case studies showed that in most situations, the forecasting error does not exceed 10% with several cases up to 25%. The proposed methodology can be useful for energy managers of animal farm facilities, and help them provide a better prognosis of their energy consumption for the Energy Market. The proposed methodology could be improved by selecting additional features, such as the variation of the controlled meteorological parameters over the last couple of days and the schedule of technological processes.

The generation of realistic electrical load profiles is essential for advancing smart grid analytics, demand forecasting, and privacy-preserving data sharing. Traditional approaches often rely on large, high-resolution datasets and complex recurrent neural architectures, which can be unstable or ineffective when training data are limited. This paper proposes a data-driven framework based on a lightweight 1D Convolutional Wasserstein GAN with Gradient Penalty (Conv1D-WGAN-GP) for generating high-fidelity synthetic 24 h load profiles. The model is specifically designed to operate on small- to medium-sized datasets, where recurrent models often fail due to overfitting or training instability. The approach leverages the ability of Conv1D layers to capture localized temporal patterns while remaining compact and stable during training. We benchmark the proposed model against vanilla GAN, WGAN-GP, and Conv1D-GAN across four datasets with varying consumption patterns and sizes, including industrial, agricultural, and residential domains. Quantitative evaluations using statistical divergence measures, Real-vs-Synthetic Distinguishability Score, and visual similarity confirm that Conv1D-WGAN-GP consistently outperforms baselines, particularly in low-data scenarios. This demonstrates its robustness, generalization capability, and suitability for privacy-sensitive energy modeling applications where access to large datasets is constrained.

Digital energy systems rely on actual data about power consumption and generation, which are not always available and, in certain situations, can be replaced with synthetic forms. This study presents a methodology for generating synthetic time-series data of electrical power consumers. It is based on the Markov chains theory, and unlike previous studies, the data are divided into hourly and hour-change monthly records, which leads to the generation of 48 transition matrices for each month. This study aimed to ensure statistical and probabilistic similarity between the original and synthetic data, which was assessed using the Frobenius distance, the coefficient of determination, variance, and standard deviation. The methodology was applied to three load profiles obtained from different types of consumers—domestic, agricultural, and industrial. In all three cases, the statistical and probabilistic characteristics of the generated data were very similar to those of the original datasets; however, the visual comparison showed that it is recommended to increase the number of states to lower the data scattering. Based on the results, recommendations are proposed on choosing the number of states for the transition matrices to optimize the statistical and probabilistic similarity. The described methodology can be used by experts involved in the design of systems with renewable energy sources and by scientists dealing with long-term studies.

The degradation of pastures and meadows is a global problem with a wide range of impacts. It affects farmers in different ways, such as decreases in cattle production, milk yield, and forage quality. Still, it also has other side effects, such as loss of biodiversity, loss of resources, etc. In this study, the degradation of a semi-natural pasture near the village of Obichnik, Bulgaria, was evaluated using machine learning algorithms, and an unmanned aerial vehicle (UAV) obtained visual spectrum images. A high-quality (HQ) orthomosaic of the area was created and numerous regions of interest were manually marked for training and validation purposes. Three machine learning algorithms were used—Maximum likelihood, Random trees (RT), and Support Vector Machine (SVM). Furthermore, object-based and pixel-based approaches were utilized. The obtained results indicate that the object-based RT and SVM models provide significantly better accuracy, with their Cohen’s Kappa reaching 0.86 and 0.82, respectively. The performed classification showed that approximately 61% of the investigated pasture area is covered with grass, which indicates light-to-medium degradation.

Animal welfare is a daily concern for livestock farmers. It is known that the activity of cows characterizes their general physiological state and deviations from the normal parameters could be an indicator of different kinds of diseases and conditions. This pilot study investigated the application of machine learning for identifying the behavioral activity of cows using a collar-mounted gyroscope sensor and compared the results with the classical accelerometer approach. The sensor data were classified into three categories, describing the behavior of the animals: “standing and eating”, “standing and ruminating”, and “laying and ruminating”. Four classification algorithms were considered—random forest ensemble (RFE), decision trees (DT), support vector machines (SVM), and naïve Bayes (NB). The training relied on manually classified data with a total duration of 6 h, which were grouped into 1s, 3s, and 5s piles. The obtained results showed that the RFE and DT algorithms performed the best. When using the accelerometer data, the obtained overall accuracy reached 88%; and when using the gyroscope data, the obtained overall accuracy reached 99%. To the best of our knowledge, no other authors have previously reported such results with a gyroscope sensor, which is the main novelty of this study.

This paper explores the evolving landscape of electronic word-of-mouth (eWOM) and its impact on consumer behavior. With the transition from traditional word-of-mouth to online platforms (users’ reviews), businesses now have access to vast amounts of user-generated data. This publication reviews methodologies for sentiment analysis (SA) and possibilities for automatic classification, key approaches in understanding consumer opinions, and discusses some of the most notable methods and practices. Additionally, it examines the preprocess of the reviews and the steps that should be done before the classification. Finally, future research directions include personalization of ratings, integration with social networks, and addressing challenges related to fake reviews are mentioned. Embracing these advancements can help businesses leverage eWOM to inform marketing strategies and enhance consumer experiences.

This paper investigates the energy consumption of street lighting in a medium-sized city and the possibility of automated on-off control of the lamps using a microcontroller, a photo sensor and a set illuminance threshold. It uses the data collected from the daily street lighting management in two ways - with a time schedule and an analogue sensor, the data from a photo sensor on the illuminance, to determine the possible appropriate threshold. As a result of the analysis of the lighting duration and consumption, it has been proven that for this type of cities and with such consumption, the investment in more complex automated street lighting control systems is not justified.

The modern cars use information about the speed from the ABS system. This paper proposes a solution for taxicabs. The developed taximeter device uses the impulses from ABS for measurement of the distance of road and amount of money to be charged. This module reads current information about the speed using an internal CAN interface and generates a number of impulses proportional to the current vehicle speed. The device doesn't influence the work of the other electronic systems of the vehicle. It can be used in any modules produced after 2000. The device is cheap. It was approved in real road conditions and its accuracy is 1.5%.

Content-based image retrieval methods in present days are used in modern social media and search engines. They give techniques for analyzing, organizing, processing and searching through million images uploaded daily in the internet. For that reason, searching is the most critical process in CBIR. It should be accurate and complete in reasonable amount of time. Proper metadata should be extracted from the images and used to meet the performance requirements. From the other hand, to meet the subsequent processing this metadata should be indexed and stored in appropriate way.This paper describes some of the most popular image extraction and analysis systems known as Content Based Image Retrieval Systems (CBIR). It reveals how examined different CBIR systems work and how closer are generated similarity results. At the end, information is summarized, and conclusions are made regarding existing solutions and methods used in these applications.

The paper describes our experience with using social networks and especially Facebook as a learning environment. During the last five years we have collected statistical data from surveys with all students of our courses. The survey results show that the use of Facebook group improves learning process by extending the communication outside classes and helps students increase their interest and motivation. Most of the students are satisfied. They have better results and achieve more than they expected. There are more inconveniences for the lecturers, because they have to re-publish their materials (for each group) and follow the discussions in all groups.