Ilze Birzniece

This article addresses the challenge of predicting electrical grid damage in the Latvian regions of Zemgale and Kurzeme using machine learning and quantile regression techniques. The study leverages a comprehensive dataset spanning 2009–2025, incorporating environmental, infrastructure, seasonal, and weather-related features. To handle the significant data imbalance, various spatial and temporal aggregation strategies are tested. Feature selection and aggregation are carefully tailored to preserve correlations between predictors and damage counts. The XGBoost algorithm, configured for quantile regression, is employed with extensive hyperparameter tuning and cross-validation. Results indicate that models trained at the maintenance-region scale (6-cell) achieve the best overall balance between accuracy and reliability, with a mean absolute error of 4.09 and an R2 of 0.53 for daily damage prediction. While the state region (2-cell) model excels in predicting high damage count events (30 or more), it also provides more precise minimum and maximum bounds, offering actionable uncertainty bounds for operational planning. The findings highlight the importance of spatial aggregation and feature engineering in improving predictive performance for rare-event forecasting in power grids. Several promising directions for further development have been identified, and the obtained results are sufficiently promising to support the application of the proposed methodology to broader geographical regions.

Electricity distribution networks are increasingly affected by extreme meteorological conditions, which pose significant risks to above-ground energy infra

This research article explores the contextualization of information objects in enhancing knowledge management within digital workspaces. It emphasizes the critical role of context in managing unstructured data and presents a systematic approach for extracting context dimensions and attributes for information object context modeling. The research article discusses several implications of context-aware computing for organizational productivity: efficient information retrieval, improved knowledge management, support for remote and hybrid work models, reduced data loss, enhanced user activities, and business-level services. The article emphasizes the CASAD matrix modeling method and proposes the approach of extracting the set of attributes for building a context model. A case study is presented to demonstrate the practical application of this approach in an organizational setting. It is shown how combining large language models (LLMs) and organization-specific metamodels contributes to computing secondary context attributes. The research concludes that contextualizing information objects, supported by artificial intelligence and LLMs, can enhance organizational productivity by providing a ground for personalized digital workspaces, efficient information handling, and improved knowledge management processes. It can also support the evolving needs of organizations, such as remote and hybrid work models.

With the latest advances in natural language processing technologies, multi-participant conversation summarization features are now embedded in the most widely used collaboration platforms offered by industry leaders such as Microsoft, Google, and Zoom. This allows employees to streamline their work and increase efficiency by summarizing long chat threads. In this study, an attempt has been made to perceive summarized chat conversations as a tool for knowledge discovery and reusable information extraction within an organization in general or during projects. To this end, recent scientific articles have been reviewed to identify the most effective techniques and approaches for summarizing chat threads and conversations alongside the challenges and peculiarities of collaborative text-based communication. In addition, significant attention has been paid to the further utilization of the extracted information to represent the knowledge for further reuse.

Predicting the growth of broiler chickens is an essential task in the poultry industry. The data used in the study include both the production environmental indicators (temperature, gas concentration, humidity, and others) and the growth rates of poultry (weight, amount of feed consumed, fall) by analyzing their correlations throughout several production cycles. The proposed approach includes several stages, starting with data pre-processing, broiler weight data augmentation, comparison with a reference model, definition, and detection of uncomfortable and dangerous environmental conditions. For the model-building part, the Long short-term memory (LSTM) artificial neural network is applied. The validation of the forecasting model is done by comparing the forecasted weight provided by the model with the actual weight measurements during the randomly selected bird life cycle and varied environmental conditions. The acquired results showed that the provided forecast accuracy is sufficient for production management.

The presented work proposes a practical approach to bird weight data processing and augmentation to enable production outcome forecast model training, which contributes to higher productivity. We suggest using the parametrized model, where parameter values are found through genetic optimization and thus are closely corresponding to broiler body weight factual measurements. The proposed approach is implemented as a stand-alone software system, exposing the models through containerized web services enabling different use scenarios.

This systematic literature review examines the deep learning (DL) models for retail sales forecast. The accuracy of a retail sales forecast is a prevalent force for uninterrupted business operations. Accuracy for retailers means limiting supply chain and storage costs, ensuring no product is out of stock, and facilitating smooth promotional operations. The study analyses the DL frameworks used in reviewed literature. Tested DL models are listed, as well as other machine learning and linear models used for the evaluation comparison. Additionally, the review presents the metrics used by the authors for the model evaluation. This article concludes by describing the benefits and limitations of DL models for sales forecasting.

Development of Bankruptcy Prediction Model for Latvian Companies