<?xml version="1.0" encoding="UTF-8"?>
<xml><records><RECORD><source-app name="Bibcite" version="8.x">Drupal-Bibcite</source-app><REFERENCE_TYPE>31</REFERENCE_TYPE><CONTRIBUTORS><AUTHORS><AUTHOR><style face="normal" font="default" size="100%">Marzena Halama</style></AUTHOR><AUTHOR><style face="normal" font="default" size="100%">Katarzyna Filus</style></AUTHOR><AUTHOR><style face="normal" font="default" size="100%">Joanna Domańska</style></AUTHOR></AUTHORS></CONTRIBUTORS><TITLES><TITLE><style face="normal" font="default" size="100%">Robust category recognition based on deep templates for educational mobile applications</style></TITLE></TITLES><KEYWORDS/><DATES/><AUTHORS><style face="normal" font="default" size="100%"/></AUTHORS><YEAR><style face="normal" font="default" size="100%">2023</style></YEAR><SECONDARY_TITLE><style face="normal" font="default" size="100%">2023 IEEE International Conference on Big Data</style></SECONDARY_TITLE><PLACE_PUBLISHED><style face="normal" font="default" size="100%">Sorrento, Italy</style></PLACE_PUBLISHED><LANGUAGE><style face="normal" font="default" size="100%">eng</style></LANGUAGE><PUBLISHER><style face="normal" font="default" size="100%">IEEE International Conference on Big Data</style></PUBLISHER><DATE><style face="normal" font="default" size="100%">01/2024</style></DATE><title><style face="normal" font="default" size="100%">Robust category recognition based on deep templates for educational mobile applications</style></title></RECORD><RECORD><source-app name="Bibcite" version="8.x">Drupal-Bibcite</source-app><REFERENCE_TYPE>31</REFERENCE_TYPE><CONTRIBUTORS><AUTHORS><AUTHOR><style face="normal" font="default" size="100%">Łukasz Sobczak</style></AUTHOR><AUTHOR><style face="normal" font="default" size="100%">Katarzyna Filus</style></AUTHOR><AUTHOR><style face="normal" font="default" size="100%">Marzena Halama</style></AUTHOR><AUTHOR><style face="normal" font="default" size="100%">Joanna Domańska</style></AUTHOR></AUTHORS></CONTRIBUTORS><TITLES><TITLE><style face="normal" font="default" size="100%">Visual examination of relations between known classes for deep neural network classifiers.</style></TITLE></TITLES><KEYWORDS/><DATES/><AUTHORS><style face="normal" font="default" size="100%"/></AUTHORS><YEAR><style face="normal" font="default" size="100%">2023</style></YEAR><SECONDARY_TITLE><style face="normal" font="default" size="100%">2023 IEEE International Conference on Big Data</style></SECONDARY_TITLE><PLACE_PUBLISHED><style face="normal" font="default" size="100%">Sorrento, Italy</style></PLACE_PUBLISHED><LANGUAGE><style face="normal" font="default" size="100%">eng</style></LANGUAGE><PUBLISHER><style face="normal" font="default" size="100%">IEEE</style></PUBLISHER><DATE><style face="normal" font="default" size="100%">01/2024</style></DATE><title><style face="normal" font="default" size="100%">Visual examination of relations between known classes for deep neural network classifiers.</style></title></RECORD><RECORD><source-app name="Bibcite" version="8.x">Drupal-Bibcite</source-app><REFERENCE_TYPE>0</REFERENCE_TYPE><CONTRIBUTORS><AUTHORS><AUTHOR><style face="normal" font="default" size="100%">Wojciech Kempa</style></AUTHOR><AUTHOR><style face="normal" font="default" size="100%">Joanna Rydarowska-Kurzbauer</style></AUTHOR><AUTHOR><style face="normal" font="default" size="100%">Marzena Halama</style></AUTHOR><AUTHOR><style face="normal" font="default" size="100%">Elżbieta Smuda</style></AUTHOR><AUTHOR><style face="normal" font="default" size="100%">Maciej Biel</style></AUTHOR></AUTHORS></CONTRIBUTORS><TITLES><TITLE><style face="normal" font="default" size="100%">Statistical and Econometric Analysis  of Selected Effects of COVID-19 Pandemic</style></TITLE></TITLES><KEYWORDS/><DATES/><AUTHORS><style face="normal" font="default" size="100%"/></AUTHORS><YEAR><style face="normal" font="default" size="100%">2021</style></YEAR><SECONDARY_TITLE><style face="normal" font="default" size="100%">Multidisciplinary Aspects of Production Engineering </style></SECONDARY_TITLE><LANGUAGE><style face="normal" font="default" size="100%">eng</style></LANGUAGE><VOLUME><style face="normal" font="default" size="100%">4</style></VOLUME><ISSUE><style face="normal" font="default" size="100%">1</style></ISSUE><SECTION><style face="normal" font="default" size="100%">395</style></SECTION><DATE><style face="normal" font="default" size="100%">06/2021</style></DATE><title><style face="normal" font="default" size="100%">Statistical and Econometric Analysis  of Selected Effects of COVID-19 Pandemic</style></title></RECORD><RECORD><source-app name="Bibcite" version="8.x">Drupal-Bibcite</source-app><REFERENCE_TYPE>0</REFERENCE_TYPE><CONTRIBUTORS><AUTHORS><AUTHOR><style face="normal" font="default" size="100%">Marzena Halama</style></AUTHOR><AUTHOR><style face="normal" font="default" size="100%">Sławomir Nowak</style></AUTHOR><AUTHOR><style face="normal" font="default" size="100%">Konrad Połys</style></AUTHOR></AUTHORS></CONTRIBUTORS><TITLES><TITLE><style face="normal" font="default" size="100%">Semantic Orientation for Indoor Navigation System using Large Language Models</style></TITLE></TITLES><KEYWORDS/><DATES/><AUTHORS><style face="normal" font="default" size="100%"/></AUTHORS><YEAR><style face="normal" font="default" size="100%">2025</style></YEAR><SECONDARY_TITLE><style face="normal" font="default" size="100%">Scientific Reports</style></SECONDARY_TITLE><LANGUAGE><style face="normal" font="default" size="100%">eng</style></LANGUAGE><DATE><style face="normal" font="default" size="100%">2025</style></DATE><ABSTRACT><style face="normal" font="default" size="100%">&lt;p&gt;Autonomous robots play an important role in modern indoor navigation, but existing systems often struggle with seamless human interaction and semantic understanding of environments. This paper presents an Artificial Intelligence (AI)-driven object recognition system enhanced by Large Language Models (LLMs), such as GPT-4 Vision and Gemini, to bridge this gap. Our approach combines vision-based mapping techniques with natural language processing and interactions to enable intuitive collaboration in solving navigation tasks. By leveraging multimodal input and vector space analysis, our system achieves enhanced object recognition, semantic embedding, and context-aware responses, setting a new standard for autonomous indoor navigation. This approach provides a novel framework for improving spatial understanding and dynamic interaction, making it suitable for complex indoor environments.&lt;/p&gt;&#13;
</style></ABSTRACT><URL><style face="normal" font="default" size="100%">https://link.springer.com/article/10.1038/s41598-025-25281-0</style></URL><title><style face="normal" font="default" size="100%">Semantic Orientation for Indoor Navigation System using Large Language Models</style></title></RECORD><RECORD><source-app name="Bibcite" version="8.x">Drupal-Bibcite</source-app><REFERENCE_TYPE>0</REFERENCE_TYPE><CONTRIBUTORS><AUTHORS><AUTHOR><style face="normal" font="default" size="100%">Nur Kelesoglu</style></AUTHOR><AUTHOR><style face="normal" font="default" size="100%">Marzena Halama</style></AUTHOR><AUTHOR><style face="normal" font="default" size="100%">Anna Strzoda</style></AUTHOR></AUTHORS></CONTRIBUTORS><TITLES><TITLE><style face="normal" font="default" size="100%">Enhancing LoRa-based Outdoor Localization Accuracy Using Machine Learning</style></TITLE></TITLES><KEYWORDS/><DATES/><AUTHORS><style face="normal" font="default" size="100%"/></AUTHORS><YEAR><style face="normal" font="default" size="100%">2025</style></YEAR><SECONDARY_TITLE><style face="normal" font="default" size="100%">IEEE Access</style></SECONDARY_TITLE><LANGUAGE><style face="normal" font="default" size="100%">eng</style></LANGUAGE><VOLUME><style face="normal" font="default" size="100%">13</style></VOLUME><DATE><style face="normal" font="default" size="100%">07/2025</style></DATE><ABSTRACT><style face="normal" font="default" size="100%">&lt;p&gt;The Internet of Things is gaining significant relevance, driving increasing interest in location-&lt;br /&gt;&#13;
based services using wireless signals, particularly Low Power Wide Area Network (LPWAN) technology.&lt;br /&gt;&#13;
LoRa (Long Range), together with LoRaWAN, is a prominent LPWAN standard that provides long-range&lt;br /&gt;&#13;
connectivity and low energy consumption, making it viable for IoT-based positioning systems in smart&lt;br /&gt;&#13;
cities. For localization systems leveraging LoRa signals, Machine Learning (ML) approaches are being&lt;br /&gt;&#13;
increasingly explored, as ML-based solutions offer a powerful way to enhance the accuracy of positioning.&lt;br /&gt;&#13;
In this study, we propose various ML approaches for LoRa-based positioning in outdoor environments. We&lt;br /&gt;&#13;
evaluate six different ML models: k-NN, CNN, SVR, ANN, XG-Boost, and LightGBM-using an open-&lt;br /&gt;&#13;
source urban LoRaWAN dataset. We further propose a Hybrid Model that combines convolutional feature&lt;br /&gt;&#13;
extraction with gradient-boosted regression. This architecture integrates the strengths of deep learning and&lt;br /&gt;&#13;
tree-based models, aiming to capture both temporal signal patterns and structured input correlations for&lt;br /&gt;&#13;
improved localization accuracy. The models are trained offline and tested for performance in terms of&lt;br /&gt;&#13;
localization accuracy, mean square error, and computational efficiency. Additionally, we investigate the&lt;br /&gt;&#13;
impact of different Feature Vector (FV) subsets on localization performance by analyzing the significance of&lt;br /&gt;&#13;
LoRaWAN signal attributes. Our results highlight the effectiveness of ML models in enhancing localization&lt;br /&gt;&#13;
accuracy for LoRa-based outdoor positioning systems, demonstrating performance improvements ranging&lt;br /&gt;&#13;
from 10% to 73% compared to previous ML studies in outdoor localization.&lt;/p&gt;&#13;
</style></ABSTRACT><URL><style face="normal" font="default" size="100%">https://ieeexplore.ieee.org/document/11080010</style></URL><title><style face="normal" font="default" size="100%">Enhancing LoRa-based Outdoor Localization Accuracy Using Machine Learning</style></title></RECORD><RECORD><source-app name="Bibcite" version="8.x">Drupal-Bibcite</source-app><REFERENCE_TYPE>31</REFERENCE_TYPE><CONTRIBUTORS><AUTHORS><AUTHOR><style face="normal" font="default" size="100%">Marzena Halama</style></AUTHOR><AUTHOR><style face="normal" font="default" size="100%">Konrad Połys</style></AUTHOR><AUTHOR><style face="normal" font="default" size="100%">Joanna Domańska</style></AUTHOR></AUTHORS></CONTRIBUTORS><TITLES><TITLE><style face="normal" font="default" size="100%">Speech-based analysis of aggression in social content: resistance of Large Language Models to signal degradation</style></TITLE></TITLES><KEYWORDS/><DATES/><AUTHORS><style face="normal" font="default" size="100%"/></AUTHORS><YEAR><style face="normal" font="default" size="100%">2025</style></YEAR><SECONDARY_TITLE><style face="normal" font="default" size="100%">2025 IEEE International Conference on Big Data</style></SECONDARY_TITLE><PLACE_PUBLISHED><style face="normal" font="default" size="100%">Macau SAR, China</style></PLACE_PUBLISHED><LANGUAGE><style face="normal" font="default" size="100%">eng</style></LANGUAGE><PUBLISHER><style face="normal" font="default" size="100%">IEEE BigData 2025</style></PUBLISHER><DATE><style face="normal" font="default" size="100%">2025</style></DATE><ABSTRACT><style face="normal" font="default" size="100%">&lt;p&gt;Artificial Intelligence (AI) systems, including robotic assistants and voice interfaces, are increasingly present in public spaces such as airports, train stations, hospitals, and government offices, offering new opportunities to enhance user safety and comfort. Detecting aggression and hate speech in audio data from such locations is critical to protecting users and creating safe spaces. Previous approaches in this area have mainly relied on classification using classical Machine Learning (ML) methods and Deep Learning (DL) techniques, primarily focused on pure text analysis. However, most systems do not take into account real-world challenges such as background noise, incomplete utterances, or transcription errors resulting from automatic speech recognition. In this work, we propose a comprehensive approach that exploits the potential of Large Language Models (LLMs) to classify aggressive content in degraded audio transcriptions. We create a realistic test environment by converting tagged social media posts with offensive content into recordings with simulated noise and compare the performance of the models under different data quality conditions. Our research provides practical guidance on how to build more resilient and accessible voice moderation systems using LLM.&lt;/p&gt;&#13;
</style></ABSTRACT><title><style face="normal" font="default" size="100%">Speech-based analysis of aggression in social content: resistance of Large Language Models to signal degradation</style></title></RECORD><RECORD><source-app name="Bibcite" version="8.x">Drupal-Bibcite</source-app><REFERENCE_TYPE>31</REFERENCE_TYPE><CONTRIBUTORS><AUTHORS><AUTHOR><style face="normal" font="default" size="100%">Marzena Halama</style></AUTHOR></AUTHORS></CONTRIBUTORS><TITLES><TITLE><style face="normal" font="default" size="100%">Optimization for Pre-trained CNNs</style></TITLE></TITLES><KEYWORDS/><DATES/><AUTHORS><style face="normal" font="default" size="100%"/></AUTHORS><YEAR><style face="normal" font="default" size="100%">2025</style></YEAR><SECONDARY_TITLE><style face="normal" font="default" size="100%">SCIENCE TECHNOLOGY ENGINEERING MATHEMATICS</style></SECONDARY_TITLE><PLACE_PUBLISHED><style face="normal" font="default" size="100%">Poznań, Polska</style></PLACE_PUBLISHED><LANGUAGE><style face="normal" font="default" size="100%">eng</style></LANGUAGE><PUBLISHER><style face="normal" font="default" size="100%">1st International Conference PUT STEM Day 2025: Book of Abstracts</style></PUBLISHER><DATE><style face="normal" font="default" size="100%">01/2025</style></DATE><ISBN><style face="normal" font="default" size="100%">978-83-955437-7-7</style></ISBN><ABSTRACT><style face="normal" font="default" size="100%">Convolutional neural networks (CNNs) constitute a fundamental cornerstone of computer vision. With increasing complexity, the need for effective optimisation strategies remains crucial. Techniques such as transfer learning (TL), utilising pre-trained networks, enable the deployment of advanced models on mobile devices with limited computing capacity, including autonomous vehicles and educational applications. The study explores optimisation strategies for Keras models, focusing on the impact of different algorithms on performance and accuracy. The results demonstrate that appropriate optimiser selection enhances learning efficiency, mitigates overlearning, and supports accurate image recognition.</style></ABSTRACT><URL><style face="normal" font="default" size="100%">https://putpoznanpl-my.sharepoint.com/personal/stemday_put_poznan_pl/_layouts/15/onedrive.aspx?id=%2Fpersonal%2Fstemday%5Fput%5Fpoznan%5Fpl%2FDocuments%2FKN%20PUT%20STEM%2FStemDay%2FSTEM%20Day%202026%2FPUT%20STEM%20Day%202025%2F1st%20International%20Confe</style></URL><title><style face="normal" font="default" size="100%">Optimization for Pre-trained CNNs</style></title></RECORD><RECORD><source-app name="Bibcite" version="8.x">Drupal-Bibcite</source-app><REFERENCE_TYPE>31</REFERENCE_TYPE><CONTRIBUTORS><AUTHORS><AUTHOR><style face="normal" font="default" size="100%">Marzena Halama</style></AUTHOR><AUTHOR><style face="normal" font="default" size="100%">Joanna Domańska</style></AUTHOR><AUTHOR><style face="normal" font="default" size="100%">Anna Gancarczyk</style></AUTHOR><AUTHOR><style face="normal" font="default" size="100%">Mirzokhid Abdirakhimov</style></AUTHOR></AUTHORS></CONTRIBUTORS><TITLES><TITLE><style face="normal" font="default" size="100%">Tworzenie bazy danych zeolitów z użyciem LLM</style></TITLE></TITLES><KEYWORDS/><DATES/><AUTHORS><style face="normal" font="default" size="100%"/></AUTHORS><YEAR><style face="normal" font="default" size="100%">2025</style></YEAR><LANGUAGE><style face="normal" font="default" size="100%">eng</style></LANGUAGE><ABSTRACT><style face="normal" font="default" size="100%">&lt;p&gt;Praca dotyczy opracowania zautomatyzowanego systemu tworzenia i zarządzania bazą danych zeolitów z wykorzystaniem dużych modeli językowych (LLM). Zaprojektowane rozwiązanie umożliwia ekstrakcję, ujednolicanie i strukturyzację informacji dotyczących syntezy, właściwości oraz zastosowań zeolitów na podstawie dokumentów tekstowych, takich jak publikacje naukowe i raporty badawcze. W procesie budowy bazy wykorzystano dane International Zeolite Association – Structure Commission oraz model LLM do identyfikacji kluczowych parametrów syntezy. Opracowana baza danych stanowi fundament pod przyszły system rekomendacyjny wspierający dobór odpowiednich zeolitów do konkretnych zastosowań.&lt;/p&gt;&#13;
</style></ABSTRACT><title><style face="normal" font="default" size="100%">Tworzenie bazy danych zeolitów z użyciem LLM</style></title></RECORD><RECORD><source-app name="Bibcite" version="8.x">Drupal-Bibcite</source-app><REFERENCE_TYPE>31</REFERENCE_TYPE><CONTRIBUTORS><AUTHORS><AUTHOR><style face="normal" font="default" size="100%">Marzena Halama</style></AUTHOR><AUTHOR><style face="normal" font="default" size="100%">Konrad Połys</style></AUTHOR><AUTHOR><style face="normal" font="default" size="100%">Joanna Domańska</style></AUTHOR></AUTHORS></CONTRIBUTORS><TITLES><TITLE><style face="normal" font="default" size="100%">AI-Assisted Zeolite Design through Retrieval-Augmented Scientific Language Models</style></TITLE></TITLES><KEYWORDS/><DATES/><AUTHORS><style face="normal" font="default" size="100%"/></AUTHORS><YEAR><style face="normal" font="default" size="100%">2026</style></YEAR><SECONDARY_TITLE><style face="normal" font="default" size="100%">SCIENCE TECHNOLOGY ENGINEERING MATHEMATICS</style></SECONDARY_TITLE><PUBLISHER><style face="normal" font="default" size="100%">2nd International Conference PUT STEM Day 2026: Book of Abstracts</style></PUBLISHER><ABSTRACT><style face="normal" font="default" size="100%">&lt;p style="border-style:none;line-height:normal;margin-bottom:.0001pt;text-align:justify;"&gt;&lt;span style="color:black;font-size:11.0pt;font-weight:normal;" lang="EN-US"&gt;Designing materials such as zeolites is a major challenge due to the wide range of possible structures and synthesis conditions. Furthermore, knowledge on this subject is widely scattered across numerous publications and experimental notes. Therefore, large language models (LLMs) represent a promising tool for building knowledge bases, supporting the analysis of scientific literature, although their responses may be incomplete or fallible. In addition, in the case of zeolites, the relationship between material properties and their topology is of crucial importance, which limits the effectiveness of approaches based solely on text. In this study, we investigate a Retrieval-Augmented Generation (RAG) approach extended with a multimodal component that combines textual and structural information.&lt;/span&gt;&lt;/p&gt;&lt;p style="border-style:none;line-height:normal;margin-bottom:.0001pt;text-align:justify;"&gt;&#160;&lt;/p&gt;&lt;p style="border-style:none;line-height:normal;margin-bottom:.0001pt;text-align:justify;"&gt;&#160;&lt;/p&gt;&lt;p style="border-style:none;line-height:normal;margin-bottom:.0001pt;text-align:justify;"&gt;&#160;&lt;/p&gt;</style></ABSTRACT><title><style face="normal" font="default" size="100%">AI-Assisted Zeolite Design through Retrieval-Augmented Scientific Language Models</style></title></RECORD><RECORD><source-app name="Bibcite" version="8.x">Drupal-Bibcite</source-app><REFERENCE_TYPE>31</REFERENCE_TYPE><CONTRIBUTORS><AUTHORS><AUTHOR><style face="normal" font="default" size="100%">Marzena Halama</style></AUTHOR><AUTHOR><style face="normal" font="default" size="100%">Konrad Połys</style></AUTHOR><AUTHOR><style face="normal" font="default" size="100%">Sławomir Nowak</style></AUTHOR><AUTHOR><style face="normal" font="default" size="100%">Joanna Domańska</style></AUTHOR></AUTHORS></CONTRIBUTORS><TITLES><TITLE><style face="normal" font="default" size="100%">External Semantic Memory as a Cognitive Layer for Large Language Models</style></TITLE></TITLES><KEYWORDS/><DATES/><AUTHORS><style face="normal" font="default" size="100%"/></AUTHORS><YEAR><style face="normal" font="default" size="100%">2026</style></YEAR><SECONDARY_TITLE><style face="normal" font="default" size="100%">PP-RAI 2026</style></SECONDARY_TITLE><PUBLISHER><style face="normal" font="default" size="100%">AGH University Press</style></PUBLISHER><title><style face="normal" font="default" size="100%">External Semantic Memory as a Cognitive Layer for Large Language Models</style></title></RECORD><RECORD><source-app name="Bibcite" version="8.x">Drupal-Bibcite</source-app><REFERENCE_TYPE>0</REFERENCE_TYPE><CONTRIBUTORS><AUTHORS><AUTHOR><style face="normal" font="default" size="100%">Marzena Halama</style></AUTHOR><AUTHOR><style face="normal" font="default" size="100%">Natalia Polańska</style></AUTHOR></AUTHORS></CONTRIBUTORS><TITLES><TITLE><style face="normal" font="default" size="100%">Bielik i GPT w analizie polskiego prawa karnego: wpływ RAG  i grafów wiedzy na jakość odpowiedzi</style></TITLE></TITLES><KEYWORDS/><DATES/><AUTHORS><style face="normal" font="default" size="100%"/></AUTHORS><YEAR><style face="normal" font="default" size="100%">2026</style></YEAR><SECONDARY_TITLE><style face="normal" font="default" size="100%">Journal of Management and Digital Transformation</style></SECONDARY_TITLE><ABSTRACT><style face="normal" font="default" size="100%">&lt;p&gt;&lt;span style="font-family:"Times New Roman",serif;font-size:11.0pt;" lang="EN-US"&gt;Rozwój dużych modeli językowych stwarza nowe możliwości wspomagania wyszukiwania i analizy informacji prawnych. Problemem pozostaje ryzyko, że modele generują wiarygodnie brzmiące odpowiedzi, które nie mają podstaw w przepisach lub orzecznictwie, zwłaszcza gdy trzeba połączyć informacje z kilku źródeł prawnych. Celem badania było porównanie jakości odpowiedzi modeli językowych na pytania z zakresu polskiego prawa karnego z wykorzystaniem różnych sposobów dostępu do wiedzy zewnętrznej. Analizie poddano 4 warianty: model bez kontekstu; Retrieval-Augmented Generation (RAG) oparty na wyszukiwaniu wektorowym; rozwiązanie wykorzystujące graf wiedzy oraz architekturę hybrydową łączącą wyszukiwanie wektorowe i&#160;grafowe. Badanie obejmowało ocenę podobieństwa semantycznego i&#160;kompletności odpowiedzi, jakości wyszukiwania źródeł oraz zdolności do rozpoznawania braku informacji w&#160;korpusie. Szczególną uwagę poświęcono pytaniom wymagającym łączenia informacji pochodzących z wielu źródeł.&lt;/span&gt;&lt;/p&gt;</style></ABSTRACT><title><style face="normal" font="default" size="100%">Bielik i GPT w analizie polskiego prawa karnego: wpływ RAG  i grafów wiedzy na jakość odpowiedzi</style></title></RECORD></records></xml>
