Publikacje naukowe Agnieszka Nowy
Tytuł: SmartBuildSim: An Open-Source Synthetic-Twin Framework for Reproducible AI Benchmarking in Smart-Building Analytics
Autor/Autorzy: Tymoteusz Miller, Irmina Durlik, Agnieszka Nowy, Ewelina Kostecka
Miejsce publikacji: SENSORS
Rok: 2025
Słowa kluczowe: synthetic data, anomaly detection, smart building, AI benchmarking, forecasting, reinforcement learning
Abstrakt: This paper introduces SmartBuildSim, an open-source synthetic-twin framework that generates configurable and reproducible multi-sensor building streams using lightweight statistical models with tunable trend, seasonality, correlation, delays, and anomaly mechanisms. Deterministic seeding ensures experiment-level reproducibility, while modular pipelines support unified evaluation across forecasting, anomaly detection, and RL tasks. A comprehensive validation against an ASHRAE Great Energy Predictor III reference signal demonstrates that the synthetic data capture realistic magnitude and variability (KS ≈ 0.32; DTW ≈ 9.69), while preserving interpretable and controllable temporal structure. Benchmark results show that simple linear models achieve strong forecasting performance (RMSE ≈ 21.27), IsolationForest reliably outperforms LOF in anomaly detection (F1 ≈ 0.17 vs. 0.10), and Soft-Q Learning provides substantially more stable RL convergence than tabular Q-learning (variance reduced by >95%). Scenario-level analyses further illustrate reproducible daily cycles, zone-specific differences, and the scalability of model behaviour across building configurations. By combining declarative YAML configurations, deterministic randomness management, and an extensible scenario engine, SmartBuildSim provides a transparent and lightweight alternative to high-fidelity building simulators. The framework offers a practical, reproducible testbed for smart-building AI research, bridging the gap between simplistic synthetic datasets and complex physical digital twins. All code, tables, figures, and a Google Colab workflow are openly available to ensure full replicability.
Adres strony internetowej (link) do pełnego tekstu publikacji: pełny tekst
DOI: 10.3390/s25237263
Tytuł: Integrating Artificial Intelligence Agents with the Internet of Things for Enhanced Environmental Monitoring: Applications in Water Quality and Climate Data
Autor/Autorzy: Tymoteusz Miller, Irmina Durlik, Ewelina Kostecka, Polina Kozlovska, Adrianna Łobodzińska, Sylwia Sokołowska, Agnieszka Nowy
Miejsce publikacji: Electronics
Rok: 2025
Słowa kluczowe: water quality, predictive analytics, Internet of Things (IoT), environmental monitoring, artificial intelligence (AI) agents, climate data, real-time decision making, smart environmental systems
Abstrakt: The integration of artificial intelligence (AI) agents with the Internet of Things (IoT) has marked a transformative shift in environmental monitoring and management, enabling advanced data gathering, in-depth analysis, and more effective decision making. This comprehensive literature review explores the integration of AI and IoT technologies within environmental sciences, with a particular focus on applications related to water quality and climate data. The methodology involves a systematic search and selection of relevant studies, followed by thematic, meta-, and comparative analyses to synthesize current research trends, benefits, challenges, and gaps. The review highlights how AI enhances IoT’s data collection capabilities through advanced predictive modeling, real-time analytics, and automated decision making, thereby improving the accuracy, timeliness, and efficiency of environmental monitoring systems. Key benefits identified include enhanced data precision, cost efficiency, scalability, and the facilitation of proactive environmental management. Nevertheless, this integration encounters substantial obstacles, including issues related to data quality, interoperability, security, technical constraints, and ethical concerns. Future developments point toward enhancements in AI and IoT technologies, the incorporation of innovations like blockchain and edge computing, the potential formation of global environmental monitoring systems, and greater public involvement through citizen science initiatives. Overcoming these challenges and embracing new technological trends could enable AI and IoT to play a pivotal role in strengthening environmental sustainability and resilience.
Adres strony internetowej (link) do pełnego tekstu publikacji: pełny tekst
Tytuł: Modeling of vessel traffic flow for waterway design–port of Świnoujście case study
Autor/Autorzy: Agnieszka Nowy, Kinga Łazuga, Lucjan Gucma, Andrej Androjna, Marko Perkovič, Jure Srše
Miejsce publikacji: Applied Sciences-Basel
Rok: 2021
Słowa kluczowe: probabilistic model, safety of navigation, vessel traffic flow, Świnoujście approach
Abstrakt: The paper presents an analysis of ship traffic using the port of Świnoujście and the problems associated with modelling vessel traffic flows. Navigation patterns were studied using the Automatic Identification System (AIS); an analysis of vessel traffic was performed with statistical methods using historical data; and the paper presents probabilistic models of the spatial distribution of vessel traffic and its parameters. The factors that influence the spatial distribution were considered to be the types of vessels, dimensions, and distances to hazards. The results show a correlation between the standard deviation of the traffic flow, the vessel sizes, and the distance to the hazard.These can be used in practice to determine the safety of navigation and the design of non-existing waterways and to create a general model of vessel traffic flow. The creation of the practical applications is intended to improve navigation efficiency, safety, and risk analysis in any particular area.
Adres strony internetowej (link) do pełnego tekstu publikacji: pełny tekst
DOI: 10.3390/app11178126
Tytuł: Use of a multiple regression model to determine the parameters of vessel traffic flow in port areas
Autor/Autorzy: Agnieszka Nowy, Lucjan Gucma
Miejsce publikacji: TransNav-International Journal on Marine Navigation and Safety of Sea Transportation
Rok: 2020
Słowa kluczowe: Maritime Traffic Engineering, Vessel Traffic Flow, Port Areas, Multiple Regression Model, Fairway, Fairway Parameters, Automatic Identification System (AIS), AIS Data
Abstrakt: The paper presents the method of determining ships traffic stream parameters by means of regression method. The aim of the studies was to determine the correlation between the ship’s parameters and the parameters of the fairway. Developing the presented model with information on the position of the vessel’s antenna and information on the accuracy of position determination will allow creating a model for predicting the parameters of waterways.
Adres strony internetowej (link) do pełnego tekstu publikacji: pełny tekst
Tytuł: Modelling the lateral distribution of ship traffic in traffic separation schemes
Autor/Autorzy: Agnieszka Nowy, Lucjan Gucma
Miejsce publikacji: Scientific Journals of the Maritime University of Szczecin
Rok: 2018
Słowa kluczowe: vessel traffic streams, ships’ traffic flow, safety of navigation, probabilistic model, traffic separa-tion scheme, modelling
Abstract: This paper presents the method used for the creation of ship traffic models in Southern Baltic Traffic Separation Schemes (TSS). The analysis of ship traffic was performed by means of statistical methods with the use of his-torical AIS data. The paper presents probabilistic models of ship traffic’s spatial distribution and its parameters. The results showed that there is a correlation between the standard deviation of traffic flow and TSS lane width that can be
used in practical applications to ensure the safety of navigation; improve navigation efficiency, safe-ty and risk analysis in given area, and for the creation of a general model of ship traffic flow.
Adres strony internetowej (link) do pełnego tekstu publikacji: pełny tekst
DOI: 10.17402/269
Tytuł: Verification of automatic drift calculation accuracy using an automatic radar plotting aid
Autor/Autorzy: Wiesław Juszkiewicz, Agnieszka Nowy
Miejsce publikacji: Scientific Journals of the Maritime University of Szczecin
Rok: 2016
Słowa kluczowe: IMO performance standards, automatic drift calculation, ARPA, safety of navigation, radar simulator, radar picture stabilization
Abstrakt: One consideration required in the resolution concerning radar and automatic radar plotting aid (ARPA) equipment is the possibility of an automatic drift calculation being realized in the base of fixed target tracking. This information is very important to providing safe navigation, especially in restricted areas. This paper presents an analysis of the present regulations contained in IMO resolutions and the results of an experiment conducted in the ARPA simulator. The aim of the simulations was to verify the reliability of the information presented on the ARPA display and to determine the accuracy of the automatic drift calculation implemented in the simulator.
Adres strony internetowej (link) do pełnego tekstu publikacji: pełny tekst
DOI: 10.17402/123