25 citations · 45 across the 14 of their papers we have counts for
16 papers
Toward Seasonal Guidelines for Robust Deep-Learning Sentinel-2 Building Detection in Different Area Types
Michał Romaszewski, Kamil Drejer, Katarzyna Kołodziej +7
Sentinel-2 imagery offers open access, global coverage, and frequent revisit times, making it attractive for practical building mapping at scale; however, its native 10m resolution…
Enabling Cloud-Level Accuracy in Edge AI through IoT Data Preprocessing
Aygün Varol, Katarzyna Kołodziej, Łukasz Sobczak +5
Large language models (LLMs) offer a natural-language interface for interpreting Internet of Things (IoT) sensor data in smart environments; however, cloud deployment introduces la…
From Articles to Canopies: Knowledge-Driven Pseudo-Labelling for Tree Species Classification using LLM Experts
Michał Romaszewski, Dominik Kopeć, Michał Cholewa +6
Hyperspectral tree species classification is challenging due to limited and imbalanced class labels, spectral mixing (overlapping light signatures from multiple species), and ecolo…
Semantic Depth Matters: Explaining Errors of Deep Vision Networks through Perceived Class Similarities
Katarzyna Filus, Michał Romaszewski, Mateusz Żarski
Understanding deep neural network (DNN) behavior requires more than evaluating classification accuracy alone; analyzing errors and their predictability is equally crucial. Current…
Quantum-aware Transformer model for state classification
Przemysław Sekuła, Michał Romaszewski, Przemysław Głomb +2
Entanglement is a fundamental feature of quantum mechanics, playing a crucial role in quantum information processing. However, classifying entangled states, particularly in the mix…
Efficient Numerical Calibration of Water Delivery Network Using Short-Burst Hydrant Trials
Katarzyna Kołodziej, Michał Cholewa, Przemysław Głomb +2
Calibration is a critical process for reducing uncertainty in Water Distribution Network Hydraulic Models (WDN HM). However, features of certain WDNs, such as oversized pipelines,…
`Just One More Sensor is Enough' -- Iterative Water Leak Localization with Physical Simulation and a Small Number of Pressure Sensors
Michał Cholewa, Michał Romaszewski, Przemysław Głomb +6
In this article, we propose an approach to leak localisation in a complex water delivery grid with the use of data from physical simulation (e.g. EPANET software). This task is usu…
Through the Thicket: A Study of Number-Oriented LLMs derived from Random Forest Models
Michał Romaszewski, Przemysław Sekuła, Przemysław Głomb +2
Large Language Models (LLMs) have shown exceptional performance in text processing. Notably, LLMs can synthesize information from large datasets and explain their decisions similar…
Data structure > labels? Unsupervised heuristics for SVM hyperparameter estimation
Michał Cholewa, Michał Romaszewski, Przemysław Głomb
Classification is one of the main areas of pattern recognition research, and within it, Support Vector Machine (SVM) is one of the most popular methods outside of field of deep lea…
Improving Autoencoder Training Performance for Hyperspectral Unmixing with Network Reinitialisation
Kamil Książek, Przemysław Głomb, Michał Romaszewski +3
Neural networks, in particular autoencoders, are one of the most promising solutions for unmixing hyperspectral data, i.e. reconstructing the spectra of observed substances (endmem…
Hyperspectral classification of blood-like substances using machine learning methods combined with genetic algorithms in transductive and inductive scenarios
Filip Pałka, Wojciech Książek, Paweł Pławiak +2
This study is focused on applying genetic algorithms (GA) to model and band selection in hyperspectral image classification. We use a forensic-inspired data set of seven hyperspect…
Comparison of surface thermal patterns of horses and donkeys in IRT images
Małgorzata Domino, Michał Romaszewski, Tomasz Jasiński +1
Infrared thermography (IRT) is a valuable diagnostic tool in equine veterinary medicine however, little is known about its application in donkeys. The aim was to find patterns in t…
A Dataset for Evaluating Blood Detection in Hyperspectral Images
Michał Romaszewski, Przemysław Głomb, Arkadiusz Sochan +1
The sensitivity of imaging spectroscopy to haemoglobin derivatives makes it a promising tool for detecting blood. However, due to complexity and high dimensionality of hyperspectra…
Band selection with Higher Order Multivariate Cumulants for small target detection in hyperspectral images
Przemysław Głomb, Krzysztof Domino, Michał Romaszewski +1
In the small target detection problem a pattern to be located is on the order of magnitude less numerous than other patterns present in the dataset. This applies both to the case o…
Compression of animated 3D models using HO-SVD
Michał Romaszewski, Piotr Gawron, Sebastian Opozda
This work presents an analysis of Higher Order Singular Value Decomposition (HO-SVD) applied to lossy compression of 3D mesh animations. We describe strategies for choosing a numbe…
Natural hand gestures for human identification in a Human-Computer Interface
Michał Romaszewski, Przemysław Głomb, Piotr Gawron
The goal of this work is the identification of humans based on motion data in the form of natural hand gestures. In this paper, the identification problem is formulated as classifi…