I recently completed my PhD in Machine Learning and Intelligent Systems at Wroclaw University of Science and Technology. In 2021, I was honored as a distinguished early-stage researcher and awarded the prestigious Marie Skłodowska-Curie Fellowship by the European Union. This fellowship supported my doctoral studies as part of the European Training Network's MOIRA program, focused on monitoring large-scale complex systems.
My research focuses on developing lightweight deep convolutional neural networks (DCNNs) and generative adversarial networks (GANs) for computer vision and heterogeneous data processing applications. During my PhD, I designed and evaluated state-of-the-art deep learning models, including U-NET-based and fusion-based DCNN architectures, to address tasks such as object segmentation, classification, and decision fusion. I also explored DCNN models for the classification and visualization of high-dimensional data, advancing methodologies for image processing and decision-making applications.
My research focuses on developing lightweight deep convolutional neural networks (DCNNs) and generative adversarial networks (GANs) for computer vision and heterogeneous data processing applications. During my PhD, I designed and evaluated state-of-the-art deep learning models, including U-NET-based and fusion-based DCNN architectures, to address tasks such as object segmentation, classification, and decision fusion. I also explored DCNN models for the classification and visualization of high-dimensional data, advancing methodologies for image processing and decision-making applications.
Recent journal papers
Advanced Image Analytics for Mobile Robot-Based Condition Monitoring in Hazardous Environments: A Comprehensive Thermal Defect Processing Framework
Journal: Sensors, May 2024, Link to the paper
Semantic Segmentation of Thermal Defects in Belt Conveyor Idlers Using Thermal Image Augmentation and U-Net based Convolutional Neural Network
Journal: Nature - Scientific Reports, February 2024, Link to the paper
Automated Identification of Overheated Belt Conveyor Idlers in Thermal Images with Complex Backgrounds Using Binary Classification with CNN
Journal: Sensors, October 2022, Link to paper
Design of an Infrared Image Processing Pipeline for Robotic Inspection of Conveyor Systems in Opencast Mining Sites
Journal: Energies, September 2022, Link to paper
Deep Learning-Based Semantic Segmentation of Thermal Defects Using AResU-Net and REAL-ESRGAN for the Infrared Image Resolution Enhancement
Conference : UK, Huddersfield, September 2023, Link to paper
For the full list of my conference papers please check out my Google Scholar page
Journal: Sensors, May 2024, Link to the paper
Semantic Segmentation of Thermal Defects in Belt Conveyor Idlers Using Thermal Image Augmentation and U-Net based Convolutional Neural Network
Journal: Nature - Scientific Reports, February 2024, Link to the paper
Automated Identification of Overheated Belt Conveyor Idlers in Thermal Images with Complex Backgrounds Using Binary Classification with CNN
Journal: Sensors, October 2022, Link to paper
Design of an Infrared Image Processing Pipeline for Robotic Inspection of Conveyor Systems in Opencast Mining Sites
Journal: Energies, September 2022, Link to paper
Deep Learning-Based Semantic Segmentation of Thermal Defects Using AResU-Net and REAL-ESRGAN for the Infrared Image Resolution Enhancement
Conference : UK, Huddersfield, September 2023, Link to paper
For the full list of my conference papers please check out my Google Scholar page
Selected conferences and workshops (2021-2024)
[Gallery picture]
University of Oxford - 2022
[Gallery picture]
University of Oxford - 2022
[Gallery picture]
Survishno conference - Toulouse - 2023
[Gallery picture]
University of Huddersfield - 2023
[Gallery picture]
PhD defense ceremony - Wroclaw, 2024
[Gallery picture]
Luleå University of Technology - 2024
👨🔬
Some interesting pics from my previous published papers
[Picture]
https://www.mdpi.com/1424-8220/22/24/10004
[Picture]
https://doi.org/10.1038/s41598-024-55864-2
[Picture]
The architecture of CNNs to efficiently extract the pixel features and classify them to perform semantic segmentation tasks. https://doi.org/10.3390/s24113421
[Picture]
PCA plot showing the first three principal components of the dataset. https://doi.org/10.3390/s24113421