Damian Pliszczuk
Damian Pliszczuk has a total of 30 co-authors. Here are the top co-authors by number of shared publications:
- Michał Maj
WSEI University, Lublin, Poland
8 shared publications - Tomasz Cieplak
Lublin University of Technology
7 shared publications Tomasz Cieplak
6 shared publications- Tomasz Rymarczyk
WSEI University, 20-209 Lublin, Poland
6 shared publications - Jakub Pizoń
Department of Enterprise Organization, Faculty of Management, Lublin University of Technology, ul. Nadbystrzycka 38, 20-618 Lublin, Poland
3 shared publications Michał MAJ
3 shared publications
Latest Publications
- Open Access
- 26 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 1552-1554
WiP: Camera-Assisted Training for Radio-Only Indoor Human Sensing
- 26 October 2026
- Published by Association for Computing Machinery (ACM)
- p. 1552-1554
Open AccessWiP: Camera-Assisted Training for Radio-Only Indoor Human Sensing
- 28 April 2026
- Published by Wydawnictwo SIGMA-NOT, sp. z.o.o. in PRZEGLĄD ELEKTROTECHNICZNY
- Vol. 1 (4) , 42-46
Performance evaluation of tSVD and Tikhonov regularization in indoor radio tomographic imaging using custom hardware
We compare truncated SVD and Tikhonov regularization for radio tomographic imaging on a custom platform consisting of 16 wireless nodes. Across 450 reconstructions we assess shape metrics (circularity, elongation) and boundary stability, with regularization parameters selected using the L-curve method and energy-based criteria. tSVD yields higher circularity (0.72 vs 0.66; p = 0.082) and significantly lower elongation (p = 0.003), showing greater robustness to noise and edge artifacts.
- 28 April 2026
- Published by Wydawnictwo SIGMA-NOT, sp. z.o.o. in PRZEGLĄD ELEKTROTECHNICZNY
- Vol. 1 (4) , 42-46
Performance evaluation of tSVD and Tikhonov regularization in indoor radio tomographic imaging using custom hardware
We compare truncated SVD and Tikhonov regularization for radio tomographic imaging on a custom platform consisting of 16 wireless nodes. Across 450 reconstructions we assess shape metrics (circularity, elongation) and boundary stability, with regularization parameters selected using the L-curve method and energy-based criteria. tSVD yields higher circularity (0.72 vs 0.66; p = 0.082) and significantly lower elongation (p = 0.003), showing greater robustness to noise and edge artifacts.
- Open Access
- 6 May 2025
- Published by Association for Computing Machinery (ACM)
- p. 656-657
Poster: Optimizing Radio Tomography with Edge Computing: A Low-Latency Approach for Human Detection
- 6 May 2025
- Published by Association for Computing Machinery (ACM)
- p. 656-657
Open AccessPoster: Optimizing Radio Tomography with Edge Computing: A Low-Latency Approach for Human Detection
- 24 March 2025
- Published by Wydawnictwo SIGMA-NOT, sp. z.o.o. in PRZEGLĄD ELEKTROTECHNICZNY
- Vol. 1 (3) , 89-92
Destylacja wiedzy w głębokim uczeniu za pomocą sieci multimodalnych
Artykuł opisuje zastosowanie destylacji wiedzy w głębokim uczeniu z wykorzystaniem sieci multimodalnych do stworzenia inteligentnego urządzenia. Opracowany model jednocześnie wykrywa osobę na obrazie, klasyfikuje jej emocje oraz sprawdza, czy jest zarejestrowanym użytkownikiem. Dzięki destylacji wiedzy uzyskano mniejszy model o zbliżonej skuteczności, który działa w czasie rzeczywistym na urządzeniach wbudowanych. Wyniki pokazują, że techniki multimodalne i destylacja wiedzy poprawiają wydajność modeli
- 24 March 2025
- Published by Wydawnictwo SIGMA-NOT, sp. z.o.o. in PRZEGLĄD ELEKTROTECHNICZNY
- Vol. 1 (3) , 89-92
Destylacja wiedzy w głębokim uczeniu za pomocą sieci multimodalnych
Artykuł opisuje zastosowanie destylacji wiedzy w głębokim uczeniu z wykorzystaniem sieci multimodalnych do stworzenia inteligentnego urządzenia. Opracowany model jednocześnie wykrywa osobę na obrazie, klasyfikuje jej emocje oraz sprawdza, czy jest zarejestrowanym użytkownikiem. Dzięki destylacji wiedzy uzyskano mniejszy model o zbliżonej skuteczności, który działa w czasie rzeczywistym na urządzeniach wbudowanych. Wyniki pokazują, że techniki multimodalne i destylacja wiedzy poprawiają wydajność modeli
- Open Access
- 4 November 2024
- Published by Association for Computing Machinery (ACM)
- p. 891-892
Poster: Fusing radio tomography and RGB camera data for enhanced multi-person detection and tracking
This paper presents a system that fuses radio tomography data with RGB camera information for enhanced multi-person detection and tracking in indoor environments. Experiments were conducted in an irregularly shaped room with four subjects. Due to its limited resolution, radio tomography initially represented all individuals as a single entity. By incorporating RGB camera data, we were able to accurately identify and track each person individually. Our findings underscore the significance of integrating data from both modalities for improved detection and tracking performance in indoor surveillance and security systems.
- 4 November 2024
- Published by Association for Computing Machinery (ACM)
- p. 891-892
Open AccessPoster: Fusing radio tomography and RGB camera data for enhanced multi-person detection and tracking
This paper presents a system that fuses radio tomography data with RGB camera information for enhanced multi-person detection and tracking in indoor environments. Experiments were conducted in an irregularly shaped room with four subjects. Due to its limited resolution, radio tomography initially represented all individuals as a single entity. By incorporating RGB camera data, we were able to accurately identify and track each person individually. Our findings underscore the significance of integrating data from both modalities for improved detection and tracking performance in indoor surveillance and security systems.
- Open Access
- 20 August 2024
- Published by Akademia Nauk Stosowanych WSGE im. A. De Gasperi w Józefowie in Journal of Modern Science
- Vol. 57 (3) , 485-497
Optimizing delivery time with an intelligent forecasting model: leveraging ai and machine learning for efficient logistics
Business analytics involves using various technologies to analyze data. Data mining focuses on the automated search for knowledge, patterns, or regularities in data. As a business analyst, it is essential to recognize the type of analytical technique appropriate for solving a specific problem. Exploratory Data Analysis (EDA) describes data using statistical and visualization techniques to highlight important aspects of that data for further analysis. This involves examining a data set from many angles, describing it, and summarizing it without making assumptions about its content. Exploratory data analysis is an essential step before diving into statistical modeling or machine learning to ensure that the data is really what it claims to be and that there are no apparent errors. This type of analysis should be part of data science projects in every organization. Visual analytics is sometimes confused with data visualization. Visual analysis is not simply a matter of graphically representing data. Modern, interactive visual analytics makes combining data from multiple sources easy and performs in-depth data analysis directly in the visualization. Additionally, artificial intelligence and machine learning algorithms can offer recommendations for exploration. Ultimately, visual analytics helps transform massive data sets into business insights that can positively impact an organization. Considering the previous comment about visual data analysis, it should be added that the system has extensive capabilities to create graphical dashboards containing reports and charts. It is essential that in the case of desktops, in addition to the visualizations included in the system itself, it is possible to embed reports from third-party tools.
- 20 August 2024
- Published by Akademia Nauk Stosowanych WSGE im. A. De Gasperi w Józefowie in Journal of Modern Science
- Vol. 57 (3) , 485-497
Open AccessOptimizing delivery time with an intelligent forecasting model: leveraging ai and machine learning for efficient logistics
Business analytics involves using various technologies to analyze data. Data mining focuses on the automated search for knowledge, patterns, or regularities in data. As a business analyst, it is essential to recognize the type of analytical technique appropriate for solving a specific problem. Exploratory Data Analysis (EDA) describes data using statistical and visualization techniques to highlight important aspects of that data for further analysis. This involves examining a data set from many angles, describing it, and summarizing it without making assumptions about its content. Exploratory data analysis is an essential step before diving into statistical modeling or machine learning to ensure that the data is really what it claims to be and that there are no apparent errors. This type of analysis should be part of data science projects in every organization. Visual analytics is sometimes confused with data visualization. Visual analysis is not simply a matter of graphically representing data. Modern, interactive visual analytics makes combining data from multiple sources easy and performs in-depth data analysis directly in the visualization. Additionally, artificial intelligence and machine learning algorithms can offer recommendations for exploration. Ultimately, visual analytics helps transform massive data sets into business insights that can positively impact an organization. Considering the previous comment about visual data analysis, it should be added that the system has extensive capabilities to create graphical dashboards containing reports and charts. It is essential that in the case of desktops, in addition to the visualizations included in the system itself, it is possible to embed reports from third-party tools.
- Open Access
- 20 August 2024
- Published by Akademia Nauk Stosowanych WSGE im. A. De Gasperi w Józefowie in Journal of Modern Science
- Vol. 57 (3) , 371-387
An intelligent support system and emotional state tests for people who are sick or recovering
The project aims to develop an intelligent system that has the potential to significantly improve patient care by examining and supporting the emotional state of people with chronic diseases or undergoing rehabilitation. The system will use advanced technologies such as image analysis, natural language processing and understanding (NLP/NLU), and a personal assistant module. Acting as a virtual companion, this module will support the user in everyday tasks such as setting reminders and managing schedules and provide emotional support through interactive conversations. The project also involves the development of an analytical module that automatically generates analyses and reports based on the collected data. A patient-oriented system will be created during the work to collect essential data and support him in rehabilitation. On the other hand, the system will cooperate with a doctor who can make a preliminary diagnosis and develop further treatment based on the patient's data. As feedback, the patient will receive health reports along with their interpretation and treatment recommendations created by the doctor.
- 20 August 2024
- Published by Akademia Nauk Stosowanych WSGE im. A. De Gasperi w Józefowie in Journal of Modern Science
- Vol. 57 (3) , 371-387
Open AccessAn intelligent support system and emotional state tests for people who are sick or recovering
The project aims to develop an intelligent system that has the potential to significantly improve patient care by examining and supporting the emotional state of people with chronic diseases or undergoing rehabilitation. The system will use advanced technologies such as image analysis, natural language processing and understanding (NLP/NLU), and a personal assistant module. Acting as a virtual companion, this module will support the user in everyday tasks such as setting reminders and managing schedules and provide emotional support through interactive conversations. The project also involves the development of an analytical module that automatically generates analyses and reports based on the collected data. A patient-oriented system will be created during the work to collect essential data and support him in rehabilitation. On the other hand, the system will cooperate with a doctor who can make a preliminary diagnosis and develop further treatment based on the patient's data. As feedback, the patient will receive health reports along with their interpretation and treatment recommendations created by the doctor.
- 15 April 2024
- Published by Wydawnictwo SIGMA-NOT, sp. z.o.o. in PRZEGLĄD ELEKTROTECHNICZNY
- Vol. 1 (4) , 255-258
Porównanie modeli przestrzeni barw CIE CAM i CIE LAB w celu lepszej automatyzacji optycznej kontroli jakości
Jednym z elementów systemu kontroli jakości w branżach takich jak meblarska czy też motoryzacyjna jest proces porównywania kolorów czyli określenie różnic pomiędzy kolorami referencyjnymi oraz rzeczywistymi. W ocenie różnic w kolorach pomaga określnie odpowiednich przestrzeni barw – w tym przypadku posłużono się dwoma przestrzeniami barw CIE CAM oraz CIE LAB. Porównując kolory za pomocą tych modeli różnice w trzech komponentach składających się na daną przestrzeń (jasność, nasycenie i odcień), można wykorzystać do określenia postrzeganej różnicy w wyglądzie kolorów
- 15 April 2024
- Published by Wydawnictwo SIGMA-NOT, sp. z.o.o. in PRZEGLĄD ELEKTROTECHNICZNY
- Vol. 1 (4) , 255-258
Porównanie modeli przestrzeni barw CIE CAM i CIE LAB w celu lepszej automatyzacji optycznej kontroli jakości
Jednym z elementów systemu kontroli jakości w branżach takich jak meblarska czy też motoryzacyjna jest proces porównywania kolorów czyli określenie różnic pomiędzy kolorami referencyjnymi oraz rzeczywistymi. W ocenie różnic w kolorach pomaga określnie odpowiednich przestrzeni barw – w tym przypadku posłużono się dwoma przestrzeniami barw CIE CAM oraz CIE LAB. Porównując kolory za pomocą tych modeli różnice w trzech komponentach składających się na daną przestrzeń (jasność, nasycenie i odcień), można wykorzystać do określenia postrzeganej różnicy w wyglądzie kolorów
- Open Access
- 2 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-3
Cross-Modal Perception for Customer Service
- 2 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-3
Open AccessCross-Modal Perception for Customer Service
- Open Access
Autonomous Face Classification Online Self-Training System Using Pretrained ResNet50 and Multinomial Naïve Bayes
This paper presents a novel, autonomous learning system working in real-time for face recognition. Multiple convolutional neural networks for face recognition tasks are available; however, these networks need training data and a relatively long training process as the training speed depends on hardware characteristics. Pretrained convolutional neural networks could be useful for encoding face images (after classifier layers are removed). This system uses a pretrained ResNet50 model to encode face images from a camera and the Multinomial Naïve Bayes for autonomous training in the real-time classification of persons. Faces of several persons visible in a camera are tracked using special cognitive tracking agents who deal with machine learning models. After a face in a new position of the frame appears (in a place where there was no face in the previous frames), the system checks if it is novel or not using a novelty detection algorithm based on an SVM classifier; if it is unknown, the system automatically starts training. As a result of the conducted experiments, one can conclude that good conditions provide assurance that the system can learn the faces of a new person who appears in the frame correctly. Based on our research, we can conclude that the critical element of this system working is the novelty detection algorithm. If false novelty detection works, the system can assign two or more different identities or classify a new person into one of the existing groups.
Open AccessAutonomous Face Classification Online Self-Training System Using Pretrained ResNet50 and Multinomial Naïve Bayes
This paper presents a novel, autonomous learning system working in real-time for face recognition. Multiple convolutional neural networks for face recognition tasks are available; however, these networks need training data and a relatively long training process as the training speed depends on hardware characteristics. Pretrained convolutional neural networks could be useful for encoding face images (after classifier layers are removed). This system uses a pretrained ResNet50 model to encode face images from a camera and the Multinomial Naïve Bayes for autonomous training in the real-time classification of persons. Faces of several persons visible in a camera are tracked using special cognitive tracking agents who deal with machine learning models. After a face in a new position of the frame appears (in a place where there was no face in the previous frames), the system checks if it is novel or not using a novelty detection algorithm based on an SVM classifier; if it is unknown, the system automatically starts training. As a result of the conducted experiments, one can conclude that good conditions provide assurance that the system can learn the faces of a new person who appears in the frame correctly. Based on our research, we can conclude that the critical element of this system working is the novelty detection algorithm. If false novelty detection works, the system can assign two or more different identities or classify a new person into one of the existing groups.