Doctoral Schools WUT

Search Engine for Promoters and Research Areas

Wykaz obszarów badawczych związanych z tagiem Uczenie-maszynowe:

# Obszar badawczy Dziedzina naukowa
1 Electronic tongue - study of the correlation of (soft) sensor signals with organoleptic properties. The ""Holy Grail"" of the pharmaceutical and food industry is the replacement of trained organoleptic evaluation experts (human panel) with machine-based taste and smell systems, so-called taste and smell sensors, also known as ""electronic noses"" and ""electronic tongues"". Over the last years, we have gained unique expertise in this field - we are able to develop biomimetic systems with which we can identify bitter taste masking in pediatric formulations, determine the method of food processing used to increase shelf life of foodstuff, or evaluate the effectiveness of artificial sweeteners. The aim of the doctorate will be the fabrication of (soft) sensors / (soft) sensor arrays and the acquisition of their signals, for further data mining aiming on correlating the signals with the organoleptic properties of selected foodstuff and / or pharmaceutical products.
2 bioinformatics, big data, distributed computing, machine learning
3 Convergence of high-performance computing and machine learning. Development of distributed programming methods, techniques and environments, with particular emphasis on machine learning solvers and their integration into classic HPC solutions used in a cluster, grid and cloud environments in relation to the complex issues of high-scale scientific computing e-Science. Algorithms and multi-scale computing systems using different heterogeneous GPU / IPU / CPU hardware solutions and environments in the multiprogramming-model mode, as well as resource management, task scheduling and optimization methods.
4 The research area covers the issues of image processing, computer vision, machine learning (including deep learning) and broadly understood artificial intelligence.
5 Her research interests are focused on the issues of modelling and designing effective transport and logistics networks and systems for servicing production companies and methods and tools supporting the planning and organization of transport with the use of heuristic algorithms based on evolutionary algorithms. The achievement in this area is the development and development of an original engineering methodology for assessing the effectiveness of the functioning of the supply network.
6 Her research interests are focused on the issues of modelling and designing effective transport and logistics networks and systems for servicing production companies and methods and tools supporting the planning and organization of transport with the use of heuristic algorithms based on evolutionary algorithms. The achievement in this area is the development and development of an original engineering methodology for assessing the effectiveness of the functioning of the supply network.
7 Signal processing, especially speech processing. Natural language processing, in particular in the cybersecurity context. Voice biometry. Applications of machine learning. Computer technology in therapeutical applications.
8 1)Methods of detection and classification of heart abnormalities using deep learning techniques - concerns techniques and algorithms for processing ECG signals for automatic detection and classification of heart abnormalities using deep machine learning methods. It is planned to use a variety of deep convolutional neural networks for automatic analysis of the structure (waveform) of ECG signals, as well as mechanisms for detecting anomalies (deviations) and searching for information based on autoencoder neural networks. The work will be carried out in cooperation with the Department of Cardiology-Intensive Therapy and Internal Diseases of the Medical University of Karol Marcinkowski in Poznań. 2)Methods of detection and classification of heart abnormalities using heart rate variability (HRV) parameters and machine learning techniques - concerns techniques and algorithms for processing ECG signals for automatic detection and classification of heart abnormalities using machine learning methods. It is planned to use a wide variety of heart rate variability (HRV) parameters as well as new original heart rate asymmetry (HRA) parameters. The work will be carried out in cooperation with the Department of Cardiology-Intensive Therapy and Internal Diseases of the Medical University of Karol Marcinkowski in Poznań. 3)Passive radar for space object detection using signals recorded by antennas of the international network of radio telescopes LOFAR - The research area concerns the techniques and algorithms for processing signals recorded by the antennas of the network of radio telescopes LOFAR (Low-Frequency Array for radio astronomy) in order to use them for passive radiolocation of space objects: satellites in low orbits and so-called space debris. The considered system of passive radiolocation does not require the construction of dedicated transmitters, but uses the existing so-called illuminators of opportunity, e.g. FM, DAB + or TV DVB-T transmitters. After reflecting the signals from the objects, they are received by the antennas of the LOFAR system. The research in this area, carried out in cooperation with the Space Research Center of the Polish Academy of Sciences, is pioneering on a global scale. Three LOFAR stations are located in Poland. A single LOFAR station consists of many antennas creating a large radio telescope that can receive relatively weak signals. 4) Methods and algorithms for signal processing in passive radar for small unmanned aerial vehicles (drones) - concerns techniques and algorithms for signal processing dedicated to the passive radiolocation of small unmanned aerial vehicles (drones). The work will be carried out in cooperation with the Faculty of Power and Aeronautical Engineering of the Warsaw University of Technology at the airport in Sieraków near Przasnysz, recently purchased by the Warsaw University of Technology, where the Area Monitoring Laboratory with four antenna stations was built. Problems to be solved within the research area are related to detection of small flying objects with the use of specific features of signals reflected from the considered objects, estimation of their parameters, tracking, as well as classification of detected objects, in particular, the research is to focus on the possibility of distinguishing small drones from birds. 5) Optimization of methods and algorithms of people identification based on the EEG signal with the use of machine learning techniques - concerns the methods and algorithms of people identification based on the EEG signal with the use of machine learning techniques. It is planned to use the approach based both on the spectral features of the EEG signal in its individual bands, as well as the analysis of the EEG signal itself using the so-called deep learning techniques with convolutional neural networks. The work will include the selection and optimization of EEG signal parameters and classifiers used to identify people, the number of sessions necessary to train classifiers, the minimum number of electrodes used for identification, as well as the development of headbands/caps dedicated to collecting the EEG signal for the application under consideration, and testing the developed solutions under the conditions similar to their practical implementation. The research will be carried out in cooperation with the Nencki Institute of Experimental Biology of the Polish Academy of Sciences.
9 Processing of SAR radar images with particular emphasis on the phenomenon of radar speckle. Research in this area can be conducted in two main directions. The first is the study of the possibility of using selected image processing methods to remove speckle: an analysis of the effectiveness of the existing solutions and a proposal of innovative ones, based on e.g. classic methods of adaptive filtration, morphological filtration, multi-temporal (or, generally: multi-look) filtration, but also methods of machine learning, including convolutional neural networks. The second of the above-mentioned fields is the study of the significance of the phenomenon of radar speckle for the classification of the content of radar images and the development of a methodology allowing to maximize its effectiveness - with the specification of the procedure for dealing with the phenomenon of speckle.
10 The use of machine learning in the analysis and processing of remote sensing data, mainly optical and radar. In particular, the application of deep machine learning and transfer learning in selected areas related to computer vision. The main applications of the described processing and analysis are the classification of the content of satellite, aerial and terrestial imagery, as well as, in general, image recognition. The topi is related to the automation of remote sensing image processing, which is gaining importance with the development of remote sensing: an increase in the number of Earth observation satellites and of image data itself, as well as the increasing use of image data in various types of decision-making processes, analysis of time changes, climate monitoring, etc.
11 Speech signal analysis to detect the emotional state of the speaker. The research task includes a comprehensive speech signal analysis to identify the speaker's emotional state. Data processing algorithms include analyzing static and dynamic signal features and selecting the best ones. Machine learning algorithms, including deep learning, will be used to determine the speaker's emotional state.
12 Analysis of physiological signals to detect fatigue. The research task requires developing and constructing a test stand that enables the acquisition of various physiological signals at different stages of user fatigue. It is planned to use the following signals: electroencephalographic (EEG), electrooculographic (EOG), and audio-visual. In the next step, methods of analyzing the acquired signals in terms of fatigue detection should be developed. Data processing algorithms include feature extraction, feature selection, and machine learning (also deep learning).
13 Applying chemoinformatics and machine learning in developing new QSPR empirical correlations/models (QSPR = quantitative structure-property relationship) for describing and predicitng a variety of systems and physico-chemial properties.
14 New video compression methods based on neural networks: The research problem is devoted to the development of new architectures of convolutional neural networks and other video signal processing components for effective compression of video sequences. These other elements include the use of orthogonal transformations of the DCT and DWT type, descriptors allowing for the formation of the context. Basically, the network architectures for compression are based on the autoencoder structure. However, the relationship between the layers and the structure of the layers itself depends on many hyper parameters. The goal is to find a solution that will give the best possible compression efficiency at a limited computational cost. It is advisable to use learning in the GAN configuration to adjust the compression to the human vision system.
15 Forecasting the RES generation and production of electricity in systems of various sizes using machine learning. Optimization in power engineering
16 Methods of analysis and optimisation of intelligent complex systems SoS (System-of-Systems) – autonomous interacting technology-intensive systems, communicating and interacting with the environment, involved in real-time decision-making. The primary subject of research are network systems – computer networks, mobile networks, sensor networks (potentially utility networks as well), and systems providing services and applications in those networks – in particular, 5G and Internet of Things services. Research covers problems of design, management and real-time control of systems related to structure optimisation, resource allocation, job scheduling, etc. Analysed are issues of stochastic behaviour, uncertainty, and performance, reliability, robustness and efficiency criteria. Developed are algorithms based on mathematical programming (combinatorial optimization and graph algorithms, in particular), queueing theory, machine learning, data analysis, process simulation), embedded into on-line and off-line system software.
17 1. Zebranie informacji nt.: Nowych rozwiązań stosowanych w przemysle spożywczym. 2. Przeprowadzenie badań porównawczych (kontrolnych, ocenowych i poznawczych) umożliwiających porównanie firm RP z UE. 3. Wyznaczenie kierunku dalszego rozwoju                                                                                                                                                                                             branży na rynku krajowym;
18 machine learning and artificial intelligence; autonomous systems; ML architectures, MLOps
19

Computer simulation of electrical devices (electromagnetic field, circuits and systems), construction of HV pulse generators, but also algorithms of image and three-dimensional data processing (thermal imaging defectoscopy, computed tomography, automation of diagnostics of electrical devices and systems). I am interested in evolutionary algorithms and neural networks from an algorithmic perspective.

https://www.iem.pw.edu.pl/~jstar

20

Modeling, control, and simulation of complex systems (ICT, financial engineering, medicine, water resources, etc.), computer decision support systems, recommendation systems, wireless sensor networks, mobile ad hoc networks, optimal resource allocation in data networks and computing centers, parallel and distributed programming, global optimization algorithms, machine learning and Big Data processing, blockchain technologies, cyber security.

21

Bioinformatyka, genomika obliczeniowa, sztuczna inteligencja, uczenie maszynowe

22

Bioinformatyka, genomika obliczeniowa, sztuczna inteligencja, uczenie maszynowe

23

experimental particle physics, experimental nuclear physics, ultrarelativistic collisions of heavy atomic nuclei, analysis of data from the ALICE experiment at the Large Hadron Collider at CERN, angular correlations of identified particles, measurements of hadron interactions in the final state, femtoscopy, antimatter research at the Antiproton Decelerator, bound states of matter and antimatter

24

The research area primarily includes modelling of phase stability, atomic ordering, and properties of multicomponent alloys for applications in extreme conditions, such as in fusion reactors. The main groups of investigated alloys include ferritic-martensitic steels, tungsten alloys, high-entropy alloys, and metallic glasses. The principal computational methods employed are Density Functional Theory (DFT), enabling the exploration of properties in new materials and the creation of models for simulations on higher scales. Models based on DFT results are used in Monte Carlo simulations (enabling the study of atomic ordering in alloys), molecular dynamics (enabling the examination of mechanical properties of alloys), and CALPHAD (enabling the investigation of phase stability). Statistical methods, including machine learning techniques, are applied to create models for multicomponent alloys.

25

The research topics concern two disciplines: materials engineering and computer science. The PhD thesis will focus on research on porous polyurethane materials using machine learning methods. As part of the work, one of the machine learning methods will be used - deep learning. Many characteristics of porous polyurethane materials depend on the pore microstructure of these foams, including pore size, pore perforation size, and wall thickness. The features of the foams that depend on the parameters of the pore microstructure include: properties determined during deformation of the foams.

26

First research field: artificial intelligence, machine learning, in particular, dimensionality reduction, data visualization, clustering, classification, self-organization, outlier detection, artificial neural networks, feature extraction and selection. Second research field: concurrent programming and the Java programming language.

27

Self-supervised learning (SSL) methods have shown significant potential in improving the sample efficiency of deep learning and in providing a starting point for the learning of downstream tasks. Contrastive SSL methods have become a standard pre-training approach for a range of domains such as NLP and vision. Initial results suggest that non-contrastive SSL has been able to narrow the gap to the performance levels of contrastive methods, while obviating the need for explicit construction of negative samples. The aim of this research project is two-fold: 1) investigate the extent to which contrastive and non-contrastive methods can be used in novel SSL architectures, 2) examine whether the alignment of representations in SSL can be achieved by alternative methods, such as enforcing the ability to predict an input representation from the representations of similar inputs.

28

A prevalent theme present in the contemporary representation learning approaches is to pre-train large foundation models on huge datasets. Such approaches utilize static datasets constructed at a particular point in time, which contrasts with the constantly changing and expanding nature of data available on the internet. The proposed research will explore a new paradigm where the training dataset is constructed on the fly by querying the internet, enabling efficient adaptation of representation learning models to selected target tasks. The aims of this research project include 1) design methods to query relevant training data and use it to adapt the representation learning model in a continuous manner, 2) make progress towards building self-supervised methods that given a description of a task, autonomously formulate their learning curricula, query the internet for relevant training data, and use it to iteratively optimize the model.

29

Abstract Visual Reasoning (AVR) comprises problems that resemble those appearing in human IQ tests. For example, Raven's Progressive Matrices present a set of images arranged in a 3x3 grid with a missing panel in the bottom-right corner. The test-taker has to discover relations governing 2D shapes (and their attributes) located in the images to select an answer, from a provided set of options, that best completes the matrix. In general, AVR tasks focus on fundamental cognitive abilities such as analogy-making, conceptual abstraction, or extrapolation, which makes advancements delivered by this research applicable to diverse areas, extending well beyond the investigated tasks. In this research we plan to verify the abilities of Large Language Models (LLMs) and Large Vision Models (LVMs) to solve AVR tasks, both synthetic and representing real-world images.