Search
dr hab. inż. Michał Grochowski
Employment
- Head of Department at Department of Intelligent and Decision Support Systems
- Associate professor at Department of Intelligent and Decision Support Systems
Publications
Filters
total: 72
Catalog Publications
Year 2024
-
Optimizing Control of Wastewater Treatment Plant With Reinforcement Learning: Technical Evaluation of Twin-Delayed Deep Deterministic Policy Gradient Agent
PublicationControl of the wastewater treatment processes presents significant challenges due to the fluctuating nature of inflow and wastewater composition, alongside the system’s non-linear dynamics. Traditional control methods struggle to adapt to these variations, leading to an economically suboptimal operation of the process and a violation of norms imposed on the quality of wastewater discharged to the catchment area. This study proposes...
Year 2023
-
Attention-Based Deep Learning System for Classification of Breast Lesions—Multimodal, Weakly Supervised Approach
PublicationBreast cancer is the most frequent female cancer, with a considerable disease burden and high mortality. Early diagnosis with screening mammography might be facilitated by automated systems supported by deep learning artificial intelligence. We propose a model based on a weakly supervised Clustering-constrained Attention Multiple Instance Learning (CLAM) classifier able to train under data scarcity effectively. We used a private...
-
Exploring the landscape of automatic cerebral microbleed detection: A comprehensive review of algorithms, current trends, and future challenges
PublicationThis paper provides the first review to date which gathers, describes, and assesses, to the best of our knowledge, all available publications on automating cerebral microbleed (CMB) detection. It provides insights into the current state of the art and highlights the challenges and opportunities in this topic. By incorporating the best practices identified in this review, we established guidelines for the development of CMB detection...
-
Interpretable deep learning approach for classification of breast cancer - a comparative analysis of multiple instance learning models
PublicationBreast cancer is the most frequent female cancer. Its early diagnosis increases the chances of a complete cure for the patient. Suitably designed deep learning algorithms can be an excellent tool for quick screening analysis and support radiologists and oncologists in diagnosing breast cancer.The design of a deep learning-based system for automated breast cancer diagnosis is not easy due to the lack of annotated data, especially...
Year 2022
-
How high-tech solutions support the fight against IUU and ghost fishing: a review of innovative approaches, methods, and trends
PublicationIllegal, Unreported, and Unregulated fishing is a major threat to human food supply and marine ecosystem health. Not only is it a cause of significant economic loss but also its effects have serious long-term environmental implications, such as overfishing and ocean pollution. The beginning of the fight against this problem dates since the early 2000s. From that time, a number of approaches and methods have been developed and reported....
-
Trustworthy Applications of ML Algorithms in Medicine - Discussion and Preliminary Results for a Problem of Small Vessels Disease Diagnosis.
PublicationML algorithms are very effective tools for medical data analyzing, especially at image recognition. Although they cannot be considered as a stand-alone diagnostic tool, because it is a black-box, it can certainly be a medical support that minimize negative effect of human-factors. In high-risk domains, not only the correct diagnosis is important, but also the reasoning behind it. Therefore, it is important to focus on trustworthiness...
Year 2021
-
A Comprehensive Analysis of Deep Neural-Based Cerebral Microbleeds Detection System
PublicationMachine learning-based systems are gaining interest in the field of medicine, mostly in medical imaging and diagnosis. In this paper, we address the problem of automatic cerebral microbleeds (CMB) detection in magnetic resonance images. It is challenging due to difficulty in distinguishing a true CMB from its mimics, however, if successfully solved it would streamline the radiologists work. To deal with this complex three-dimensional...
-
TOWARDS EXPLAINABLE CLASSIFIERS USING THE COUNTERFACTUAL APPROACH - GLOBAL EXPLANATIONS FOR DISCOVERING BIAS IN DATA
PublicationThe paper proposes summarized attribution-based post-hoc explanations for the detection and identification of bias in data. A global explanation is proposed, and a step-by-step framework on how to detect and test bias is introduced. Since removing unwanted bias is often a complicated and tremendous task, it is automatically inserted, instead. Then, the bias is evaluated with the proposed counterfactual approach. The obtained results...
Year 2020
-
Explainable AI for Inspecting Adversarial Attacks on Deep Neural Networks
PublicationDeep Neural Networks (DNN) are state of the art algorithms for image classification. Although significant achievements and perspectives, deep neural networks and accompanying learning algorithms have some important challenges to tackle. However, it appears that it is relatively easy to attack and fool with well-designed input samples called adversarial examples. Adversarial perturba-tions are unnoticeable for humans. Such attacks...
-
Neural Architecture Search for Skin Lesion Classification
PublicationDeep neural networks have achieved great success in many domains. However, successful deployment of such systems is determined by proper manual selection of the neural architecture. This is a tedious and time-consuming process that requires expert knowledge. Different tasks need very different architectures to obtain satisfactory results. The group of methods called the neural architecture search (NAS) helps to find effective architecture...
-
Self-Supervised Learning to Increase the Performance of Skin Lesion Classification
PublicationTo successfully train a deep neural network, a large amount of human-labeled data is required. Unfortunately, in many areas, collecting and labeling data is a difficult and tedious task. Several ways have been developed to mitigate the problem associated with the shortage of data, the most common of which is transfer learning. However, in many cases, the use of transfer learning as the only remedy is insufficient. In this study,...
Year 2019
-
Deep neural network architecture search using network morphism
PublicationThe paper presents the results of the research on neural architecture search (NAS) algorithm. We utilized the hill climbing algorithm to search for well-performing structures of deep convolutional neural network. Moreover, we used the function preserving transformations which enabled the effective operation of the algorithm in a short period of time. The network obtained with the advantage of NAS was validated on skin lesion classification...
-
DIAGNOSIS OF MALIGNANT MELANOMA BY NEURAL NETWORK ENSEMBLE-BASED SYSTEM UTILISING HAND-CRAFTED SKIN LESION FEATURES
PublicationMalignant melanomas are the most deadly type of skin cancer but detected early have high chances for successful treatment. In the last twenty years, the interest of automated melanoma recognition detection and classification dynamically increased partially because of public datasets appearing with dermatoscopic images of skin lesions. Automated computer-aided skin cancer detection in dermatoscopic images is a very challenging task...
-
MACHINE LEARNING SYSTEM FOR AUTOMATED BLOOD SMEAR ANALYSIS
PublicationIn this paper the authors propose a decision support system for automatic blood smear analysis based on microscopic images. The images are pre-processed in order to remove irrelevant elements and to enhance the most important ones - the healthy blood cells (erythrocytes) and the pathologic (echinocytes). The separated blood cells are analyzed in terms of their most important features by the eigenfaces method. The features are the...
-
Selected Technical Issues of Deep Neural Networks for Image Classification Purposes
PublicationIn recent years, deep learning and especially Deep Neural Networks (DNN) have obtained amazing performance on a variety of problems, in particular in classification or pattern recognition. Among many kinds of DNNs, the Convolutional Neural Networks (CNN) are most commonly used. However, due to their complexity, there are many problems related but not limited to optimizing network parameters, avoiding overfitting and ensuring good...
Year 2018
-
Analiza istotności cech znamion skórnych dla celów diagnostyki czerniaka złośliwego
PublicationPomimo dynamicznego rozwoju metod uczenia maszynowego i ich wdrażania do praktyki lekarskiej, automatyczna analiza znamion skórnych wciąż jest nierozwiązanym problemem. Poniższy artykuł proponuje zastosowanie algorytmu ewolucyjnego do zaprojektowania, wytrenowania i przetestowania całych populacji klasyfikatorów (sztucznych sieci neuronowych) oraz ich iteracyjnego udoskonalania w każdej kolejnej populacji, w celu osiągnięcia jak...
-
Data augmentation for improving deep learning in image classification problem
PublicationThese days deep learning is the fastest-growing field in the field of Machine Learning (ML) and Deep Neural Networks (DNN). Among many of DNN structures, the Convolutional Neural Networks (CNN) are currently the main tool used for the image analysis and classification purposes. Although great achievements and perspectives, deep neural networks and accompanying learning algorithms have some relevant challenges to tackle. In this...
-
Decision support system for design of long distance heat transportation system
PublicationDistrict Heating (DH) systems are commonly supplied using local heat sources. Nowadays, modern insulation materials allow for effective and economically viable heat transportation over long distances (over 20 km). The paper proposes a Decision Support System (DSS) for optimized selection of design and operating parameters of a long distance Heat Transportation System (HTS). The method allows for evaluation of feasibility and effectiveness...
-
Diagnozowanie stanu retinopatii cukrzycowej przy pomocy głębokich sieci neuronowych
PublicationW referacie opisano problem wykrywania oraz klasyfikacji stanu retinopatii cukrzycowej ze zdjęć dna oka przy pomocy głębokich sieci neuronowych. Retinopatia cukrzycowa jest chorobą oczu często występującą u osób z cukrzycą. Nieleczona prowadzi do uszkodzenia wzroku, a nawet ślepoty. W pracy badawczej opracowano system wykrywania retinopatii cukrzycowej na podstawie zdjęć dna oka. Opracowana sieć neuronowa przypisuje stan choroby...
-
Optimal selection of input features and an acompanying neural network structure for the classification purposes - skin lesions case study
PublicationMalignant melanomas are the most deadly type of skin cancers however detected early enough give a high chances for successful treatment. The last years saw the dynamic growth of interest of automatic computer-aided skin cancer diagnosis. Every month brings new research results on new approaches to this problem, new methods of preprocessing, new classifiers, new ideas to follow etc. In particular, the rapid development of dermatoscopy,...
-
Optimal Selection of Input Features and an Acompanying Neural Network Structure for the Classification Purposes - Skin Lesions Case Study
Publication -
Rozpoznawanie obiektów przez głębokie sieci neuronowe
PublicationW referacie zaprezentowane zostaną wyniki badań nad rozpoznawaniem obiektów w różnych warunkach za pomocą głębokich sieci neuronowych. Przeanalizowano działanie dwóch struktur – ResNet50 oraz VGG19. Systemy rozpoznawania obrazu wytrenowano oraz przetestowano na reprezentatywnej, bazie zawierającej 25 tys. zdjęć psów oraz kotów, która znacznie upraszcza analizowanie działania systemów ze względu na łatwość interpretacji zdjęć przez...
Year 2017
-
Application of data driven methods in diagnostic of selected process faults of nuclear power plant steam turbine
PublicationArticle presents a comparison of process anomaly detection in nuclear power plant steam turbine using combination of data driven methods. Three types of faults are considered: water hammering, fouling and thermocouple fault. As a virtual plant a nonlinear, dynamic, mathe- matical steam turbine model is used. Two approaches for fault detection using one class and two class classiers are tested and compared.
-
Computed aided system for separation and classification of the abnormal erythrocytes in human blood
PublicationThe human peripheral blood consists of cells (red cells, white cells, and platelets) suspended in plasma. In the following research the team assessed an influence of nanodiamond particles on blood elements over various periods of time. The material used in the study consisted of samples taken from ten healthy humans of various age, different blood types and both sexes. The markings were leaded by adding to the blood unmodified...
-
DEEP CONVOLUTIONAL NEURAL NETWORKS AS A DECISION SUPPORT TOOL IN MEDICAL PROBLEMS – MALIGNANT MELANOMA CASE STUDY
PublicationThe paper presents utilization of one of the latest tool from the group of Machine learning techniques, namely Deep Convolutional Neural Networks (CNN), in process of decision making in selected medical problems. After the survey of the most successful applications of CNN in solving medical problems, the paper focuses on the very difficult problem of automatic analyses of the skin lesions. The authors propose the CNN structure...
-
Deep neural networks approach to skin lesions classification — A comparative analysis
PublicationThe paper presents the results of research on the use of Deep Neural Networks (DNN) for automatic classification of the skin lesions. The authors have focused on the most effective kind of DNNs for image processing, namely Convolutional Neural Networks (CNN). In particular, three kinds of CNN were analyzed: VGG19, Residual Networks (ResNet) and the hybrid of VGG19 CNN with the Support Vector Machine (SVM). The research was carried...
-
Intelligent system supporting diagnosis of malignant melanoma
PublicationMalignant melanomas are the most deadly type of skin cancers. Early diagnosis is a key for successful treatment and survival. The paper presents the system for supporting the process of diagnosis of skin lesions in order to detect a malignant melanoma. The paper describes the development process of an intel-ligent system purposed for the diagnosis of malignant melanoma. Presented sys-tem can be used as a decision support system...
-
Multicriteria Optimization Approach to Design and Operation of District Heating Supply System over its Life Cycle
PublicationDistrict Heating (DH) systems are commonly supplied using local heat sources. Nowadays, modern insulation materials allow for effective and economically viable heat transportation over long distances (over 20 km). In the paper a method for optimized selection of design and operating parameters of long distance Heat Transportation System (HTS) is proposed. The method allows for evaluation of feasibility and effectivity of heat transportation...
-
Nuclear Power Plant Steam Turbine - Modeling for Model Based Control Purposes
PublicationThe nature of the processes taking place in a nuclear power plant (NPP) steam turbine is the reason why their modeling is very difficult, especially when the model is intended to be used for on-line optimal model based process control over a wide range of operating conditions, caused by changing electrical power demand e.g. when combined heat and power mode of work is utilized. The paper presents three nonlinear models of NPP steam...
Year 2016
-
Evolving neural network as a decision support system — Controller for a game of “2048” case study
PublicationThe paper proposes an approach to designing the neuro-genetic self-learning decision support system. The system is based on neural networks being adaptively learned by evolutionary mechanism, forming an evolved neural network. Presented learning algorithm enables for a selection of the neural network structure by establishing or removing of connections between the neurons, and then for a finding the beast suited values of the network...
-
Supervised model predictive control of wastewater treatment plant
PublicationAn optimizing control of a wastewater treatment plant (WWTP), allowing for cost savings over long time period and fulfilling effluent discharge limits at the same time, requires application of advanced control techniques. Model Predictive Control (MPC) is a very suitable control technology for a synthesis of such a truly multivariable controller that can handle constraints and accommodate model-based knowledge combined with hard...
-
Supervisory Control System for Adaptive Phase and Work Cycle Management of Sequencing Wastewater Treatment Plant
PublicationThe paper presents the design of the integrated control system applied to Sequencing Batch Reactor (SBR) in a biological Wastewater Treatment Plant (WWTP) in Swarzewo, which operates under activated sludge technology. Based on the real data records, ASM2d biological processes model and aeration system model, hierarchical control system for dissolved oxygen tracking and cycle management is designed. Internal Model Controller (IMC)...
-
SYSTEM WSPOMAGAJĄCY DIAGNOSTYKĘ CZERNIAKA ZŁOŚLIWEGO PRZY POMOCY METOD PRZETWARZANIA OBRAZU I ALGORYTMÓW INTELIGENCJI OBLICZENIOWEJ
PublicationNowotwory skóry są najczęściej spotykanymi nowotworami na świecie. Czerniaki złośliwe stanowią od około 5 do 7% wszystkich nowotworów złośliwych skóry u człowieka. Ich wczesne zdiagnozowanie jest kluczowym czynnikiem w późniejszej pomyślnej terapii. Niniejsza praca zawiera propozycję rozwinięcia i zautomatyzowania najważniejszej metody diagnozowania czerniaków, metody ABCD Stoltza. W artykule przedstawiono koncepcję i implementację...
-
Two-phase optimizing approach to design assessments of long distance heat transportation for CHP systems
PublicationCogeneration or Combined Heat and Power (CHP) for power plants is a method of putting to use waste heat which would be otherwise released to the environment. This allows the increase in thermodynamic efficiency of the plant and can be a source of environmental friendly heat for District Heating (DH). In the paper CHP for Nuclear Power Plant (NPP) is analyzed with the focus on heat transportation. A method for effectivity and feasibility...
Year 2015
-
Advanced Control Structures of Turbo Generator System of Nuclear Power Plant
PublicationIn the paper a synthesis of advanced control structures of turbine and synchronous generator for nuclear power plant working under changing operating conditions (supplied power level) is presented. It is based on the nonlinear models of the steam turbine and synchronous generator cooperating with the power system. Considered control structure consists of multi-regional fuzzy control systems with local linear controllers, including...
-
Advanced Control Structures of Turbo Generator System of Nuclear Power Plant
PublicationIn the paper a synthesis of advanced control structures of turbine and synchronous generator for nuclear power plant working under changing operating conditions (supplied power level) is presented. It is based on the nonlinear models of the steam turbine and synchronous generator cooperating with the power system. Considered control structure consists of multi-regional fuzzy control systems with local linear controllers, including...
-
ANALIZA MOŻLIWOŚCI ZASTOSOWANIA STEROWANIA PREDYKCYJNEGO TURBINĄ PAROWĄ ELEKTROWNI JĄDROWEJ
PublicationArtykuł przedstawia wyniki wstępnej analizy możliwości zastosowania sterowania predykcyjnego MPC turbiną parową elektrowni jądrowej. Tradycyjnie przyjmuje się, że turbina pracuje w jednym punkcie pracy odpowiadającym jej mocy nominalnej, co pozwala na stosowanie klasycznych regulatorów PID. Synteza sterowania dla warunków zmiennego punktu pracy wymaga uwzględnienia nieliniowego charakteru procesów turbiny oraz możliwości naruszania...
-
BADANIE EFEKTYWNOŚCI WYKRYWANIA ANOMALII PROCESOWYCH W DZIAŁANIU TURBINY PAROWEJ ELEKTROWNI JĄDROWEJ PRZY POMOCY METOD WIELOWYMIAROWEJ ANALIZY STATYSTYCZNEJ
PublicationW artykule przedstawiono analizę możliwości wykrywania anomalii procesowych w działaniu turbiny parowej elektrowni jądrowej przy pomocy metod wielowymiarowej analizy statystycznej. Zasymulowano symptomy dwóch rodzajów uszkodzeń turbiny parowej tj. uderzenie wodne oraz, wyciek pary z zaworu części niskoprężnej. Jako narzędzie diagnostyczne wykorzystano Metodę Składników Podstawowych PCA (z ang. Principal Component Analysis). Jako...
-
Dynamic model of nuclear power plant steam turbine
Publication -
Dynamic model of nuclear power plant turbine
PublicationThe paper presents the dynamic multivariable model of Nuclear Power Plant steam turbine. Nature of the processes occurring in a steam turbine causes a task of modeling it very difficult, especially when this model is intended to be used for on-line optimal process control (model based) over wide range of operating conditions caused by changing power demand. Particular property of developed model is that it enables calculations...
-
Optimising approach to designing kernel PCA model for diagnosis purposes with and without a priori known data reflecting faulty states
PublicationFault detection plays an important role in advanced control of complex dynamic systems since precise information about system condition enables efficient control. Data driven methods of fault detection give the chance to monitor the plant state purely based on gathered measurements. However, they especially nonlinear, still suffer from a lack of efficient and effective learning methods. In this paper we propose the two stages learning...
-
Pipeline system for heat transportation from nuclear power plant — An optimizing approach
Publication -
Pipeline System for Heat Transportation from Nuclear Power Plant – an Optimizing Approach
PublicationOver the last few years heat piping insulation technology and pump systems efficiency have been significantly improved. Reduced thermal losses encourage heat transportation over long distances. It provides an opportunity for increasing thermodynamic efficiency of Nuclear Power Plants (NPPs) that are often located in rural areas because of safety issues. It can be achieved by Combined Heat and Power (CHP) generation, as heat produced...
-
Wieloobszarowa regulacja systemu turbogeneratora elektrowni jądrowej =Multiregional control of nuclear power plant turbogenerator system
PublicationW artykule przedstawiono propozycję zaawansowanej struktury sterowania układem turbogeneratora w szerokim zakresie zmian zapotrzebowania na moc czynną. Dla potrzeb syntezy tej struktury wykorzystano nieliniowe, dynamiczne modele turbiny parowej i generatora synchronicznego współpracującego z systemem elektroenergetycznym. Zaproponowane algorytmy sterowania oparte są odpowiednio o wieloobszarowe regulatory rozmyte, z lokalnymi regulatorami...
Year 2014
-
Modelling of Nuclear Power Plant Steam Turbine
PublicationThe paper describes the approach to a Nuclear Power Plant steam turbine modelling which would enable on-line optimal process control (model based) and diagnosis over wide range of operating conditions caused by changing power demand. Presented model is static, multivariable and nonlinear. Such model enables analyzing the heat cogeneration aspects. Developed model is validated and verified by using archive data gained from researches...
-
Modelling of Nuclear Power Plant Steam Turbine
PublicationThe paper describes the approach to a Nuclear Power Plant steam turbine modelling which would enable on-line optimal process control (model based) and diagnosis over wide range of operating conditions caused by changing power demand. Presented model is static, multivariable and nonlinear. Such model enables analyzing the heat cogeneration aspects. Developed model is validated and verified by using archive data gained from researches...
-
Use of Neural Networks in Diagnostics of Rolling-Element Bearing of the Induction Motor
PublicationBearing defect is statistically the most frequent cause of an induction motor fault. The research described in the paper utilized the phenomenon of the current change in the induction motor with bearing defect. Methods based on the analysis of the supplying current are particularly useful when it is impossible to install diagnostic devices directly on the motor. The presented method of rolling-element bearing diagnostics used indirect...
Year 2013
Year 2012
-
Data-driven models for fault detection using kernel PCA: A water distribution system case study
Publication -
Data-driven models for fault detection using kernel pca:a water distribution system case study
PublicationKernel Principal Component Analysis (KPCA), an example of machine learning, can be considered a non-linear extension of the PCA method. While various applications of KPCA are known, this paper explores the possibility to use it for building a data-driven model of a non-linear system-the water distribution system of the Chojnice town (Poland). This model is utilised for fault detection with the emphasis on water leakage detection....
seen 5309 times