Search
Filters
total: 3169
-
Catalog
displaying 1000 best results Help
Search results for: MULTI-TASK LEARNING
-
On the problem of optimised allocation of water quality sensors and actuators in DWDS
PublicationThe problems of water quality sensors and actuators placement in drinking water distribution systems (DWDSs) are addressed as separate, primarily. However, against the background of control systems theory, the nature of DWDSs dynamics indicates that these both problems are interdependent and impact the design of related water quality monitoring and control structures and algorithms. The research work presented in this paper is...
-
Machine Learning and Deep Learning Methods for Fast and Accurate Assessment of Transthoracic Echocardiogram Image Quality
PublicationHigh-quality echocardiogram images are the cornerstone of accurate and reliable measurements of the heart. Therefore, this study aimed to develop, validate and compare machine learning and deep learning algorithms for accurate and automated assessment of transthoracic echocardiogram image quality. In total, 4090 single-frame two-dimensional transthoracic echocardiogram...
-
Long Distance Geographically Distributed InfiniBand Based Computing
PublicationCollaboration between multiple computing centres, referred as federated computing is becom- ing important pillar of High Performance Computing (HPC) and will be one of its key components in the future. To test technical possibilities of future collaboration using 100 Gb optic fiber link (Connection was 900 km in length with 9 ms RTT time) we prepared two scenarios of operation. In the first one, Interdisciplinary Centre for Mathematical...
-
Limiting distribution of the three-state semi-Markov model of technical state transitions of ship power plant machines and its applicability in operational decision-making.
PublicationThe article presents the three-state semi-Markov model of the process {W(t): t 0} of state transitions of a ship power plant machine, with the following interpretation of these states: s1 – state of full serviceability, s2 – state of partial serviceability, and s3 – state of unserviceability. These states are precisely defined for the ship main engine (ME). A hypothesis is proposed which explains the possibility of application...
-
Refurbishment of a historical building - design issues
PublicationOver a 10-year modernization of the main building of Gdansk University of Technology is coming to the end. The ever increasing number of students requires not only the development of the campus with new facility buildings, also the existing buildings are subject to adaptation and modernization. In addition to high-impact solutions, as restoring the former glory of the building (reconstruction of the clock tower), or introducing...
-
Multimedia industrial and medical applications supported by machine learning
PublicationThis article outlines a keynote paper presented at the Intelligent DecisionTechnologies conference providing a part of the KES Multi-theme Conference “Smart Digital Futures” organized in Rome on June 14–16, 2023. It briefly discusses projects related to traffic control using developed intelligent traffic signs and diagnosing the health of wind turbine mechanisms and multimodal biometric authentication for banking branches to provide...
-
Henryk Krawczyk prof. dr hab. inż.
PeopleDyscyplina naukowa: informatyka Sprawował urząd rektora od 2008 do 2016. Urodził się 20 maja 1946 r. w Dybowie. Studia wyższe ukończył w 1969 r. na Wydziale Elektroniki Politechniki Gdańskiej, uzyskując tytuł magistra inżyniera w zakresie informatyki. W latach 1969–1972 pracował w Przemysłowym Instytucie Telekomunikacji. W 1972 r. rozpoczął pracę na Wydziale Elektroniki Politechniki Gdańskiej, gdzie w 1976 r. uzyskał doktorat,...
-
Neural networks and deep learning
PublicationIn this chapter we will provide the general and fundamental background related to Neural Networks and Deep Learning techniques. Specifically, we divide the fundamentals of deep learning in three parts, the first one introduces Deep Feed Forward Networks and the main training algorithms in the context of optimization. The second part covers Convolutional Neural Networks (CNN) and discusses their main advantages and shortcomings...
-
Integrated membrane bioreactors modelling: A review on new comprehensive modelling framework
PublicationIntegrated Membrane Bioreactor (MBR) models, combination of biological and physical models, have been representing powerful tools for the accomplishment of high environmental sustainability. This paper, produced by the International Water Association (IWA) Task Group on Membrane Modelling and Control, reviews the state-of-the-art, identifying gaps for future researches, and proposes a new integrated MBR modelling framework. In...
-
Influence of image transformations and quality degradations on SURF detector efficiency
PublicationA method for task-oriented examination of SURF keypoint detector accuracy is presented in the paper. It consists of generating test images, based on a given exemplar, processed by affine transformations: random rotation and scaling, and varying degree of degradations: darkening, blurring, noising, and compression. Details of applied degradation procedure are presented, followed by essentials of SURF-based images matching. A distance...
-
Free randomness amplification using bipartite chain correlations
PublicationA direct analysis of the task of randomness amplification from Santha-Vazirani sources using the violation of the chained Bell inequality is performed in terms of the convex combination of no-signaling boxes required to simulate quantum violation of the inequality. This analysis is used to find the exact threshold value of the initial randomness parameter from which perfect randomness can be extracted in the asymptotic limit of...
-
Recognizing emotions on the basis of keystroke dynamics
PublicationThe article describes a research on recognizing emotional states on the basis of keystroke dynamics. An overview of various studies and applications of emotion recognition based on data coming from keyboard is presented. Then, the idea of an experiment is presented, i.e. the way of collecting and labeling training data, extracting features and finally training classifiers. Different classification approaches are proposed to be...
-
Inteligentne zarządzanie usługami chmurowymi
PublicationRozwój chmur obliczeniowych stanowi wyzwanie dla nowych efektywnych metod zarządzania zasobami chmurowymi, zwłaszcza, że oprócz usług typu SaaS rozwija się nowe kategorie usług jak obliczenia brzegowe czy wielochmurowe. W pracy zaproponowano ogólny model zarządzania usługami oraz efektywne procedury alokacji zasobów. Podkreślono potrzebę oszacowania parametrów zasobów chmury by zapewnić wykonanie żądanych usług. Przedstawiono również...
-
Agnieszka Landowska dr hab. inż.
PeopleAgnieszka Landowska works for Gdansk University of Technology, FETI, Department of Software Engineering. Her research concentrates on usability, accessibility and technology adoption, as well as affective computing methods. She initiated Emotions in HCI Research Group and conducts resarch on User eXperiene evaluation of applications and other technologies.
-
EM-Driven Multi-Objective Optimization of Antenna Structures in Multi-Dimensional Design Spaces
PublicationFeasible multi-objective optimization of antenna structures is presented. An initial set of Pareto optimal solutions is found using a multi-objective evolutionary algorithm (MOEA) working with a fast surrogate antenna model obtained by kriging interpolation of coarse-discretization EM simulation data. To make the surrogate construction computationally feasible in multi-dimensional design space, the space subset containing non-dominated...
-
Approximation task decomposition for artificial neural network.
PublicationW pracy przedstawiono wpływ dekompozycji zadania na czasochłonność projektowania oraz dokładność i szybkość obliczeń sztucznej sieci neuronowej wykorzystanej do rozwiązania rzeczywistego problemu technicznego, którego matematyczny model był znany. Celem obliczeń prowadzonych przez sieć neuronową było określenie wartości współczynnika przepływu m na podstawie znajomości wartości: przewodności dźwiękowej C i średnicy przewodu d (a...
-
A new multi-process collaborative architecture for time series classification
PublicationTime series classification (TSC) is the problem of categorizing time series data by using machine learning techniques. Its applications vary from cybersecurity and health care to remote sensing and human activity recognition. In this paper, we propose a novel multi-process collaborative architecture for TSC. The propositioned method amalgamates multi-head convolutional neural networks and capsule mechanism. In addition to the discovery...
-
Multi agent grid systems
PublicationThis chapter presents an idea of merging grid and volunteer systemswith multi agent systems. It gives some basics concerning multi agentsystem and the most followed standard. Some deliberations concerningsuch an existing systems were made in order to finally present possibilities of introducing agents into the Comcute system.
-
Blended Learning in Teaching Safety of Electrical Installations
PublicationBlended learning becomes more commonly used in teaching information technology or other subjects, which involve practice in computer laboratories. In case of subjects with no access to computer rooms blended learning supports lecturing and teaching classes e.g. interactive lessons. The article presents the use of blended learning forms in Gdansk University of Technology in teaching the subject of Safety of Electrical Installations....
-
Sesja jubileuszowa z okazji 25-lecia TASK
EventsZ okazji jubileuszu Rada Użytkowników TASK przy wsparciu CI TASK organizuje sesję „25-lecie porozumienia TASK”.
-
Low-Cost Multi-Objective Optimization Yagi-Uda Antenna in Multi-Dimensional Parameter Space
PublicationA surrogate-based technique for fast multi-objective optimization of a multi-parameter planar Yagi-Uda antenna structure is presented. The proposed method utilizes response surface approximation (RSA) models constructed using training samples obtained from evaluation of the low-fidelity antenna model. Utilization of the RSA models allowsfor fast determination of the best possible trade-offs between conflicting objectives in multi-objective...
-
Multi-state multi-reference Møller-Plesset second-order perturbation theory for molecular calculations
PublicationThis work presents multi‐state multi‐reference Møller–Plesset second‐order perturbation theory as a variant of multi‐reference perturbation theory to treat electron correlation in molecules. An effective Hamiltonian is constructed from the first‐order wave operator to treat several strongly interacting electronic states simultaneously. The wave operator is obtained by solving the generalized Bloch equation within the first‐order...
-
Towards semantic-rich word embeddings
PublicationIn recent years, word embeddings have been shown to improve the performance in NLP tasks such as syntactic parsing or sentiment analysis. While useful, they are problematic in representing ambiguous words with multiple meanings, since they keep a single representation for each word in the vocabulary. Constructing separate embeddings for meanings of ambiguous words could be useful for solving the Word Sense Disambiguation (WSD)...
-
Zastosowanie algorytmu regulacji DMC z pomiarem wartości wielkości sterującej do sterowania blokiem wymienników ciepła
PublicationW artykule opisano zastosowanie zmodyfikowanego algorytmu regulacji predykcyjnej DMC do sterowania wybranym blokiem wymienników ciepła. Przedstawiono charakterystykę obiektu sterowania, specyficzne zadania stawiane układowi regulacji oraz sposób realizacji regulatora. Omówiono właściwości opracowanego układu regulacji i zaprezentowano wyniki jego działania.A modified DMC control algorithm application for control of heat exchanger...
-
Neurocontrolled Car Speed System
PublicationThe features of the synthesis of neural controllers for the car speed control system are considered in this article. The task of synthesis is to determine the weight coefficients of neural networks that provide the implementation of proportional and proportional-integralderivative control laws. The synthesis of controllers is based on an approach that uses a reversed model of the standard. A model of the car speed control system with...
-
Optimised allocation of actuators for DWDS
PublicationThis paper addresses the problem of actuators’ allocation within networked structured system, namely allocation of disinfectant booster stations within Drinking Water Distribution System (DWDS), under receding horizon optimised control – Model Predictive Control (MPC) to be exact. The allocation task is kept within dynamic multiobjective optimisation framework. The MPC is defined as a single objective predictive operator. Two numerical...
-
Innovative design of hybrid powered inland vessel
PublicationOne of the most demanding task for European countries is rational transportation system taking into account fuel efficient and ecological propulsion. The paper presents innovative design of hybrid powered inland vessel. The most important aspects regarding new design and technical solutions are being presented, including numerical and experimental research on hull form. Combined diesel-electric propulsion supported by solar panel...
-
Uniform Model Interface for Assurance Case Integration with System Models
PublicationAssurance cases are developed and maintained in parallel with corresponding system models and therefore need to reference each other. Managing the correctness and consistency of interrelated safety argument and system models is essential for system dependability and is a nontrivial task. The model interface presented in this paper enables a uniform process of establishing and managing assurance case references to various types...
-
RECSYS CHALLENGE 2015: a BUY EVENT PREDICTION IN THE E-COMMERCE DOMAIN
PublicationIn this paper we present our approach to RecSys Challenge 2015. Given a set of e-commerce events, the task is to predict whether a user will buy something in the current session and, if yes, which of the item will be bought. We show that the data preparation and enrichment are very important in finding the solution for the challenge and that simple ideas and intuitions could lead to satisfactory results. We also show that simple...
-
SEMANTIC ANALYSIS ALGORITHMS FOR KNOWLEDGE WORKERS SUPPORT
PublicationThe paper examines various aspects of text analysis application for knowledge worker’s activity realization. Conclusions are drawn about the relevance and importance of processing the non-structured textual information in order to increase knowledge worker’s efficiency, as well as their awareness in different branches of science. The paper considers the existing algorithms of texts semantic analysis as the sphere of documents topical...
-
Using LSTM networks to predict engine condition on large scale data processing framework
PublicationAs the Internet of Things technology is developing rapidly, companies have an ability to observe the health of engine components and constructed systems through collecting signals from sensors. According to output of IoT sensors, companies can build systems to predict the conditions of components. Practically the components are required to be maintained or replaced before the end of life in performing their assigned task. Predicting...
-
Buried Object Characterization by Data-Driven Surrogates and Regression-Enabled Hyperbolic Signature Extraction
PublicationThis work addresses artificial-intelligence-based buried object characterization using FDTD-based electromagnetic simulation toolbox of a Ground Penetrating Radar (GPR) to generate B-scan data. In data collection, FDTD-based simulation tool, gprMax is used. The task is to estimate geophysical parameters of a cylindrical shape object of various radii, buried at different positions in the dry soil medium simultaneously and independently...
-
Edge-Computing based Secure E-learning Platforms
PublicationImplementation of Information and Communication Technologies (ICT) in E-Learning environments have brought up dramatic changes in the current educational sector. Distance learning, online learning, and networked learning are few examples that promote educational interaction between students, lecturers and learning communities. Although being an efficient form of real learning resource, online electronic resources are subject to...
-
Mechanical durability and electroanalytical performance of 3D-printed multi-material sensors
Open Research DataThe data set consists tensile strength, electric resistance, electrochemical characteristics and physicochemical studies of multi-material 3D printed systems, including their sensing performance during detection of antibiotics in an industrial sewage. Additionally, contact angle measurements and SEM micrographs of the electrode surfaces were included.
-
Federated Learning in Healthcare Industry: Mammography Case Study
PublicationThe paper focuses on the role of federated learning in a healthcare environment. The experimental setup involved different healthcare providers, each with their datasets. A comparison was made between training a deep learning model using traditional methods, where all the data is stored in one place, and using federated learning, where the data is distributed among the workers. The experiment aimed to identify possible challenges...
-
Speech Analytics Based on Machine Learning
PublicationIn this chapter, the process of speech data preparation for machine learning is discussed in detail. Examples of speech analytics methods applied to phonemes and allophones are shown. Further, an approach to automatic phoneme recognition involving optimized parametrization and a classifier belonging to machine learning algorithms is discussed. Feature vectors are built on the basis of descriptors coming from the music information...
-
Software Factory project for enhancement of student experiential learning
PublicationProviding opportunities for students to work on real-world software development projects for real customers is critical to prepare students for the IT industry. Such projects help students to understand what they will face in the industry and experience real customer interaction and challenges in collaborative work. To provide this opportunity in an academic environment and enhance the learning and multicultural teamwork experience,...
-
Enhancing rheological muscle models with stochastic processes
PublicationPurpose: Biological musculoskeletal systems operate under variable conditions. Muscle stiffness, activation signals, and loads change during each movement. The presence of noise and different harmonic components in force production significantly influences the behaviour of the muscular system. Therefore, it is essential to consider these factors in numerical simulations. Methods: This study aims to develop a rheological mathematical...
-
Desiging e-learning courses and distance learning (level 1. certified course)
e-Learning Courses -
Blended Learning Tasks 2
e-Learning CoursesKurs dla Wydziału Mechanicznego
-
Blended Learning Tasks 6
e-Learning CoursesKurs dla Wydziału Architektury
-
Deep Learning w Keras
e-Learning CoursesKurs przeznaczony dla słuchaczy studiów podyplomowych Sztuczna inteligencja i automatyzacja procesów biznesowych w ujęciu praktycznym - edycja biznesowa.
-
Blended Learning Tasks 4
e-Learning Courses -
Blended Learning Tasks 1
e-Learning CoursesKurs dla Wydziału Mechanicznego
-
Blended Learning Tasks 5
e-Learning CoursesKurs dla ETI
-
Blended Learning Tasks 3
e-Learning CoursesKurs dla WILiŚ
-
MULTI-OBJECTIVE OPTIMIZATION PROBLEM IN THE OptD-MULTI METHOD
PublicationNew measurement technologies, e.g. Light Detection And Ranging (LiDAR), generate very large datasets. In many cases, it is reasonable to reduce the number of measuring points, but in such a way that the datasets after reduction satisfy specific optimization criteria. For this purpose the Optimum Dataset (OptD) method proposed in [1] and [2] can be applied. The OptD method with the use of several optimization criteria is called...
-
Multi-directional analysis of the maintenance of rainwater harvesting systems
Open Research DataPresented data are the result of research activity entitled „Multi-directional analysis of the maintenance of rainwater harvesting systems” conducted as a part of MINIATURA 7 competition. The research consisted of a comprehensive assessment of the quality of rainwater collected and stored in a rooftop harvesting system and then purified using inline...
-
A Machine Learning Approach for Estimating Overtime Allocation in Software Development Projects
PublicationOvertime planning in software projects has traditionally been approached with search-based multi-objective optimization algorithms. However, the explicit solutions produced by these algorithms often lack applicability and acceptance in the software industry due to their disregard for project managers' intuitive knowledge. This study presents a machine learning model that learns the preferred overtime allocation patterns from solutions...
-
The use and development of e-learning systems in educational projects
PublicationThe article introduces the problem of usage and development of e-learning systems among Polish universities. Easily accessible internet and IT development led to changes in education. Through the use of IT tools, e-learning has become an increasingly popular form of education. Presently, majority of Polish universities use an e-learning system of their own choosing designed to support the didactic processes. The goal of the article...