Wyszukiwarka
Filtry
wszystkich: 3237
-
Katalog
- Publikacje 2690 wyników po odfiltrowaniu
- Czasopisma 188 wyników po odfiltrowaniu
- Konferencje 35 wyników po odfiltrowaniu
- Osoby 130 wyników po odfiltrowaniu
- Projekty 10 wyników po odfiltrowaniu
- Kursy Online 95 wyników po odfiltrowaniu
- Wydarzenia 12 wyników po odfiltrowaniu
- Dane Badawcze 77 wyników po odfiltrowaniu
wyświetlamy 1000 najlepszych wyników Pomoc
Wyniki wyszukiwania dla: multi-task learning
-
TASK CLOUD INFRASTRUCTURE IN THE CENTRE OF INFORMATICS – TRICITY ACADEMIC SUPERCOMPUTER & NETWORK
PublikacjaThe cloud solution called the TASK cloud is described. Its main components and the way of their implementation are described. Examples of deployed environments based on the cloud are also presented. Moreover, the idea of combining the cloud and big data platforms is suggested and discussed.
-
Analyzing content of tasks in Business Process Management. Blending task execution and organization perspectives
PublikacjaAn efficient organization, management, and execution of tasks are central for the successful functioning of any organization. This topic was on the research agenda already in the early 1950s and keeps attracting the scientific community's attention today. Continuous advances and penetration of technologies in organizations are expected to increase task variety and complexity. This creates a constant demand for new methods to analyze,...
-
Neural network agents trained by declarative programming tutors
PublikacjaThis paper presents an experimental study on the development of a neural network-based agent, trained using data generated using declarative programming. The focus of the study is the application of various agents to solve the classic logic task – The Wumpus World. The paper evaluates the effectiveness of neural-based agents across different map configurations, offering a comparative analysis to underline the strengths and limitations...
-
Discovering Rule-Based Learning Systems for the Purpose of Music Analysis
PublikacjaMusic analysis and processing aims at understanding information retrieved from music (Music Information Retrieval). For the purpose of music data mining, machine learning (ML) methods or statistical approach are employed. Their primary task is recognition of musical instrument sounds, music genre or emotion contained in music, identification of audio, assessment of audio content, etc. In terms of computational approach, music databases...
-
Constrained multi-objective optimization of compact microwave circuits by design triangulation and pareto front interpolation
PublikacjaDevelopment of microwave components is an inherently multi-objective task. This is especially pertinent to the design closure stage, i.e., final adjustment of geometry and/or material parameters carried out to improve the electrical performance of the system. The design goals are often conflicting so that the improvement of one normally leads to a degradation of others. Compact microwave passives constitute a representative case:...
-
Low-cost multi-objective optimization and experimental validation of UWB MIMO antenna
PublikacjaPurpose–The purpose of this paper is to validate methodologies for expedited multi-objective designoptimization of complex antenna structures both numerically and experimentally.Design/methodology/approach–The task of identifying the best possible trade-offs between theantenna size and its electrical performance is formulated as multi-objective optimization problem.Algorithmic frameworks are described for finding Pareto-optimal...
-
Feature Reduction Using Similarity Measure in Object Detector Learning with Haar-like Features
PublikacjaThis paper presents two methods of training complexity reduction by additional selection of features to check in object detector training task by AdaBoost training algorithm. In the first method, the features with weak performance at first weak classifier building process are reduced based on a list of features sorted by minimum weighted error. In the second method the feature similarity measures are used to throw away that features...
-
Strategic Flexibility as a Mediator in Relationship between Managerial Decisions and Organizational Learning: Ambidexterity Perspective
PublikacjaPurpose: The purpose of the article is to determine strategic flexibility in the relationship between managerial decisions and organizational learning. The analyses are conducted in the ambidexterity convection. Design/Methodology/Approach: The study was conducted at a textile company. The company is a leader in the textile recycling industry in Poland. Empirical data were collected using the PAPI technique. The survey questionnaire...
-
Examples of Original Descriptive Geometry Task Items
PublikacjaThe paper presents several descriptive geometry drawing tasks and a comprehensive approach to their evaluation. The results as the task profile include the most important features and enable interpretation of the tasks in the educational system.
-
Selection of Visual Descriptors for the Purpose of Multi-camera Object Re-identification
PublikacjaA comparative analysis of various visual descriptors is presented in this chapter. The descriptors utilize many aspects of image data: colour, texture, gradient, and statistical moments. The descriptor list is supplemented with local features calculated in close vicinity of key points found automatically in the image. The goal of the analysis is to find descriptors that are best suited for particular task, i.e. re-identification...
-
Scalability of surrogate-assisted multi-objective optimization of antenna structures exploiting variable-fidelity electromagnetic simulation models
PublikacjaMulti-objective optimization of antenna structures is a challenging task due to high-computational cost of evaluating the design objectives as well as large number of adjustable parameters. Design speedup can be achieved by means of surrogate-based optimization techniques. In particular, a combination of variable-fidelity electromagnetic (EM) simulations, design space reduction techniques, response surface approximation (RSA) models,...
-
From Scores to Predictions in Multi-Label Classification: Neural Thresholding Strategies
PublikacjaIn this paper, we propose a novel approach for obtaining predictions from per-class scores to improve the accuracy of multi-label classification systems. In a multi-label classification task, the expected output is a set of predicted labels per each testing sample. Typically, these predictions are calculated by implicit or explicit thresholding of per-class real-valued scores: classes with scores exceeding a given threshold value...
-
Improvement of Task Management with Process Models in Small and Medium Software Companies
PublikacjaSmall and medium software companies exhibit many special features that give reason for a dedicated approach to process improvement. They often cannot afford implementing maturity models or quality standards both in terms of time and money. Instead, they expect simpler solutions that can allow to run projects in more systematic and repeatable way, increase quality and knowledge management. In this paper, we present a method focused...
-
Streaming Real-time Data in Distributed Dispatcher and Teleinformation Systems for Visualization of Multimedia Data of the Border Guard
PublikacjaSurveillance of the sea borders is a very important task for the Border Guard. Monitoring of country maritime border is an important task of the Border Guard. This task can be facilitated with the use of the technology enabling gathering information from distributed sources and its supervision and visualization. This task can be accomplished using a technology that allows to collect information from distributed sensors of different...
-
Hossein Nejatbakhsh Esfahani Dr.
OsobyMy research interests lie primarily in the area of Learning-based Safety-Critical Control Systems, for which I leverage the following concepts and tools:-Robust/Optimal Control-Reinforcement Learning-Model Predictive Control-Data-Driven Control-Control Barrier Function-Risk-Averse Controland with applications to:-Aerial and Marine robotics (fixed-wing UAVs, autonomous ships and underwater vehicles)-Multi-Robot and Networked Control...
-
Behavior Based Complete Coverage Task of Unknown Area by an Autonomous Mobile Robot SCORPION with Static Obstacles in Environment
PublikacjaIn the paper the behavior based control system of an autonomous mobile robot SCORPION is presented to execute the one of the most difficult navigation task, which is the complete coverage task of unknown area with static obstacles in the environment. The main principle assumed to design control system was that the robot should cover all area only once, if it possible, to optimize the length of path and energy consumption. All commercial...
-
The System of the Supervision and the Visualization of Multimedia Data for BG
PublikacjaMonitoring of country maritime border is an important task of the Border Guard. This task can be facilitated with the use of the technology enabling gathering information from distributed sources and its supervision and visualization. The system presented in the paper is an extension and enhancement of the previously developed distributed system map data exchange system. The added functionalities allow supplementation of map data...
-
Voice command recognition using hybrid genetic algorithm
PublikacjaAbstract: Speech recognition is a process of converting the acoustic signal into a set of words, whereas voice command recognition consists in the correct identification of voice commands, usually single words. Voice command recognition systems are widely used in the military, control systems, electronic devices, such as cellular phones, or by people with disabilities (e.g., for controlling a wheelchair or operating a computer...
-
A Task-Scheduling Approach for Efficient Sparse Symmetric Matrix-Vector Multiplication on a GPU
PublikacjaIn this paper, a task-scheduling approach to efficiently calculating sparse symmetric matrix-vector products and designed to run on Graphics Processing Units (GPUs) is presented. The main premise is that, for many sparse symmetric matrices occurring in common applications, it is possible to obtain significant reductions in memory usage and improvements in performance when the matrix is prepared in certain ways prior to computation....
-
Rozproszone usługi obliczeniowe na klastrach TASK z dostępem przez WWW i Web Services.
PublikacjaArtykuł omawia architekturę i doświadczenia wstępnych faz specyfikacji wymagań i analizy projektu, który umożliwi zdalne wykorzystanie równoległych klastrów i/lub superkomputerów sieci TASK przez użytkowników z rozproszonych geograficznie lokalizacji. System zapewni dotychczasowym i nowym użytkownikom klastrów i superkomputerów TASK zdalne uruchamianie i zarządzanie aplikacjami, bibliotekami równoległymi i sekwencyjnymi poprzez...
-
Justyna Szostak dr inż.
OsobyI Gdańsk University of Technology: Chair of the Rector’s Internationalization Committee (October 2020 - Present) Erasmus + Coordinator for students and staff members, Faculty of Applied Physics and Mathematics (Mar 2017 - Present) Dean's Proxy for Internationalization, Faculty of Applied Physics and Mathematics (October 2020 - Present) Coordinator of the International Relations Office of the Faculty of Applied Physics and...
-
Classification of Sea Going Vessels Properties Using SAR Satellite Images
PublikacjaThe aim of the project was to analyze the possibility of using machine learning and computer vision to identify (indicate the location) of all sea-going vessels located in the selected area of the open sea and to classify the main attributes of the vessel. The key elements of the project were to download data from the Sentinel-1 satellite [1], download data on the sea vessels [2], then automatically tag data and develop a detection...
-
Investigating Feature Spaces for Isolated Word Recognition
PublikacjaMuch attention is given by researchers to the speech processing task in automatic speech recognition (ASR) over the past decades. The study addresses the issue related to the investigation of the appropriateness of a two-dimensional representation of speech feature spaces for speech recognition tasks based on deep learning techniques. The approach combines Convolutional Neural Networks (CNNs) and timefrequency signal representation...
-
Weakly-Supervised Word-Level Pronunciation Error Detection in Non-Native English Speech
PublikacjaWe propose a weakly-supervised model for word-level mispronunciation detection in non-native (L2) English speech. To train this model, phonetically transcribed L2 speech is not required and we only need to mark mispronounced words. The lack of phonetic transcriptions for L2 speech means that the model has to learn only from a weak signal of word-level mispronunciations. Because of that and due to the limited amount of mispronounced...
-
From Sequential to Parallel Implementation of NLP Using the Actor Model
PublikacjaThe article focuses on presenting methods allowing easy parallelization of an existing, sequential Natural Language Processing (NLP) application within a multi-core system. The actor-based solution implemented with the Akka framework has been applied and compared to an application based on Task Parallel Library (TPL) and to the original sequential application. Architectures, data and control flows are described along with execution...
-
Design of a microrobotic wrist for needle laparoscopic surgery
PublikacjaThe paper addresses the design of a micro wrist for needle laparoscopic surgery (needlescopy) using MEMS technology and an original 3 degree of freedom, 3D architecture. Advancement in needlescopy drives the development of multi-dof micro-tools 1-2mmin diameter with 3D mobility but standard available fabricationtechniques are for 2.5D structures. The paper discusses thedevelopment steps and design solutions for the realization...
-
Training of Deep Learning Models Using Synthetic Datasets
PublikacjaIn order to solve increasingly complex problems, the complexity of Deep Neural Networks also needs to be constantly increased, and therefore training such networks requires more and more data. Unfortunately, obtaining such massive real world training data to optimize neural networks parameters is a challenging and time-consuming task. To solve this problem, we propose an easy-touse and general approach to training deep learning...
-
Deep-Learning-Based Precise Characterization of Microwave Transistors Using Fully-Automated Regression Surrogates
PublikacjaAccurate models of scattering and noise parameters of transistors are instrumental in facilitating design procedures of microwave devices such as low-noise amplifiers. Yet, data-driven modeling of transistors is a challenging endeavor due to complex relationships between transistor characteristics and its designable parameters, biasing conditions, and frequency. Artificial neural network (ANN)-based methods, including deep learning...
-
Eigenfaces, Fisherfaces, Laplacianfaces, Marginfaces – How to Face the Face Verification Task
PublikacjaThis paper describes the exhaustive tests of four known methods of linear transformations (Eigenfaces, Fisherfaces, Laplacianfaces and Marginfaces) in the context of face verification task. Additionally, we introduce a new variant of the transformation (Laplacianface + LDA), and the specific interval-based decision rule. Both of them improve the performance of face verification, in general, however, our experiments show that the...
-
Updating a hospital building. A task for innovation design
PublikacjaRefurbishment of a hospital, especially located in a historical building, is a task that goes far beyond a standard framework of architectural practice. A concept of modularity in the architecture of the late nineteenth and early twentieth century was only just to happen, building system installations and technical equipment appeared as the simplest solutions. Inscribing complex functional solutions into such a space is an interesting...
-
Intelligent Audio Signal Processing − Do We Still Need Annotated Datasets?
PublikacjaIn this paper, intelligent audio signal processing examples are shortly described. The focus is, however, on the machine learning approach and datasets needed, especially for deep learning models. Years of intense research produced many important results in this area; however, the goal of fully intelligent signal processing, characterized by its autonomous acting, is not yet achieved. Therefore, a review of state-of-the-art concerning...
-
Optymalizacja zasobów chmury obliczeniowej z wykorzystaniem inteligentnych agentów w zdalnym nauczaniu
PublikacjaRozprawa dotyczy optymalizacji zasobów chmury obliczeniowej, w której zastosowano inteligentne agenty w zdalnym nauczaniu. Zagadnienie jest istotne w edukacji, gdzie wykorzystuje się nowoczesne technologie, takie jak Internet Rzeczy, rozszerzoną i wirtualną rzeczywistość oraz deep learning w środowisku chmury obliczeniowej. Zagadnienie jest istotne również w sytuacji, gdy pandemia wymusza stosowanie zdalnego nauczania na dużą skalę...
-
Parallel Computations of Text Similarities for Categorization Task
PublikacjaIn this chapter we describe the approach to parallel implementation of similarities in high dimensional spaces. The similarities computation have been used for textual data categorization. A test datasets we create from Wikipedia articles that with their hyper references formed a graph used in our experiments. The similarities based on Euclidean distance and Cosine measure have been used to process the data using k-means algorithm....
-
AITP - AI Thermal Pedestrians Dataset
PublikacjaEfficient pedestrian detection is a very important task in ensuring safety within road conditions, especially after sunset. One way to achieve this goal is to use thermal imaging in conjunction with deep learning methods and an annotated dataset for models training. In this work, such a dataset has been created by capturing thermal images of pedestrians in different weather and traffic conditions. All images were manually annotated...
-
Multi-agent graph searching and exploration algorithms
PublikacjaA team of mobile entities, which we refer to as agents or searchers interchangeably, starting from homebases needs to complete a given task in a graph.The goal is to build a strategy, which allows agents to accomplish their task. We analyze strategies for their effectiveness (e.g., the number of used agents, the total number of performed moves by the agents or the completion time).Currently, the fields of on-line (i.e., agents...
-
A Generative Approach to Hull Design for a Small Watercraft
PublikacjaIn the field of ocean engineering, the task of spatial hull modelling is one of the most complicated problems in ship design. This study presents a procedure applied as a generative approach to the design problems for the hull geometry of small vessels using elements of concurrent design with multi-criteria optimisation processes. Based upon widely available commercial software, an algorithm for the mathematical formulation of...
-
Robust and Efficient Machine Learning Algorithms for Visual Recognition
PublikacjaIn visual recognition, the task is to identify and localize all objects of interest in the input image. With the ubiquitous presence of visual data in modern days, the role of object recognition algorithms is becoming more significant than ever and ranges from autonomous driving to computer-aided diagnosis in medicine. Current models for visual recognition are dominated by models based on Convolutional Neural Networks (CNNs), which...
-
Investigating Feature Spaces for Isolated Word Recognition
PublikacjaThe study addresses the issues related to the appropriateness of a two-dimensional representation of speech signal for speech recognition tasks based on deep learning techniques. The approach combines Convolutional Neural Networks (CNNs) and time-frequency signal representation converted to the investigated feature spaces. In particular, waveforms and fractal dimension features of the signal were chosen for the time domain, and...
-
Poprawa jakości klasyfikacji głębokich sieci neuronowych poprzez optymalizację ich struktury i dwuetapowy proces uczenia
PublikacjaW pracy doktorskiej podjęto problem realizacji algorytmów głębokiego uczenia w warunkach deficytu danych uczących. Głównym celem było opracowanie podejścia optymalizującego strukturę sieci neuronowej oraz zastosowanie uczeniu dwuetapowym, w celu uzyskania mniejszych struktur, zachowując przy tym dokładności. Proponowane rozwiązania poddano testom na zadaniu klasyfikacji znamion skórnych na znamiona złośliwe i łagodne. W pierwszym...
-
Performance Evaluation of the Parallel Codebook Algorithm for Background Subtraction in Video Stream
PublikacjaA background subtraction algorithm based on the codebook approach was implemented on a multi-core processor in a parallel form, using the OpenMP system. The aim of the experiments was to evaluate performance of the multithreaded algorithm in processing video streams recorded from monitoring cameras, depending on a number of computer cores used, method of task scheduling, image resolution and degree of image content variability....
-
Muhammad Usman PhD
OsobyMuhammad Usman is a researcher at the Gdansk University of Technology, currently working on the BE-Light project focused on face skin analysis using multimodal imaging and machine learning methods. He previously worked as a Hardware Test Engineer at Apple Inc., specializing in the rigorous testing and validation of electronic systems, ensuring reliability and performance. He holds a Master of Science in Automation and Control from...
-
Surface sliding in human abdominal wall numerical models: Comparison of single-surface and multi-surface composites
PublikacjaDetermining mechanical properties of abdominal soft tissues requires a coupled experimental-numerical study, but first an appropriate numerical model needs to be built. Precise modeling of human abdominal wall mechanics is difficult because of its complicated multi-layer composition and large variation between specimens. There are several approaches concerning simplification of numerical models, but it is unclear how far one could...
-
Dysfunctional prefrontal cortical network activity and interactions following cannabinoid receptor activation.
PublikacjaCoordinated activity spanning anatomically distributed neuronal networks underpins cognition and mediates limbic-cortical interactions during learning, memory, and decision-making. We used CP55940, a potent agonist of brain cannabinoid receptors known to disrupt coordinated activity in hippocampus, to investigate the roles of network oscillations during hippocampal and medial prefrontal cortical (mPFC) interactions in rats. During...
-
Tolerance-Aware Multi-Objective Optimization of Antennas by Means of Feature-Based Regression Surrogates
PublikacjaAssessing the immunity of antenna design to fabrication tolerances is an important consideration, especially when the manufacturing process has not been predetermined. At the same time, the antenna parameter tuning should be oriented toward improving the performance figures pertinent to both electrical (e.g., input matching) and field properties (e.g., axial ratio bandwidth) as much as possible. Identification of available trade-offs...
-
The Application of Vibration Recording and Analysis in Tribological Research on Sliding Friction
PublikacjaThe paper reports on a tribological research on the macroscopic manifestation and characteristics of sliding friction. The aim of the task was to measure friction in lubricated sliding contacts and test the interactions between the environment (the test rig) and the experimental friction contact. Friction-induced vibrations were observed and studied as a manifestation of the process. The typical set of velocity and force/torque...
-
Approximate and analytic flow models for leak detection and identification
PublikacjaThe article presents a comprehensive quantitative comparison of four analytical models that, in different ways, describe the flow process in transmission pipelines necessary in the task of detecting and isolating leaks. First, the analyzed models are briefly presented. Then, a novel model comparison framework was introduced along with a methodology for generating data and assessing diagnostic effectiveness. The study presents basic...
-
Jerzy Proficz dr hab. inż.
OsobyJerzy Proficz – dyrektor Centrum Informatycznego Trójmiejskiej Akademickiej Sieci Komputerowej (CI TASK) na Politechnice Gdańskiej. Uzyskał stopień naukowy doktora habilitowanego (2022) w dyscyplinie: Informatyka techniczna i telekomunikacja. Autor i współautor ponad 50 artykułów w czasopismach i na konferencjach naukowych związanych głównie z równoległym przetwarzaniem danych na komputerach dużej mocy (HPC, chmura obliczeniowa). Udział...
-
Data Partitioning and Task Management in the Clustered Server Layer of the Volunteer-based Computation System
PublikacjaWhile the typical volunteer-based distributed computing system focus on the computing performance, the Comcute system was designed especially to keep alive in the emergency situations. This means that designers had to take into account not only performance, but the safety of calculations as well. Quadruple-layered architecture was proposed to separate the untrusted components from the core of the system. The main layer (W) consists...
-
How to Design Affect-aware Educational Systems – the AFFINT Process Approach
PublikacjaComputer systems, that support learning processes, can adapt to the needs and states of a learner. The adaptation might directly address the knowledge deficits and most tutoring systems apply an adaptable learning path of that kind. Apart from a preliminary knowledge state, there are more factors, that influence education effectiveness and among those there are fluctuating emotional states. The tutoring systems may recognize or...
-
Speaker Recognition Using Convolutional Neural Network with Minimal Training Data for Smart Home Solutions
PublikacjaWith the technology advancements in smart home sector, voice control and automation are key components that can make a real difference in people's lives. The voice recognition technology market continues to involve rapidly as almost all smart home devices are providing speaker recognition capability today. However, most of them provide cloud-based solutions or use very deep Neural Networks for speaker recognition task, which are...