Wyszukiwarka
Wyniki wyszukiwania dla: training methods
-
Adaptive Hounsfield Scale Windowing in Computed Tomography Liver Segmentation
PublikacjaIn computed tomography (CT) imaging, the Hounsfield Unit (HU) scale quantifies radiodensity, but its nonlinear nature across organs and lesions complicates machine learning analysis. This paper introduces an automated method for adaptive HU scale windowing in deep learning-based CT liver segmentation. We propose a new neural network layer that optimizes HU scale window parameters during training. Experiments on the Liver Tumor...
-
Analysis of Denoising Autoencoder Properties Through Misspelling Correction Task
PublikacjaThe paper analyzes some properties of denoising autoencoders using the problem of misspellings correction as an exemplary task. We evaluate the capacity of the network in its classical feed-forward form. We also propose a modification to the output layer of the net, which we called multi-softmax. Experiments show that the model trained with this output layer outperforms traditional network both in learning time and accuracy. We...
-
Education of Logisticians in Poland: Problems and Prospects in Students’ Opinion
PublikacjaLogistics is one of the key sectors of the Polish economy. Its value reflects not only its own capacity, but also the role it plays in ensuring the proper functioning of the entire economy. The rapid development of the industry and the highest demands on logistics solutions bring to the fore the problem of preparing a new generation of specialists in logistics. That is why the question of compliance to learning expectations of...
-
TensorHive: Management of Exclusive GPU Access for Distributed Machine Learning Workloads
PublikacjaTensorHive is a tool for organizing work of research and engineering teams that use servers with GPUs for machine learning workloads. In a comprehensive web interface, it supports reservation of GPUs for exclusive usage, hardware monitoring, as well as configuring, executing and queuing distributed computational jobs. Focusing on easy installation and simple configuration, the tool automatically detects the available computing...
-
Anna Maria Trzaskowska dr inż.
OsobyAnna Maria Trzaskowska od 2017 roku jest zatrudniona na stanowisku adiunkta na Wydziale Zarządzania i Ekonomii w Katedrze Informatyki w Zarządzaniu. Przez ponad 2 lata pełniła funkcję Zastępcy Kierownika Katedry oraz Quality Lead na studiach MBA prowadzonych na wydziale. Od 2018 roku Kierownik Programu międzywydziałowego kierunku Inżynieria Danych. Od 2021 roku Kierownik Projektu oraz członek kilku projektów międzynarodowych w...
-
THE ONLINE APPLICATION AND E-LEARNING IN THE COMPETENCE-BASED MANAGEMENT IN PUBLIC ADMINISTRATION ORGANIZATIONS
PublikacjaThe integration of effective management of work-related processes and utilization of human resources potential leads to the development of organization. The purpose of this paper was to examine how the principles of competences-based management can be introduced to enhance organization’s effectiveness in human resources management. A model of assessment and development of competences-based management, embracing an online application...
-
Uniform sampling in constrained domains for low-cost surrogate modeling of antenna input characteristics
PublikacjaIn this letter, a design of experiments technique that permits uniform sampling in constrained domains is proposed. The discussed method is applied to generate training data for construction of fast replacement models (surrogates) of antenna input characteristics. The modeling process is design-oriented with the surrogate domain spanned by a set of reference designs optimized with respect to the performance figures and/or operating...
-
A survey of neural networks usage for intrusion detection systems
PublikacjaIn recent years, advancements in the field of the artificial intelligence (AI) gained a huge momentum due to the worldwide appliance of this technology by the industry. One of the crucial areas of AI are neural networks (NN), which enable commer‐ cial utilization of functionalities previously not accessible by usage of computers. Intrusion detection system (IDS) presents one of the domains in which neural networks are widely tested...
-
Cost-Efficient Two-Level Modeling of Microwave Passives Using Feature-Based Surrogates and Domain Confinement
PublikacjaA variety of surrogate modelling techniques has been utilized in high-frequency design over the last two decades. Yet, the curse of dimensionality still poses a serious challenge in setting up re-liable design-ready surrogates of modern microwave components. The difficulty of the model-ing task is only aggravated by nonlinearity of circuit responses. Consequently, constructing a practically usable surrogate model, valid across...
-
Evaluating Industry 4.0 Implementation Challenges Using Interpretive Structural Modeling and Fuzzy Analytic Hierarchy Process
PublikacjaThe fourth industrial revolution known as Industry 4.0 is reshaping and evolving the way industries produce products and individuals live and work therefore, gaining massive attraction from academia, business and politics. The manufacturing industries are optimistic regarding the opportunities Industry 4.0 may offer such as, improved efficiency, productivity and customization. The present research contributes to the Industry 4.0...
-
Elective Project I _ Shelter_learning by doing
Kursy OnlineElective Project I _ Shelter - learning by doing “Your creativity and skills play an important role in making an impact in responding to humanitarian challenges and global crises” The world seems to be reeling from one crisis to another. Recently we experienced climate crises, global pandemic (Covid-19), economic uncertainty, wars, floods, wildfire, and earthquakes. Proceeding from the challenges facing humanity at the global...
-
Monitoring Parkinson's disease patients employing biometric sensors and rule-based data processing
PublikacjaArtykuł prezentuje automatyczny system wykrywania pogorszenia zdrowia pacjentów z chorobą Parkinsona opracowany w ramach projektu PERFORM.The paper presents how rule-based processing can be applied to automatically evaluate the motor state of Parkinson's Disease patients. Automatic monitoring of patients by using biometric sensors can provide assessment of the Parkinson's Disease symptoms. All data on PD patients' state are compared...
-
TeleCAD w kształceniu studentów Wydziału Inżynierii Lądowej Politechniki Gdańskiej
PublikacjaPrzedstawiono system TeleCAD opracowany w ramach projektu Leonardo da Vinci - Teleworkers Training for CAD Systems Users (1998-2001). Głównym celem projektu było stworzenie środowiska obsługi kursów programu AutoCAD bazującego na Internecie jako medium do komunikacji między uczestnikami oraz do dostarczania materiałów kursowych. W artykule zaprezentowano również system służący do oceny jakości szkoleń na odległość. Szkolenie TeleCAD...
-
Rapid surrogate-assisted statistical analysis of compact microstrip couplers
PublikacjaIn this paper, a technique for low-cost statistical analysis and yield estimation of compact microwave couplers has been presented. The analysis is executed at the level of a fast surrogate model representing selected characteristic points of the coupler response that are critical to determine satisfaction/violation of the prescribed design specifications. Because of less nonlinear dependence of the characteristic points on geometry...
-
Investigation of Performance and Energy Consumption of Tokenization Algorithms on Multi-core CPUs Under Power Capping
PublikacjaIn this paper we investigate performance-energy optimization of tokenizer algorithm training using power capping. We focus on parallel, multi-threaded implementations of Byte Pair Encoding (BPE), Unigram, WordPiece, and WordLevel run on two systems with different multi-core CPUs: Intel Xeon 6130 and desktop Intel i7-13700K. We analyze execution times and energy consumption for various numbers of threads and various power caps and...
-
Neural network model of ship magnetic signature for different measurement depths
PublikacjaThis paper presents the development of a model of a corvette-type ship’s magnetic signature using an artificial neural network (ANN). The capabilities of ANNs to learn complex relationships between the vessel’s characteristics and the magnetic field at different depths are proposed as an alternative to a multi-dipole model. A training dataset, consisting of signatures prepared in finite element method (FEM) environment Simulia...
-
Bridge Ergonomic Design: A Review
PublikacjaHuman error remains the most common cause of marine incidents and it is worth emphasizing that navigator’s performance is directly affected by ergonomic factors on the bridge. Studies regarding influence of bridge design and work environment on the operator are rare, thus the main purpose of this paper is to fill in this gap. Documents issued by recognized organizations, research publications and additional sources were reviewed...
-
Breast MRI segmentation by deep learning: key gaps and challenges
PublikacjaBreast MRI segmentation plays a vital role in early diagnosis and treatment planning of breast anomalies. Convolutional neural networks with deep learning have indicated promise in automating this process, but significant gaps and challenges remain to address. This PubMed-based review provides a comprehensive literature overview of the latest deep learning models used for breast segmentation. The article categorizes the literature...
-
The evolution of education spaces - from plan as generator to regenerative architecture, virtual rooms and green campuses
PublikacjaThe study programmes are often considered the main formative factors in the process of educating future architects. Another highly influential component is the architectural characteristics of learning spaces, and consequently the impact of the physical built environment on the quality of education has been widely discussed. However, not often do we realise that the characteristics of education spaces correlate with the organisational...
-
Neural networks and deep learning
PublikacjaIn 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...
-
Three-objective antenna optimization by means of kriging surrogates and domain segmentation
PublikacjaIn this paper, an optimization framework for multi-objective design of antenna structures is discussed which exploits data-driven surrogates, a multi-objective evolutionary algorithm, response correction techniques for design refinement, as well as generalized domain segmentation. The last mechanism is introduced to constrain the design space region subjected to sampling, which permits reduction of the number of training data samples...
-
RSS-Based DoA Estimation for ESPAR Antennas Using Support Vector Machine
PublikacjaIn this letter, it is shown how direction-of-arrival (DoA) estimation for electronically steerable parasitic array radiator (ESPAR) antennas, which are designed to be integrated within wireless sensor network nodes, can be improved by applying support vector classification approach to received signal strength (RSS) values recorded at an antenna's output port. The proposed method relies on ESPAR antenna's radiation patterns measured...
-
Using Eye-tracking to get information on the skills acquisition by the radiology residents
PublikacjaThis paper describes the possibility of monitoring the progress of knowledge and skills acquisition by the students of radiology. It is achieved by an analysis of a visual attention distribution patterns during image-based tasks solving. The concept is to use the eye-tracking data to recognize the way how the radiographic images are read by recognized experts, radiography residents involved in the training program, and untrained...
-
A Bayesian regularization-backpropagation neural network model for peeling computations
PublikacjaA Bayesian regularization-backpropagation neural network (BRBPNN) model is employed to predict some aspects of the gecko spatula peeling, viz. the variation of the maximum normal and tangential pull-off forces and the resultant force angle at detachment with the peeling angle. K-fold cross validation is used to improve the effectiveness of the model. The input data is taken from finite element (FE) peeling results. The neural network...
-
Multi-Aspect Quality Assessment Of Mobile Image Classifiers For Companion Applications In The Publishing Sector
PublikacjaThe paper presents the problem of quality assessment of image classifiers used in mobile phones for complimentary companion applications. The advantages of using this kind of applications have been described and a Narrator on Demand (NoD) functionality has been described as one of the examples, where the application plays an audio file related to a book page that is physically in front of the phone's camera. For such a NoD application,...
-
Method for Clustering of Brain Activity Data Derived from EEG Signals
PublikacjaA method for assessing separability of EEG signals associated with three classes of brain activity is proposed. The EEG signals are acquired from 23 subjects, gathered from a headset consisting of 14 electrodes. Data are processed by applying Discrete Wavelet Transform (DWT) for the signal analysis and an autoencoder neural network for the brain activity separation. Processing involves 74 wavelets from 3 DWT families: Coiflets,...
-
Lessons learned from developing an Industry 4.0 mobile process management system supported by Artificial Intelligence
PublikacjaResearch, development and innovation (RDI) projects are undertaken in order to improve existing, or develop new, more efficient products and services. Moreover, the goal of innovation is to produce new knowledge through research, and disseminating it through education and training. In this line of thinking, this paper reports and discusses the lessons learned from the undertaken project, regarding three areas: machine learning...
-
Optimized Deep Learning Model for Flood Detection Using Satellite Images
PublikacjaThe increasing amount of rain produces a number of issues in Kerala, particularly in urban regions where the drainage system is frequently unable to handle a significant amount of water in such a short duration. Meanwhile, standard flood detection results are inaccurate for complex phenomena and cannot handle enormous quantities of data. In order to overcome those drawbacks and enhance the outcomes of conventional flood detection...
-
Obtaining a Well-Trained Artificial Intelligence Algorithm from Cross-Validation in Endoscopy
PublikacjaThe article shortly discusses endoscopic video analysis problems and artificial intelligence algorithms supporting it. The most common method of efficiency testing of these algorithms is to perform intensive cross-validation. This allows for accurately evaluate their performance of generalization. One of the main problems of this procedure is that there is no simple and universal way of obtaining a specific instance of a well-trained...
-
CNN Architectures for Human Pose Estimation from a Very Low Resolution Depth Image
PublikacjaThe paper is dedicated to proposing and evaluating a number of convolutional neural network architectures for calculating a multiple regression on 3D coordinates of human body joints tracked in a single low resolution depth image. The main challenge was to obtain a high precision in case of a noisy and coarse scan of the body, as observed by a depth sensor from a large distance. The regression network was expected to reason about...
-
An Improved Convolutional Neural Network for Steganalysis in the Scenario of Reuse of the Stego-Key
PublikacjaThe topic of this paper is the use of deep learning techniques, more specifically convolutional neural networks, for steganalysis of digital images. The steganalysis scenario of the repeated use of the stego-key is considered. Firstly, a study of the influence of the depth and width of the convolution layers on the effectiveness of classification was conducted. Next, a study on the influence of depth and width of fully connected...
-
Antecedents to Achieve Kanban Optimum Benefits in Software Companies
PublikacjaIn 2004, Kanban successfully entered into the Agile and Lean realm. Since then software companies have been increasingly using it in software development teams. The goal of this study is to perform an empirical investigation on antecedents considered as important for achieving optimum benefits of Kanban use and to discuss the practical implications of the findings. We conducted an online survey with software professionals from...
-
Difference in Perceived Speech Signal Quality Assessment Among Monolingual and Bilingual Teenage Students
PublikacjaThe user perceived quality is a mixture of factors, including the background of an individual. The process of auditory perception is discussed in a wide variety of fields, ranging from engineering to medicine. Many studies examine the difference between musicians and non-musicians. Since musical training develops musical hearing and other various auditory capabilities, similar enhancements should be observable in case of bilingual...
-
DOROTKA, czyli Doskonalenie Organizacji, ROzwoju oraz Tworzenia Kursów Akademickich przez Internet.
PublikacjaW artykule zaprezentowano dedykowaną platformę wspierającą kształcenie na odległość opracowaną i uruchomioną w ramach projektu Leonardo da Vinci TeleCAD (Teleworkers Training for CAD System Users, 1998-2001), wykorzystywaną w latach 2000-2003 do wspomagania przedmiotu Podstawy Informatyki na Wydziale Inżynierii Lądowej Politechniki Gdańskiej. Przedstawiono również, bazujący na wieloletnich doświadczeniach, model DOROTKA (Doskonalenie...
-
Paradygmat jakościowy w analizie interakcji międzykulturowych – interpretacja na bazie wybranych teorii psychologicznych
PublikacjaIntercultural interactions in a multicultural work environment are a peculiar type of social interactions. The results of prior research on the effects of interactions in such environment are inconclusive. The majority of the previous studies have emphasized problems, applied a quantitative methodology and interpreted the results with regard to social identity and categorization theory, information-processing theory and intergroup contact...
-
Low-Cost Data-Driven Surrogate Modeling of Antenna Structures by Constrained Sampling
PublikacjaFull-wave electromagnetic (EM) analysis has become one of the major design tools for contemporary antenna structures. Although reliable, it is computationally expensive which makes automated simulation-driven antenna design (e.g., parametric optimization) difficult. This difficulty can be alleviated by utilization of fast and accurate replacement models (surrogates). Unfortunately, conventional data-driven modeling of antennas...
-
Cloud solutions as a platform for building advanced learning platform, that stimulate the real work environment for project managers
PublikacjaImproving skills of managers and executives require, that during the transfer of knowledge (in different ways: during studies, trainings, workshops and other forms of education) it is necessary to use tools and solutions that are (or will be) used in real world environments, where people being educated are working or will work. Cloud solutions allow educational entities (universities, training companies, trainers, etc.) to provide...
-
Buried Object Characterization Using Ground Penetrating Radar Assisted by Data-Driven Surrogate-Models
PublikacjaThis work addresses artificial-intelligence-based buried object characterization using 3-D full-wave electromagnetic simulations of a ground penetrating radar (GPR). The task is to characterize cylindrical shape, perfectly electric conductor (PEC) object buried in various dispersive soil media, and in different positions. The main contributions of this work are (i) development of a fast and accurate data driven surrogate modeling...
-
Improved Uniform Sampling in Constrained Domains for Data-Driven Modelling of Antennas
PublikacjaData-driven surrogate modelling of antenna structures is an attractive way of accelerating the design process, in particular, parametric optimization. In practice, construction of surrogates is hindered by curse of dimensionality as well as wide ranges of geometry parameters that need to be covered in order to make the model useful. These difficulties can be alleviated by constrained performance-driven modelling with the surrogate...
-
Multi-objective design optimization of antennas for reflection, size, and gain variability using kriging surrogates and generalized domain segmentation
PublikacjaCost-efficient multi-objective design optimization of antennas is presented. The framework exploits auxiliary data-driven surrogates, a multi-objective evolutionary algorithm for initial Pareto front identification, response correction techniques for design refinement, as well as generalized domain segmentation. The purpose of this last mechanism is to reduce the volume of the design space region that needs to be sampled in order...
-
Potential and Use of the Googlenet Ann for the Purposes of Inland Water Ships Classification
PublikacjaThis article presents an analysis of the possibilities of using the pre-degraded GoogLeNet artificial neural network to classify inland vessels. Inland water authorities monitor the intensity of the vessels via CCTV. Such classification seems to be an improvement in their statutory tasks. The automatic classification of the inland vessels from video recording is a one of the main objectives of the Automatic Ship Recognition and...
-
Rapid Multi-band Patch Antenna Yield Estimation Using Polynomial Chaos-Kriging
PublikacjaYield estimation of antenna systems is important to check their robustness with respect to the uncertain sources. Since the Monte Carlo sampling-based real physics simulation model evaluations are computationally intensive, this work proposes the polynomial chaos-Kriging (PC-Kriging) metamodeling technique for fast yield estimation. PC-Kriging integrates the polynomial chaos expansion (PCE) as the trend function of Kriging metamodel...
-
Ranking Speech Features for Their Usage in Singing Emotion Classification
PublikacjaThis paper aims to retrieve speech descriptors that may be useful for the classification of emotions in singing. For this purpose, Mel Frequency Cepstral Coefficients (MFCC) and selected Low-Level MPEG 7 descriptors were calculated based on the RAVDESS dataset. The database contains recordings of emotional speech and singing of professional actors presenting six different emotions. Employing the algorithm of Feature Selection based...
-
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...
-
Neural Modelling of Steam Turbine Control Stage
PublikacjaThe paper describes possibility of steam turbine control stage neural model creation. It is of great importance because wider application of green energy causes severe conditions for control of energy generation systems operation Results of chosen steam turbine of 200 MW power measurements are applied as an example showing way of neural model creation. They serve as training and testing data of such neural model. Relatively simple...
-
Marketing office management with leadership competences application in a manufacturing and service company
PublikacjaThe article presents a description of comprehensive leadership competencies in a company, with the emphasis on managing the marketing department. The publication commences with the indication of the leadership in the light of this literature, explaining what leadership competencies are, how they are identified and what competencies we distinguish. It also explains the purpose of applying leadership...
-
Low-Cost Multi-Objective Optimization Yagi-Uda Antenna in Multi-Dimensional Parameter Space
PublikacjaA 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...
-
Engineering education for smart grid systems in the quasi-industrial environment of the LINTE^2 laboratory
PublikacjaSmart grid systems are revolutionising the electric power sector, integrating advanced technologies to enhance efficiency, reliability and sustainability. It is important for higher education to equip the prospective smart grid professional with the competencies enabling them to navigate through the related complexities and drive innovation. To achieve this, interdisciplinary education programmes are necessary, addressing inter...
-
Investigating Noise Interference on Speech Towards Applying the Lombard Effect Automatically
PublikacjaThe aim of this study is two-fold. First, we perform a series of experiments to examine the interference of different noises on speech processing. For that purpose, we concentrate on the Lombard effect, an involuntary tendency to raise speech level in the presence of background noise. Then, we apply this knowledge to detecting speech with the Lombard effect. This is for preparing a dataset for training a machine learning-based...
-
Video Classification Technology in a Knowledge-Vision-Integration Platform for Personal Protective Equipment Detection: An Evaluation
PublikacjaThis work is part of an effort for the development of a Knowledge-Vision Integration Platform for Hazard Control (KVIP-HC) in industrial workplaces, adaptable to a wide range of industrial environments. This paper focuses on hazards resulted from the non-use of personal protective equipment (PPE), and examines a few supervised learning techniques to compose the proposed system for the purpose of recognition of three protective...