Filtry
wszystkich: 3058
wybranych: 2717
-
Katalog
- Publikacje 2717 wyników po odfiltrowaniu
- Czasopisma 16 wyników po odfiltrowaniu
- Konferencje 14 wyników po odfiltrowaniu
- Osoby 39 wyników po odfiltrowaniu
- Wynalazki 1 wyników po odfiltrowaniu
- Projekty 3 wyników po odfiltrowaniu
- Kursy Online 59 wyników po odfiltrowaniu
- Wydarzenia 4 wyników po odfiltrowaniu
- Dane Badawcze 205 wyników po odfiltrowaniu
Filtry wybranego katalogu
wyświetlamy 1000 najlepszych wyników Pomoc
Wyniki wyszukiwania dla: PRE-TRAINED MODELS
-
What Is Troubling IT Analysts? A Survey Report from Poland on Requirements-Related Problems
PublikacjaRequirements engineering and business analysis are activities considered to be important to software project success but also difficult and challenging. This paper reports on a survey conducted in Polish IT industry, aimed at identifying most widespread problems/challenges related to requirements. The survey was targeted at people performing role of analyst in commercial IT projects. The questionnaire included 64 pre-defined problems...
-
Using Synchronously Registered Biosignals Dataset for Teaching Basics of Medical Data Analysis – Case Study
PublikacjaMedical data analysis and processing strongly relies on the data quality itself. The correct data registration allows many unnecessary steps in data processing to be avoided. Moreover, it takes a certain amount of experience to acquire data that can produce replicable results. Because consistency is crucial in the teaching process, students have access to pre-recorded real data without the necessity of using additional equipment...
-
The Impact of Covid-19 on the Performance of Exchange Traded Funds on Developed and Emerging Markets
PublikacjaIn this paper an endeavour was made to evaluate the impact of Covid-19 on the achievement of the investment objectives by selected ETFs in developed and emerging markets. For this purpose, the tracking errors calculated for 18 different ETFs operating on the basis of American, Asian and European stock indexes were analyzed. The time range of the research was selected in such a way as to compare the period before the pandemic(pre-Covid)...
-
Development of an AI-based audiogram classification method for patient referral
PublikacjaHearing loss is one of the most significant sensory disabilities. It can have various negative effects on a person's quality of life, ranging from impeded school and academic performance to total social isolation in severe cases. It is therefore vital that early symptoms of hearing loss are diagnosed quickly and accurately. Audiology tests are commonly performed with the use of tonal audiometry, which measures a patient's hearing...
-
Open-Set Speaker Identification Using Closed-Set Pretrained Embeddings
PublikacjaThe paper proposes an approach for extending deep neural networks-based solutions to closed-set speaker identification toward the open-set problem. The idea is built on the characteristics of deep neural networks trained for the classification tasks, where there is a layer consisting of a set of deep features extracted from the analyzed inputs. By extracting this vector and performing anomaly detection against the set of known...
-
Multiplicative Long Short-Term Memory with Improved Mayfly Optimization for LULC Classification
PublikacjaLand Use and Land Cover (LULC) monitoring is crucial for global transformation, sustainable land control, urban planning, urban growth prediction, and the establishment of climate regulations for long-term development. Remote sensing images have become increasingly important in many environmental planning and land use surveys in recent times. LULC is evaluated in this research using the Sat 4, Sat 6, and Eurosat datasets. Various...
-
Optimal detection observers based on eigenstructure assignment. W: FaultDiagnosis. Models, artificial intelligence, applications. Ed. J. Korbicz, J.M. Kościelny, Z. Kowalczuk, W. Cholewa. Berlin: Springer Verlag**2004 s. 219-259, 7 rys. bibliogr. 41 poz. Optymalne obseratory detekcyjne oparte na strukturze własnej.
PublikacjaPraca dotyczy analitycznych metod syntezy algorytmów detekcji uszkodzeń. De-finiując wektor resztowy jako ważony błąd uzyskanej oceny wyjścia danego o-biektu, poszukuje się takich obserwatorów stanu, dostarczających owych osza-cowań, dla których wektor resztowy jest w możlwie wysokim stopniu niezależnyod niemierzalnych zakłóceń oddziałujących na obiekt oraz od niemierzalnychszumów w torach pomiarowych. Rozważa się algorytmy...
-
Development and validation of a model that includes two ultrasound parameters and the plasma D-dimer level for predicting malignancy in adnexal masses: an observational study
PublikacjaBackground: Pre-operative discrimination of malignant from benign adnexal masses is crucial for planning additional imaging, preparation, surgery and postoperative care. This study aimed to define key ultrasound and clinical variables and develop a predictive model for calculating preoperative ovarian tumor malignancy risk in a gynecologic oncology referral center. We compared our model to a subjective ultrasound assessment (SUA)...
-
Data-Driven Surrogate-Assisted Optimization of Metamaterial-Based Filtenna Using Deep Learning
PublikacjaIn this work, a computationally efficient method based on data driven surrogate models is pro-posed for the design optimization procedure of a Frequency Selective Surface (FSS)-based filtering antenna (Filtenna). A Filtenna acts as a as module that simultaneously pre-filters unwanted sig-nals, and enhances the desired signals at the operating frequency. However, due to a typically large number of design variables of FSS unit elements,...
-
Depth Images Filtering In Distributed Streaming
PublikacjaIn this paper, we propose a distributed system for point cloud processing and transferring them via computer network regarding to effectiveness-related requirements. We discuss the comparison of point cloud filters focusing on their usage for streaming optimization. For the filtering step of the stream pipeline processing we evaluate four filters: Voxel Grid, Radial Outliner Remover, Statistical Outlier Removal and Pass Through....
-
The Influence of Low-Temperature Disintegration on the Co-Fermentation Process of Distillation Residue and Waste-Activated Sludge
Publikacja: Innovative low-temperature disintegration (process temperature 55 ◦C and oxygen concentration 0.2 mg/dm3 ) can be an economically rational technology to intensifying energy production from renewable sources. The proposed process can achieve a degree of disintegration—under optimal conditions—of about 50%, which is excellent when compared with other methods of feed pre-treatment. The low-temperature disintegration of distillation...
-
Block-based Representation of Application Execution on Modern Parallel Systems
PublikacjaThe chapter presents how to model execution of a parallel computational application that is to be executed in a large-scale parallel or distributed environment with potentially thousands to millions of execution units. The representation uses pre- viously attributes and factors representative of modern high performance systems including multicore CPUs, GPUs, dedicated accelerators such as Intel Phi.
-
Abdominal Aortic Aneurysm segmentation from contrast-enhanced computed tomography angiography using deep convolutional networks
PublikacjaOne of the most common imaging methods for diagnosing an abdominal aortic aneurysm, and an endoleak detection is computed tomography angiography. In this paper, we address the problem of aorta and thrombus semantic segmentation, what is a mandatory step to estimate aortic aneurysm diameter. Three end-to-end convolutional neural networks were trained and evaluated. Finally, we proposed an ensemble of deep neural networks with underlying...
-
Artificial Neural Networks as an architectural design tool- generating new detail forms based on the Roman Corinthian order capital
PublikacjaThe following paper presents the results of the research in the field of the machine learning, investigating the scope of application of the artificial neural networks algorithms as a tool in architectural design. The computational experiment was held using the backward propagation of errors method of training the artificial neural network, which was trained based on the geometry of the details of the Roman Corinthian order capital....
-
A Study on Influence of Normalization Methods on Music Genre Classification Results Employing kNN Algorithms
PublikacjaThis paper presents a comparison of different normalization methods applied to the set of feature vectors of music pieces. Test results show the influence of min-nlax and Zero-Mean normalization methods, employing different distance functions (Euclidean, Manhattan, Chebyshev, Minkowski) as a pre-processing for genre classification, on k-Nearest Neighbor (kNN) algorithm classification results.
-
Identification of the customer meter assignment to phases in LV grid: Selected issues of UPGRID project realization
PublikacjaThe paper presents selected issues on the European UPGRID grant implemented by a consortium of companies from seven European states, including from Poland, on the monitoring and control of low voltage grid using measurement pre-registered data by smart AMI meters. The paper focuses on the issue of lack of information on the assignment of communal meters to individual phases.
-
DEPTH IMAGES FILTERING IN DISTRIBUTED STREAMING
PublikacjaIn this paper we discuss the comparison of point cloud filters focusing on their applicability for streaming optimization. For the filtering stage within a stream pipeline processing we evaluate three filters: Voxel Grid, Pass Through and Statistical Outlier Removal. For the filters we perform series of the tests aiming at evaluation of changes of point cloud size and transmitting frequency (various fps ratio). We propose a distributed...
-
Drop-coating deposition surface-enhanced Raman spectroscopy on silver substrates for biofluid analysis
PublikacjaUtilization of surface-enhanced Raman spectroscopy as a measurement technique is of particular interest in biodetection due to its superb chemical specificity and high sensitivity. The use of SERS substrates further improve this method by massive enhancement of the molecule Raman spectrum, permitting very low levels of detection. Therefore it is important to seek for new ways to develop reliable substrates, which are quickly and...
-
Simulations of hydro-fracking in rock mass at meso-scale using fully coupled DEM/CFD approach
PublikacjaThe paper deals with two-dimensional (2D) numerical modelling of hydro-fracking (hydraulic fracturing) in rocks at the meso-scale. A numerical model was developed to characterize the properties of fluid-driven fractures in rocks by combining the discrete element method (DEM) with computational fluid dynamics (CFD). The mechanical behaviour of the rock matrix was simulated with DEM and the behaviour of the fracturing fluid flow...
-
Rapid Design of 3D Reflectarray Antennas by Inverse Surrogate Modeling and Regularization
PublikacjaReflectarrays (RAs) exhibit important advantages over conventional antenna arrays, especially in terms of realizing pencil-beam patterns without the employment of the feeding networks. Unfortunately, microstrip RA implementations feature narrow bandwidths, and are severely affected by losses. A considerably improved performance can be achieved for RAs involving grounded dielectric layers, which are also easy to manufacture using...
-
Context-aware User Modelling and Generation of Recommendations in Recommender Systems
PublikacjaRecommender systems are software tools and techniques which aim at suggesting new items that may be of interest to a user. This dissertation is focused on four problems in recommender systems domain. The first one is context-awareness, i.e. how to obtain relevant contextual information, how to model user preferences in a context and use them to make predictions. The second one is multi-domain recommendation, which aim at suggesting...
-
Low-Cost Automated Design of Compact Branch-Line Couplers
PublikacjaBranch-line couplers (BLCs) are important components of wireless communication systems. Conventional BLCs are often characterized by large footprints which make miniaturization an important prerequisite for their application in modern devices. State-of-the-art approaches to design of compact BLCs are largely based on the use of high-permittivity substrates and multi-layer topologies. Alternative methods involve replacement of transmission-line...
-
Inverse Modeling and Optimization of CSRR-based Microwave Sensors for Industrial Applications
PublikacjaDesign optimization of multivariable resonators is a challenging topic in the area of microwave sensors for industrial applications. This paper proposes a novel methodology for rapid re-design and parameter tuning of complementary split-ring resonators (CSRRs). Our approach involves inverse surrogate models established using pre-optimized resonator data as well as analytical correction techniques to enable rapid adjustment of geometry...
-
In-Out Surface Modification of Halloysite Nanotubes (HNTs) for Excellent Cure of Epoxy: Chemistry and Kinetics Modeling
PublikacjaIn-out surface modification of halloysite nanotubes (HNTs) has been successfully performed by taking advantage of 8-hydroxyquinolines in the lumen of HNTs and precisely synthesized aniline oligomers (AO) of different lengths (tri- and pentamer) anchored on the external surface of the HNTs. Several analyses, including FTIR, H-NMR, TGA, UV-visible spectroscopy, and SEM, were used to establish the nature of the HNTs’ surface engineering....
-
Fatigue damage evaluation of organic coatings subjected to mechanical stress
PublikacjaZnaczna liczba konstrukcji ulega niszczeniu zmęczeniowemu w wyniku oddziaływania cyklicznych naprężeń mechanicznych. Jednakże w dziedzinie organicznych powłok ochronnych czynnik ten pozostaje niedoceniany. W pracy dokonano porównania wpływu cyklicznych naprężeń mechanicznych na nowe i pre-eksponowane (w podwyższonej temperaturze lub promieniowaniu UV) powłoki epoksydowe.
-
Network Approach to Increments of RR-intervals for Visualization of Dynamics of Cardiac Regulation
PublikacjaThe transition network for RR -increments is pre- sented in a directed and weighted graph, with vertices represent- ing RR -increments and edges corresponding to the order in a sequence of increments. The adjacency matrix and the transition matrix of this network provide a graphical tool which could be useful in the assessment of cardiac regulation. As an example, the method is applied in detecting differences between diurnal activity...
-
Dempster-shafer theory-based trust and selfishness evaluation in mobile ad hoc networks
PublikacjaThe paper addresses the problem of selfishness detec-tion in mobile ad hoc networks. It describes an approach based on Dempster-Shafer theory of evidence. Special attention is paid to trust evaluation and using it as a metric for coping with (weighted) recommendations from third-party nodes. Efficiency and robustness of the pre-sented solution is discussed with an emphasis on resil-iency to false recommendations.
-
The moonuments of gdynia post-war construction pace
PublikacjaThe impresive pace of building objects realisation in the 1950s and 1960s was a continuation of the traditional gdynia building pace of the pre-war period. A particular attention and admiration must the reserved for the use at almost every construction site in Gdynia of a considerable quantify of prototypical meterial/construction solutions implemented above all in order to simplify technology and accelerate the pace of building...
-
METHOD OF TRAINING THE ENDOSCOPIC VIDEO ANALYSIS ALGORITHMS TO MAXIMIZE BOTH ACCURACY AND STABILITY
PublikacjaIn the article a new training and testing method of endoscopic video analysis algorithms is presented. Classical methods take into account only eciency of recognizing objects on single video frames. Proposed method additionally considers stability of classiers output for real video input. The method is simple and can be trained on data sets created for other solutions. Therefore, it is easily applicable to existing endoscopic video...
-
DNAffinity: a machine-learning approach to predict DNA binding affinities of transcription factors
PublikacjaWe present a physics-based machine learning approach to predict in vitro transcription factor binding affinities from structural and mechanical DNA properties directly derived from atomistic molecular dynamics simulations. The method is able to predict affinities obtained with techniques as different as uPBM, gcPBM and HT-SELEX with an excellent performance, much better than existing algorithms. Due to its nature, the method can...
-
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...
-
IMPROVING STUDENT SKILLS WITH ENGAGING IN HERITAGE PROTECTION PROJECTS. CASE STUDY OF ARCHITECTURAL INVENTORY WORKS AT WISŁOUJŚCIE FORTRESS, POLAND (2017)
PublikacjaToday's educational offer at universities contains a lot of theoretical and general knowledge, which becomes less understandable and less suitable for students of the new generation. Student's educational needs aimed at increasing the practical experience necessary for future professional life. Heritage conservation projects are a good opportunity to implement project-based learning methods. Such projects can be scientific and...
-
Ensembling noisy segmentation masks of blurred sperm images
PublikacjaBackground: Sperm tail morphology and motility have been demonstrated to be important factors in determining sperm quality for in vitro fertilization. However, many existing computer-aided sperm analysis systems leave the sperm tail out of the analysis, as detecting a few tail pixels is challenging. Moreover, some publicly available datasets for classifying morphological defects contain images limited only to the sperm head. This...
-
Between therapy effect and false-positive result in animal experimentation
PublikacjaDespite the animal models’ complexity, researchers tend to reduce the number of animals in experiments for expenses and ethical concerns. This tendency makes the risk of false-positive results, as statistical significance, the primary criterion to validate findings, often fails if testing small samples. This study aims to highlight such risks using an example from experimental regenerative therapy and propose a machine-learning...
-
Accurate Modeling of Antenna Structures by Means of Domain Confinement and Pyramidal Deep Neural Networks
PublikacjaThe importance of surrogate modeling techniques has been gradually increasing in the design of antenna structures over the recent years. Perhaps the most important reason is a high cost of full-wave electromagnetic (EM) analysis of antenna systems. Although imperative in ensuring evaluation reliability, it entails considerable computational expenses. These are especially pronounced when carrying out EM-driven design tasks such...
-
Adaptacyjny algorytm filtracji sygnału fonokardiograficznego wykorzystujący sztuczną sieć neuronową
PublikacjaPodstawowym problemem podczas projektowania systemu autodiagnostyki chorób serca, bazującego na analizie sygnału fonokardiograficznego (PCG), jest konieczność zapewnienia, niezależnie od warunków zewnętrznych, sygnału o wysokiej jakości. W artykule, bazując na zdolności Sztucznej Sieci Neuronowej (SSN) do predykcji sygnałów periodycznych oraz quasi-periodycznych, został opracowany adaptacyjny algorytm filtracji dźwięków serca....
-
Effects of Salvia officinalis and Thymus vulgaris on oxidant-induced DNA damage and antioxidant status in HepG2 cells
PublikacjaSalvia officinalis (SO) and Thymus vulgaris (TV) are medicinal plants well known for their curative powers. However, the molecular mechanisms responsible for these abilities of sage and thyme have not been fully understood yet. In this study we investigated the composition and the quantitative estimation of plant extracts, the protective effects of plant extracts against hydrogen peroxide- and 2,3-dimethoxy-1,4 naphthoquinone-induced...
-
Buckling resistance of a metal column in a corrugated sheet silo - experiments and non-linear stability calculations
PublikacjaThe results of experimental and numerical tests of a single corrugated sheet silo column’s buckling resistance are presented in this study. The experiments were performed in a real silo with and without bulk solid (wheat). A very positive impact of the bulk solid on the column buckling resistance occurred. The experimental results were first compared to the buckling resistance calculated by Eurocode 3 formulae. The comparison revealed that...
-
Using deep learning to increase accuracy of gaze controlled prosthetic arm
PublikacjaThis paper presents how neural networks can be utilized to improve the accuracy of reach and grab functionality of hybrid prosthetic arm with eye tracing interface. The LSTM based Autoencoder was introduced to overcome the problem of lack of accuracy of the gaze tracking modality in this hybrid interface. The gaze based interaction strongly depends on the eye tracking hardware. In this paper it was presented how the overall the...
-
Conceptualizing Digital Government for Social Solidarity
PublikacjaThis paper motivates the study of the impact of digital government on social solidarity; builds a conceptual foundation with four types of solidarity – group-based, compassionate, instrumental and emphatic; relates digital government to the type and moment – pre-technological, technological and post-technological of solidarity; and puts forward the type-moment frame to study how digital government is supporting social solidarity...
-
Adaptive CAD-Model Construction Schemes
PublikacjaTwo advanced surrogate model construction techniques are discussed in this paper. The models employ radial basis function (RBF)interpolation scheme or artificial neural networks (ANN) with a new training algorithm. Adaptive sampling technique is applied withrespect to all variables. Histograms showing the quality of the models are presented. While the quality of RBF models is satisfactory, theperformance of the ANN models obtained...
-
CoRBAC – kontekstowo zorientowany model bezpieczeństwa
PublikacjaZaproponowano uogólniony model kontroli dostępu do usługowych systemów internetowych uwzględniający różne kategorie kontekstu. Określono wpływ kontekstu na model jak i architekturę systemu bezpieczeństwa. Podano przykład implementacji modelu i architektury bezpieczeństwa dla zestawu usług dotyczących e-uczelni i wstępnie oszacowano zalety takiego rozwiązania.
-
Extending touch-less interaction with smart glasses by implementing EMG module
PublikacjaIn this paper we propose to use temporal muscle contraction to perform certain actions. Method: The set of muscle contractions corresponding to one of three actions including “single-click”, “double-click” “click-n-hold” and “non-action” were recorded. After recording certain amount of signals, the set of five parameters was calculated. These parameters served as an input matrix for the neural network. Two-layer feedforward neural...
-
System for monitoring road slippery based on CCTV cameras and convolutional neural networks
PublikacjaThe slipperiness of the surface is essential for road safety. The growing number of CCTV cameras opens the possibility of using them to automatically detect the slippery surface and inform road users about it. This paper presents a system of developed intelligent road signs, including a detector based on convolutional neural networks (CNNs) and the transferlearning method employed to the processing of images acquired with video...
-
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...
-
Active Learning Based on Crowdsourced Data
PublikacjaThe paper proposes a crowdsourcing-based approach for annotated data acquisition and means to support Active Learning training approach. In the proposed solution, aimed at data engineers, the knowledge of the crowd serves as an oracle that is able to judge whether the given sample is informative or not. The proposed solution reduces the amount of work needed to annotate large sets of data. Furthermore, it allows a perpetual increase...
-
Ion conduction in beryllium-alumino-silicate glasses doped with sodium or sodium and lithium ions
PublikacjaElectrical properties of beryllium-alumino-silicate glasses containing sodium ions or sodium and lithium ions were studied with impedance spectroscopy technique over a frequency range from 10 mHz to 1 MHz and at temperature range from 213 to 473 K. The frequency- and temperature-dependent conductivity spectra of individual single alkali glasses were superimposed by means of the Summerfield scaling. Mixed-alkali glasses do not overlap...
-
Advantageous conditions of saccharification of lignocellulosic biomass for biofuels generation via fermentation processes
PublikacjaProcessing of lignocellulosic biomass includes four major unit operations: pre-treatment, hydrolysis, fermentation and product purifcation prior to biofuel generation via anaerobic digestion. The microorganisms involved in the fermentation metabolize only simple molecules, i.e., monosugars which can be obtained by carrying out the degradation of complex polymers, the main component of lignocellulosic biomass. The object of this...
-
Modeling emotions for affect-aware applications
PublikacjaThe chapter concerns emotional states representation and modeling for software systems, that deal with human affect. A review of emotion representation models is provided, including discrete, dimensional and componential models. The paper provides also analysis of emotion models used in diverse types of affect-aware applications: games, mood trackers or tutoring systems. The analysis is supported with two design cases. The study...
-
Low and high energy explosive materials used in shale gas recovery
PublikacjaNowadays the explosives are widely used in many areas of life, including industry and mining. A wide range of explosive materials is used in the petroleum industry - from low to high explosives. Recently, as the unconventional oil and gas production became possible, explosives are also found to be used in perforators during the pre-completion stage of the fracturing process. This paper presents literature on theoretical and practical...