Search
Filters
total: 817
filtered: 629
Search results for: background-level data augmentation
-
Learning sperm cells part segmentation with class-specific data augmentation
PublicationInfertility affects around 15% of couples worldwide. Male fertility problems include poor sperm quality and low sperm count. The advanced fertility treatment methods like ICSI are nowadays supported by vision systems to assist embryologists in selecting good quality sperm. Computer-Assisted Semen Analysis (CASA) provides quantitative and qualitative sperm analysis concerning concentration, motility, morphology, vitality, and fragmentation....
-
Establishing the background level of base oxidation in human lymphocyte DNA: results of an interlaboratory validation study
Publication -
Detecting Lombard Speech Using Deep Learning Approach
PublicationRobust Lombard speech-in-noise detecting is challenging. This study proposes a strategy to detect Lombard speech using a machine learning approach for applications such as public address systems that work in near real time. The paper starts with the background concerning the Lombard effect. Then, assumptions of the work performed for Lombard speech detection are outlined. The framework proposed combines convolutional neural networks...
-
Toward Robust Pedestrian Detection With Data Augmentation
PublicationIn this article, the problem of creating a safe pedestrian detection model that can operate in the real world is tackled. While recent advances have led to significantly improved detection accuracy on various benchmarks, existing deep learning models are vulnerable to invisible to the human eye changes in the input image which raises concerns about its safety. A popular and simple technique for improving robustness is using data...
-
Musical Instrument Tagging Using Data Augmentation and Effective Noisy Data Processing
PublicationDeveloping signal processing methods to extract information automatically has potential in several applications, for example searching for multimedia based on its audio content, making context-aware mobile applications (e.g., tuning apps), or pre-processing for an automatic mixing system. However, the last-mentioned application needs a significant amount of research to reliably recognize real musical instruments in recordings....
-
Data augmentation for improving deep learning in image classification problem
PublicationThese days deep learning is the fastest-growing field in the field of Machine Learning (ML) and Deep Neural Networks (DNN). Among many of DNN structures, the Convolutional Neural Networks (CNN) are currently the main tool used for the image analysis and classification purposes. Although great achievements and perspectives, deep neural networks and accompanying learning algorithms have some relevant challenges to tackle. In this...
-
Detection of Lexical Stress Errors in Non-Native (L2) English with Data Augmentation and Attention
PublicationThis paper describes two novel complementary techniques that improve the detection of lexical stress errors in non-native (L2) English speech: attention-based feature extraction and data augmentation based on Neural Text-To-Speech (TTS). In a classical approach, audio features are usually extracted from fixed regions of speech such as the syllable nucleus. We propose an attention-based deep learning model that automatically de...
-
Preprzedsiębiorczość
PublicationKsiążka składa się z czterech rozdziałów, poprzedzonych wstępem i zwieńczonych częścią podsumowującą całość. Rozdział pierwszy nakreśla tło dla dalszych rozważań. W rozdziale tym wyodrębniono trzy zasadnicze ujęcia: ujęcie ekonomiczne, ujęcie psychologiczne oraz socjologiczno-kulturowe. W dalszej części tego rozdziału przeanalizowano związki między przedsiębiorczością a wzrostem gospodarczym. Wskazano także mniej znane kierunki...
-
Management of Textual Data at Conceptual Level
PublicationThe article presents the approach to the management of a large repository of documents at conceptual level. We describe our approach to representing Wikipedia articles using their categories. The representation has been used to construct groups of similar articles. Proposed approach has been implemented in prototype system that allows to organize articles that are search results for a given query. Constructed clusters allow to...
-
Systems of Public Higher Education in Poland and Germany. Evidence from Institution Level Data
PublicationThe chapter presents a comparative analysis of public higher education systems (HES) in Germany and Poland. Instead of limiting our study to macro indicators such as gross expenditure on higher education or R&D as per cent of GDP, we draw on the evidence based on micro data especially collected for this study and concerning individual higher education institutions (HEIs). Comparative analysis is based on a sample of 71 public...
-
Application Of Generative Adversarial Network for Data Augmentation and Multiplication to Automated Cell Segmentation of the Corneal Endothelium
PublicationConsidering the automatic segmentation of the endothelial layer, the available data of the corneal endothelium is still limited to a few datasets, typically containing an average of only about 30 images. To fill this gap, this paper introduces the use of Generative Adversarial Networks (GANs) to augment and multiply data. By using the ``Alizarine'' dataset, we train a model to generate a new synthetic dataset with over 513k images....
-
NLITED - New Level of Integrated Techniques for Daylighting Education: Preliminary Data on the Use of an E-learning Platform
PublicationProject NLITED – New Level of Integrated Techniques for Daylighting Education - is an educational project for students and professionals. The project's objective is to create and develop an online eLearning platform with 32 eModules dedicated to daylight knowledge. The project also offers e-learners two summer school training where the theory is put into practice. The platform was launched on January 31, 2022. The paper...
-
Low-Level Aerial Photogrammetry as a Source of Supplementary Data for ALS Measurements
Publication -
Low-Level Aerial Photogrammetry as a Source of Supplementary Data for ALS Measurements
PublicationThe development of laser scanning technology ALS allows to make high-resolution measurements for large areas result-ing in significant reduction of costs. The main stakeholders at heights data received from the airborne laser scanning is mainly state administration. The state institutions appear among projects such as ISOK. Each point is classified in ac-cordance with the standard LAS 1.2, our research focuses on the class 6 -...
-
Extraction of mass spectra free of background and neighboring component contributions from gas chromatography/mass spectrometry data
Publication -
Methotrexate Decreases the Level of PCSK9—A Novel Indicator of the Risk of Proatherogenic Lipid Profile in Psoriasis. The Preliminary Data
Publication -
Layered background modeling for automatic detection of unattended objects in camera images
PublicationAn algorithm for automatic detection of unattended objects in video camera images is presented. First, background subtraction is performed, using an approach based on the codebook method. Results of the detection are then processed by assigning the background pixels to time slots, based on the codeword age. Using this data, moving objects detected during a chosen period may be extracted from the background model. The proposed approach...
-
Closer Look at the Uncertainty Estimation in Semantic Segmentation under Distributional Shift
PublicationWhile recent computer vision algorithms achieve impressive performance on many benchmarks, they lack robustness - presented with an image from a different distribution, (e.g. weather or lighting conditions not considered during training), they may produce an erroneous prediction. Therefore, it is desired that such a model will be able to reliably predict its confidence measure. In this work, uncertainty estimation for the task...
-
Using Principal Component Analysis and Canonical Discriminant Analysis for multibeam seafloor characterisation data
PublicationThe paper presents the seafloor characterisation based on multibeam sonar data. It relies on using the integrated model and description of three types of multibeam data obtained during seafloor sensing: 1) the grey-level sonar images (echograms) of seabed, 2) the 3D model of the seabed surface which consists of bathymetric data, 3) the set of time domain bottom echo envelopes received in the consecutive sonar beams. The classification...
-
A Fast Method of Separation of the Noisy Background from the Head-Cross Section in the Sequence of MRI Scans
PublicationThe paper presents a new method of removing the noisy background from the sequence of magnetic resonance imaging (MRl) scans. The sequence of scans is required in order to monitor a passage of a contrast agent through the brain tissue. The scans contain the noisy head-cross data and also the noisy background data. The latter has to be removed and excluded from a further analysis. It is achieved by applying some basic morphological...
-
Categorization of emotions in dog behavior based on the deep neural network
PublicationThe aim of this article is to present a neural system based on stock architecture for recognizing emotional behavior in dogs. Our considerations are inspired by the original work of Franzoni et al. on recognizing dog emotions. An appropriate set of photographic data has been compiled taking into account five classes of emotional behavior in dogs of one breed, including joy, anger, licking, yawning, and sleeping. Focusing on a particular...
-
Multi-core processing system for real-time image processing in embedded computer vision applications
PublicationW artykule opisano architekturę wielordzeniowego programowalnego systemu do przetwarzania obrazów w czasie rzeczywistym. Dane obrazu są przetwarzane równocześnie przez wszystkie procesory. System umożliwia niskopoziomowe przetwarzanie obrazów,np. odejmowanie tła, wykrywanie obiektów ruchomych, transformacje geometryczne, indeksowanie wykrytych obiektów, ocena ich kształtu oraz podstawowa analiza trajektorii ruchu. Ang:This paper...
-
All-gather Algorithms Resilient to Imbalanced Process Arrival Patterns
PublicationTwo novel algorithms for the all-gather operation resilient to imbalanced process arrival patterns (PATs) are presented. The first one, Background Disseminated Ring (BDR), is based on the regular parallel ring algorithm often supplied in MPI implementations and exploits an auxiliary background thread for early data exchange from faster processes to accelerate the performed all-gather operation. The other algorithm, Background Sorted...
-
Main complications connected with detection, identification and determination of trace organic constituents in complex matrix samples
PublicationIt is well known that some problems with the determination of organic analytes at trace level can occur. This issue is connected with contamination during each stage of the analytical procedure from sampling to sample preparation up to chromatographic analysis, which often leads to false-positive or overestimated results. Another problem associated with determination of analytes occurs at trace- and ultra-trace level is a background...
-
Could thermal imaging supplement surface electromyography measurements for skeletal muscles?
PublicationAbstract—(1) Background: The aim of this study is to present the results of experiments in which surface electromyography (sEMG) and thermal imaging were used to assess muscle activation during gait and to verify the hypothesis that there is a relationship in the case of low fatigue level between sEMG measured muscle activation, assessed in the frequency domain, and thermal factors calculated as minimum, maximum, kurtosis, mean,...
-
A framework for automatic detection of abandoned luggage in airport terminal
PublicationA framework for automatic detection of events in a video stream transmitted from a monitoring system is presented. The framework is based on the widely used background subtraction and object tracking algorithms. The authors elaborated an algorithm for detection of left and removed objects based on mor-phological processing and edge detection. The event detection algorithm collects and analyzes data of all the moving objects in...
-
Spatial Visualization Based on Geodata Fusion Using an Autonomous Unmanned Vessel
PublicationThe visualization of riverbeds and surface facilities on the banks is crucial for systems that analyze conditions, safety, and changes in this environment. Hence, in this paper, we propose collecting, and processing data from a variety of sensors—sonar, LiDAR, multibeam echosounder (MBES), and camera—to create a visualization for further analysis. For this purpose, we took measurements from sensors installed on an autonomous, unmanned...
-
Visual Traffic Noise Monitoring in Urban Areas
PublicationThe paper presents an advanced system for railway and road traffic noise monitoring in metropolitan areas. This system is a functional part of a more complex solution designed for environmental monitoring in cities utilizing analyses of sound, vision and air pollution, based on a ubiquitous computing approach. The system consists of many autonomous, universal measuring units and a multimedia server, which gathers, processes and...
-
Individual Characteristics and Cognitions of Students with Different Levels of Entrepreneurial Intensity
PublicationRESEARCH OBJECTIVE: The objective of the current paper is to verify in what way university students who declare high individual level of entrepreneurial intensity differ from those who are characterized by its intensity level. THE RESEARCH PROBLEM AND METHODS: A statistical analysis of obtained survey results was conducted. The group of research participants included 413 business students. Following statistical methods were used...
-
Robustness in Compressed Neural Networks for Object Detection
PublicationModel compression techniques allow to significantly reduce the computational cost associated with data processing by deep neural networks with only a minor decrease in average accuracy. Simultaneously, reducing the model size may have a large effect on noisy cases or objects belonging to less frequent classes. It is a crucial problem from the perspective of the models' safety, especially for object detection in the autonomous driving...
-
Mobilenet-V2 Enhanced Parkinson's Disease Prediction with Hybrid Data Integration
PublicationThis study investigates the role of deep learning models, particularly MobileNet-v2, in Parkinson's Disease (PD) detection through handwriting spiral analysis. Handwriting difficulties often signal early signs of PD, necessitating early detection tools due to potential impacts on patients' work capacities. The study utilizes a three-fold approach, including data augmentation, algorithm development for simulated PD image datasets,...
-
A New Approach to Assess Quality of Motion in Functional Task of Upper Limb in Duchenne Muscular Dystrophy
Publication(1) Background: This study presents a new method for the motion quantitative analysis of Duchenne muscular dystrophy patients (DMD) performing functional tasks in clinical conditions. (2) Methods: An experimental study was designed to define how different levels of external mass (light and heavy) influence the performance of the upper limbs of a tested DMD and reference subject (RS) during horizontal movements (level of the waist)...
-
Spiral Search Grasshopper Features Selection with VGG19-ResNet50 for Remote Sensing Object Detection
PublicationRemote sensing object detection plays a major role in satellite imaging and is required in various scenarios such as transportation, forestry, and the ocean. Deep learning techniques provide efficient performance in remote sensing object detection. The existing techniques have the limitations of data imbalance, overfitting, and lower efficiency in detecting small objects. This research proposes the spiral search grasshopper (SSG)...
-
Effect of the integration into Global Value Chains on the employment contract in Central and Eastern European countries
PublicationResearch background: In the era of globalization, there is a need to address decent work deficits in Global Value Chains (GVCs). The forms of working conditions reveal a broad dispersion of contents. The literature review exposes hardly any Europe-focused research assessing the socioeconomic impact of global production links and going beyond their pure economic effects assessed in terms of employment, productivity or wages. Purpose...
-
Sub-national structures matter when evaluating physical activity promotion: Lessons from Germany
PublicationBackground Public policies are increasingly acknowledged as important part of promoting physical activity (PA). However, especially in states with sub-national administrative structures such as Germany, national and sub-national approaches differ considerably. In Germany, sport for all (SfA) promotion is mostly organized at sub-national level, which is usually not covered in national evaluations. Knowledge of these structures helps...
-
Determinants of trade balance in Polish and Czech manufacturing sectors
PublicationResearch background: A strong industrial base is essential for achieving long-term sustainable economic growth and export competitiveness. In that sense, manufacturing remains a significant contributor to exports in the CEE countries. However, its role and its influence vary between CEE economies and change over time. Purpose of the article: The main objective of this paper is to compare the determinants of the international competitiveness,...
-
Level of public finances decentralization in European Union countries
PublicationResearch background: Despite of the universality of the implementation in democratic countries the principle of decentralization resulting from the belief that it is an instrument to improve the efficiency of public funds management, both the scope of public services and the level of decentralization in individual countries are not identical. Purpose of the article: Comparison the scope of fiscal decentralization...
-
Clinical anatomy of the spatial structure of the right ventricular outflow trac
PublicationBackground. The right ventricular outflow tract (RVOT) is located above the supraventricular crest and reaches the level of the pulmonary valve. Detailed knowledge of the RVOT spatial structure and its morphology is extremely important for cardiac invasive therapeutic procedures. Objectives. To examine the spatial structure of the RVOT using virtual models of the right ventricle (RV) interior obtained post mortem. Material and...
-
Trace Elements in Aquatic Environments
PublicationA trace element is defined as a chemical element whose the average concentration is less than 100 ppm (mg/kg, mg/L – in the case of a water matrix). In aquatic environments the concentrations of trace elements are usually at the level of picomoles per liter and lower. This causes extreme analytical problems, especially in situations where low content is in the range of background levels. Taking into account the role of trace elements...
-
Fuel price, income and road safety as determinants of the level of the population’s economic well-being in Poland
PublicationThe opportunity to travel is one of the most favorite human activities, given that on a trip a person gets new knowledge, impressions and positive emotions. Recreational trips occupy a prominent place in the concept of the economics of happiness, and the study of factors that influence decision-making regarding travel is important for forecasting the number of tourists, infrastructure development, income and expenses of businesses...
-
Implementation of International Standards of Fiscal and Monetary Transparency - Case of Poland
PublicationResearch background: Financial managers, investors, lenders, counterparties and citizens should have useful, reliable, timely, complete, comparable, readable information on fiscal and monetary policy. The actions taken and instruments used by fiscal and monetary authorities have an important impact on economic conditions. Purpose of the article: The aim of the article is to assess Poland's compliance with international standards...
-
Organic matter removal efficiency in treatment wetlands simulation by COD fractions
PublicationThe objective of this paper was to investigate the organic fraction (colloidal, particulate, and dissolved) in sewage treatment in treatment wetland. Performance of TWs was simulated well with a simple first order model k – C* based on monitoring data. In this investigation background or residual concentration (C*) was assumed to be equal concentration of input influent organic matter in particulate (CODp). Calculated reaction...
-
Estimating inequality aversion from subjective assessments of the just noticeable differences in welfare
PublicationResearch background: In Economics, the concept of inequality aversion corresponds with the concept of risk aversion in the literature on making decision under uncertainty. The risk aversion is estimated on the basis of subjective reactions of people to various lottery prospects. In Economics, however, an efficient method of estimating inequality aversion has not been developed yet. Purpose of the article: The main aim of this paper...
-
GVC and wage dispersion. Firm-level evidence from employee-employer database
PublicationResearch background: Wage inequalities are still part of an interesting policy-oriented research area. Given the developments in international trade models (heterogeneity of firms) and increasing availability of micro-level data, more and more attention is paid to wage differences observed within and be-tween firms. Purpose of the article: The aim of the paper is to address the research gap concerning limited cross-country evidence...
-
Gesture Recognition With the Linear Optical Sensor and Recurrent Neural Networks
PublicationIn this paper, the optical linear sensor, a representative of low-resolution sensors, was investigated in the multiclass recognition of near-field hand gestures. The recurrent neural network (RNN) with a gated recurrent unit (GRU) memory cell was utilized as a gestures classifier. A set of 27 gestures was collected from a group of volunteers. The 27 000 sequences obtained were divided into training, validation, and test subsets....
-
Modelling selected road safety measures at the regional level in Europe
PublicationRegions are Europe’s basic levels of management. The literature was reviewed to identify regional safety analyses and some of the factors that are important for road safety in the regions. Next, data were collected atthe regional NUTS 2 level in Europe for the years 1999-2008. An analysis of the data helped identify f actors which have the strongest bearing on fatalities and other safety measures. This paper presents the initial...
-
A review of design approaches for the implementation of low-frequency noise measurement systems
PublicationElectronic noise has its roots in the fundamental physical interactions between matter and charged particles, carrying information about the phenomena that occur at the microscopic level. Therefore, Low-Frequency Noise Measurements (LFNM) are a well-established technique for the characterization of electron devices and materials and, compared to other techniques, they offer the advantage of being non-destructive and of providing...
-
Towards Precise Visual Navigation and Direct Georeferencing for MAV Using ORB-SLAM2
PublicationA low accuracy of positioning using Global Navigation Satellite System (GNSS) are not meet geodetic requirements for direct images georeferencing for Unmanned Aerial Vehicle (UAV) photogrammetry. A majority of UAVs are equipped with a monocular or stereo non-metric cameras for either visual data gathering or live video feed for operator. A cheap positioning techniques used on board commercial UAVs are not that precise as geodetic...
-
Investigating Feature Spaces for Isolated Word Recognition
PublicationThe 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...
-
Performance evaulation of video object tracking algorithm in autonomous surveillance system
PublicationResults of performance evaluation of a video object tracking algorithm are presented. The method of moving objects detection and tracking is based on background modelling with mixtures of Gaussians and Kalman filters. An emphasis is put on algorithm's efficiency with regards to its settings. Utilized methods of performance evaluation based on comparison of algorithm output to manually prepared reference data are introduced. The...