Search
Filters
total: 3364
-
Catalog
displaying 1000 best results Help
Search results for: multi-task learning
-
On the modelling of anisotropy and destructuration of soft clays within the multi-laminate framework.
PublicationZaproponowano nowy model konstytutywny dla słabonośnych gruntów drobnoziarnistych, w którym anizotropię cech wytrzymałościowych połączono ze zmianami struktury szkieletu gruntowego. Model ten został sformułowany w ramach tzw. modeli wielopłaszczyznowych (multi-laminate) bazujących na teorii sprężysto-plastyczności. Przedstawiono praktyczne zastosowanie modelu do obliczeń nasypu drogowego na podłożu słabonośnym metodą elementów...
-
Deep Learning-Based LOS and NLOS Identification in Wireless Body Area Networks
PublicationIn this article, the usage of deep learning (DL) in ultra-wideband (UWB) Wireless Body Area Networks (WBANs) is presented. The developed approach, using channel impulse response, allows higher efficiency in identifying the direct visibility conditions between nodes in off-body communication with comparison to the methods described in the literature. The effectiveness of the proposed deep feedforward neural network was checked on...
-
A numerical and experimental analysis of multi-hole orifice in turbulent flow
PublicationIn this research study, the comprehensive metrological analysis is investigated for a 4-hole orifice with module m = 0.25 installed in the pipeline with an internal diameter of 50 mm. A detailed numerical simulation was performed for the turbulence models: k-ε-realizable and k-ω-BSL. The novelties of the research include model validation by comparing the results of numerical studies with the experiment conducted in the area of...
-
From Janus nanoparticles to multi-headed structure - photocatalytic H2 evolution
PublicationThe generation of stable, high-performance photocatalysts with appropriate charge distribution for solar energy conversion is currently one of the urgent missions of photocatalytic science. Recent studies have shown that the Janus NPs with characteristic varied, asymmetric structure may boost overall efficiency of photocatalys. However, there is still a lack of systematic studies in which Janus-type particles are used in the hydrogen...
-
Design Space Reduction for Expedited Multi-Objective Design Optimization of Antennas in Highly-Dimensional Spaces
PublicationA surrogate-based technique for efficient multi-objective antenna optimization is discussed. Our approach exploits response surface approximation (RSA) model constructed from low-fidelity antenna model data (here, obtained through coarse-discretization electromagnetic simulations). The RSA model enables fast determination of the best available trade-offs between conflicting design goals. The cost of RSA model construction for multi-parameter...
-
Power Consumption Optimization in 5G/6G mmWave Networks with User Multi-Connectivity
PublicationIn the fifth generation (5G) and the upcoming sixth generation (6G) millimeter wave (mmWave) networks, the recent emerging ultra-reliable low-latency (URLLC) applications such as telemedicine and self-driven vehicles require strict availability and reliability requirements. Using user multi-connectivity (i.e., connecting each user to multiple base stations (BSs) simultaneously) has emerged as an efficient solution for providing...
-
LDNet: A Robust Hybrid Approach for Lie Detection Using Deep Learning Techniques
PublicationDeception detection is regarded as a concern for everyone in their daily lives and affects social interactions. The human face is a rich source of data that offers trustworthy markers of deception. The deception or lie detection systems are non-intrusive, cost-effective, and mobile by identifying facial expressions. Over the last decade, numerous studies have been conducted on deception detection using several advanced techniques....
-
Machine learning-based prediction of preplaced aggregate concrete characteristics
PublicationPreplaced-Aggregate Concrete (PAC) is a type of preplaced concrete where coarse aggregate is placed in the mold and a Portland cement-sand grout with admixtures is injected to fill the voids. Due to the complex nature of PAC, many studies were conducted to determine the effects of admixtures and the compressive and tensile strengths of PAC. Considering that a prediction tool is needed to estimate the compressive and tensile...
-
Deep learning-based waste detection in natural and urban environments
PublicationWaste pollution is one of the most significant environmental issues in the modern world. The importance of recycling is well known, both for economic and ecological reasons, and the industry demands high efficiency. Current studies towards automatic waste detection are hardly comparable due to the lack of benchmarks and widely accepted standards regarding the used metrics and data. Those problems are addressed in this article by...
-
Machine learning-based prediction of preplaced aggregate concrete characteristics
PublicationPreplaced-Aggregate Concrete (PAC) is a type of preplaced concrete where coarse aggregate is placed in the mold and a Portland cement-sand grout with admixtures is injected to fill the voids. Due to the complex nature of PAC, many studies were conducted to determine the effects of admixtures and the compressive and tensile strengths of PAC. Considering that a prediction tool is needed to estimate the compressive and tensile strengths...
-
Platelet RNA Sequencing Data Through the Lens of Machine Learning
PublicationLiquid biopsies offer minimally invasive diagnosis and monitoring of cancer disease. This biosource is often analyzed using sequencing, which generates highly complex data that can be used using machine learning tools. Nevertheless, validating the clinical applications of such methods is challenging. It requires: (a) using data from many patients; (b) verifying potential bias concerning sample collection; and (c) adding interpretability...
-
Single and Series of Multi-valued Decision Diagrams in Representation of Structure Function
PublicationStructure function, which defines dependency of performance of the system on performance of its components, is a key part of system description in reliability analysis. In this paper, we compare two approaches for representation of the structure function. The first one is based on use of a single Multi-valued Decision Diagram (MDD) and the second on use of a series of MDDs. The obtained results indicate that the series of MDDs...
-
DNAffinity: a machine-learning approach to predict DNA binding affinities of transcription factors
PublicationWe 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...
-
Projektowanie zajęć prowadzonych na odległość (10h e-learning)
e-Learning Courses -
Koło naukowe CJO - Tech-Enhanced English Learning (TEEL)
e-Learning Courses -
Multi-fidelity robust aerodynamic design optimization under mixed uncertainty
PublicationThe objective of this paper is to present a robust optimization algorithm for computationally efficient airfoil design under mixed (inherent and epistemic) uncertainty using a multi-fidelity approach. This algorithm exploits stochastic expansions derived from the Non-Intrusive Polynomial Chaos (NIPC) technique to create surrogate models utilized in the optimization process. A combined NIPC expansion approach is used, where both...
-
Memetic approach for multi-objective overtime planning in software engineering projects
PublicationSoftware projects often suffer from unplanned overtime due to uncertainty and risk incurred due to changing requirement and attempt to meet up with time-to-market of the software product. This causes stress to developers and can result in poor quality. This paper presents a memetic algorithmic approach for solving the overtime-planning problem in software development projects. The problem is formulated as a three-objective optimization...
-
W-dominance: Tradeoff-inspired dominance relation for preference-based evolutionary multi-objective optimization
PublicationThe paper presents a method of incorporating decision maker preferences into multi-objective meta-heuristics. It is based on tradeoffcoefficients and extends their applicability from bi-objective to multi-objective. The method assumes that a decision maker specifies a priori each objective’s importance as a weight interval. Based on this, w-dominance relation is introduced, which extends Pareto dominance. By replacing reference...
-
Optimizing the process of railway geometrical layout designing with multi-criteria assessment method
PublicationThe paper presents the main assumptions of the Multi-criteria assessment method used in process of upgrading the railway geometrical layout. The advantages of metaheuristic search were described. The criteria influencing the investment were defined. The fitness function used in the analysis was described. The example of using the optimization algorithm with the help of self developed computer software was described.
-
Intra-subject class-incremental deep learning approach for EEG-based imagined speech recognition
PublicationBrain–computer interfaces (BCIs) aim to decode brain signals and transform them into commands for device operation. The present study aimed to decode the brain activity during imagined speech. The BCI must identify imagined words within a given vocabulary and thus perform the requested action. A possible scenario when using this approach is the gradual addition of new words to the vocabulary using incremental learning methods....
-
Assessment of the Accuracy of a Virtual Multi-Channel Temperature Measuring Instrument
PublicationThe multi-channel temperature measurement system developed works with NTC thermistors. The article presents the results of theoretical and empirical evaluation of accuracy obtained in measurement channels. The basis for the theoretical assessment is the mathematical model for each of the measurement channels and the characteristics of the system elements included in the circuits of the measurement channel. Two different methods were...
-
Manufacture and research of TPS/PE biocomposites properties
PublicationIn this paper the process of native starch preparing for modification by extrusion and manufacture of biocomposites is presented. The first aim of this study was to determine the mixing and granulating condition of native starch to obtain granulated native starch. For mixing and granulation of native starch Intensive Mixer manufactured by Maschinenfabrik Gustav Eirich was used. Mixing and granulation in a single process is a new...
-
Body surface area formulae: an alarming ambiguity
PublicationBody surface area (BSA) plays a key role in several medical fields, including cancer chemotherapy, transplantology, burn treatment and toxicology. BSA is often a major factor in the determination of the course of treatment and drug dosage. A series of formulae to simplify the process have been developed. Because easy-to-identify, yet general, body coefficient results of those formulae vary considerably, the question arises as to...
-
Improving depth maps of plants by using a set of five cameras
PublicationObtaining high-quality depth maps and disparity maps with the use of a stereo camera is a challenging task for some kinds of objects. The quality of these maps can be improved by taking advantage of a larger number of cameras. The research on the usage of a set of five cameras to obtain disparity maps is presented. The set consists of a central camera and four side cameras. An algorithm for making disparity maps called multiple...
-
Using Statistical Methods to Estimate The Worst Case Response Time of Network Software Running on Indeterministic Hardware Platforms
PublicationIn this paper we investigate whether the statistical Worst Case Execution Time (WCET) estimation methods devised for embedded platforms can be successfully applied to find the Worst Case Response Time (WCRT) of a network application running on a complex hardware platform such as a contemporary commercial off-the-shelf (COTS) system. Establishing easy-to-use timing validation techniques is crucial for real-time applications and...
-
Dynamic model of nuclear power plant turbine
PublicationThe paper presents the dynamic multivariable model of Nuclear Power Plant steam turbine. Nature of the processes occurring in a steam turbine causes a task of modeling it very difficult, especially when this model is intended to be used for on-line optimal process control (model based) over wide range of operating conditions caused by changing power demand. Particular property of developed model is that it enables calculations...
-
CFD and FEM model of an underwater vehicle propeller
PublicationDuring the project execution of design and optimization the Remotely Operated Vehicle (ROV) research on its propulsion has been carried out. The entire project was supported by CFD and FEM calculations, which taking into account the characteristics of underwater vehicle. One of the tasks was to optimize the semi-open duct for horizontal propellers, which provided propulsion and controllability in horizontal plane. In order to...
-
Providing a Desired Quality of BPG Compressed Images for FSIM Metric
PublicationIt is a common task in image lossy compression to provide a reasonable trade-off between a desired compression ratio (as large as possible) and an appropriate (preset according to a chosen metric) quality. Recently, a Better Portable Graphics (BPG) coder has been proposed that might become a new standard. A quality parameter Q is used in it to vary image quality and compression ratio. However, a given Q for particular images...
-
Report for the Short Term Scientific Mission within COST Action FP1101: development of the in-field sensor for estimation of fracture toughness and shear strength by measuring cutting forces
PublicationKnowledge on the fracture properties of materials is essential to assure structural integrity and proper design of mechanical connections in timber constructions. Measurement of this property is, however, a very challenging task. The linear fracture mechanics is usually used for its assessment assisted with experimental data acquired by means of various techniques, usually of destructive nature. The cutting force is an energetic...
-
Optimal control at energy performance index of the mobile robots following dynamically created trajectories
PublicationIn practice, the problem of motion control of the wheeled mobile robots is often neglected. Wheeled mobile robots are strongly nonlinear systems and restricted by non-holonomic constraints. Motion control of such systems is not trivial task and usage of non-optimal control signals can lead to deterioration of the overall robot system’s performance. In case of autonomous application of the mobile robots all parts of its control...
-
Numerical crash analysis of the cable barrier
PublicationSafety barriers are used to increase road safety. Their basic task is to prevent the errant vehicle from getting off the road in places which are potentially dangerous for vehicle passengers. Barriers, which are used on European roads, must fulfill the requirements of EN 1317 standards by passing appropriate crash tests. Because of their high cost, numerical simulations are increasingly used to evaluate the properties of safety...
-
Photoelectrochemically Active N‐Adsorbing Ultrathin TiO2 Layers for Water‐Splitting Applications Prepared by Pyrolysis of Oleic Acid on Iron Oxide Nanoparticle Surfaces under Nitrogen Environment
PublicationHighly performing photocatalytic surfaces are nowadays highly desirable in energy fields, mainly due to their applicability as photo water‐splitting electrodes. One of the current challenges in this field is the production of highly controllable and efficient photoactive surfaces on many substrates. Atomic layer deposition has allowed the deposition of photoactive TiO2 layers over wide range of materials and surfaces. However,...
-
Influence of the air phase on water flow in dikes
PublicationNumerical models are often used to describe flow and deformation processes occurring in dikes during flood events. Modeling of such phenomena is a challenging task, due to the complexity of the system, consisting of three material phases: soil skeleton, pore water and pore air. Additional difficulties are transient loading caused by variable in time water levels, heterogeneity of the soil or air...
-
Wage response to global production links: evidence for workers from 28 European countries (2005–2014)
PublicationUsing rich individual-level data on workers from 28 European countries, this study provides the first so extensive cross-country assessment of wage response to global production links within GVC in the period 2005–2014. Unlike the other studies, the authors (i) address the importance of backward linkages in globally integrated production structures (capturing imports of goods and services needed in any stage of the production of...
-
Exploratory analysis and ranking of analytical procedures for short-chain chlorinated paraffins determination in environmental solid samples
PublicationShort-chain chlorinated paraffins are ones of the most recent chemical compounds that have been classified as persistent organic pollutants. They have various applications and are emitted to the environment. Despite the fact, that the content levels of these compounds in the environmental compartments should be monitored, there is still a lack of well-defined and validated analytical procedures, proposed or suggested by the national...
-
Performance measurements and optimization of visualization of routes traveled in the distributed dispatcher and teleinformation system for visualization of multimedia data for the Border Guard
PublicationMonitoring of country maritime border is an important task of the Border Guard. This activity can be enhanced with the use of the technology enabling gathering information from distributed sources, processing of that information and its visualization. The system presented in the paper is an advancement of the previously developed distributed map data exchange system. The added functionality allows to supplement the map data with...
-
Optimizing FSO networks resilient to adverse weather conditions by means of enhanced uncertainty sets
PublicationThis work deals with dimensioning of wireless mesh networks (WMN) composed of FSO (free space optics) links. Although FSO links realize broadband transmission at low cost, their drawback is sensitivity to adverse weather conditions causing transmission degradation on multiple links. Hence, designing such FSO networks requires an optimization model to find the cheapest configuration of link capacities that will be able to carry...
-
Creating Polish space language dictionary - lessons learned
PublicationPolish space industry suffers from lack of space vocabulary. Since joining European Space Agency in 2012, the sector has expanded rapidly now employing over 1000 specialists focusing mainly on space sustainability, space debris detection and tracking, robotics and propulsion systems. The Polish Space Agency together with The Polish Committee for Standardization have committed to creating the first lexicon of space language, along...
-
Exergy analysis of a negative CO2 emission gas power plant based on water oxy-combustion of syngas from sewage sludge gasification and CCS
PublicationA power cycle with water-injected oxy-combustion (water cycle) is investigated by exergy analysis. It is fueled with syngas (aka. producer gas) from gasification of sewage sludge. The cycle is equipped with a spray-ejector condenser (SEC). CO2 is separated and compressed for transportation and storage. The net delivered electric power is 31% of the fuel exergy. The task efficiency is 39% when the flue gas bleed to gasification...
-
Recent advances in 3D bioprinted tumor models for personalized medicine
PublicationCancerous tumors are among the most fatal diseases worldwide, claiming nearly 10 million lives in 2020. Due to their complex and dynamic nature, modeling tumors accurately is a challenging task. Current models suffer from inadequate translation between in vitro and in vivo results, primarily due to the isotropic nature of tumors and their microenvironment's relationship. To address these limitations, hydrogel-based 3D bioprinting...
-
Love your mistakes!—they help you adapt to change. How do knowledge, collaboration and learning cultures foster organizational intelligence?
PublicationPurpose: The study aims to determine how the acceptance of mistakes is related to adaptability to change in a broad organizational context. Therefore it explores how knowledge, collaboration, and learning culture (including “acceptance of mistakes”) might help organizations overcome their resistance to change. Methodology: The study uses two sample groups: students aged 18–24 (330 cases) and employees aged >24 (326 cases) who work...
-
Modeling a Traffic Remapping Attack Game in a Multi-hop Ad Hoc Network
PublicationIn multi-hop ad hoc networks, selfish nodes may unduly acquire high quality of service (QoS) by assigning higher priority to source packets and lower priority to transit packets. Such traffic remapping attacks (TRAs) are cheap to launch, impossible to prevent, hard to detect, and harmful to non-selfish nodes. While studied mostly in single-hop wireless network settings, TRAs have resisted analysis in multi-hop settings. In this paper...
-
Technology-Enhanced Environmental Learning: Co-design of Educational Mobile Application Case
PublicationThe process of co-creating an educational mobile application to support environmentally friendly behavior is presented in this paper. The research material consisted of quantitative data collected on the application during the first testing phase by early adopters. The results suggest that the most frequently used features of the app were related to transport and educational activities. While women tended to split their time between...
-
The effects of relational and psychological capital on work engagement: the mediation of learning goal orientation
PublicationPurpose – This paper proposes a research model in which learning goal orientation (LGO) mediates the impacts of relational capital and psychological capital (PsyCap) on work engagement. Design/methodology/approach – Data obtained from 475 managers and employees in the manufacturing and service industries in Poland were utilized to assess the linkages given above. Common method variance was controlled by the unmeasured latent method...
-
Simple multi-laminate model for soft soils incorporating structural anisotropy and destructuration
PublicationZaproponowano nowy model konstytutywny należący do rodziny tzw. modeli wielopłaszczyznowych (multi-laminate) dla gruntów słabonośnych. Oryginalnymi rozwiązaniami w modelu są: wprowadzenie kierunkowo zależnej prekonsolidacji oraz uwzględnienie zmian anizotropii wytrzymałości na ściskanie podczas destrukturyzacji naturalnych gruntów słabonośnych. Model zweryfikowano dla podstawowych badań elementowych.
-
Optimizing Medical Personnel Speech Recognition Models Using Speech Synthesis and Reinforcement Learning
PublicationText-to-Speech synthesis (TTS) can be used to generate training data for building Automatic Speech Recognition models (ASR). Access to medical speech data is because it is sensitive data that is difficult to obtain for privacy reasons; TTS can help expand the data set. Speech can be synthesized by mimicking different accents, dialects, and speaking styles that may occur in a medical language. Reinforcement Learning (RL), in the...
-
Forewarned Is Forearmed: Machine Learning Algorithms for the Prediction of Catheter-Induced Coronary and Aortic Injuries
PublicationCatheter-induced dissections (CID) of coronary arteries and/or the aorta are among the most dangerous complications of percutaneous coronary procedures, yet the data on their risk factors are anecdotal. Logistic regression and five more advanced machine learning techniques were applied to determine the most significant predictors of dissection. Model performance comparison and feature importance ranking were evaluated. We identified...
-
Attention-Based Deep Learning System for Classification of Breast Lesions—Multimodal, Weakly Supervised Approach
PublicationBreast cancer is the most frequent female cancer, with a considerable disease burden and high mortality. Early diagnosis with screening mammography might be facilitated by automated systems supported by deep learning artificial intelligence. We propose a model based on a weakly supervised Clustering-constrained Attention Multiple Instance Learning (CLAM) classifier able to train under data scarcity effectively. We used a private...
-
Expert system against machine learning approaches as a virtual sensor for ventricular arrhythmia risk level estimation
PublicationRecent advancements in machine learning have opened new avenues for preventing fatal ventricular arrhythmia by accurately measuring and analyzing QT intervals. This paper presents virtual sensor based on an expert system designed to prevent the risk of fatal ventricular arrhythmias associated with QT-prolonging treatments. The expert system categorizes patients into three risk levels based on their electrocardiogram-derived QT...
-
Mariusz Jaczewski dr inż.
People