Search
Filters
total: 3108
-
Catalog
displaying 1000 best results Help
Search results for: multi-task learning
-
Real-Time Facial Features Detection from Low Resolution Thermal Images with Deep Classification Models
PublicationDeep networks have already shown a spectacular success for object classification and detection for various applications from everyday use cases to advanced medical problems. The main advantage of the classification models over the detection models is less time and effort needed for dataset preparation, because classification networks do not require bounding box annotations, but labels at the image level only. Yet, after passing...
-
Blended Learning Model for Computer Techniques for Students of Architecture
PublicationAbstract: The article summarizes two-year experience of implementing hybrid formula for teaching Computer Techniques at the Faculty of Architecture at the Gdansk University of Technology. Original educational e-materials, consisting of video clips, text and graphics instructions, as well as links to online resources are embedded in the university e-learning educational platform. The author discusses technical constraints associated...
-
Wear of Ultra-thin DLC or Tungsten-modified DLC Coatings under Reciprocating Sliding
PublicationIn the paper results are presented from tests in reciprocating sliding of self mated specimens of DLC and tungsten modified DLC coatings on stainless steel substrate. The contact geometry chosen for the research task was ball on flat. The contacts were lubricated either with distilled water or medical saline solution. Results are presented with regard to wear resistance as a function of material type and lubricant used.
-
Deep Learning: A Case Study for Image Recognition Using Transfer Learning
PublicationDeep learning (DL) is a rising star of machine learning (ML) and artificial intelligence (AI) domains. Until 2006, many researchers had attempted to build deep neural networks (DNN), but most of them failed. In 2006, it was proven that deep neural networks are one of the most crucial inventions for the 21st century. Nowadays, DNN are being used as a key technology for many different domains: self-driven vehicles, smart cities,...
-
Four-state stochastic model of changes in the reliability states of a motor vehicle
PublicationThe properties of semi-Markov processes have been generally characterized and the applicability of the theory of such processes to the determining of the reliability of motor cars and other road vehicles has been explained. A formal description of the process of changes in the motor vehicle technical states considered as reliability states and a model of this process in the form of a one-dimensional stochastic process have been...
-
Comparison of Selected Neural Network Models Used for Automatic Liver Tumor Segmentation
PublicationAutomatic and accurate segmentation of liver tumors is crucial for the diagnosis and treatment of hepatocellular carcinoma or metastases. However, the task remains challenging due to imprecise boundaries and significant variations in the shape, size, and location of tumors. The present study focuses on tumor segmentation as a more critical aspect from a medical perspective, compared to liver parenchyma segmentation, which is the...
-
Optimisation of turbine shaft heating process under steam turbine run-up conditions
PublicationAn important operational task for thermal turbines during run-up and run-down is to keep the stresses in the structural elements at a right level. This applies not only to their instantaneous values, but also to the impact of them on the engine lifetime. The turbine shaft is a particularly important element. The distribution of stresses depends on geometric characteristics of the shaft and its specific locations. This means a groove manufactured...
-
Microgrid Energy Management System
PublicationIn the era of rapid development of "green energy” and storage devices, microgrids implemented in line with the concept of distributed generation can be an effective form of power management. There is a need for an efficient, optimal and reliable control of the combined infrastructure. The article presents a flexible, configurable microgrid's resources control system, which executes the task of meeting the electricity demand of...
-
Expedited Re-Design of Multi-Band Passive Microwave Circuits Using Orthogonal Scaling Directions and Gradient-Based Tuning
PublicationGeometry scaling of microwave circuits is an essential but challenging task. In particular, the employment of a given passive structure in a different application area often requires re-adjustment of the operating frequencies/bands while maintaining top performance. Achieving this necessitates utilization of numerical optimization methods. Nonetheless, if the intended frequencies are distant from the ones at the starting point,...
-
Social learning in cluster initiatives
PublicationPurpose – The purpose of the paper is to portray social learning in cluster initiatives (CIs), namely: 1) to explore, with the lens of the communities of practice (CoPs) theory, in what ways social learning occurs in CIs; 2) to discover how various CoPs emerge and evolve in CIs to facilitate a collective journey in their learning process. Subsequently, the authors address the research questions: In what ways does social learning...
-
Distinct hippocampal-prefrontal neural assemblies coordinate memory encoding, maintenance, and recall
PublicationShort-term memory enables incorporation of recent experience into subsequent decision-making. This processing recruits both the prefrontal cortex and hippocampus, where neurons encode task cues, rules, and outcomes. However, precisely which information is carried when, and by which neurons, remains unclear. Using population decoding of activity in rat medial prefrontal cortex (mPFC) and dorsal hippocampal CA1, we confirm that mPFC...
-
Maritime traffic situation awareness analysis via high-fidelity ship imaging trajectory
PublicationSituation awareness provides crucial yet instant information to maritime traffic participants, and significant attentions are paid to implement traffic situation awareness task via various maritime data source (e.g., automatic identification system, maritime surveillance video, radar, etc.). The study aims to analyze traffic situation with the support of ship imaging trajectory. First, we employ the dark channel prior model to...
-
Selected problems of decision making modelling in power engineering
PublicationThe paper presents the selected problems of decision making modelling in power engineering specially investment risk evaluation methods. The proposed model can be used in the range programming the development and investing process in power engineering. Decision making problems in power engineering and the evaluation of investment effectiveness in particular are closely related to modelling which relatively accurately reflects...
-
Clothes Detection and Classification Using Convolutional Neural Networks
PublicationIn this paper we describe development of a computer vision system for accurate detection and classification of clothes for e-commerce images. We present a set of experiments on well established architectures of convolutional neural networks, including Residual networks, SqueezeNet and Single Shot MultiBox Detector (SSD). The clothes detection network was trained and tested on DeepFashion dataset, which contains box annotations...
-
Efficacy of coping with work-related stress by firemen
PublicationThe aim of this study was efficacy of coping with work-related stress by firemen with reference to subjective health evaluation. Theoretical model of process of stress by Lazarus was applied. The group consistent of 230 line-duty firemen. Participation in traumatic events and sense of coherence both directly and indirectly, by stress, affected the health among firemen. In stress confrontation a wider array of task and emotional...
-
Research of Accuracy of RSSI Fingerprint-Based Indoor Positioning BLE System
PublicationRadio localization in indoor environment is still a challenging task due to environment volatility. In the paper are compared achieved localization accuracies for RSSI-Fingerprinting method utilizing Bluetooth Low Energy (BLE) for two different environments: large empty hall and narrow corridor. Measurements were done by 6 different smartphones of 3 different producers, which makes those measurements unique as accuracies achieved...
-
Research of Accuracy of RSSI Fingerprint-Based Indoor Positioning BLE System
PublicationRadio localization in indoor environment is still a challenging task due to environment volatility. In the paper are compared achieved localization accuracies for RSSI-Fingerprinting method utilizing Bluetooth Low Energy (BLE) for two different environments: large empty hall and narrow corridor. Measurements were done by 6 different smartphones of 3 different producers, which makes those measurements unique as accuracies achieved...
-
Direct algorithm for optimizing robust MPC of drinking water distribution systems hydraulics
PublicationModel-based predictive control is an effective method for control the large scale systems [1]–[6], [8], [16], [17]. Method is based on on-line solution of the control task over the control horizon using current and past measurements, as well as the system model. Only a first element of calculated control sequence is applied to the plant. At the next sampling instant, based on new process output measurements, control procedure is...
-
STUDY OF SEASONAL ACOUSTIC PROPERTIES OF SEA WATER IN SELECTED WATERS OF THE SOUTHERN BALTIC
PublicationClimate Research of the globe is a current task, in particular to confirm the general hypothesis of global warming associated with an increase in average temperature. The sea acoustic climate is derived from the concept of climate and refers to the conditions of propagation of acoustic waves in a particular basin. In this paper, the results of systematic measurements of temperature, salinity and velocity distributions of sound...
-
TensorHive: Management of Exclusive GPU Access for Distributed Machine Learning Workloads
PublicationTensorHive 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...
-
Cooperation areas between universities and industry - case studies in the area of civil engineering
PublicationThe paper describes the areas of cooperation between universities and industry in the area of civil engineering. Presented examples are related to didactics, research grants and commissioned works. On the basis of the authors own experiences the mutual benefits of cooperation in different areas are described. As well as the assessment criteria of the areas of cooperation by the scientific community. The first area of cooperation...
-
Modeling Volunteer Based Systems
PublicationThere are two main approaches to processing tasks requiring high amounts of computational power. One approach is using clusters of mostly identical hardware, placed in dedicated locations [1, 2, 3]. The other approach is outsourcing computing resources from large numbers of volunteers connected to the Internet [7]. This chapter presents an application of a mathematical model of the volunteer computing presented in Volume 1 of this...
-
Assessing Word Difficulty for Quiz-Like Game
PublicationMappings verification is a laborious task. Our research aims at providing a framework for manual verification of mappings using crowdsourcing approach. For this purpose we plan on implementing a quiz like game. For this purpose the mappings have to be evaluated in terms of difficulty to better present texts in respect of game levels. In this paper we present an algorithm for assessing word difficulty. Three approaches...
-
Composite sandwich footbridge - measured dynamic response vs. FEA
PublicationThe paper describes a process of in situ dynamic tests of a composite sandwich footbridge before its accepta-tion for exploitation in real traffic conditions. It is only a part of a big research task that includes design, manufacture and introduce practical application of the bridge. The in situ measured natural modes and fre-quencies are compared with numerically determined ones. Finite element analysis is established to estimate...
-
Model szkolenia "Blended learning" z wykorzystaniem platformy Oracle I-learning.
PublicationW artykule zaproponowano modele organizacyjne szkoleń "blended learning", które pokazują możliwości współpracy firm prywatnych z instytucjami edukacyjnymi w dziedzinie e-learningu. W ramach wspólnego eksperymentu firm Oracle, Incenti S.A., WiedzaNet Sp. z o.o. oraz Centrum Edukacji Niestacjonarnej Politechniki Gdańskiej w semestrze letnim roku akademickiego 2003/2004 udostępniony będzie kurs dla studentów Wydziału Inzynierii Lądowej...
-
Fusion-based Representation Learning Model for Multimode User-generated Social Network Content
PublicationAs mobile networks and APPs are developed, user-generated content (UGC), which includes multi-source heterogeneous data like user reviews, tags, scores, images, and videos, has become an essential basis for improving the quality of personalized services. Due to the multi-source heterogeneous nature of the data, big data fusion offers both promise and drawbacks. With the rise of mobile networks and applications, UGC, which includes...
-
Modelowanie zjawisk zachodzących w strefie tworzywo-forma podczas procesu wtryskiwania.
PublicationPodczas wtrysku w warstwie tworzywa przy ściance formy występują zjawiska, które są źródłem wad powierzchni wypraski. Zjawisko to opisano, oraz zaprezentowano model zachowania się tworzywa w tej strefie, opierając się na symulacji komputerowej procesu wtrysku. Symulację wykonano na komputerach CI TASK przy wykorzystaniu programu FIDAP. Występujące wady powierzchni opisano w oparciu materiał fotograficzny i profilogramów powierzchni.
-
E-learning versus traditional learning - Polish case
PublicationE-learning jest współczesnym fenomenem, który pozwala na dostęp do kształcenia i treści edukacyjnych, niezależnie od czasu i miejsca, dla każdego użytkownika. E-learnig tworzy ogromne możliwości dla uczelni akademickich, organizacji, instytucji komercyjnych i szkoleniowych, dostarczając na żądanie kształcenia i szkoleń w wirtualnym środowisku. Student może stworzyć własny plan kształcenia, dostosowując go do swojej pracy i sytuacji...
-
The task graph assignment for KASKADA platform
PublicationArtykuł opisuje model obliczeniowy wykorzystany w platformie KASKADA. Opiera się on na dwóch podstawowych elementach: węzłach klastra obliczeniowego oraz grafie zadań. Przeanalizowane zostały algorytmy przydzielania węzłów obliczeniowych dla zadań w zależności od kryteriów: minimalizacja fragmentacji klastra i minimalizacja opóźnienia przetwarzania danych. Zostały przedstawione wyniki symulacji opisanych algorytmów oraz ich...
-
The 5S methodology as a tool for improving organization of production
PublicationThe chapter presents the 5S method as a tool for continuous improving lean management processes, whose task is to create a highly efficient, clean, and ergonomic working environment. The method is presented as a collection of 5 simple rules, and at the same time it is a tool that allows you to control the workplace visually. The history of the 5S tool originates from Japanese philosophy, namely the five basic elements of the system: Seiri...
-
No-local-broadcasting theorem for multipartite quantum correlations
PublicationWe prove that the correlations present in a multipartite quantum state have an operational quantum character even if the state is unentangled, as long as it does not simply encode a multipartite classical probability distribution. Said quantumness is revealed by the new task of local broadcasting, i.e., of locally sharing preestablished correlations, which is feasible if and only if correlations are stricly classical. Our operational...
-
Fast Approximate String Search for Wikification
PublicationThe paper presents a novel method for fast approximate string search based on neural distance metrics embeddings. Our research is focused primarily on applying the proposed method for entity retrieval in the Wikification process, which is similar to edit distance-based similarity search on the typical dictionary. The proposed method has been compared with symmetric delete spelling correction algorithm and proven to be more efficient...
-
Blade Section Prpfile Array Lifting Surface Design Method for Marine Screw Propeller Blade
PublicationThe lifting surface model is widely used in screw propeller design and analysis applications. It serves as a reliable tool for determination of the propeller blade mean line and pitch distribution. The main idea of this application was to determine the blade shape that would satisfy the kinematic boundary condition on its surface with the prescribed bound circulation distribution over it. In this paper a simplified lifting surface...
-
Comparison of modelling and measurement results of spectra emitted by a programmable lamp
PublicationNowadays artificial light with an optimized spectrum is used in many different applications. For instance, it is widely used in museums and exhibitions to illuminate the art. Moreover, such light stimulates the growth of plants, or can be applied in industry and healthcare. To achieve the best results for each application, the adjusting of a dedicated spectrum is required, which is a complicated task. The ongoing research is focused...
-
From a Point Cloud to a 3D Model - an Exercise for Users of AutoCAD and Revit
PublicationThe paper presents a proposal of the topic of an exercise for students of building faculties as part of classes on 3D modelling. The task consists in creating a three-dimensional model based on the measurement obtained with the Leica P30 laser scanner. Due to the maximum number of points in the cloud in the presented programs, the output files must be properly cleared and reduced. The point cloud was pre-processed in Cyclone software....
-
High-Efficacy Global Optimization of Antenna Structures by Means of Simplex-Based Predictors
PublicationDesign of modern antenna systems has become highly dependent on computational tools, especially full-wave electromagnetic (EM) simulation models. EM analysis is capable of yielding accurate representation of antenna characteristics at the expense of considerable evaluation time. Consequently, execution of simulation-driven design procedures (optimization, statistical analysis, multi-criterial design) is severely hindered by the...
-
Raw data of AuAg nanoalloy plasmon resonances used for machine learning method
Open Research DataRaw data used for machine learning process. UV-vis measurements of AuAg alloyed nanostructures created from thin films. Plasmonic band position dependence on fabrication parameters. Small presentation reviewing achieved structures and their properties.
-
Machine Learning and Deep Learning Methods for Fast and Accurate Assessment of Transthoracic Echocardiogram Image Quality
PublicationHigh-quality echocardiogram images are the cornerstone of accurate and reliable measurements of the heart. Therefore, this study aimed to develop, validate and compare machine learning and deep learning algorithms for accurate and automated assessment of transthoracic echocardiogram image quality. In total, 4090 single-frame two-dimensional transthoracic echocardiogram...
-
Collective Uncertainty Entanglement Test
PublicationFor a given pure state of a composite quantum system we analyze the product of its projections onto aset of locally orthogonal separable pure states. We derive a bound for this product analogous to theentropic uncertainty relations. For bipartite systems the bound is saturated for maximally entangled statesand it allows us to construct a family of entanglement measures, we shall call collectibility. As thesequantities are experimentally...
-
Dynamics Conscious Approach to Tribometer Design and Tribo-testing
PublicationIn the paper findings are discussed on the issue of dynamic characteristics of a tribometer as a factor influencing the result of the tribological experiment. An advanced approach to tribo-testing is attempted with integrated dynamic analysis of the tribometer and the sliding pair. The fundamental idea is explored of the tribometer being regarded as any machine in which friction is inflicted with all the resulting consequences...
-
Modeling of flow phenomena on the mould plastic interface associated withpolymer injection. Trends Production Technol.**2002 Bd 3 s. 122-137, 11 rys Proceedings of the International Colloquium on Production Science. Gdańsk, April 15th 2002. Ed. D. Spaht. Modelowanie zjawisk zachodzących podczas wtrysku w strefie tworzywo-forma.
PublicationPodczas wtrysku występują w warstwie tworzywa przy ściance formy zjawiska,które są źródłem wad. Opisano powyższe zjawiska oraz zaprezentowano model zachowania się tworzywa w strefie przyściennej z wykorzystaniem symulacji komputerowej procesu wtrysku. Symulację wykonano na komputerach CI TASK przyuzyciu programu FIDAP. Ponadto przedstawiono wyniki badań doświadczalnych w postaci fotografii i profilogramów powierzchni, które...
-
Ship Dynamic Positioning Based on Nonlinear Model Predictive Control
PublicationThe presented work explores the simulation test results of using nonlinear model predictive control algorithm for ship dynamic positioning. In the optimization task, a goal function with a penalty was proposed with a variable prediction step. The results of the proposed control algorithm were compared with backstepping and PID. The effect of estimation accuracy on the control quality with the implemented algorithms was investigated....
-
Embedded Representations of Wikipedia Categories
PublicationIn this paper, we present an approach to building neural representations of the Wikipedia category graph. We test four different methods and examine the neural embeddings in terms of preservation of graphs edges, neighborhood coverage in representation space, and their influence on the results of a task predicting parent of two categories. The main contribution of this paper is application of neural representations for improving the...
-
On the problem of optimised allocation of water quality sensors and actuators in DWDS
PublicationThe problems of water quality sensors and actuators placement in drinking water distribution systems (DWDSs) are addressed as separate, primarily. However, against the background of control systems theory, the nature of DWDSs dynamics indicates that these both problems are interdependent and impact the design of related water quality monitoring and control structures and algorithms. The research work presented in this paper is...
-
Camera angle invariant shape recognition in surveillance systems
PublicationA method for human action recognition in surveillance systems is described. Problems within this task are discussed and a solution based on 3D object models is proposed. The idea is shown and some of its limitations are talked over. Shape description methods are introduced along with their main features. Utilized parameterization algorithm is presented. Classification problem, restricted to bi-nary cases is discussed. Support vector...
-
Pathological brain network activity: memory impairment in epilepsy
PublicationOur thinking, memory and cognition in general, relies upon precisely timed interactions among neurons forming brain networks that support cognitive processes. The surgical evaluation of drug-resistant epilepsy using intracranial electrodes provides a unique opportunity to record directly from human brain and to investigate the coordinated activity of cognitive networks. In this issue of Neurology®, Kleen and colleagues1 implicate...
-
Game with a Purpose for Mappings Verification
PublicationMappings verification is a laborious task. The paper presents a Game with a Purpose based system for verification of automatically generated mappings. General description of idea standing behind the games with the purpose is given. Description of TGame system, a 2D platform mobile game with verification process included in the gameplay, is provided. Additional mechanisms for anti-cheating, increasing player’s motivation and gathering...
-
Thermal imaging in automatic rodent’s social behaviour analysis
PublicationLaboratory rodent social behaviour analysis is an extremely important task for biological, medical and pharmacological researches. In this work thermal images features that facilitate analysis are presented. Methods to distinguish objects on the basis of thermal distribution are tested. Actions of grooming or biting one rodent by another - important social behaviour incidents - are clearly visible...
-
Limiting distribution of the three-state semi-Markov model of technical state transitions of ship power plant machines and its applicability in operational decision-making.
PublicationThe article presents the three-state semi-Markov model of the process {W(t): t 0} of state transitions of a ship power plant machine, with the following interpretation of these states: s1 – state of full serviceability, s2 – state of partial serviceability, and s3 – state of unserviceability. These states are precisely defined for the ship main engine (ME). A hypothesis is proposed which explains the possibility of application...
-
Long Distance Geographically Distributed InfiniBand Based Computing
PublicationCollaboration between multiple computing centres, referred as federated computing is becom- ing important pillar of High Performance Computing (HPC) and will be one of its key components in the future. To test technical possibilities of future collaboration using 100 Gb optic fiber link (Connection was 900 km in length with 9 ms RTT time) we prepared two scenarios of operation. In the first one, Interdisciplinary Centre for Mathematical...