Search
Filters
total: 6858
filtered: 5740
-
Catalog
Chosen catalog filters
displaying 1000 best results Help
Search results for: MACHINE LEARNING METHODS.
-
Innovative e-learning approach in teaching based on case studies - Innocase project
PublicationThe article presents the application of innovative e-learning approach for the creation of case study content. Case study methodology is becoming more and more widely applied in modern education, especially in business and management field. Although case study methodology is quite well recognized and used in education, there are still few examples of developing e-learning content on the basis of case studies. This task is to be...
-
Interpretable Deep Learning Model for the Detection and Reconstruction of Dysarthric Speech
PublicationWe present a novel deep learning model for the detection and reconstruction of dysarthric speech. We train the model with a multi-task learning technique to jointly solve dysarthria detection and speech reconstruction tasks. The model key feature is a low-dimensional latent space that is meant to encode the properties of dysarthric speech. It is commonly believed that neural networks are black boxes that solve problems but do not...
-
Examining Influence of Distance to Microphone on Accuracy of Speech Recognition
PublicationThe problem of controlling a machine by the distant-talking speaker without a necessity of handheld or body-worn equipment usage is considered. A laboratory setup is introduced for examination of performance of the developed automatic speech recognition system fed by direct and by distant speech acquired by microphones placed at three different distances from the speaker (0.5 m to 1.5 m). For feature extraction from the voice signal...
-
Deep neural networks approach to skin lesions classification — A comparative analysis
PublicationThe paper presents the results of research on the use of Deep Neural Networks (DNN) for automatic classification of the skin lesions. The authors have focused on the most effective kind of DNNs for image processing, namely Convolutional Neural Networks (CNN). In particular, three kinds of CNN were analyzed: VGG19, Residual Networks (ResNet) and the hybrid of VGG19 CNN with the Support Vector Machine (SVM). The research was carried...
-
Parallel Background Subtraction in Video Streams Using OpenCL on GPU Platforms
PublicationImplementation of the background subtraction algorithm using OpenCL platform is presented. The algorithm processes live stream of video frames from the surveillance camera in on-line mode. Processing is performed using a host machine and a parallel computing device. The work focuses on optimizing an OpenCL algorithm implementation for GPU devices by taking into account specific features of the GPU architecture, such as memory access,...
-
Examination method of the effect of the incidence angle of laser beam on distance measurement accuracy to surfaces with different colour and roughness
PublicationInterest in the influence of the incidence angle of a laser beam to distance measurements can be seen in many areas of science and technology: geodesy, glaciology, archaeology, machine automation, and others. This paper presents results of measurements of the effect of the incidence angle of a laser beam to distance measurements to the surfaces of different colour and roughness by Topcon's electro-optical total station with an...
-
Experimental ultimate strength assessment of stiffened plates subjected to marine immersed corrosion
PublicationThis study experimentally analyses the impact of marine immersed corrosion degradation on the compressive strength of the stiffened plates where the lower degradation levels were considered. The corrosion degradation test was accelerated by controlling the natural corrosion environmental factors, avoiding applying an electric current. Different groups of corrosion degradation levels and initial plate thicknesses were investigated....
-
Dead time effects compensation strategy by third harmonic injection for a five-phase inverter
PublicationThis paper proposes a method for compensation of dead-time effects for a fivephase inverter. In the proposed method an additional control subsystem was added to the field-oriented control (FOC) scheme in the coordinate system mapped to the third harmonic. The additional control loop operates in the fixed, orthogonal reference frame ( α - β coordinates) without the need for additional Park transformations. The purpose of this method...
-
Chemical and Mechanical Properties of 70-Year-Old Concrete
PublicationThe aim of this research is to determine the durability and strength of concrete continuous footing based on the chosen mechanical, physical, and chemical properties of the concrete. The presented investigations constitute some opinions from experts on the bearing capacity of concrete continuous footing and the possibilities of carrying additional loads and extended working life. The cylindrical specimens were taken from continuous...
-
Experimental investigations of damage evolution in concrete during bending by continuous micro-CT scanning
PublicationThe paper describes experimental investigation results of fracture in notched concrete beams under quasi-static three-point bending. To visualize 3D fracture in concrete under bending, an extended X-ray micro-computed tomography system was used, i.e. the tomography system SkyScan 1173 was connected to the loading machine ISTRON 5569. This combined system enabled to shot images of deforming concrete beams during a continuous deformation...
-
Methods of ZnO nanoparticles synthesis
PublicationZinc oxide nanostructures are interesting nanomaterials with a wide range of applications. Since the physical and chemical properties of ZnO nanoparticles are influenced both by their shape and size, a control of morphology of ZnO structures is needed for their commercial usage. Different chemical, physical, and biological methods used to produce ZnO nanostructures can be found in the literature. The production of ZnO nanoparticles...
-
Total Completion Time Minimization for Scheduling with Incompatibility Cliques
PublicationThis paper considers parallel machine scheduling with incompatibilities between jobs. The jobs form a graph equivalent to a collection of disjoint cliques. No two jobs in a clique are allowed to be assigned to the same machine. Scheduling with incompatibilities between jobs represents a well-established line of research in scheduling theory and the case of disjoint cliques has received increasing attention in recent...
-
Underground Water Level Prediction in Remote Sensing Images Using Improved Hydro Index Value with Ensemble Classifier
PublicationThe economic sustainability of aquifers across the world relies on accurate and rapid estimates of groundwater storage changes, but this becomes difficult due to the absence of insitu groundwater surveys in most areas. By closing the water balance, hydrologic remote sensing measures offer a possible method for quantifying changes in groundwater storage. However, it is uncertain to what extent remote sensing data can provide an...
-
Mechanical response of human thoracic spine ligaments under quasi-static loading: An experimental study
PublicationPurpose This study aimed to investigate the geometrical and mechanical properties of human thoracic spine ligaments subjected to uniaxial quasi-static tensile test. Methods Four human thoracic spines, obtained through a body donation program, were utilized for the study. The anterior longitudinal ligament (ALL), posterior longitudinal ligament (PLL), capsular ligament (CL), ligamenta flava (LF), and the interspinous ligament and...
-
Towards Scalable Simulation of Federated Learning
PublicationFederated learning (FL) allows to train models on decentralized data while maintaining data privacy, which unlocks the availability of large and diverse datasets for many practical applications. The ongoing development of aggregation algorithms, distribution architectures and software implementations aims for enabling federated setups employing thousands of distributed devices, selected from millions. Since the availability of...
-
Organizational Wisdom: The Impact of Organizational Learning on the Absorptive Capacity of an Enterprise
PublicationPurpose: In this article, we analyze the concept of organizational wisdom, indicating its key elements and verifieng the relationships between them. Design/Methodology/Approach: The study was conducted at Vive Textile Recycling Sp. z o.o in Poland. Empirical data was collected from 138 managers using the PAPI technique. Structural equation modelling (SEM) was performed to test the research hypotheses. Additionally, the significance...
-
Colossus from Algebron – Gamification as a Tool to Engage Students in Learning Mathematics
PublicationGamification is a tool that allows for high engagement in performing tasks that have been previously considered difficult or uninteresting. It works exceptionally well in education as it supports students in developing habits of learning and provides them with a visual representation of their progress in acquiring knowledge and skills. Skillful design of gamified academic courses enables the achievement of educational goals set...
-
CE-MS and GC-MS as “Green” and Complementary Methods for the Analysis of Biogenic Amines in Wine
PublicationTwo novel complementary analytical methods, namely an extraction-free capillary electrophoresis coupled to mass spectrometry (CE-MS) and direct immersion-solid-phase microextraction combined with gas chromatography-mass spectrometry (DI-SPME-GC-MS), have been developed and successfully applied for the determination of biogenic amines (BAs) in wine and fruit wine. They have been rigorously compared to each other in terms of various...
-
Z type Observer Backstepping For Induction Machines
PublicationThis paper contains a relatively new synthesis method for non-linear objects, named backstepping. This method can be used to obtain the observer structure. The paper presents the structure of the speed observer which is a new proposition of observer backstepping with additional state variables marked Z. The rotor speed can be estimated in three different ways. The first is based on the adaptive approach, the second on the nonadaptive...
-
The effect of a belt position in the spindle driving system on critical rotational speeds
PublicationThe aim of this paper was to examine how the belt pulley position affects critical rotational speeds of the modernized spindle of the sliding table saw Fx3. Methodology of determination of critical rotational speeds of the spindle in a function of the spindle design features and its driving system is presented. Spindles in these kind of machine tools are mainly driven with V-belts, and the pulleys on the spindles might be positioned:...
-
Domestic ORC micro-CHP combined with a commercial gas boiler
PublicationThe chapter presents the results of experimental studies conducted during the launch of the first in Poland demonstration prototype of the micro ORC coupled to a domestic gas boiler. The accomplished studies indicated the possibility for the ORC module to work with such boiler (autonomous source of heat) with a prototype single-stage axial micro turbine as the expansion machine. Confirmation of that fact has been delineated in...
-
CUTTING POWER FORECASTING WHILE WOOD SAWING: FRACTURE MECHANICS APPROACH AND AXELSSON’S MODEL COMPARISON
PublicationIn the classical approach, energetic effects (cutting forces and cutting power) of wood sawing process are generally calculated on the basis of the specific cutting resistance, which is in the case of wood cutting the function of more or less important factors. On the other hand, cutting forces (power) could be considered from a point of view of modern fracture mechanics. Another way is to forecast cutting power consumption on...
-
Sensorless low speed PMSM motor control with cogging torque compensation
PublicationThe paper presents sensorless control of a low speed permanent magnet synchronous machine with use of modified state observer. An overview of the PMSM motor used in the research setup was presented. The problem of drive torque ripple, resulting mainly from the occurrence of a significant cogging torque, was discussed. A solution compensating the torque ripple of the PMSM motor was proposed. A start-up procedure of the speed control...
-
INFLUENCE OF TACK WELDS DISTRIBUTION AND WELDING SEQUENCE ON THE ANGULAR DISTORTION OF TIG WELDED JOINT
PublicationIn this paper the influence of tack welds distribution and welding sequence on angular distortion of the Tungsten Inert Gas (TIG) welded joint was tested. Additionally, the effect of welding current on angular distortion was assessed. For research X2CrTiNb18 (AISI 441) stainless steel (2.5 mm thick) was chosen. During research specimens were prepared with different distributionsof tack...
-
DESIGN AND THEORETICAL ANALYSIS OF A PROTOTYPE TILTING-PAD RADIAL BEARING WITH ADJUSTABLE CLEARANCE
PublicationThe article introduces a design and analysis results of a prototype ORC (organic Rankine cycle) turbo generator rotor assembly of 300kW power, supported by tilting-pad bearings of original design. The calculations were performed for a prototype turbo generator rotor. The shaft of this machine is supported with two radial bearings, lubricated with an unusual lubricant – a low-boiling-point agent. The main objective of the presented...
-
I, Robot: between angel and evil
PublicationThe boosting of most digital innovations within recent technology progress by artificial intelligence (AI) constitutes a growing topic of interest. Besides its technical aspects, increasing research activity may be observed in the domain of security challenges, and therefore of responsibility related to the controlled or hypothetically uncontrolled or autonomous emergence of AI solutions. Consequently, responsibility and ethics...
-
A Highly Scalable, Modular Architecture for Computer Aided Assessment e-Learning Systems
PublicationIn this chapter, the authors propose a novel e-learning system, dedicated strictly to knowledge assessment tasks. In its functioning it utilizes web-based technologies, but its design differs radically from currently popular e-learning solutions which rely mostly on thin-client architecture. The authors' research proved that such architecture, while well suited for didactic content distribution systems is ill-suited for knowledge...
-
Continuous learning as a method of raising qualifications – the perspective of workers, employers and training organizations
PublicationContinuous learning is discussed in strategic documents of Poland and the European Union. In Poland, the idea of continuous learning is not very popular. However, in the context of strong competition in the labour market and the progressive globalization processes, the skills issue takes on new meaning — both for employees and employers. In order to adapt skills to labour market needs it is necessary to conduct adequate studies...
-
Application of analytical methods for the determination of bioactive compounds in some berries
PublicationFluorometry, ESI-MS, FTIR, and radical scavenging assays were used for characterization of bioactive compounds and the levels of their antioxidant activities. Polyphenols, flavonoids, anthocyanins, and ascorbic acid and the level of antioxidant activity of water extracts of “Murtilla-like” [Myrteola nummularia (Poiret) Berg.], and other widely consumed berries were determined and compared. The contents of bioactive compounds and...
-
Visual Content Learning in a Cognitive Vision Platform for Hazard Control (CVP-HC)
PublicationThis work is part of an effort for the development of a Cognitive Vision Platform for Hazard Control (CVP-HC) for applications in industrial workplaces, adaptable to a wide range of environments. The paper focuses on hazards resulted from the nonuse of personal protective equipment (PPE). Given the results of previous analysis of supervised techniques for the problem of classification of a few PPE (boots, hard hats, and gloves...
-
Divide and not forget: Ensemble of selectively trained experts in Continual Learning
PublicationClass-incremental learning is becoming more popular as it helps models widen their applicability while not forgetting what they already know. A trend in this area is to use a mixture-of-expert technique, where different models work together to solve the task. However, the experts are usually trained all at once using whole task data, which makes them all prone to forgetting and increasing computational burden. To address this limitation,...
-
Review on Wikification methods
PublicationThe paper reviews methods on automatic annotation of texts with Wikipedia entries. The process, called Wikification aims at building references between concepts identified in the text and Wikipedia articles. Wikification finds many applications, especially in text representation, where it enables one to capture the semantic similarity of the documents. Also, it can be considered as automatic tagging of the text. We describe typical...
-
Color transformation methods for dichromats
PublicationColor blindness is a serious perception problem. Suffering individuals cannot understand messages, which are carrying by many images, especially those, distributed by WWW. In this paper we are proposing three image processing methods to enhance image recognition and understanding by persons with dichromacy. Color difference image is introduced to represent color perception dissimilarity. Two color transformation methods are presented....
-
The 3D scanning system for the machine vision based positioning of workpieces on the CNC machine tools
Publication -
Feature Reduction Using Similarity Measure in Object Detector Learning with Haar-like Features
PublicationThis paper presents two methods of training complexity reduction by additional selection of features to check in object detector training task by AdaBoost training algorithm. In the first method, the features with weak performance at first weak classifier building process are reduced based on a list of features sorted by minimum weighted error. In the second method the feature similarity measures are used to throw away that features...
-
The Toolbox of Methods for Multidirectional Characterization of Dietary Nucleic Acids; Verification for Raw and Processed Food Products
PublicationCurrently, the nutritional value of food is associated mainly with components such as proteins, carbohydrates, and lipids. However, another important macromolecules present in many foods are dietary nucleic acids (dietNA), i.e., DNA as well as both coding and non-coding RNAs. In the context of food chemistry and nutrition, dietNA are nowadays vastly neglected. In consequence, there are no dedicated methodologies to characterize...
-
Optimizing Construction Engineering Management Using Metaheuristic Methods and Bayesian Networks
PublicationThe construction of buildings invariably involves time and costs, and disruptions impact ongoing construction projects. Crisis situations in management strategies, structural confusion, and finan-cial miscalculations often arise due to misguided decision-making. This article proposes a method that combines the learning of Bayesian Networks and heuristic techniques to optimize deci-sion-making processes in construction scheduling....
-
Deep-Learning-Based Precise Characterization of Microwave Transistors Using Fully-Automated Regression Surrogates
PublicationAccurate models of scattering and noise parameters of transistors are instrumental in facilitating design procedures of microwave devices such as low-noise amplifiers. Yet, data-driven modeling of transistors is a challenging endeavor due to complex relationships between transistor characteristics and its designable parameters, biasing conditions, and frequency. Artificial neural network (ANN)-based methods, including deep learning...
-
Methods of material parameters identification for isotropic damage in viscoplastic flow conditions
PublicationW pracy zaprezentowano trzy metody identyfikacji parametrów materiałowych dla izotropowego zniszczenia w warunkach lepkoplastycznego płynięcia. Przedstawiono wyniki identyfikacji dla dwóch stopów aluminium, które następnie zweryfikowano porównując wyniki symulacji numerycznych z wynikami eksperymentalnymi.
-
Computational intelligence methods in production management
PublicationThis chapter presents a survey of selected computational intelligence methods used in production management. This group of methods includes, among others, approaches based on the artificial neural networks, the evolutionary algorithms, the fuzzy logic systems and the particle swarm optimization mechanisms. From the abovementioned methods particularly noteworthy are the evolutionary and the particle swarm algorithms, which are successfully...
-
Review of titanium and steel welding methods
PublicationThe paper presents review of methods of titanium and steel welding. On basis of professional literature it was stated that titanium can be joined with steel by means of explosive welding or brazing.Joining titanium with steel by TIG welding and friction welding methods is possible with the use of copper and tantalum or vanadium interlayer.
-
A new open-source software developed for numerical simulations usingdiscrete modeling methods
PublicationThe purpose of this work is to present the development of an open-source software based on a discrete description of matter applied to study the behavior of geomaterials. This software uses Object Oriented Programming techniques, and its methodology design uses three different methods, which are the Discrete Element Method (DEM) [F. Donzé, S.A. Magnier, Formulation of a three-dimensional numerical model of brittle behavior, Geophys....
-
Computational Simulation of the Effects of Different Culture Types and Leader Qualities on Mistake Handling and Organisational Learning
PublicationThis chapter investigates computationally the following research hypotheses: (1) Higher flexibility and discretion in organisational culture results in better mistake management and thus better organisational learning, (2) Effective organisational learning requires a transformational leader to have both high social and formal status and consistency, and (3) Company culture and leader’s behavior must align for the best learning...
-
Deep Learning-Based Intrusion System for Vehicular Ad Hoc Networks
PublicationThe increasing use of the Internet with vehicles has made travel more convenient. However, hackers can attack intelligent vehicles through various technical loopholes, resulting in a range of security issues. Due to these security issues, the safety protection technology of the in-vehicle system has become a focus of research. Using the advanced autoencoder network and recurrent neural network in deep learning, we investigated...
-
COMPARISON OF BLOOD PRESSURE PREDICTION METHODS
PublicationIn the paper dierent approaches of predicting blood pressure values are presented. Basically, two methods and theirs modifications are considered. In total, seven algorithms have been examined. Tests have been conducted using both synthetic and clinical data. From our study it follows that none of the examined methods is superior to other.
-
General concept of functional safety - standarisation and sector aspects
PublicationRozdział poświęcono koncepcji bezpieczeństwa funkcjonalnego. Bezpieczeństwo funkcjonalne jest częścią bezpieczeństwa całkowitego zależną od odpowiedniej odpowiedzi systemów sterowania i/lub zabezpieczeń na sygnały wejściowe podczas wystąpienia stanów nienormalnych maszyny, instalacji lub obiektu podwyższonego ryzyka. Koncepcja bezpieczeństwa funkcjonalnego przedstawiona w normie IEC 51508 stanowi przykład dobrej praktyki inżynierskiej...
-
An integrated e-learning services management system providing HD videoconferencing and CAA services
PublicationIn this paper we present a novel e-learning services management system, designed to provide highly modifiable platform for various e-learning tools, able to fulfill its function in any network connectivity conditions (including no connectivity scenario). The system can scale from very simple setup (adequate for servicing a single exercise) to a large, distributed solution fit to support an enterprise. Strictly modular architecture...
-
Deep learning for ultra-fast and high precision screening of energy materials
PublicationSemiconductor materials for energy storage are the core and foundation of modern information society and play important roles in photovoltaic system, integrated circuit, spacecraft technology, lighting applications, and other fields. Unfortunately, due to the long experiment period and high calculation cost, the high-precision band gap (the basic characteristic parameter) of semiconductor is difficult to obtain, which hinders the...
-
The Methods for RTS Noise Identification
PublicationIn the paper authors present two methods, which allows to identify the RTS noise in noise signal of semiconductor devices. The first one was elaborated to identify the RTS noise and also to estimate the number of its levels. The second one can be used to estimate all of the parameters of Gaussian and non-Gaussian components in the noise signal in a frequency domain.
-
Wisdom from Experience Paradox: Organizational Learning, Mistakes, Hierarchy and Maturity Issues
PublicationOrganizations often perceive mistakes as negligence and low-performance indicators, yet they can be a precious learning resource. However, organizations cannot learn from mistakes if they have not accepted them. This study aimed to explore how organizational hierarchy and maturity levels influence the relationship between mistakes acceptance and the ability to change. A sample composed of 380 Polish employees working in knowledge-driven...