Wyszukiwarka
Filtry
wszystkich: 4340
-
Katalog
- Publikacje 3500 wyników po odfiltrowaniu
- Czasopisma 186 wyników po odfiltrowaniu
- Konferencje 31 wyników po odfiltrowaniu
- Osoby 84 wyników po odfiltrowaniu
- Projekty 11 wyników po odfiltrowaniu
- Kursy Online 83 wyników po odfiltrowaniu
- Wydarzenia 9 wyników po odfiltrowaniu
- Dane Badawcze 436 wyników po odfiltrowaniu
wyświetlamy 1000 najlepszych wyników Pomoc
Wyniki wyszukiwania dla: ACTIVE LEARNING ALGORITHM
-
Analyzing the relationship between sound, color, and emotion based on subjective and machine-learning approaches
PublikacjaThe aim of the research is to analyze the relationship between sound, color, and emotion. For this purpose, a survey application was prepared, enabling the assignment of a color to a given speaker’s/singer’s voice recordings. Subjective tests were then conducted, enabling the respondents to assign colors to voice/singing samples. In addition, a database of voice/singing recordings of people speaking in a natural way and with expressed...
-
Bimodal deep learning model for subjectively enhanced emotion classification in films
PublikacjaThis research delves into the concept of color grading in film, focusing on how color influences the emotional response of the audience. The study commenced by recalling state-of-the-art works that process audio-video signals and associated emotions by machine learning. Then, assumptions of subjective tests for refining and validating an emotion model for assigning specific emotional labels to selected film excerpts were presented....
-
Deep learning based thermal image segmentation for laboratory animals tracking
PublikacjaAutomated systems for behaviour classification of laboratory animals are an attractive alternative to manual scoring. However, the proper animals separation and tracking, especially when they are in close contact, is the bottleneck of the behaviour analysis systems. In this paper, we propose a method for the segmentation of thermal images of laboratory rats that are in close contact during social behaviour tests. For this, we are...
-
An optimized system for sensor ontology meta-matching using swarm intelligent algorithm
PublikacjaIt is beneficial to annotate sensor data with distinct sensor ontologies in order to facilitate interoperability among different sensor systems. However, for this interoperability to be possible, comparable sensor ontologies are required since it is essential to make meaningful links between relevant sensor data. Swarm Intelligent Algorithms (SIAs), namely the Beetle Swarm Optimisation Algorithm (BSO), present a possible answer...
-
Pareto Ranking Bisection Algorithm for Expedited Multi-Objective Optimization of Antenna Structures
PublikacjaThe purpose of this letter is introduction of a novel methodology for expedited multi-objective design of antenna structures. The key component of the presented approach is fast identification of the initial representation of the Pareto front (i.e., a set of design representing the best possible trade-offs between conflicting objectives) using a Pareto-ranking bisection algorithm. The algorithm finds a discrete set of Pareto-optimal...
-
Convex set of quantum states with positive partial transpose analysed by hit and run algorithm
PublikacjaThe convex set of quantum states of a composite K×K system with positive partial transpose is analysed. A version of the hit and run algorithm is used to generate a sequence of random points covering this set uniformly and an estimation for the convergence speed of the algorithm is derived. For K >3 or K=3 this algorithm works faster than sampling over the entire set of states and verifying whether the partial transpose is positive....
-
Supporting First Year Students Through Blended-Learning - Planning Effective Courses and Learner Support
PublikacjaHigher education has been actively encouraged to find more effective and flaxible delivery models to provide all students with access to good quality learning experiences. This paper describes students opinion about using e-learning techniques and their participation in courses provided in different ways as additional help and expectations of first year students.
-
Evolutionary algorithm and decisional DNA for multiple travelling salesman problem
PublikacjaIn the real world, it is common to face optimization problems that have two or more objectives that must be optimized at the same time, that are typically explained in different units, and are in conflict with one another. This paper presents a hybrid structure that combines set of experience knowledge structures (SOEKS) and evolutionary algorithms, NSGA-II (Non-dominated Sorting Genetic Algorithm II), to solve multiple optimization...
-
Hardware implementation of digital image stabilization using optical flow algorithm and FPGA technology
PublikacjaW artykule przedstawiono efektywną procedurę uproszczenia algorytmu przepływu optycznego oraz jego realizację w układzie programowalnym FPGA. Zmodyfikowany algorytm wykorzystuję metodę blokowego dopasowania podobszarów oraz jednowymiarową reprezentację podobszarów. Dodatkowo, funkcja korelacji oparta jest o normę L1. W rezultacie uzyskano zmniejszenie zużytych zasobów kosztem nieznacznej utraty dokładności. Zarówno dokładność,...
-
Vident-real: an intra-oral video dataset for multi-task learning
Dane BadawczeWe introduce Vident-real, a large dataset of 100 video sequences of intra-oral scenes from real conservative dental treatments performed at the Medical University of Gdańsk, Poland. The dataset can be used for multi-task learning methods including:
-
Variable Resolution Machine Learning Optimization of Antennas Using Global Sensitivity Analysis
PublikacjaThe significance of rigorous optimization techniques in antenna engineering has grown significantly in recent years. For many design tasks, parameter tuning must be conducted globally, presenting a challenge due to associated computational costs. The popular bio-inspired routines often necessitate thousands of merit function calls to converge, generating prohibitive expenses whenever the design process relies on electromagnetic...
-
Adaptive Dynamical Systems Modelling of Transformational Organizational Change: with Focus on Organizational Culture and Organizational Learning
PublikacjaTransformative Organizational Change becomes more and more significant both practically and academically, especially in the context of organizational culture and learning. However computational modeling and a formalization of organizational change and learning processes are still largely unexplored. This paper aims to provide an adaptive network model of transformative organizational change and translate a selection of organizational...
-
Adaptive Dynamical Systems Modelling of Transformational Organizational Change with Focus on Organizational Culture and Organizational Learning
PublikacjaTransformative Organizational Change becomes more and more significant both practically and academically, especially in the context of organizational culture and learning. However computational modeling and a formalization of organizational change and learning processes are still largely unexplored. This paper aims to provide an adaptive network model of transformative organizational change and translate a selection of organizational...
-
A new approach to active noise and vibration control - [Part II: unknown frequency case]
PublikacjaThis paper presents a new approach to rejection of complex-valued sinusoidal disturbances acting at the output of a discrete-time stable linear plant with unknown and possibly timevarying dynamics. It is assumed that both the instantaneous frequency of the sinusoidal disturbance and its amplitude may be slowly varying with time and that the output signal is contaminated with wideband measurement noise. It is not assumed that a...
-
Open source solution LMS for supporting e-learning/blended learning engineers
PublikacjaW artykule zaprezentowano darmowe systemy zarządzania kształceniem na odległość wspomagające e-learningowe/mieszane nauczanie inżynierów. Pierwszy system TeleCAD został opracowany w ramach projektu Leonardo da Vinci (1998-2001). System TeleCAD był propozycją w projekcie V Ramowy CURE (2003-2006). W roku 2003 dzięki projektowi Leonardo da Vinci EMDEL (2001-2005) Centrum Edukacji Niestacjonarnej Politechniki Gdańskiej wybrało system...
-
An facile Fortran-95 algorithm to simulate complex instabilities in three-dimensional hyperbolic systems
Dane BadawczeIt is well know that the simulation of fractional systems is a difficult task from all points of view. In particular, the computer implementation of numerical algorithms to simulate fractional systems of partial differential equations in three dimensions is a hard task which has no been solved satisfactorily. Here, we provide a Fortran-95 code to solve...
-
Obtaining a Well-Trained Artificial Intelligence Algorithm from Cross-Validation in Endoscopy
PublikacjaThe article shortly discusses endoscopic video analysis problems and artificial intelligence algorithms supporting it. The most common method of efficiency testing of these algorithms is to perform intensive cross-validation. This allows for accurately evaluate their performance of generalization. One of the main problems of this procedure is that there is no simple and universal way of obtaining a specific instance of a well-trained...
-
Journal of Biologically Active Products from Nature
Czasopisma -
Structured deformation of granular material in the state of active earth pressure
PublikacjaThe paper focuses on the ability of granular materials to undergo structured deformation by analysing the data from the retaining wall model tests and discrete element simulations. The structured deformation means the movement of a granular material which produces a stable, regular pattern of multiple shear bands. The paper's primary purpose is to study this kind of deformation for the selected data representing the state of active...
-
Cost-Efficient Multi-Objective Design of Miniaturized Microwave Circuits Using Machine Learning and Artificial Neural Network
PublikacjaDesigning microwave components involves managing multiple objectives such as center frequencies, impedance matching, and size reduction for miniaturized structures. Traditional multi-objective optimization (MO) approaches heavily rely on computationally expensive population-based methods, especially when exe-cuted with full-wave electromagnetic (EM) analysis to guarantee reliability. This paper introduces a novel and cost-effective...
-
Efficient algorithm for blinking LED detection dedicated to embedded systems equipped with high performance cameras
PublikacjaThis paper presents the concept and implementation of an efficient algorithm for detection of blinking LED or similar signal sources. Algorithm is designed for embedded devices equipped with high performance cameras being a part of an indoor positioning embedded system. An algorithm to be implemented in such a system should be efficient in terms of computational power what is hard to be achieved when large amount of data from camera...
-
Enhanced switched parasitic antenna with switched active monopoles for indoor positioning systems
PublikacjaThis paper presents the concept of enhanced reduced-size steerable antenna array with two rows of switched active and passive elements. Designed array is similar to ESPAR antenna but it has a set of switched monopoles instead of central one. It is intended for 2.4 GHz ISM applications with emphasis on indoor positioning systems (IPS). Proposed antenna provides improved radiation parameters and reduced dimensions in comparison to...
-
Distance learning trends: introducing new solutions to data analysis courses
PublikacjaNowadays data analysis of any kind becomes a piece of art. The same happens with the teaching processes of statistics, econometrics and other related courses. This is not only because we are facing (and are forced to) teach online or in a hybrid mode. Students expect to see not only the theoretical part of the study and solve some practical examples together with the instructor. They are waiting to see a variety of tools, tutorials,...
-
LOS and NLOS identification in real indoor environment using deep learning approach
PublikacjaVisibility conditions between antennas, i.e. Line-of-Sight (LOS) and Non-Line-of-Sight (NLOS) can be crucial in the context of indoor localization, for which detecting the NLOS condition and further correcting constant position estimation errors or allocating resources can reduce the negative influence of multipath propagation on wireless communication and positioning. In this paper a deep learning (DL) model to classify LOS/NLOS...
-
Experimental and Machine-Learning-Assisted Design of Pharmaceutically Acceptable Deep Eutectic Solvents for the Solubility Improvement of Non-Selective COX Inhibitors Ibuprofen and Ketoprofen
PublikacjaDeep eutectic solvents (DESs) are commonly used in pharmaceutical applications as excellent solubilizers of active substances. This study investigated the tuning of ibuprofen and ketoprofen solubility utilizing DESs containing choline chloride or betaine as hydrogen bond acceptors and various polyols (ethylene glycol, diethylene glycol, triethylene glycol, glycerol, 1,2-propanediol, 1,3-butanediol) as hydrogen bond donors. Experimental...
-
Experimental and Machine-Learning-Assisted Design of Pharmaceutically Acceptable Deep Eutectic Solvents for the Solubility Improvement of Non-Selective COX Inhibitors Ibuprofen and Ketoprofen
PublikacjaDeep eutectic solvents (DESs) are commonly used in pharmaceutical applications as excellent solubilizers of active substances. This study investigated the tuning of ibuprofen and ketoprofen solubility utilizing DESs containing choline chloride or betaine as hydrogen bond acceptors and various polyols (ethylene glycol, diethylene glycol, triethylene glycol, glycerol, 1,2-propanediol, 1,3-butanediol) as hydrogen bond donors. Experimental...
-
Solubility of dapsone in deep eutectic solvents: Experimental analysis, molecular insights and machine learning predictions
PublikacjaBackground. Dapsone (DAP) is an anti-inflammatory and antimicrobial active pharmaceutical ingredient used to treat, e.g., AIDS-related diseases. However, low solubility is a feature hampering its efficient use. Objectives. First, deep eutectic solvents...
-
Quantitative Risk Assessment in Construction Disputes Based on Machine Learning Tools
PublikacjaA high monetary value of the construction projects is one of the reasons of frequent disputes between a general contractor (GC) and a client. A construction site is a unique, one-time, and single-product factory with many parties involved and dependent on each other. The organizational dependencies and their complexity make any fault or mistake propagate and influence the final result (delays, cost overruns). The constant will...
-
Detecting Lombard Speech Using Deep Learning Approach
PublikacjaRobust 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...
-
Implementation of magnitude calculation of complex numbers using improved alpha max plus beta min algorithm
PublikacjaThe paper presents the hardware implementation of the improved alpha max plus beta min algorithm for calculating the magnitude of complex numbers. This version of the algorithm requires the general division which is performed using a noniterative multiplicative division algorithm. We analyze in detail the division algorithm, its error and the impact of finite word-length signal representations on the assumed total computation error....
-
FPGA-Based Implementation of Real Time Optical Flow Algorithm and Its Applications for Digital Image Stabilization
PublikacjaAn efficient simplification procedure of the optical flow (OF) algorithm as well as its hardware implementation using the field programmable gate array (FPGA) technology is presented. The modified algorithm is based on block matching of subsets of successive frames, and exploits one-dimensional representation of subsets as well as the adaptive adjustments of their sizes. Also, an l1-norm-based correlation function requiring no...
-
An optimal nonlinear fractional order controller for passive/active base isolation building equipped with friction-tuned mass dampers
PublikacjaThis paper presents an optimal nonlinear fractional-order controller (ONFOC) designed to reduce the seismic responses of tall buildings equipped with a base-isolation (BI) system and friction-tuned mass dampers (FTMDs). The parameters for the BI and FTMD systems, as well as their combinations (BI-FTMD and active BI-FTMD or ABI-FTMD), were optimized separately using a multi-objective quantum-inspired seagull optimization algorithm...
-
User -friendly E-learning Platform: a Case Study of a Design Thinking Approach Use
PublikacjaE-learning systems are very popular means to support the teaching process today. These systems are mainly used by universities as well as by commercial training centres. We analysed several popular e-learning platforms used in Polish universities and find them very unfriendly for the users. For this reason, the authors began the work on the creation of a new system that would be not only useful, but also usable for students, teachers...
-
Selected anionic and cationic surface active agents determined in river sediments – the Klodnica catchment
PublikacjaSurface active agents (SAAs) are specific compounds that contain hydrophilic/ hydrophobic group in their molecules named as amphiphilic structures. According to charge on the hydrophilic part of surfactants they can be classified into three main groups: anionic, cationic and non-ionic compounds. Due to the amphiphilic structure of SAAs they have specific properties (e.g. ability to adsorption at different surfaces, reduction of...
-
Low-Cost Multi-Objective Optimization of Antennas By Means Of Generalized Pareto Ranking Bisection Algorithm
PublikacjaThis paper introduces a generalized Pareto ranking bisection algorithm for low-cost multi-objective design optimization of antenna structures. The algorithm allows for identifying a set of Pareto optimal sets of parameters (that represent the best trade-offs between considered objectives) by iterative partitioning of the intervals connecting previously found designs and executing a Pareto-ranking-based poll search. The initial...
-
The study on the appearance of deformation defects in the yacht lamination process using an AI algorithm and expert knowledge
PublikacjaThis article describes the application of the A-priori algorithm for defining the rule-based relationships between individual defects caused during the lamination process, affecting the deformation defect of the yacht shell. The data from 542 yachts were collected and evaluated. For the proper development of the algorithm, a technological process of the yacht lamination supported by expert decisions was described. The laminating...
-
Training of Deep Learning Models Using Synthetic Datasets
PublikacjaIn order to solve increasingly complex problems, the complexity of Deep Neural Networks also needs to be constantly increased, and therefore training such networks requires more and more data. Unfortunately, obtaining such massive real world training data to optimize neural networks parameters is a challenging and time-consuming task. To solve this problem, we propose an easy-touse and general approach to training deep learning...
-
Single-phase power electronics transformer with active functions for smart grid
PublikacjaThis paper presents the control of one cell of a modular single-phase power electronics transformer with active functions for meeting the smart grid concept. In this way, the converter could be used not only as a conventional transformer but also for grid such as reactive power, harmonic elimination and energy storage. The topology of the cell is composed by a bidirectional converter with three stages: a half bridge in the input...
-
A Self-Adaptive Complex Root Tracing Algorithm for the Analysis of Propagation and Radiation Problem
PublikacjaAn improved complex root tracing algorithm for radiation and propagation issues is proposed. The approach is based on a self-adaptive discretization of Cauchy’s argument principle for a C × R space and requires a reduced number of function calls in comparison to other procedures presented in the literature. A few different examples concerning propagation and radiation problems have been considered to verify the validity and efficiency...
-
INVESTIGATION OF THE LOMBARD EFFECT BASED ON A MACHINE LEARNING APPROACH
PublikacjaThe Lombard effect is an involuntary increase in the speaker’s pitch, intensity, and duration in the presence of noise. It makes it possible to communicate in noisy environments more effectively. This study aims to investigate an efficient method for detecting the Lombard effect in uttered speech. The influence of interfering noise, room type, and the gender of the person on the detection process is examined. First, acoustic parameters...
-
Hybrid evolutionary partitioning algorithm for heat transfer enhancement in VLSI circuits
PublikacjaW niniejszym artykule przedstawiono metodę pozwalającą na polepszenie transferu ciepła z układu scalonego do otoczenia poprzez zwiększenie liczby połączeń zewnętrznych, co pozwoliło na polepszenie przewodności cieplnej układu scalonego. Dla osiągnięcia tego celu opracowano nowy, hybrydowy, ewolucyjny algorytm podziału (ang. Hybrid Evolutionary Partitioning Algorithm - HEPA). Obliczenia przeprowadzone dla wybranych przykładów testowych...
-
Task Assignments in Logistics by Adaptive Multi-Criterion Evolutionary Algorithm with Elitist Selection
PublikacjaAn evolutionary algorithm with elitist selection has been developed for finding Pareto-optimal task assignments in logistics. A multi-criterion optimization problem has been formulated for finding a set of Pareto- optimal solutions. Three criteria have been applied for evaluation of task assignment: the workload of a bottleneck machine, the cost of machines, and the numerical performance of system. The machine constraints have...
-
Autonomous port management based AGV path planning and optimization via an ensemble reinforcement learning framework
PublikacjaThe rapid development of shipping trade pushes automated container terminals toward the direction of intelligence, safety and efficiency. In particular, the formulation of AGV scheduling tasks and the safety and stability of transportation path is an important part of port operation and management, and it is one of the basic tasks to build an intelligent port. Existing research mainly focuses on collaborative operation between...
-
Looking through the past: better knowledge retention for generative replay in continual learning
PublikacjaIn this work, we improve the generative replay in a continual learning setting to perform well on challenging scenarios. Because of the growing complexity of continual learning tasks, it is becoming more popular, to apply the generative replay technique in the feature space instead of image space. Nevertheless, such an approach does not come without limitations. In particular, we notice the degradation of the continually trained...
-
Utilization of a Non-Linear Error Function in a Positioning Algorithm for Distance Measurement Systems Designed for Indoor Environments
PublikacjaA new positioning algorithm for distance measurement systems is outlined herein. This algorithm utilizes a non-linear error function which allows us to improve the positioning accuracy in highly difficult indoor environments. The non-linear error function also allows us to adjust the performance of the algorithm to the particular environmental conditions. The well-known positioning algorithms have limitations, mentioned by their...
-
Underfrequency Load Shedding: An Innovative Algorithm Based on Fuzzy Logic
PublikacjaIn contemporary power systems, the load shedding schemes are typically based on disconnecting a pre-specified amount of load after the frequency drops below a predetermined value. The actual conditions at the time of disturbance may largely dier from the assumptions, which can lead to non-optimal or ineective operation of the load shedding scheme. For many years, increasing the eectiveness of the underfrequency load shedding (UFLS)...
-
Robust and Efficient Machine Learning Algorithms for Visual Recognition
PublikacjaIn visual recognition, the task is to identify and localize all objects of interest in the input image. With the ubiquitous presence of visual data in modern days, the role of object recognition algorithms is becoming more significant than ever and ranges from autonomous driving to computer-aided diagnosis in medicine. Current models for visual recognition are dominated by models based on Convolutional Neural Networks (CNNs), which...
-
An O ( n log n ) algorithm for finding edge span of cacti
PublikacjaLet G=(V,E) be a nonempty graph and xi be a function. In the paper we study the computational complexity of the problem of finding vertex colorings c of G such that: (1) |c(u)-c(v)|>=xi(uv) for each edge uv of E; (2) the edge span of c, i.e. max{|c(u)-c(v)|: uv belongs to E}, is minimal. We show that the problem is NP-hard for subcubic outerplanar graphs of a very simple structure (similar to cycles) and polynomially solvable for...
-
Evaluation of Machine Learning Methods for the Experimental Classification and Clustering of Higher Education Institutions
PublikacjaHigher education institutions have a big impact on the future of skills supplied on the labour market. It means that depending on the changes in labour market, higher education institutions are making changes to fields of study or adding new ones to fulfil the demand on labour market. The significant changes on labour market caused by digital transformation, resulted in new jobs and new skills. Because of the necessity of computer...
-
Systemy z Uczeniem Maszynowym / Systems with Machine Learning
Kursy Online