Search
Search results for: STATE-OF-ART
-
Implicit Space Mapping for Variable-Fidelity EM-Driven Design of Compact Circuits
PublicationSpace mapping (SM) belongs to the most successful surrogate-based optimization (SBO) methods in microwave engineering. Among available SM variations, implicit SM (ISM) is particularly attractive due to its simplicity and separation of extractable surrogate model parameters and design variables of the circuit/system at hand. Unlike other SM approaches, ISM exploits a set of preassigned parameters to align the surrogate with the...
-
Architectural Modifications to Enhance Steganalysis with Convolutional Neural Networks
PublicationThis paper investigates the impact of various modifications introduced to current state-of-the-art Convolutional Neural Network (CNN) architectures specifically designed for the steganalysis of digital images. Usage of deep learning methods has consistently demonstrated improved results in this field over the past few years, primarily due to the development of newer architectures with higher classification accuracy compared to...
-
Exploring Neural Networks for Musical Instrument Identification in Polyphonic Audio
PublicationThe purpose of this paper is to introduce neural network-based methods that surpass state-of-the-art (SOTA) models, either by training faster or having simpler architecture, while maintaining comparable effectiveness in musical instrument identification in polyphonic music. Several approaches are presented, including two authors’ proposals, i.e., spiking neural networks (SNN) and a modular deep learning model named FMCNN (Fully...
-
Design of a Cellular Dual-Band Sticker Antenna for Thickness-Independent 3D-Printed Substrates
PublicationAdditive manufacturing technology provides high flexibility in designing custom enclosures for prototype devices such as nodes of distributed sensor networks. Although integration of components is desired from the perspective of sensor mobility, it might negatively affect the performance of radio-connectivity due to couplings between the antenna and system peripherals, as well as other unaccounted effects of the 3D printed enclosure....
-
Top k Recommendations using Contextual Conditional Preferences Model
PublicationRecommender systems are software tools and techniques which aim at suggesting to users items they might be interested in. Context-aware recommender systems are a particular category of recommender systems which exploit contextual information to provide more adequate recommendations. However, recommendation engines still suffer from the cold-start problem, namely where not enough information about users and their ratings is available....
-
Pareto Ranking Bisection Algorithm for EM-Driven Multi-Objective Design of Antennas in Highly-Dimensional Parameter Spaces
PublicationA deterministic technique for fast surrogate-assisted multi-objective design optimization of antennas in highly-dimensional parameters spaces has been discussed. In this two-stage approach, the initial approximation of the Pareto set representing the best compromise between conflicting objectives is obtained using a bisection algorithm which finds new Pareto-optimal designs by dividing the line segments interconnecting previously...
-
Deep Features Class Activation Map for Thermal Face Detection and Tracking
PublicationRecently, capabilities of many computer vision tasks have significantly improved due to advances in Convolutional Neural Networks. In our research, we demonstrate that it can be also used for face detection from low resolution thermal images, acquired with a portable camera. The physical size of the camera used in our research allows for embedding it in a wearable device or indoor remote monitoring solution for elderly and disabled...
-
Modeling SARS‐CoV‐2 proteins in the CASP‐commons experiment
PublicationCritical Assessment of Structure Prediction (CASP) is an organization aimed at advancing the state of the art in computing protein structure from sequence. In the spring of 2020, CASP launched a community project to compute the structures of the most structurally challenging proteins coded for in the SARS-CoV-2 genome. Forty-seven research groups submitted over 3000 three-dimensional models and 700 sets of accuracy estimates on...
-
A Survey of Fast-Recovery Mechanisms in Packet-Switched Networks
PublicationIn order to meet their stringent dependability requirements, most modern packet-switched communication networks support fast-recovery mechanisms in the data plane. While reactions to failures in the data plane can be significantly faster compared to control plane mechanisms, implementing fast recovery in the data plane is challenging, and has recently received much attention in the literature. This survey presents a systematic,...
-
Polysaccharides in fabrication of membranes: A review
PublicationSustainability concerns have motivated and directed a great deal of interest over the past decade towards the development of green technologies. Polysaccharides are green polymers, which experienced growing demand to substitute chemically synthetic polymers. Different types of polysaccharides i.e. cellulose-, starch-, chitin- alginate-, and chitosan-based carbohydrate polymers have been applied in the fabrication of separation...
-
Fiber-optic sensors based on microspheres with nanocoatings (Zastosowanie mikrosfer optycznych z cienkowarstwowymi pokryciami w czujnikach światłowodowych)
PublicationTemperature is one of the most important physical quantities. Temperature measurements are used in every field of life, especially electronics, electrical engineering, energy-related fields, including energy source and storage devices. The goal of this dissertation is to design and optimize the microsphere-based fiber-optic sensors construction for measurement of the sensor surrounding medium temperature, including selection of...
-
A Triplet-Learnt Coarse-to-Fine Reranking for Vehicle Re-identification
PublicationVehicle re-identification refers to the task of matching the same query vehicle across non-overlapping cameras and diverse viewpoints. Research interest on the field emerged with intelligent transportation systems and the necessity for public security maintenance. Compared to person, vehicle re-identification is more intricate, facing the challenges of lower intra-class and higher inter-class similarities. Motivated by deep...
-
Numerical analysis of the container vessel's self-propulsion at different rudder deflection angles
PublicationNowadays, CFD becomes one of the most commonly used research method in ship hydrodynamics, limited to the analyses of hull resistance in calm water. With continuously improving computing power and increasingly more accurate numerical methods it is possible to simulate more complex cases. State of the art CFD tools also enable development of new ways of assessing ship maneuvering performance. This paper presents an attempt on...
-
Manufacturing Parameters, Materials, and Welds Properties of Butt Friction Stir Welded Joints–Overview
PublicationThe modern and eco-friendly friction stir welding (FSW) method allows the combination of even such materials that are considered to be non-weldable. The development of FSW technology in recent years has allowed a rapid increase in the understanding of the mechanism of this process and made it possible to perform the first welding trials of modern polymeric and composite materials, the joining of which was previously a challenge....
-
Light Symposium. Connecting health research with lighting practice
PublicationThanks to state-of-the-art medical and environmental research, our current understanding about the impact of light and lighting is improving at a rapid rate. While the evolution of lighting technologies offers promising design possibilities, it also poses new challenges to planners and the general public. This is further complicated by the fact that today’s modern indoor lifestyle means we can be completely disconnected from nature...
-
Cross-Lingual Knowledge Distillation via Flow-Based Voice Conversion for Robust Polyglot Text-to-Speech
PublicationIn this work, we introduce a framework for cross-lingual speech synthesis, which involves an upstream Voice Conversion (VC) model and a downstream Text-To-Speech (TTS) model. The proposed framework consists of 4 stages. In the first two stages, we use a VC model to convert utterances in the target locale to the voice of the target speaker. In the third stage, the converted data is combined with the linguistic features and durations...
-
Low-Cost Behavioral Modeling of Antennas by Dimensionality Reduction and Domain Confinement
PublicationBehavioral modeling has been rising in importance in modern antenna design. It is primarily employed to diminish the computational cost of procedures involving massive full-wave electromagnetic (EM) simulations. Cheaper alternative offer surrogate models, yet, setting up data-driven surrogates is impeded by, among others, the curse of dimensionality. This article introduces a novel approach to reduced-cost surrogate modeling of...
-
Motion Trajectory Prediction in Warehouse Management Systems: A Systematic Literature Review
PublicationBackground: In the context of Warehouse Management Systems, knowledge related to motion trajectory prediction methods utilizing machine learning techniques seems to be scattered and fragmented. Objective: This study seeks to fill this research gap by using a systematic literature review approach. Methods: Based on the data collected from Google Scholar, a systematic literature review was performed, covering the period from 2016...
-
Buried Object Characterization Using Ground Penetrating Radar Assisted by Data-Driven Surrogate-Models
PublicationThis work addresses artificial-intelligence-based buried object characterization using 3-D full-wave electromagnetic simulations of a ground penetrating radar (GPR). The task is to characterize cylindrical shape, perfectly electric conductor (PEC) object buried in various dispersive soil media, and in different positions. The main contributions of this work are (i) development of a fast and accurate data driven surrogate modeling...
-
Arterial cannula shape optimization by means of the rotational firefly algorithm
PublicationThe article presents global optimization results of arterial cannula shapes by means of the newly modified firefly algorithm. The search for the optimal arterial cannula shape is necessary in order to minimize losses and prepare the flow that leaves the circulatory support system of a ventricle (i.e. blood pump) before it reaches the heart. A modification of the standard firefly algorithm, the so-called rotational firefly algorithm,...
-
Genre-Based Music Language Modeling with Latent Hierarchical Pitman-Yor Process Allocation
PublicationIn this work we present a new Bayesian topic model: latent hierarchical Pitman-Yor process allocation (LHPYA), which uses hierarchical Pitman-Yor pr ocess priors for both word and topic distributions, and generalizes a few of the existing topic models, including the latent Dirichlet allocation (LDA), the bi- gram topic model and the hierarchical Pitman-Yor topic model. Using such priors allows for integration of -grams with a topic...
-
CSR in Family Business- Ethnocentric Meaning Socially Responsible?
PublicationThe aim of this paper is to provide framework and key issues relevant for research on social responsibility of family business. From providing two theoretical approaches towards social responsibility such as social capital concept commenting on the familiness as a family firm resource and capability; and the stakeholder theory we move to the state of the art of family business. Then, we discuss heterogeneity among family firms...
-
Principles and Developments of Solid-Phase Microextraction
PublicationSample preparation has been commonly considered a critical step of the analytical process. In this sense, remarkable efforts have been made to develop efficient sample preparation techniques which could overcome the limitations of conventional approaches. Since its inception in the early 1990’s, solid-phase microextraction (SPME) has become a widespread miniaturized sample preparation technique for extraction and preconcentration...
-
A design framework for rigorous constrained EM-driven optimization of miniaturized antennas with circular polarization
PublicationCompact radiators with circular polarization are important components of modern mobile communication systems. Their design is a challenging process which requires maintaining simultaneous control over several performance figures but also the structure size. In this work, a novel design framework for multi-stage constrained miniaturization of antennas with circular polarization is presented. The method involves sequential optimization...
-
Advances in olfaction-inspired biomaterials applied to bioelectronic noses
PublicationAmong all the senses, olfactory system of mammals is the least characterised as far as the mechanisms of odour identification are concerned. The results of recent investigations allow better understanding of the operation mechanism of the sense of smell. Progress in this field is crucial for the development of sensor technology based on olfaction-inspired biomaterials, which simulate the olfactory system of the biological counterparts....
-
Multitaper-Based Post-processing of Compact Antenna Responses Obtained in Non-anechoic Conditions
PublicationThe process of developing antenna structures typically involves prototype measurements. While accurate validation of far-field performance can be performed in dedicated facilities like anechoic chambers, high cost of construction and maintenance might not justify their use for teaching, or low-budget research scenarios. Non-anechoic experiments provide a cost-effective alternative, however the performance metrics obtained in such...
-
Comparison of 3D Point Cloud Completion Networks for High Altitude Lidar Scans of Buildings
PublicationHigh altitude lidar scans allow for rapid acquisition of big spatial data representing entire city blocks. Unfortunately, the raw point clouds acquired by this method are largely incomplete due to object occlusions and restrictions in scanning angles and sensor resolution, which can negatively affect the obtained results. In recent years, many new solutions for 3D point cloud completion have been created and tested on various objects;...
-
Bimodal Emotion Recognition Based on Vocal and Facial Features
PublicationEmotion recognition is a crucial aspect of human communication, with applications in fields such as psychology, education, and healthcare. Identifying emotions accurately is challenging, as people use a variety of signals to express and perceive emotions. In this study, we address the problem of multimodal emotion recognition using both audio and video signals, to develop a robust and reliable system that can recognize emotions...
-
Genre-Based Music Language Modeling with Latent Hierarchical Pitman-Yor Process Allocation
PublicationIn this work we present a new Bayesian topic model: latent hierarchical Pitman-Yor process allocation (LHPYA), which uses hierarchical Pitman-Yor pr ocess priors for both word and topic distributions, and generalizes a few of the existing topic models, including the latent Dirichlet allocation (LDA), the bi- gram topic model and the hierarchical Pitman-Yor topic model. Using such priors allows for integration of -grams with a topic model,...
-
Diffusible Hydrogen Control in Flux Cored Arc Welding Process
PublicationOne of the types of hydrogen degradation of steel welded joints is cold cracking. The direct cause of the formation of cold cracks is simultaneous presence of hydrogen, residual stresses and brittle structure. The way of preventing the occurring of degradation is to eliminate at least one of these factors. Practice has shown that the best solution is to control the amount of hydrogen in deposited metal. In this paper an experimental...
-
Entrepreneurship Vulnerability to Business Cycle. A New Methodology for Identification Pro-cyclical and Counter-cyclical Patterns of Entrepreneurial Activity
PublicationIn literature, there is ongoing discussion whether entrepreneurial activity, approximated by, for instance, changes in self-employment, tends to behave pro-cyclically, counter-cyclically or rather is a-cyclical. Thus far, both theoretical and empirical evidence, where various multiple methodological approaches are used, does not provide clear answer to the latter; while widely offered explanations are scattered and lack robustness....
-
Determination of aminoglycoside antibiotics: current status and future trends
PublicationThe use of aminoglycoside antibiotics is prevalent in medicine and agriculture. Their overuse increases their mobility in the environment, resulting in a need for reliable methods for their determination in a variety of matrices. However, the properties of aminoglycosides, in particular their high polarity, make the development of such methods a non-trivial task, inciting researchers to tackle this complex issue from different...
-
Electrodeposited Biocoatings, Their Properties and Fabrication Technologies: A Review
PublicationCoatings deposited under an electric field are applied for the surface modification of biomaterials. This review is aimed to characterize the state-of-art in this area with an emphasis on the advantages and disadvantages of used methods, process determinants, and properties of coatings. Over 170 articles, published mainly during the last ten years, were chosen, and reviewed as the most representative. The most recent developments...
-
Weakly-Supervised Word-Level Pronunciation Error Detection in Non-Native English Speech
PublicationWe propose a weakly-supervised model for word-level mispronunciation detection in non-native (L2) English speech. To train this model, phonetically transcribed L2 speech is not required and we only need to mark mispronounced words. The lack of phonetic transcriptions for L2 speech means that the model has to learn only from a weak signal of word-level mispronunciations. Because of that and due to the limited amount of mispronounced...
-
MobileNet family tailored for Raspberry Pi
PublicationWith the advances in systems-on-a-chip technologies, there is a growing demand to deploy intelligent vision systems on low-cost microcomputers. To address this challenge, much of the recent research has focused on reducing the model size and computational complexity of contemporary convolutional neural networks (CNNs). The state-of-the-art lightweight CNN is MobileNetV3. However, it was designed to achieve a good trade-off between...
-
Design and Implementation of a Dual-band Filtering Wil-kinson Power Divider Using Coupled T-shaped Dual-band Resonators
PublicationThe paper introduces a novel structure of a dual-band filtering Wilkinson power divider (WPD). Its essential component is a dual-band bandpass filter (BPF), implemented using coupling lines and two T-shaped resonators. The BPF is incorporated into the divider structure to suppress the unwanted harmonics within the circuit. The latter is achieved owing to a wide stopband of the filter. The deigned dual-band WPD can suppress third...
-
Towards Use of OntoClean for Ontology Contextualization
PublicationOntologies are formal systems of concepts used to describe numerous domains of interest. Ontologies are usually very expressive, but it comes at a price of computationally expensive reasoning over them. In our previous work we discussed the possible performance benefits that can be obtained by decomposing an ontology into contexts. While the benefits are appealing, we discovered that, in our case, the main obstacle against using...
-
Tuning of the finesse coefficient of optoelectronic devices
PublicationOptoelectronic devices attracted considerable attention in many branches of science and technology, which can be attributed to their unique properties. Many of them use optical cavities which parameters can be adopted to specific requirements. This thesis investigates the introduction of diamond structures (nitrogen-doped diamond film, boron-doped diamond film, undoped diamond sheet) to optical cavities to tune their finesse coefficient....
-
Electromagnetic Simulation with 3D FEM for Design Automation in 5G Era
PublicationElectromagnetic simulation and electronic design automation (EDA) play an important role in the design of 5G antennas and radio chips. The simulation challenges include electromagnetic effects and long simulation time and this paper focuses on simulation software based on finite-element method (FEM). The state-of-the-art EDA software using novel computational techniques based on FEM can not only accelerate numerical analysis, but...
-
MP3vec: A Reusable Machine-Constructed Feature Representation for Protein Sequences
Publication—Machine Learning (ML) methods have been used with varying degrees of success on protein prediction tasks, with two inherent limitations. First, prediction performance often depends upon the features extracted from the proteins. Second, experimental data may be insufficient to construct reliable ML models. Here we introduce MP3vec, a transferable representation for protein sequences that is designed to be used specifically for sequence-to-sequence...
-
Framework for Structural Health Monitoring of Steel Bridges by Computer Vision
PublicationThe monitoring of a structural condition of steel bridges is an important issue. Good condition of infrastructure facilities ensures the safety and economic well-being of society. At the same time, due to the continuous development, rising wealth of the society and socio-economic integration of countries, the number of infrastructural objects is growing. Therefore, there is a need to introduce an easy-to-use and relatively low-cost...
-
Methodology for Performing Bathymetric Measurements of Shallow Waterbodies Using an UAV, and their Processing Based on the SVR Algorithm
PublicationState-of-art methods of bathymetric measurements for shallow waterbodies use Global Navigation Satellite System (GNSS) receiver, bathymetric Light Detection and Ranging (LiDAR) sensor or satellite imagery. Currently, photogrammetric methods with the application of Unmanned Aerial Vehicles (UAV) are gathering great importance. This publication aims to present step-by-step methodology for carrying out the bathymetric measurements...
-
Constrained aerodynamic shape optimization using neural networks and sequential sampling
PublicationAerodynamic shape optimization (ASO) involves computational fluid dynamics (CFD)-based search for an optimal aerodynamic shape such as airfoils and wings. Gradient-based optimization (GBO) with adjoints can be used efficiently to solve ASO problems with many design variables, but problems with many constraints can still be challenging. The recently created efficient global optimization algorithm with neural network (NN)-based prediction...
-
Mural i jego rola w przestrzeni zurbanizowanej
PublicationCzym tak naprawdę jest mural? Definicji jest bardzo wiele. Według Słownika języka polskiego PWN mural to „wielkie malowidło wykonane bezpośrednio na ścianie budynku”. Pierwotnymi malowidłami tego typu były prace naskalne z epoki paleolitu. Następnie ważnymi epokami dla rozwoju tego typu prac był starożytny Egipt i starożytny Rzym. Samo słowo „mural” pochodzi z języka hiszpańskiego (h. mural – ścienny; malarstwo ścienne). To dzięki...
-
Processing of Biomass Prior to Hydrogen Fermentation and Post-Fermentative Broth Management
PublicationUsing bioconversion and simultaneous value-added product generation requires purifica- tion of the gaseous and the liquid streams before, during, and after the bioconversion process. The effect of diversified process parameters on the efficiency of biohydrogen generation via biological pro- cesses is a broad object of research. Biomass-based raw materials are often applied in investigations regarding biohydrogen generation using...
-
POTENCJALNE MOŻLIWOŚCI APLIKACJ TECHNIKI E-NOS W DIAGNOSTYCE MEDYCZNEJ=APPLICATION POTENTIALITIES OF E-NOSE TECHNIQUE IN MEDICAL DIAGNOSTICS
PublicationW pracy przedstawiono i omówiono zasadę działania instrumentu analitycznego - elektronicznego nosa (e-nos) zdolnego rozróżnić i sklasyfikować intensywność zapachu. Urządzenia te służą do automatycznej analizy i rozróżniania próbek zapachowych o złożonym składzie, do rozpoznawania ich charakterystycznych właściwości i najczęściej przeznaczone są do szybkiej analizy jakościowej. Dzięki unikatowym właściwościom technika ta znalazła...
-
E-Learning Service Management System For Migration Towards Future Internet Architectures
PublicationAs access to knowledge and continuous learning are among the most valuable assets in modern, technological society, it is hardly surprising that e-learning solutions can be counted amongst the most important groups of services being deployed in modern network systems. Based on analysis of their current state-of-the-art, we decided to concentrate our research and development work on designing and implementing a management system...
-
Technology-Driven Internationalization: Central-Eastern European Perspective
PublicationSince the 1990s of the twentieth century onward, Central-Eastern European countries have been extensively involved in these two processes—regarding increasing share of ICT and high-tech exports in country’s total export value—and additionally, across these economies, changes in the level of access to and use of ICT have been observed. The main target of this research is to contribute to the present state of the art, by proving...
-
SYNTHESIZING MEDICAL TERMS – QUALITY AND NATURALNESS OF THE DEEP TEXT-TO-SPEECH ALGORITHM
PublicationThe main purpose of this study is to develop a deep text-to-speech (TTS) algorithm designated for an embedded system device. First, a critical literature review of state-of-the-art speech synthesis deep models is provided. The algorithm implementation covers both hardware and algorithmic solutions. The algorithm is designed for use with the Raspberry Pi 4 board. 80 synthesized sentences were prepared based on medical and everyday...
-
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,...