Search
displaying 1000 best results Help
Search results for: ACCURACY
-
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...
-
An automatic selection of optimal recurrent neural network architecture for processes dynamics modelling purposes
PublicationA problem related to the development of algorithms designed to find the structure of artificial neural network used for behavioural (black-box) modelling of selected dynamic processes has been addressed in this paper. The research has included four original proposals of algorithms dedicated to neural network architecture search. Algorithms have been based on well-known optimisation techniques such as evolutionary algorithms and...
-
Comparison of safety levels required by adequate regulations for cargo ships of different types
PublicationDuring the currently ongoing development of methods for assessing the safety of ships, it is imperative that a compromise between the accuracy of the results and the accessibility of obtaining results is reached. This paper shows the calculations of a theoretical hull against damage stability regulations as included in SOLAS 2020, ICLL 66/88 as amended in 2003 and MARPOL 78. The rules included in the currently valid regulations require...
-
Comparison of the effectiveness of automatic EEG signal class separation algorithms
PublicationIn this paper, an algorithm for automatic brain activity class identification of EEG (electroencephalographic) signals is presented. EEG signals are gathered from seventeen subjects performing one of the three tasks: resting, watching a music video and playing a simple logic game. The methodology applied consists of several steps, namely: signal acquisition, signal processing utilizing z-score normalization, parametrization and...
-
Two- and three-dimensional elastic networks with rigid junctions: modeling within the theory of micropolar shells and solids
PublicationFor two- and three-dimensional elastic structures made of families of flexible elastic fibers undergoing finite deformations, we propose homogenized models within the micropolar elasticity. Here we restrict ourselves to networks with rigid connections between fibers. In other words, we assume that the fibers keep their orthogonality during deformation. Starting from a fiber as the basic structured element modeled by the Cosserat...
-
Food Classification from Images Using a Neural Network Based Approach with NVIDIA Volta and Pascal GPUs
PublicationIn the paper we investigate the problem of food classification from images, for the Food-101 dataset extended with 31 additional food classes from Polish cuisine. We adopted transfer learning and firstly measured training times for models such as MobileNet, MobileNetV2, ResNet50, ResNet50V2, ResNet101, ResNet101V2, InceptionV3, InceptionResNetV2, Xception, NasNetMobile and DenseNet, for systems with NVIDIA Tesla V100 (Volta) and...
-
A coarse‐grained approach to NMR ‐data‐assisted modeling of protein structures
PublicationThe ESCASA algorithm for analytical estimation of proton positions from coarse-grained geometry developed in our recent work has been implemented in modeling protein structures with the highly coarse-grained UNRES model of polypeptide chains (two sites per residue) and nuclear magnetic resonance (NMR) data. A penalty function with the shape of intersecting gorges was applied to treat ambiguous distance restraints, which automatically...
-
Tensor Decomposition for Imagined Speech Discrimination in EEG
PublicationMost of the researches in Electroencephalogram(EEG)-based Brain-Computer Interfaces (BCI) are focused on the use of motor imagery. As an attempt to improve the control of these interfaces, the use of language instead of movement has been recently explored, in the form of imagined speech. This work aims for the discrimination of imagined words in electroencephalogram signals. For this purpose, the analysis of multiple variables...
-
A Model-Order Reduction Approach for Electromagnetic Problems With Nonaffine Frequency Dependence
PublicationThe aim of this paper is to present a novel model-order reduction (MOR) technique for the efcient frequency-domain nite-element method (FEM) simulation of microwave components. It is based on the standard reduced-basis method, but the subsequent expansion frequency points are selected following the so-called sparsied greedy strategy. This feature makes it especially useful to perform a fast-frequency sweep of problems that lead...
-
Numerical modelling of the mesofracture process of sintered 316L steel under tension using microtomography
PublicationThis paper concerns numerical modelling of the deformation process, taking into account the local fracture of porous 316L sinters at the mesoscopic scale using the finite element method. Calculations are performed with the use of geometrical models, to map the realistic shape of the porous mesostructure of the material, obtained by means of computed microtomography. The microtomographic device has limited and insufficient measurement...
-
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...
-
Automated Classifier Development Process for Recognizing Book Pages from Video Frames
PublicationOne of the latest developments made by publishing companies is introducing mixed and augmented reality to their printed media (e.g. to produce augmented books). An important computer vision problem that they are facing is classification of book pages from video frames. The problem is non-trivial, especially considering that typical training data is limited to only one digital original per book page, while the trained classifier...
-
1D convolutional context-aware architectures for acoustic sensing and recognition of passing vehicle type
PublicationA network architecture that may be employed to sensing and recognition of a type of vehicle on the basis of audio recordings made in the proximity of a road is proposed in the paper. The analyzed road traffic consists of both passenger cars and heavier vehicles. Excerpts from recordings that do not contain vehicles passing sounds are also taken into account and marked as ones containing silence....
-
Studying the Effect of Working Conditions on WEDM Machining Performance of Super Alloy Inconel 617
PublicationWire electrical discharge machining (WEDM) has been for many years a precise and efficient non-conventional manufacturing solution in various industrial applications, mostly involving the use of hard-to machine materials like, among other, the Inconel super alloys. The focus of the present study is on exploring the effect of selected control parameters, including pulse duration, pulse-off time and the dielectric flow pressure on...
-
Coarse-grained simulation - an efficient approach for studying motions of large proteins
PublicationOne of the most important challenges in performing Molecular Dynamics (MD) simulations of large protein complexes is to accommodate the model accuracy and the simulation timescale. Hitherto, for the most relevant dynamics of protein aggregates in an explicit aqueous environment, the timescale reachable for the all-atoms simulations is of hundreds of nanoseconds. This range is four to six orders of magnitude smaller than processes...
-
Calculations of the resistance values of 20 thermistors at 0°C
Open Research DataThe presented data set is part of the research aimed at determining the actual characteristics of each thermistor in a package of twenty NTC10k type sensors.
-
SegSperm - a dataset of sperm images for blurry and small object segmentation
Open Research DataMany deep learning applications require figure-ground segmentation. The performance of segmentation models varies across modalities and acquisition settings.
-
Comment on "Quantitative comparison of analysis methods for spectroscopic optical coherence tomography"
PublicationIn a recent paper by Bosschaart et al. [Biomed. Opt. Express 4, 2570 (2013)] various algorithms of time-frequency signal analysis have been tested for their performance in blood analysis with spectroscopic optical coherence tomography sOCT). The measurement of hemoglobin concentration and oxygen saturation based on blood absorption spectra have been considered. Short time Fourier transform (STFT) was found as the best method for...
-
An Application Supporting Gastroesophageal Multichannel Intraluminal Impedance-pH Analysis
PublicationDue to a significant rise in the number of patients diagnosed with diseases of the upper gastrointestinal tract and the high cost of treatment, there is a need to further research on one of the most popular diagnostic tests used in this case – esophageal Multichannel Intraluminal Impedance and pH measurement. This may lead to finding new diagnostically relevant information, used to quicken and improve the diagnostic procedure....
-
3D Machine Vision System for Inspection of Contact Strips in Railway Vehicle Current Collectors
PublicationConstruction and technical condition of current collectors is crucial to reliability and safety of railway transportation. According to the Technical Specifications for Interoperability railway vehicles in the European Union should be equipped with carbon contact strips. Excessive wear or defects of contact strips degrade the capability of undisturbed power transmission, cause faster wear of contact wire, and can even result in...
-
Finding the Right Solvent: A Novel Screening Protocol for Identifying Environmentally Friendly and Cost-Effective Options for Benzenesulfonamide
PublicationThis study investigated the solubility of benzenesulfonamide (BSA) as a model compound using experimental and computational methods. New experimental solubility data were collected in the solvents DMSO, DMF, 4FM, and their binary mixtures with water. The predictive model was constructed based on the best-performing regression models trained on available experimental data, and their hyperparameters were optimized using a newly...
-
Balance errors generated by numerical diffusion in the solution of non-linear open channel flow equations
PublicationThe paper concerns the untypical aspect of application of the dissipative numerical methods to solve nonlinear hyperbolic partial differential equations used in open channel hydraulics. It is shown that in some cases the numerical diffusion generated by the applied method of solution produces not only inaccurate solution but as well as a balance error. This error may occur even for an equation written in the conservative form not...
-
Real-Time PCR: molecular technique of many applications
PublicationReal-Time PCR is a sensitive DNA amplification technique initially applied in genetics and molecular biology. It enables in vivo copying of the selected DNA fragment (flanked by two primers) by the thermostable polymerase (in the presence of magnesium ions and deoxynucleotide triphosphates) and simultaneous measurement of the fluorescence. For one or more specific sequences in a DNA sample, real-time PCR enables both detection...
-
Comparison of PM10 concentration in Gdansk and London using electron microscopy
PublicationParticulate matter (PM) has been considered as one of the most dangerous elements of air pollution. Multiply analytical methods are employed to identify the composition of particles present in the air. The theoretical part of this work is a description of different research centres all over the world where particulate matter is being analyzed using various techniques. The purpose of this project is to analyze and compare particles...
-
Modeling two phase flow in large scale fractured porous media with an extended multiple interacting continua method
PublicationWe present a two phase flow conceptual model, the corresponding simulator (2pMINC) and a workflow for large-scale fractured reservoirs, based on a continuum fracture approach which uses the multiple interacting continua (MINC) method complemented with an improved upscaling technique. The complex transient behavior of the flow processes in fractured porous media is captured by subgridding the coarse blocks in nested volume elements...
-
Noise sources in Raman spectroscopy of biological objects
PublicationWe present an overview of noise sources deteriorating the quality of the recorded biological Raman spectra and the ability to determine the specimen composition. The acquired Raman spectra exhibit intense additive noise components or drifts because of low intensity of the scattered light. Therefore we have to apply expensive or bulky measurement setups to limit their inherent noise or to apply additional signal processing to reduce...
-
Results of the application of tropospheric corrections from different troposphere models for precise GPS rapid static positioning
PublicationIn many surveying applications, determination of accurate heights is of significant interest. The delay caused by the neutral atmosphere is one of the main factors limiting the accuracy of GPS positioning and affecting mainly the height coordinate component rather than horizontal ones. Estimation of the zenith total delay is a commonly used technique for accounting for the tropospheric delay in static positioning. However, in the...
-
Sensitivity analysis based on non-intrusive regression-based polynomial chaos expansion for surgical mesh modelling
PublicationThe modelling of a system containing implants used in ventral hernia repair and human tissue suffers from many uncertainties. Thus, a probabilistic approach is needed. The goal of this study is to define an efficient numerical method to solve non-linear biomechanical models supporting the surgeon in decisions about ventral hernia repair. The model parameters are subject to substantial variability owing to, e.g., abdominal wall...
-
The influence of meteorological conditions and anthropogenic activities on the seasonal fluctuations of BTEX in the urban air of the Hanseatic city of Gdansk, Poland
PublicationThe results of studies conducted in Gdansk in the period from January to December 2013 and focused on the determination of BTEX in the atmospheric air are presented. At the stage of the isolation and/or enrichment of analytes from the gaseous medium, a passive sampling technique—Radiello® diffusive passive samplers, was applied. The time-weighted average annual concentration of benzene, toluene, ethylbenzene, and total xylenes...
-
Adaptive dynamic control allocation for dynamic positioning of marine vessel based on backstepping method and sequential quadratic programming
PublicationIt is generally assumed in dynamic positioning of over-actuated marine vessels that the control effectiveness matrix (input matrix) is known and constant, or, in case of fault information, it is estimated by the fault detection and diagnosis system. The purpose of the study is to develop the adaptive dynamic positioning control system for an over-actuated marine vessel in the presence of uncertainties and with emphasis on limited...
-
Speech Analytics Based on Machine Learning
PublicationIn this chapter, the process of speech data preparation for machine learning is discussed in detail. Examples of speech analytics methods applied to phonemes and allophones are shown. Further, an approach to automatic phoneme recognition involving optimized parametrization and a classifier belonging to machine learning algorithms is discussed. Feature vectors are built on the basis of descriptors coming from the music information...
-
Photovoltaic Maximum Power Point Technique based on Incremental Conductance (INCON) control algorithm
PublicationMaximum output power status can significantly improve the deployment rate of solar energy system. In order to get the maximum power output, issue of tracking maximum power point (MPP), reduced harmonics around MPP and improve efficiency of the solar power energy system, this paper presents the improved maximum power point tracking (MPPT) control...
-
Estimation of the amplitude of the signal for the active optical gesture sensor with sparse detectors
PublicationIn this paper we deal with the problem of precise gesture recognition for the active optical proximity sensor with sparse 8 photodiodes. We particularly focus on developing the method of estimating the real, usually not observable, maximum signal value representing maximum intensity of light reflected from an obstacle present in the front of the sensor. Different configurations of the fingers were used as an obstacle. The Monte Carlo...
-
Investigation of vortex assisted magnetic deep eutectic solvent based dispersive liquid–liquid microextraction for separation and determination of vanadium from water and food matrices: Multivariate analysis
PublicationA new and simple vortex assisted magnetic deep eutectic solvent dispersive liquid–liquid microextraction procedure (VA-MDES-DLLME) was developed for the determination of vanadium (V) in food and water samples by flame atomic absorption spectrometry (FAAS). In the extraction medium, a bis(acetylpivalylmethane) ethylenediimine (H2APM2en) was used for the complexation of V(V) in sample solution at pH 6. The VA-MDES-DLLME was optimized...
-
Flow boiling of R1233zd(E) in a 3 mm vertical tube at moderate and high reduced pressures
PublicationThe results of flow boiling of R1233zd(E) in a 3 mm vertical stainless steel tube are presented at moderate and high saturation temperatures. Integral flow characteristics in the form of pressure drop and heat transfer coefficient are discussed for saturation temperatures ranging from 115 to 145 °C (corresponding reduced pressures from 0.2 to 0.7), mass velocity of 800 kg/m2s and heat flux of 20 kW/m2. All of the obtained heat...
-
A Novel Spatio–Temporal Deep Learning Vehicle Turns Detection Scheme Using GPS-Only Data
PublicationWhether the computer is driving your car or you are, advanced driver assistance systems (ADAS) come into play on all levels, from weather monitoring to safety. These modern-day ADASs use various assisting tools for drivers to keep the journey safe; these sophisticated tools provide early signals of numerous events, such as road conditions, emerging traffic scenarios, and weather warnings. Many urban applications, such as car-sharing...
-
Atypical application of the parametric method for track infrastructure inventory
PublicationFor many years, satellite systems have seen widespread use in a variety of technical applications, as well as in operations related to setting-out and the exploitation of track infrastructure. Their main applications include an inventory of the trackage course and detecting changes in its position. In both of these tasks, the most important element that determines the quality of an analyses is the high accuracy of the determinations...
-
Analysis of Validation and Simplification of Timber-Frame Structure Design Stage with PU-Foam Insulation
PublicationThe transition from experimental studies to the realm of numerical simulations is often necessary for further studies, but very difficult at the same time. This is especially the case for extended seismic analysis and earthquake-resistant design. This paper describes an approach to moving from the experimental testing of an elementary part of a wood-frame building structure to a numerical model, with the use of a commercial engineering...
-
The Role of Electrostatics in Enzymes: Do Biomolecular Force Fields Reflect Protein Electric Fields?
PublicationPreorganization of large, directionally oriented, electric fields inside protein active sites has been proposed as a crucial contributor to catalytic mechanism in many enzymes, and it may be efficiently investigated at the atomistic level with molecular dynamics simulations. Here, we evaluate the ability of the AMOEBA polarizable force field, as well as the additive Amber ff14SB and Charmm C36m models, to describe the electric...
-
Numerical Solution of the Two-Dimensional Richards Equation Using Alternate Splitting Methods for Dimensional Decomposition
PublicationResearch on seepage flow in the vadose zone has largely been driven by engineering and environmental problems affecting many fields of geotechnics, hydrology, and agricultural science. Mathematical modeling of the subsurface flow under unsaturated conditions is an essential part of water resource management and planning. In order to determine such subsurface flow, the two-dimensional (2D) Richards equation can be used. However,...
-
Comparison of Two Methods for the Determination of Selected Pesticides in Honey and Honeybee Samples
PublicationDeveloped and validated analytical methods for the determination of a wide spectrum of pesticide residues in honey and honeybee samples after the modification of QuEChERS extraction in combination with gas chromatography–tandem quadrupole mass spectrometry (GC-MS/MS) and liquid chromatography–tandem quadrupole mass spectrometry (LC-MS/MS) were discussed and compared. The developed methods were evaluated regarding the utilized equipment...
-
Local Nusselt number evaluation in the case of jet impingement
PublicationJet impingement still is one of demanding cases regarding computational fluid dynamics, due to its highly turbulent behaviour, with occurrence of turbulent-laminar transition. Even recently developed methods exhibit some drawbacks – RANS based simulations lack accuracy, LES and DNS based ones require too much computational time. Hybrid methods also exist, but their development and validation is in progress. Nevertheless, CFD application...
-
A Pilot Study on Machining Difficult-to-Cut Materials with the Use of Tools Fabricated by SLS Technology
PublicationThe growing use of contemporary materials in various industrial sectors, such as aerospace, automotive, as well as the oil and gas industry, requires appropriate machining methods and tools. Currently, apart from the necessity to obtain high-dimensional and shape accuracy, the efficiency and economic aspects of the selected manufacturing process are equally important, especially when difficult-to-cut materials, such as hard and...
-
Prediction of Wastewater Quality at a Wastewater Treatment Plant Inlet Using a System Based on Machine Learning Methods
PublicationOne of the important factors determining the biochemical processes in bioreactors is the quality of the wastewater inflow to the wastewater treatment plant (WWTP). Information on the quality of wastewater, sufficiently in advance, makes it possible to properly select bioreactor settings to obtain optimal process conditions. This paper presents the use of classification models to predict the variability of wastewater quality at...
-
Vibro piles performance prediction using result of CPT
PublicationVibro piles belong to the group of full displacement piles with an expanded base, characterised by a very high load capacity, especially in non-cohesive soils. The problem is to adopt a reliable method for the determination of full load–settlement (Q–s) curve. A frequent difficulty is the determination of the load capacity limit based on the static load test because the course of the load–settlement curve is of a linear nature....
-
Soft Sensor Application in Identification of the Activated Sludge Bulking Considering the Technological and Economical Aspects of Smart Systems Functioning
PublicationThe paper presented the methodology for the construction of a soft sensor used for activated sludge bulking identification. Devising such solutions fits within the current trends and development of a smart system and infrastructure within smart cities. In order to optimize the selection of the data-mining method depending on the data collected within a wastewater treatment plant (WWTP), a number of methods were considered, including:...
-
Automatic Breath Analysis System Using Convolutional Neural Networks
PublicationDiseases related to the human respiratory system have always been a burden for the entire society. The situation has become particularly difficult now after the outbreak of the COVID-19 pandemic. Even now, however, it is common for people to consult their doctor too late, after the disease has developed. To protect patients from severe disease, it is recommended that any symptoms disturbing the respiratory system be detected as...
-
Compact global association based adaptive routing framework for personnel behavior understanding
PublicationPersonnel behavior understanding under complex scenarios is a challenging task for computer vision. This paper proposes a novel Compact model, which we refer to as CGARPN that incorporates with Global Association relevance and Adaptive Routing Pose estimation Network. Our framework firstly introduces CGAN backbone to facilitate the feature representation by compressing the kernel parameter space compared with typical algorithms,...
-
Preparatory Railway Track Geometry Estimation Based on GNSS and IMU Systems
PublicationThe article discusses an important issue of railway line construction and maintenance, which fundamentally is the verification of geometric parameters of the railway track. For this purpose, mobile measurements have been performed using a measuring platform with two properly arranged GNSS receivers, which made it possible to determine the base vector of the platform. The measuring functionality of the system was extended by IMU....
-
Automatic Breath Analysis System Using Convolutional Neural Networks
PublicationDiseases related to the human respiratory system have always been a burden for the entire society. The situation has become particularly difficult now after the outbreak of the COVID-19 pandemic. Even now, however, it is not uncommon for people to consult their doctor too late, after the disease has developed. To protect patients from severe disease, it is recommended that any symptoms disturbing the respiratory system be detected...