Wyniki wyszukiwania dla: prediction
-
Elimination of impulsive disturbances from archive audio files – comparison of three noise pulse detection schemes
PublikacjaThe problem of elimination of impulsive disturbances (such as clicks, pops, ticks, crackles, and record scratches) from archive audio recordings is considered and solved using autoregressive modeling. Three classical noise pulse detection schemes are examined and compared: the approach based on open-loop multi-step-ahead signal prediction, the approach based on decision-feedback signal prediction, and the double threshold approach,...
-
Efficient uncertainty quantification using sequential sampling-based neural networks
PublikacjaUncertainty quantification (UQ) of an engineered system involves the identification of uncertainties, modeling of the uncertainties, and the forward propagation of the uncertainties through a system analysis model. In this work, a novel surrogate-based forward propagation algorithm for UQ is proposed. The proposed algorithm is a new and unique extension of the recent efficient global optimization using neural network (NN)-based...
-
On ship roll resonance frequency
PublikacjaThe paper deals with the problem of modeling of rolling motion under a variety of excitation parameters. Special emphasis is put on the analysis and prediction of the frequency of the resonant mode of rolling, since it is often an essential issue in terms of motion of a ship related to her safety against capsizing or excessive amplitudes of roll. The research is performed for both free rolling and excited rolling and it is based...
-
Global Surrogate Modeling by Neural Network-Based Model Uncertainty
PublikacjaThis work proposes a novel adaptive global surrogate modeling algorithm which uses two neural networks, one for prediction and the other for the model uncertainty. Specifically, the algorithm proceeds in cycles and adaptively enhances the neural network-based surrogate model by selecting the next sampling points guided by an auxiliary neural network approximation of the spatial error. The proposed algorithm is tested numerically...
-
Trim Optimisation - Theory and Practice
PublikacjaForce Technology has been working intensively with trim optimisation tests for almost last 10 years. Focus has primarily been put on the possible power savings and exhaust gases reduction. This paper describes the trim optimisation process for a large cargo vessel. The physics behind changed propulsive power is described and the analyses in order to elaborate the optimum trimmed conditions are presented. Different methods for prediction...
-
Elimination of clicks from archive speech signals using sparse autoregressive modeling
PublikacjaThis paper presents a new approach to elimination of impulsivedisturbances from archive speech signals. The proposedsparse autoregressive (SAR) signal representation is given ina factorized form - the model is a cascade of the so-called formantfilter and pitch filter. Such a technique has been widelyused in code-excited linear prediction (CELP) systems, as itguarantees model stability. After detection of noise pulses usinglinear...
-
New semi-causal and noncausal techniques for detection of impulsive disturbances in multivariate signals with audio applications
PublikacjaThis paper deals with the problem of localization of impulsive disturbances in nonstationary multivariate signals. Both unidirectional and bidirectional (noncausal) detection schemes are proposed. It is shown that the strengthened pulse detection rule, which combines analysis of one-step-ahead signal prediction errors with critical evaluation of leave-one-out signal interpolation errors, allows one to noticeably improve detection results...
-
Chemistry and Nanochemistry 2022.
Kursy OnlineThe course consists of lectures (15 x 2 hours) and laboratories (5 x 3 hours).The goal of this course is to teach general chemistry and adequately apply it to nano-size systems, their synthesis and analysis. An emphasis is laid on an analysis of electronic structure of molecules and prediction of resulting properties and reasons of consequent behaviour in chemical reactions. The course also encloses laboratory classes, where the...
-
TOWARDS EXPLAINABLE CLASSIFIERS USING THE COUNTERFACTUAL APPROACH - GLOBAL EXPLANATIONS FOR DISCOVERING BIAS IN DATA
PublikacjaThe paper proposes summarized attribution-based post-hoc explanations for the detection and identification of bias in data. A global explanation is proposed, and a step-by-step framework on how to detect and test bias is introduced. Since removing unwanted bias is often a complicated and tremendous task, it is automatically inserted, instead. Then, the bias is evaluated with the proposed counterfactual approach. The obtained results...
-
Traffic Noise Analysis Applied to Automatic Vehicle Counting and Classification
PublikacjaProblems related to determining traffic noise characteristics are discussed in the context of automatic dynamic noise analysis based on noise level measurements and traffic prediction models. The obtained analytical results provide the second goal of the study, namely automatic vehicle counting and classification. Several traffic prediction models are presented and compared to the results of in-situ noise level measurements. Synchronized...
-
An algorithm for selecting a machine learning method for predicting nitrous oxide emissions in municipal wastewater treatment plants
PublikacjaThis study presents an advanced algorithm for selecting machine learning (ML) models for nitrous oxide (N2O) emission prediction in wastewater treatment plants (WWTPs) employing the activated sludge process. The examined ML models comprised multivariate adaptive regression spline (MARS), support vector machines (SVM), and extreme gradient boosting (XGboost). The study explores the concept that involves new criteria to select the...
-
Machine learning-based seismic response and performance assessment of reinforced concrete buildings
PublikacjaComplexity and unpredictability nature of earthquakes makes them unique external loads that there is no unique formula used for the prediction of seismic responses. Hence, this research aims to implement the most well-known Machine Learning (ML) methods in Python software to propose a prediction model for seismic response and performance assessment of Reinforced Concrete Moment-Resisting Frames (RC MRFs). To prepare 92,400 data...
-
Computational collective intelligence for enterprise information systems
PublikacjaCollective intelligence is most often understood as a kind of intelligence which arises on the basis of a group (collective) of autonomous unites (people, systems) which is taskoriented. There are two important aspects of an intelligent collective: The cooperation aspect and the competition aspect (Levy 1997). The first of them means the possibility for integrating the decisions made by the collective members for creating the decision of...
-
Andrzej Chybicki dr inż.
OsobyZ wykształcenia informatyk, absolwent Wydziału Elektroniki, Telekomunikacji i Informatyki Politechniki Gdańskiej, doktor nauk technicznych w dziedzinie informatyka specjalizujący się w przetwarzaniau danych przestrzennych w rozproszonych systemach informatycznych. Ukierunkowany na wykorzystywanie osiągnięć i wiedzy zakresu prowadzonych badań w przemyśle. Współpracował z szeregiem podmiotów przemysłu informatycznego, geodezyjnego...
-
Multi-Criteria Knowledge-Based Recommender System for Decision Support in Complex Business Processes
PublikacjaIn this paper, we present a concept of a multi-criteria knowledge-based Recommender System (RS) designed to provide decision support in complex business process (BP) scenarios. The developed approach is based on the knowledge aspects of Stylistic Patterns, Business Sentiment and Decision-Making Logic extracted from the BP unstructured texts. This knowledge serves as an input for a multi-criteria RS algorithm. The output is prediction...
-
Aerodynamic shape optimization by variable-fidelity computational fluid dynamics models: a review of recent progress
PublikacjaA brief review of some recent variable-fidelity aerodynamic shape optimization methods is presented.We discuss three techniques that—by exploiting information embedded in low-fidelity computationalfluid dynamics (CFD) models—are able to yield a satisfactory design at a low computational cost, usu-ally corresponding to a few evaluations of the original, high-fidelity CFD model to be optimized. Thespecific techniques considered here...
-
Chained machine learning model for predicting load capacity and ductility of steel fiber–reinforced concrete beams
PublikacjaOne of the main issues associated with steel fiber–reinforced concrete (SFRC) beams is the ability to anticipate their flexural response. With a comprehensive grid search, several stacked models (i.e., chained, parallel) consisting of various machine learning (ML) algorithms and artificial neural networks (ANNs) were developed to predict the flexural response of SFRC beams. The flexural performance of SFRC beams under bending was...
-
OCENA PRZYDATNOŚCI WIELOWYMIAROWYCH MODELI DYSKRYMINACYJNYCH DO PROGNOZOWANIA UPADŁOŚCI PRZEDSIĘBIORSTW HANDLOWYCH
PublikacjaCelem badań była ocena przydatności użycia modeli opartych na wielowymiarowej analizie dyskryminacyjnej do prognozowania upadłości polskich przedsiębiorstw handlowych oraz próba zwiększenia ich sprawności poprzez zmianę wartości ich punktów granicznych. Badaniu poddano modele: E. I. Altmana „B”, D. Hadasik, A. Hołdy oraz M. Hamrola, B. Czajki i M. Piechockiego. Do oceny modeli wykorzystano iloraz szans oraz macierz klasyfikacji...
-
Akcelerator predykcji wewnątrzramkowej H.264 do kompresji obrazu w sensorach wizyjnych
PublikacjaW komunikacie przedstawiono konfigurowalny cyfrowy akcelerator predykcji wewnątrzramkowej przeznaczony dla enkodera wideo standardu H.264. Akcelerator realizuje predykcję typu „intra” dla makrobloków luminancji o wymiarach 4x4 i 16x16. Akcelerator wstępnie zaimplementowano w układzie FPGA, gdzie został on pomyślnie zweryfikowany, a następnie zaimplementowano go w układzie ASIC w technologii UMC 90 nm. Szczegółowe wyniki testów...
-
System do prototypowania bezprzewodowych inteligentnych urządzeń monitoringu audio-video
PublikacjaW komunikacie przedstawiono system prototypowania bezprzewodowych urządzeń do monitoringu audio-video. System bazuje na układach FPGA Virtex6 i wielu dodatkowych wspierających urządzeniach jak: szybka pamięć DDR3, mała kamera HD, mikrofon z konwerterem A/C, moduł radiowy WiFi, itp. Funkcjonalność systemu została szczegółowo opisana w komunikacie. System został zoptymalizowany do pracy pod kontrolą systemu operacyjnego Linux, zostały...
-
Akcelerator predykcji wewnątrzramkowej H.264 do kompresji obrazu w sensorach wizyjnych
PublikacjaW artykule przedstawiono konfigurowalny cyfrowy akcelerator predykcji wewnątrzramkowej przeznaczony dla enkodera wideo standardu H.264. Akcelerator realizuje predykcję typu „intra” dla makrobloków luminancji o wymiarach 4x4 i 16x16. Akcelerator wstępnie zaimplementowano w układzie FPGA, gdzie został on pomyślnie zweryfikowany, a następnie zaimplementowano go w układzie ASIC w technologii UMC 90 nm. Szczegółowe wyniki testów akceleratora...
-
On joint order and bandwidth selection for identification of nonstationary autoregressive processes
PublikacjaWhen identifying a nonstationary autoregressive process, e.g. for the purpose of signal prediction or parametric spectrum estimation, two important decisions must be taken. First, one should choose the appropriate order of the autoregressive model, i.e., the number of autoregressive coefficients that will be estimated. Second, if identification is carried out using the local estimation technique, such as the localized version of...
-
Performance of Noise Map Service Working in Cloud Computing Environment
PublikacjaIn the paper a noise map service designated for the user interested in environmental noise subject is presented. It is based on cloud computing. Noise prediction algorithm and source model, developed for creating acoustic maps, are working in cloud computing environment. In the study issues related to noise modeling of sound propagation in urban spaces are discussed with a special focus on road noise. Examples of results obtained...
-
New generation of analytical tests based on the assessment of enzymatic and nuclear receptor activity changes induced by environmental pollutants
PublikacjaAnalytical methods show great potential in biological tests. The analysis of biological response that results from environmental pollutant exposure allows: (i) prediction of the risk of toxic effects and (ii) provision of the background for the development of markers of the toxicants presence. Bioanalytical tests based on changes in enzymatic activity and nuclear receptor action provide extremely high specificity and sensitivity....
-
Predicting bankruptcy with the use of macroeconomic variables
PublikacjaRegarding the current global financial crisis, the firms can expect the increased uncertainty of their existence. The relevant literature includes extensive studies on bankruptcy prediction. Studies show that the most popular method used for prediction of firms' failures are discriminant analyses (30,3% of all models), then logit and probit models (21,3%), which all three are parametric models. The nature, the structure of the...
-
Mathematical Modeling of Ice Dynamics as a Decision Support Tool in River Engineering
PublikacjaThe prediction of winter flooding is a complicated task since it is affected by many meteorological and hydraulic factors. Typically, information on river ice conditions is based on historical observations, which are usually incomplete. Recently, data have been supplemented by information extracted from satellite images. All the above mentioned factors provide a good background of the characteristics of ice processes, but are not...
-
Implementation of Extended Kalman Filter with Optimized Execution Time for Sensorless Control of a PMSM Using ARM Cortex-M3 Microcontroller
PublikacjaThis paper addresses the implementation and optimization of an Extended Kalman Filter (EKF) for the Permanent Magnet Synchronous Motor (PMSM) sensorless control using an ARM Cortex-M3 microcontroller. A various optimization levels based on arithmetic calculation reduction was implemented in ARM Cortex-M3 microcontroller. The execution time of EKF estimator was reduced from 260.4 μs to 37.7 μs without loss of accuracy. To further...
-
The Use of Artificial Neural Networks and Decision Trees to Predict the Degree of Odor Nuisance of Post-Digestion Sludge in the Sewage Treatment Plant Process
PublikacjaThis paper presents the application of artificial neural networks and decision trees for the prediction of odor properties of post-fermentation sludge from a biological-mechanical wastewater treatment plant. The input parameters were concentrations of popular compounds present in the sludge, such as toluene, p-xylene, and p-cresol, and process parameters including the concentration of volatile fatty acids, pH, and alkalinity in...
-
On Noncausal Identification of Nonstationary Multivariate Autoregressive Processes
PublikacjaThe problem of identification of nonstationary multivariate autoregressive processes using noncausal local estimation schemes is considered and a new approach to joint selection of the model order and the estimation bandwidth is proposed. The new selection rule, based on evaluation of pseudoprediction errors, is compared with the previously proposed one, based on the modified Akaike’s final prediction error criterion.
-
Long-term hindcast simulation of sea level in the Baltic Sea
Dane BadawczeThe dataset contains the results of numerical modelling of sea level fluctuations over a period of 50 years (1958-2007) in the Baltic Sea. A long-term hindcast simulation was performed using a three-dimensional hydrodynamic model PM3D (Kowalewski and Kowalewska-Kalkowska, 2017), a new version of the M3D model (Kowalewski, 1997). The hydrodynamic model...
-
Survival time prognosis under a Markov model of cancer development
PublikacjaIn this study we look at a breast cancer data set of women from Pomerania region collected in year 1987-1992 in the Medical University of Gdańsk. We analyze the clinical risk factors in conjunction with Markov model of cancer development. We evaluate Artificial Neural Network (ANN) survival time prediction via a simulation study.
-
An Ontology-based Contextual Pre-filtering Technique for Recommender Systems
PublikacjaContext-aware Recommender Systems aim to provide users with the most adequate recommendations for their current situation. However, an exact context obtained from a user could be too specific and may not have enough data for accurate rating prediction. This is known as the data sparsity problem. Moreover, often user preference representation depends on the domain or the specific recommendation approach used. Therefore, a big effort...
-
Things You Might Not Know about the k-Nearest Neighbors Algorithm
PublikacjaRecommender Systems aim at suggesting potentially interesting items to a user. The most common kind of Recommender Systems is Collaborative Filtering which follows an intuition that users who liked the same things in the past, are more likely to be interested in the same things in the future. One of Collaborative Filtering methods is the k Nearest Neighbors algorithm which finds k users who are the most similar to an active user...
-
Pose-Invariant Face Detection by Replacing Deep Neurons with Capsules for Thermal Imagery in Telemedicine
PublikacjaAbstract— The aim of this work was to examine the potential of thermal imaging as a cost-effective tool for convenient, non- intrusive remote monitoring of elderly people in different possible head orientations, without imposing specific behavior on users, e.g. looking toward the camera. Illumination and pose invariant head tracking is important for many medical applications as it can provide information, e.g. about vital signs, sensory...
-
Predicting seismic response of SMRFs founded on different soil types using machine learning techniques
PublikacjaPredicting the Maximum Interstory Drift Ratio (M-IDR) of Steel Moment-Resisting Frames (SMRFs) is a useful tool for designers to approximately evaluate the vulnerability of SMRFs. This study aims to explore supervised Machine Learning (ML) algorithms to build a surrogate prediction model for SMRFs to reduce the need for complex modeling. For this purpose, twenty well-known ML algorithms implemented in Python software are trained...
-
The analysis of soil resistance during screw displacement pile installation
PublikacjaThe analysis of soil resistances during screw displacement pile installation based on model and field tests. The investigations were carried out as a part of research project, financed by the Polish Ministry of Science and Higher Education. A proposal of empirical method for prediction of rotation resistance (torque) during screw auger penetration in non-cohesive subsoil based on CPT result.
-
Adam Inglot dr inż.
OsobyAdam Inglot (urodzony 3 października 1984 w Rzeszowie) studiował Inżynierię Środowiska oraz Geodezję i Kartografię na Wydziale Geodezji Górniczej i Inżynierii Środowiska Akademii Górniczo-Hutniczej w Krakowie. Inżynierię Środowiska ukończył w 2011 w stopniu mgr inż. broniąc pracę „Weryfikacja przydatności modelu GeoMod do prognozowania procesu urbanizacji w aglomeracji krakowskiej” u dra inż. Wojciecha Drzewieckiego. Natomiast...
-
Formowanie napięć wyjściowych trójfazowego przekształtnika sieciowego
PublikacjaW artykule przedstawiono kompensację dwu zasadniczych zjawisk powodujących zniekształcenia prądów fazowych przekształtnika sieciowego. Pierwszym z nich są zniekształcenia napięcia sieci. W celu ich eliminacji zaproponowano uśrednianie za okres podstawowej harmonicznej uchybu regulatora napięcia obwodu pośredniczącego oraz predykcję napięcia sieci. Drugim natomiast są zniekształcenia napięć wyjściowych przekształtnika sieciowego....
-
Study on the accuracy of axle load spectra used for pavement design
PublikacjaWeigh-in-Motion (WIM) systems are used in order to reduce the number of overloaded vehicles. Data collected from WIM provide characteristics of vehicle axle loads that are crucial for pavement design as well as for the development of pavement distress prediction models. The inaccuracy of WIM data lead to erroneous estimation of traffic loads and in consequence inaccurate prediction of pavement distress process. The objective of...
-
Edgewise Compressive Behavior of Composite Structural Insulated Panels with Magnesium Oxide Board Facings
PublikacjaEdgewise compression response of a composite structural insulated panel (CSIP) with magnesium oxide board facings was investigated. The discussed CSIP is a novel multifunctional sandwich panel introduced to the housing industry as a part of the wall, floor, and roof assemblies. The study aims to propose a computational tool for reliable prediction of failure modes of CSIPs subjected to concentric and eccentric axial loads. An advanced...
-
Sensing Direction of Human Motion Using Single-Input-Single-Output (SISO) Channel Model and Neural Networks
PublikacjaObject detection Through-the-Walls enables localization and identification of hidden objects behind the walls. While numerous studies have exploited Channel State Information of Multiple Input Multiple Output (MIMO) WiFi and radar devices in association with Artificial Intelligence based algorithms (AI) to detect and localize objects behind walls, this study proposes a novel non-invasive Through-the-Walls human motion direction...
-
Data on LEGO sets release dates and worldwide retail prices combined with aftermarket transaction prices in Poland between June 2018 and June 2023
PublikacjaThe dataset contains LEGO bricks sets item count and pricing history for AI-based set pricing prediction. The data spans the timeframe from June 2018 to June 2023. The data was obtained from three sources: Brickset.com (LEGO sets retail prices, release dates, and IDs), Lego.com official web page (ID number of each set that was released by Lego, its retail prices, the current status of the set) and promoklocki.pl web page (the retail...
-
Can Web Search Queries Predict Prices Change on the Real Estate Market?
PublikacjaThis study aims to explore whether the intensity of internet searches, according to the Google Trends search volume index (SVI), is a predictor of changes in real estate prices. The motivation of this study is the possibility to extend the understanding of the extra predictive power of Google search engine query volume of future housing price change (shift direction) by (i) the introduction of a research approach that combines...
-
Predicting Ice Phenomena in a River Using the Artificial Neural Network and Extreme Gradient Boosting
PublikacjaForecasting ice phenomena in river systems is of great importance because these phenomena are a fundamental part of the hydrological regime. Due to the stochasticity of ice phenomena, their prediction is a difficult process, especially when data sets are sparse or incomplete. In this study, two machine learning models—Multilayer Perceptron Neural Network (MLPNN) and Extreme Gradient Boosting (XGBoost)—were developed to predict...
-
ANALYSIS OF POSSIBILITIES FOR THE USE OF VOLUME-DELAY FUNCTIONS IN THE PLANNING MODULE OF THE TRISTAR SYSTEM
PublikacjaTravel time is a measure commonly used for traffic flow modelling and traffic control. It also helps to evaluate the quality of traffic control systems in urban areas. Traffic control systems that use traffic models to predict changes and disruptions in vehicle flows have to use vehicle speed-prediction models. Travel time estimation studies the effects of traffic volumes on a street section at an average speed. The TRISTAR Integrated...
-
Long-term hindcast simulation of water temperature and salinity in the Baltic Sea
Dane BadawczeThe dataset contains the results of numerical modelling of water temperature and salinity over a period of 50 years (1958-2007) in the Baltic Sea. A long-term hindcast simulation was performed using a three-dimensional hydrodynamic model PM3D (Kowalewski and Kowalewska-Kalkowska, 2017), a new version of the M3D model (Kowalewski, 1997). The hydrodynamic...
-
Long-term hindcast simulation of currents in the Baltic Sea
Dane BadawczeThe dataset contains the results of numerical modelling of currents over a period of 50 years (1958-2007) in the Baltic Sea . A long-term hindcast simulation was performed using a three-dimensional hydrodynamic model PM3D (Kowalewski and Kowalewska-Kalkowska, 2017), a new version of the M3D model (Kowalewski, 1997). The hydrodynamic model was coupled...
-
Fundamenty palowe, obliczenia z zastosowaniem zasad Eurokodu 7 i doświadczeń krajowych
PublikacjaPrzedstawiono zagadnienia obliczania fundamentów palowych w nawiązaniu do zaleceń Eurokodu 7. Zwrócono uwagę, że zgodnie z założeniami Eurokodu 7, projektant i inżynier ma swobodę w wyborze metod obliczeniowych.Przytoczono i zarekomendowano metody i propozycje miedzy innymi obliczania statycznego układów palowych, określania nośności pali, prognozowania osiadań fundamentów palowych oraz charakterystyk obciążenie-osiadanie pali...
-
GIS Solution for Weather Forecast Data Analysis
PublikacjaIn this paper authors present the GIS system for the analysis of the numerical weather prediction data. This kind of data has multidimensional character (three dimensions and time) and its analysis should consider all the available factors. Proposed GIS system consists of RASDAMAN application with implemented OLAP cube mechanism, which enables the user to process data in the spatial-time domain. It also simplifies the meteorological...
-
A new quantum-inspired approach to reduce the blocking probability of demands in resource-constrained path computation scenarios
PublikacjaThis article presents a new approach related with end-to-end routing, which, owing to quantum-inspired mecha-nisms of prediction of availability of network resources, results in improved blocking probability of incoming requests to establish transmission paths. The proposed scheme has been analyzed for three network topologies and several scenarios of network load. Obtained results show a significant (even twofold) reduction of...