Search results

1

ПРО МЕХАНІЗМ МЕТАКОГНІТИВНОГО РОЗВИТКУ ЗДІБНОСТЕЙ СТУДЕНТІВ В ПРОЦЕСІ МАТЕМАТИЧНОЇ ПІДГОТОВКИ

100%

Тетяна Є.

Педагогічні науки: теорія, історія, інноваційні технології

|

2017

|

issue 2(66)

70-80

EN

Active approach to the cognitive process provides the conditions of cognitive development, cognitive development of the abilities. The articleis dedicatedto theproblemof development of mathematical abilities of students of technical profile in the modern university. It is noted that detailed understanding of the mechanism of cognitive and metacognitive development of students’ abilities in the context of increasing mathematical and professional culture is on a par with the strategic components of modernization of the mathematical education in the three-stage system of higher education.The article explores the mechanisms of constructing cognitive and metacognitive space in accordance with modern views of modeling of the functional properties of neural networks.The obtained information will help to answer the question about the mechanisms of information storage and access in the processes of thinking. The approach to the analysis of complex mechanisms of thinking process, when a neural network is represented by a two-component structure, is grounded. Static image in the form of semantic relations of static images is stored in a static neural structure. Spatio-temporal images in the form of semantic networks of dynamic situations are stored in dynamic neural structure. The mechanism of the formation of static and dynamic semantic networks, in which images and situations in the process of thinking arise chaotically, is studied. The author believes that neural network with chaotic neurons triggers the appearance of chaotic images in the process of thinking. In this model, chaotic and not chaotic neurons have different parameters of interaction and “refractaire”. The role of chaotic neurons is reduced to the choice part of the semantic communications and to the merger with other semantic communication. The author concludes that such a process in dynamic semantic networks leads to unexpected spatio-temporal images. The process of the emergence of unexpected static images can be represented as the development of meta-skills; the emergence of the spatio-temporal situations can be linked to the mechanism of metacognition. The arguments point to the existence in thinking of the mechanism of metacognition, when the unexpected images, new algorithms for solving the problem, the strategy and the tactics of the behavior are formed. The emergence of thinking processes with elements of metacognition stimulates cognitive system of the individual to further development of skills and enhance mathematical and professional culture.

2

Comparison of the accuracy of forecasts based on neural networks before and after the outbreak of the COVID-19 pandemic on the example of selected exchange rates

100%

Morkowski J.

Przegląd Statystyczny

|

2022

|

vol. 69

|

issue 4

41-60

EN

This article examines the impact of the COVID-19 pandemic on the accuracy of forecasts for three currency pairs before and after its outbreak based on neural networks (ELM, MLP and LSTM) in terms of three factors: the forecast horizon, hyper parameterisation and network type.

3

Practical Comparison of Results of Statistic Regression Analysis and Neural Network Regression Analysis

100%

Marek V.

Littera Scripta

|

2016

|

issue 2

156-168

EN

There are many discussions and arguments about accuracy of the results of statistic regression analysis and neural network regression analysis among experts. Of course all of them look for the best method usable in practice. The objective of the contribution is to use a case study to answer the question which of the methods provides better results. As a case study will be used time series of US Gross Domestic Product. It starts in 1966 and ends in 2014. The future development of the variable for the following 20 years will be calculated. Software Statistica 12 developed by Dell corporation will be used for both analyses. The first one will use multiple regression of the software. The second one will use data mining section with its neural networks. Generalized Regression Neural Networks, Multi-layer Perceptron Network, Radial Basis Function Neural Networks, Linear Neural Networks will by calculated. The results are two curves, the first based on statistic regression analysis. The second curve is provided by the best model of neural networks. Both the curves will describe development of the US GDP in 20 next years.

4

How to reconstruct the unknown physical quantities using neural networks?

100%

Wolter M., Institute of Nuclear Physics P. A. o. S.

Acta Universitatis Lodziensis. Folia Oeconomica

|

2008

|

vol. 216

EN

In this article an application of neural networks to the reconstruction of unknown physical quantities in particle physics is presented. As an example the mass reconstruction of the hypothetical Higgs boson in the typical high energy physics experiment is used. Monte Carlo events are used to determine the probability distributions of observables (energies of two jets and the angle between them) for various Higgs boson mass, which are later fitted using a Neural Network. These distributions are used to determine the mass probability distribution of the measured particle. The mass is reconstructed without knowing the functional dependence between the observables and the measured quantity. The miscalibration of the measured quantities is automatically corrected in this method.

PL

W artykule zaprezentowane jest zastosowanie sieci neuronowych do rekonstrukcji nieznanych wielkości w fizyce cząstek elementarnych. Jako przykład użyta jest rekonstrukcja masy hipotetycznego bozonu Higgsa oparta na symulowanych danych. Dane te zostały użyte do wyznaczenia rozkładów prawdopodobieństwa mierzonych wielkości (energie dwóch dżetów oraz kąt pomiędzy nimi) dla różnych mas cząstki Higgsa. Rozkłady te zostały następnie sparametryzowane za pomocą sieci neuronowych oraz wyznaczenia rozkładu prawdopodobieństwa masy mierzonej cząstki. Masa jest wyznaczona bez użycia zależności funkcyjnej pomiędzy mierzonymi wielkościami a rekonstruowaną masą. Kalibracja wielkości pomiarowych jest automatycznie korygowana poprzez rozkłady prawdopodobieństwa.

5

Cluster analysis of the impact of currency regime type on features of the spread of financial crises

88%

STRELCHENKO I.

Operations Research and Decisions

|

2018

|

vol. 28

|

issue 2

71-84

EN

The paper presents the results of research on the impact of currency regime type on features of the spread of financial crises. The focus is on constructing a neural network to identify groups of countries exhibiting similar behaviour in the dynamics of the index of flexibility in the effective exchange rate, exchange market pressure and external public debt markets in times of sudden changes in the environment. The alpha-criterion for optimality constructed in this way is based on the use of a concordance coefficient. The result of modelling is a self-organization map with a hidden layer consisting of six clusters. This cluster structure allows us to analyse the relationship between the type of currency regime and the consequences of the global crisis in 2007–2009 for the domestic financial markets of the investigated countries. It is found that the result of the division is significantly influenced by the proximity of administrative boundaries and historically predetermined close trade and economic channels of interaction between economies. The results obtained can be used to formulate directions in the currency policies of developing countries, including Ukraine.

6

Demand forecasting: an alternative approach based on technical indicator Pbands

88%

Kolková A., Ključnikov A.

Oeconomia Copernicana

|

2021

|

vol. 12

|

issue 4

1063-1094

EN

Research background: Demand forecasting helps companies to anticipate purchases and plan the delivery or production. In order to face this complex problem, many statistical methods, artificial intelligence-based methods, and hybrid methods are currently being developed. However, all these methods have similar problematic issues, including the complexity, long computing time, and the need for high computing performance of the IT infrastructure. Purpose of the article: This study aims to verify and evaluate the possibility of using Google Trends data for poetry book demand forecasting and compare the results of the application of the statistical methods, neural networks, and a hybrid model versus the alternative possibility of using technical analysis methods to achieve immediate and accessible forecasting. Specifically, it aims to verify the possibility of immediate demand forecasting based on an alternative approach using Pbands technical indicator for poetry books in the European Quartet countries. Methods: The study performs the demand forecasting based on the technical analysis of the Google Trends data search in case of the keyword poetry in the European Quartet countries by several statistical methods, including the commonly used ETS statistical methods, ARIMA method, ARFIMA method, BATS method based on the combination of the Cox-Box transformation model and ARMA, artificial neural networks, the Theta model, a hybrid model, and an alternative approach of forecasting using Pbands indicator. The study uses MAPE and RMSE approaches to measure the accuracy. Findings & value added: Although most currently available demand prediction models are either slow or complex, the entrepreneurial practice requires fast, simple, and accurate ones. The study results show that the alternative Pbands approach is easily applicable and can predict short-term demand changes. Due to its simplicity, the Pbands method is suitable and convenient to monitor short-term data describing the demand. Demand prediction methods based on technical indicators represent a new approach for demand forecasting. The application of these technical indicators could be a further forecasting models research direction. The future of theoretical research in forecasting should be devoted mainly to simplifying and speeding up. Creating an automated model based on primary data parameters and easily interpretable results is a challenge for further research.

7

Artificial intelligence in predicting the bankruptcy of non-financial corporations

75%

Gavurova B., Jencova S., Bacik R., Miskufova M., Letkovsky S.

Oeconomia Copernicana

|

2022

|

vol. 13

|

issue 4

1215-1251

EN

Research background: In a modern economy, full of complexities, ensuring a business' financial stability, and increasing its financial performance and competitiveness, has become especially difficult. Then, monitoring the company's financial situation and predicting its future development becomes important. Assessing the financial health of business entities using various models is an important area in not only scientific research, but also business practice. Purpose of the article: This study aims to predict the bankruptcy of companies in the engineering and automotive industries of the Slovak Republic using a multilayer neural network and logistic regression. Importantly, we develop a novel an early warning model for the Slovak engineering and automotive industries, which can be applied in countries with undeveloped capital markets. Methods: Data on the financial ratios of 2,384 companies were used. We used a logistic regression to analyse the data for the year 2019 and designed a logistic model. Meanwhile, the data for the years 2018 and 2019 were analysed using the neural network. In the prediction model, we analysed the predictive performance of several combinations of factors based on the industry sector, use of the scaling technique, activation function, and ratio of the sample distribution to the test and training parts. Findings & value added: The financial indicators ROS, QR, NWC/A, and PC/S reduce the likelihood of bankruptcy. Regarding the value of this work, we constructed an optimal network for the automotive and engineering industries using nine financial indicators on the input layer in combination with one hidden layer. Moreover, we developed a novel prediction model for bankruptcy using six of these indicators. Almost all sampled industries are privatised, and most companies are foreign owned. Hence, international companies as well as researchers can apply our models to understand their financial health and sustainability. Moreover, they can conduct comparative analyses of their own model with ours to reveal areas of model improvements.

8

Modelling Electricity Price Expectations in a Day-Ahead Market: A Case of Latvia

75%

Bobinaite V., Zuters J.

Economics and Business

|

2016

|

vol. 29

|

issue 1

12-26

EN

The paper aims at modelling the electricity generator’s expectations about price development in the Latvian day-ahead electricity market. Correlation and sensitivity analysis methods are used to identify the key determinants of electricity price expectations. A neural network approach is employed to model electricity price expectations. The research results demonstrate that electricity price expectations depend on the historical electricity prices. The price a day ago is the key determinant of price expectations and the importance of the lagged prices reduces as the time backwards lengthens. Nine models of electricity price expectations are prepared for different natural seasons and types of the day. The forecast accuracy of models varies from high to low, since errors are 7.02 % to 59.23 %. The forecasting power of models for weekends is reduced; therefore, additional determinants of electricity price expectations should be considered in the models and advanced input selection algorithms should be applied in future research. Electricity price expectations affect the generator’s loss through the production decisions, which are made considering the expected (forecasted) prices. The models allow making the production decision at a sufficient level of accuracy.

9

Predicting Dropout Student: An Application of Data Mining Methods in an Online Education Program

75%

Yukselturk E., Ozekes S., Türel Y. K.

European Journal of Open, Distance and E-Learning

|

2014

|

vol. 17

|

issue 1

118-133

EN

This study examined the prediction of dropouts through data mining approaches in an online program. The subject of the study was selected from a total of 189 students who registered to the online Information Technologies Certificate Program in 2007-2009. The data was collected through online questionnaires (Demographic Survey, Online Technologies Self-Efficacy Scale, Readiness for Online Learning Questionnaire, Locus of Control Scale, and Prior Knowledge Questionnaire). The collected data included 10 variables, which were gender, age, educational level, previous online experience, occupation, self efficacy, readiness, prior knowledge, locus of control, and the dropout status as the class label (dropout/not). In order to classify dropout students, four data mining approaches were applied based on k-Nearest Neighbour (k-NN), Decision Tree (DT), Naive Bayes (NB) and Neural Network (NN). These methods were trained and tested using 10-fold cross validation. The detection sensitivities of 3-NN, DT, NN and NB classifiers were 87%, 79.7%, 76.8% and 73.9% respectively. Also, using Genetic Algorithm (GA) based feature selection method, online technologies self-efficacy, online learning readiness, and previous online experience were found as the most important factors in predicting the dropouts.

10

Wrzeciono CNC małej mocy jako obiekt badawczy dla metod CI na przykładzie detekcji prędkości

75%

Piecuch G.

Dydaktyka informatyki

|

2017

|

vol. (12)2017

224-232

PL

Artykuł omawia zastosowanie stanowiska dydaktycznego wyposażonego we wrzeciono CNC małej mocy do nauki metod inteligencji obliczeniowej na kierunkach technicznych wyższych uczelni np. automatyka i robotyka. Przedstawiono praktyczny przykład ćwiczenia, które zaznaja-mia studentów z rzeczywistym sprzętem sprzężonym z oprogramowaniem inżynierskim takim jak Matlab/Simulink, umożliwiającym stosowanie i analizę działania poszczególnych metod CI, także w czasie rzeczywistym.

XX

The article discusses the use of didactic station equipped with a low-power CNC spindle to teach computational intelligence methods to technical majors at universities, e.g. Automatic con-trol and Robotics. This paper presents a practical example of exercises, which acquaint students with actual hardware integrated with engineering software such as Matlab/Simulink, which allows implementation and analysis of the operation of various CI methods, also in real time.

11

Jak mózg/umysł przetwarza język/mowę? Zarys pewnego scenariusza

71%

Nowak T.

Polonica

|

2016

|

vol. 36

111-144

EN

This paper aims to presenting the development of modern neurolinguistics research. The author reflects on the linguistic interpretation of the results of the neurolinguistics experiments. At the end the author put an catalog of the correlations between language functions and neural networks and extensive bibliography, containing last publications in the field of neurolinguistics.

12

Innowacyjne rozwiązania finansowe dla inteligentnego rozwoju miast

63%

Waśniewski K., Maicki M.

MAZOWSZE Studia Regionalne

|

2019

|

issue 29

35-65

PL

Niniejszy artykuł przedstawia wyniki badań nad zmianami społeczno-ekonomicznymi w polskich miastach w kontekście wyzwań związanych ze zmianami technologicznymi. Metody klasycznej analizy ekonometrycznej połączono w artykule z zastosowaniem sieci neuronalnej dla zidentyfikowania prawidłowości rozwojowych w siedmiu dużych polskich miastach: Warszawie, Krakowie, Poznaniu, Wrocławiu, Gdańsku, Łodzi i Kielcach. Wykonane badania dostarczają mieszanych przesłanek na temat tendencji na przyszłość, zwłaszcza w zakresie demografii. Pewne są jednak dwa zjawiska: wzrost skłonności do zakładania nowych przedsiębiorstw oraz spadek udziału wydatków inwestycyjnych w budżetach miejskich. Symulacja za pomocą sieci neuronalnej wskazuje na możliwość szybkiej eksplozji demograficznej badanych miast, mimo obecnej stagnacji, oraz możliwość dalszego, znacznego wzmocnienia zachowań przedsiębiorczych. W konkluzji artykułu omawiany jest zarys rozwiązania finansowego wykorzystującego zaobserwowane tendencje. Rozwiązanie to łączy elementy funduszu inwestycyjnego z crowdfundingiem (finansowanie społecznościowe).

EN

This article studies socio-economic changes in Polish cities in the context of technological change and the resulting challenges. Classical econometric analysis has been combined with a neural network, in order to define development patterns in seven big Polish cities: Warsaw, Cracow, Poznań, Wrocław, Gdańsk, Łodź and Kielce. The study provides mixed indications concerning future tendencies, specifically as regards demographics. Still, two phenomena are certain: a growing tendency to start new businesses, and a decrease in the relative importance of investment outlays in municipal budgets. A simulation with a neural network indicates the possibility of a demographic explosion, despite the present stagnation, as well as a further, strong increase in the incidence of entrepreneurial behaviour. In the conclusion, this article outlines a financial solution that the observed tendencies, and combines crowdfunding with an investment fund.

13

The model of multifunctional neural element of intelligent systems

63%

MARTYNIUK T., KOZHEMIAKO A., BUDA A., KUPERSHTEIN L.

Edukacja-Technika-Informatyka

|

2013

|

vol. 4

|

issue 2

366-371

EN

The article shows the features of realization of multioperand processing in neural structures on the base of difference cuts, that allow to expand functional capabilities and to reduce time consumptions in neural processing. The structural organization of the parallel-pipeline processor for neural-like vector data processing on the DCs base are proposed. This parallel-pipeline processor on CPLD base are implemented, which allow realize neural chip with a fragment of the neural network layer.

14

Využití umělé inteligence pro analýzu pohybu lidí ve veřejném prostoru. Případová studie Mariánské náměstí v Praze

51%

Zdráhalová J., Kurilla L., Prášek P., Berka Z.

Urbanismus a územní rozvoj

|

2023

|

issue 5

26-35

EN

The search for a relationship between the nature of public space and the ways in which people use that space is one of the standard tasks of urban design (Sitte, 2012; Whyte, 1980; Gehl, 1971; Lynch, 1960). Human activities in space and people's reactions to the urban and architectural characteristics of a place can be monitored through mental maps and interviews (Lynch, 1960; Benda et al., 1978), photographs and films (Whyte, 1980; Gehl, 1971), or through local experiences and observations, such as following people's routes by tracing a trampled footprint in the snow (Sitte, 2012). The knowledge gained is typically used to create an informed design of a public space that addresses, in particular, the usability of the space, safety issues, and the elimination of collisions between road traffic and people's residential activities. This text presents an urban experiment that tested the possibilities of involving artificial intelligence in mapping activities in public space. It presents the results of a four-year research, supported by TA ČR NCK TN01000024, which used CCTV camera recordings to monitor activities in a given public space. Specifically, we focused on Mariánské Square in the capital city of Prague, where five CCTV cameras that continuously monitored the space of the square were placed. Data collection took place in two cycles, each lasting four days. The first one took place in October 2019 before the reconstruction of the space, the second one a month later - after the road traffic in the square was regulated and new furnishing was added (Prague chairs, a large table, mobile flowerpots and concrete blocks to prevent the traffic). In both cases, the space was recorded from Thursday to Sunday to capture both the weekdays and the weekend. The collected data from the CCTV cameras was converted into trajectories using a neural network, which was used to create heatmaps. The heatmap shows the density of mobile and stationary activities of people in the square area. The physical space was described in terms of material design, height characteristics (curbs, stairs), location of furnishings, parking spaces and traffic organization. The heatmap intensity was compared with the physical characteristics of the space in order to find connections, relationships and a deeper understanding of the patterns of people's behaviour in the space. The comparison of the results of both observations showed how the specific design of the square influences the frequency of people in the space, increases residential activities and also leads to the use of elements in the space for new and unintended activities (for example, the use of concrete blocks as benches). The use of artificial intelligence to collect and interpret people's movements in public space has shown benefits that conventional participant observation does not provide. These include the objectivity of the collected data not burdened by the personalities of the observers, the comparability of data from different time periods, the possibility of accurately collecting data from large areas of public space, the possibility of accurately locating the trajectories of people in space, and the representation of dynamic patterns of space use. Furthermore, the data collected in this way allows for detailed interpretations of the relationship between people's trajectories, space characteristics and other environmental influences such as temperature, shading, noise pollution, etc., however, these are beyond the scope of this paper.

XX

Tento text zkoumá možnosti využití umělé inteligence pro interpretaci aktivit ve veřejném prostoru měst. Aplikací neuronové sítě na kamerové záznamy, které po čtyři dny snímaly aktivity na Mariánském náměstí v Praze, jsou vygenerovány trajektorie jednotlivých uživatelů prostoru. Promítnutím jejich přesné polohy do půdorysu náměstí získáváme tzv. heatmapy pohybu osob, tedy zobrazení hustoty trajektorií. Výhodou tohoto přístupu je získání velkého množství informací o pohybu v celé ploše náměstí v dlouhém časovém úseku. Oproti standardnímu zkoumání metodou zúčastněného pozorování nebo pouhým počítáním osob, které projdou přes určený práh, jsou tyto informace nezatížené osobou výzkumníka, jsou přesné a mapují prostor jako celek. Pro komplexnější obrázek o využití prostoru jsme vyvinuli sémantický anotátor – nástroj, pomocí kterého výzkumník přiřazuje na základě kamerových záznamů aktivity osob k jednotlivým trajektoriím. Větší automatizace celého procesu by umožnila provádět složitější úlohy o hledání vztahu mezi daným místem a aktivitami lidí v něm.

15

Heuristic analysis in the process of detecting serial offenders, part two -Victimology and Crime Scene Reconstruction through the lenses of Abductive Reasoning

51%

Markiewicz W.

Edukacja Humanistyczna

|

2021

|

issue 2

65-77

EN

In the article, victimology, from the point of view of satisficing is defined. Utilization of the abductive reasoning in analysis of crime scene is explained. Here, the cognitive limits related to criminal profiling are determined. The article is the second in a series of publications describing the use of computer aided heuristic analysis in the process of detecting perpetrators of serial crime (ViCLAS).Using the Konolidge’s and Bylander’s definitions, abductive reasoning is explained. The paper introduces reader to basics of an AI neural network and its potential of use in above mentioned process. Author presents engagement of the abductive reasoning in to process supervised learning.

PL

W artykule zdefiniowano wiktymologię z punktu widzenia satisficing. Wyjaśniono wykorzystanie rozumowania abdukcyjnego w analizie miejsca przestępstwa. Określono tutaj limity poznawcze związane z profilowaniem przestępstw. Artykuł jest drugim w serii publikacji opisujących zastosowanie komputerowej analizy heurystycznej w procesie wykrywania sprawców przestępstw seryjnych (ViCLAS). Korzystając z definicji Konolidge’a i Biglander’a, wyjaśniono rozumowanie abdukcyjne. W artykule, czytelnikowi przedstawione zostają podstawy sieci neuronowej i jej potencjał stosowania w wyżej wymienionym procesie. Autor przedstawia również zastosowanie rozumowania abdukcyjnego w procesie uczenia nadzorowanego.

Refine search results

ПРО МЕХАНІЗМ МЕТАКОГНІТИВНОГО РОЗВИТКУ ЗДІБНОСТЕЙ СТУДЕНТІВ В ПРОЦЕСІ МАТЕМАТИЧНОЇ ПІДГОТОВКИ

Comparison of the accuracy of forecasts based on neural networks before and after the outbreak of the COVID-19 pandemic on the example of selected exchange rates

Practical Comparison of Results of Statistic Regression Analysis and Neural Network Regression Analysis

How to reconstruct the unknown physical quantities using neural networks?

Cluster analysis of the impact of currency regime type on features of the spread of financial crises

Demand forecasting: an alternative approach based on technical indicator Pbands

Artificial intelligence in predicting the bankruptcy of non-financial corporations

Modelling Electricity Price Expectations in a Day-Ahead Market: A Case of Latvia

Predicting Dropout Student: An Application of Data Mining Methods in an Online Education Program

Wrzeciono CNC małej mocy jako obiekt badawczy dla metod CI na przykładzie detekcji prędkości

Jak mózg/umysł przetwarza język/mowę? Zarys pewnego scenariusza

Innowacyjne rozwiązania finansowe dla inteligentnego rozwoju miast

The model of multifunctional neural element of intelligent systems

Využití umělé inteligence pro analýzu pohybu lidí ve veřejném prostoru. Případová studie Mariánské náměstí v Praze

Heuristic analysis in the process of detecting serial offenders, part two -Victimology and Crime Scene Reconstruction through the lenses of Abductive Reasoning