Browsing by Subject "data mining"

Now showing 1 - 20 of 23

Access status: Metadata only ,
Analiza algorytmów eksploracji danych bazujących na teorii zbiorów przybliżonych
(Data obrony: 2018-09-21) Pięta, Piotr
Wydział Elektrotechniki, Automatyki, Informatyki i Inżynierii Biomedycznej
Access status: Restricted ,
Analiza efektywności oczyszczania ścieków w wybranej oczyszczalni ścieków z wykorzystaniem metod eksploracji danych
(Data obrony: 2016-10-24) Kozak, Aneta
Wydział Geologii, Geofizyki i Ochrony Środowiska
W pracy wykorzystując metody eksploracji danych wykonano analizę efektywności oczyszczania ścieków. Obiektem badań była oczyszczalnia ścieków w Trepczy. W pracy wykorzystano wartości wskaźników ścieków surowych, procent redukcji zanieczyszczeń oraz dane pogodowe. Jako narzędzie eksploracji danych został wybrany model regresji wielorakiej oraz podstawowe statystyki opisowe. Dzięki analizie zebranych danych oraz wykorzystując powyższe metody udało się ocenić, czy redukcja zanieczyszczeń ścieków w oczyszczalni ścieków w Trepczy spełnia normy polskie oraz europejskie. Dodatkowo podjęto próbę stworzenia modelu predykcji redukcji zanieczyszczeń w ściekach na kolejne lata. Na zakończenie w pracy zwrócono uwagę na szczególne znaczenie poprawnego funkcjonowania oczyszczalni ścieków dla środowiska i społeczeństwa.
Access status: Open Access ,
Analiza przemieszczeń pala w sprężystym ośrodku trójwarstwowym przy użyciu funkcji MARS
(Wydawnictwa AGH, 2011) Kania, Mieczysław; Kubzdela, Albert
Pile foundations are used on sites with compressible soils. In some cases a pile passes through layers having large differences in soil modulus values. Displacements of a pile toe depends on position, thickness and geotechnical properties of soil layers. Influence of those factors on displacements of the pile has been investigated by the finite element method analysis the axially-symmetrical elastic problem, in the multi-factorial numerical experiment. The computations were conducted for various combinations of the main factors, such as: modulus of elasticity distribution in the three-layered medium and dimensions of particular layers. As the result of the numerical experiment, substantial amount of data was collected. The way to improve understanding of the investigated relationships, was application of a relatively novel exploratory analysis technique: Multivariate Adaptive Regression Splines (MARs). Detailed discussion of the factorial interactions in received MARs approximation is presented in the paper.
Access status: Restricted ,
Asocjacyjny system wydajnej automatycznej klasteryzacji i eksploracji danych
(Data obrony: 2017-07-04) Socha, Agata
Wydział Elektrotechniki, Automatyki, Informatyki i Inżynierii Biomedycznej
Access status: Open Access ,
Aspekty technologiczne i systemowe pozyskiwania informacji z otwartych źródeł
(Wydawnictwa AGH, 2011) Nawarecki, Edward; Kluska-Nawarecka, Stanisława; Dziaduś-Rudnicka, Joanna; Wilk-Kołodziejczyk, Dorota
W pracy rozważany jest problem poszukiwania informacji o charakterze technologicznym z sieci Internet. Przedstawiono wyniki wstępnych eksperymentów dotyczących eksploracji wiedzy o technologiach odlewniczych ze stron WWW. Zaprezentowano również schemat funkcjonalny oraz niektóre procedury obliczeniowe, komputerowego systemu do automatycznego tworzenia problemowo zorientowanych komponentów wiedzy technologicznej.
Access status: Open Access ,
Credit risk management using automatic machine learning
(AGH University of Science and Technology Press, 2020) Gaweł, Bartłomiej; Paliński, Andrzej
The article presents the basic techniques of data mining implemented in typical commercial software. They were used to assess the risk of credit card debt repayment. The article assesses the quality of classification models derived from data mining techniques and compares their results with the traditional approach using a logit model to assess credit risk. It turns out that data mining models provide similar accuracy of classification compared to the logit model, but they require much less work and facilitate the automation of the process of building scoring models.
Access status: Open Access ,
Data mining and neural network simulations can help to improve deep brain stimulation effects in Parkinson’s Disease
(Wydawnictwa AGH, 2015) Szymański, Artur; Kubis, Anna; Przybyszewski, Andrzej Wojciech
Parkinson’s Disease (PD) is primary related to substantia nigra degeneration and, thus, dopamine insufficiency. L-DOPA as a precursor of dopamine is the standard medication in PD. However, disease progression causes L-DOPA therapy efficiency decay (on-off symptom fluctuation), and neurologists often decide to classify patients for DBS (Deep Brain Stimulation) surgery. DBS treatment is based on stimulating the specific subthalamic structure: subthalamic nucleus (STN) in our case. As STN consists of parts with different physiological functions, finding the appropriate placement of the DBS electrode contacts is challenging. In order to predict the neurological effects related to different electrode-contact stimulations, we have tracked connections between the stimulated part of STN and the cortex with the help of diffusion tensor imaging (DTI). By changing a contacts number and amplitude of stimulus (proportional in size to stimulated area), we have determined connections to cortical areas and related neurological effects. We have applied data mining methods to predict which contact (and at what amplitude) should be stimulated in order to improve a particular symptom. We have compared different data mining methods: Wekas Random Forest classifier and Rough Set Exploration System (RSES). We have demonstrated that the Weka classifier was more accurate when predicting the effects of stimulations on general neurological improvements, while RSES was more accurate when using specific neurological symptoms. We have simulated other effects of stimulation related to the interruption of pathological oscillation in the basal ganglia found in PD. Our model represents possible STN neural population with inhibitory and excitatory connections that have pathologically synchronized oscillations. High-frequency electrical stimulation has interrupted synchronization. Something that is also observed in PD patients.
Access status: Open Access ,
Fundamentals of a recommendation system for the aluminum extrusion process based on data-driven modeling
(Wydawnictwa AGH, 2022) Perzyk, Marcin; Kochański, Andrzej Witold; Kozłowski, Jacek
The aluminum profile extrusion process is briefly characterized in the paper, together with the presentation of historical, automatically recorded data. The initial selection of the important, widely understood, process parameters was made using statistical methods such as correlation analysis for continuous and categorical (discrete) variables and »inverse« ANOVA and Kruskal-Wallis methods. These selected process variables were used as inputs for MLP-type neural models with two main product defects as the numerical outputs with values 0 and 1. A multi-variant development program was applied for the neural networks and the best neural models were utilized for finding the characteristic influence of the process parameters on the product quality. The final result of the research is the basis of a recommendation system for the significant process parameters that uses a combination of information from previous cases and neural models.
Access status: Open Access ,
Geoinformatyczne narzędzia w badaniu gleb
(Wydawnictwa AGH, 2006) Gruszczyński, Stanisław
Present requirements in terms of the content and purposes of documenting soils, unlike traditional soil maps, differentiate three significant circumstances: the possibility of the application of digital techniques of collecting and analysing spatial data, the increase of the role of environmental criteria for the assessment of the quality of grounds, compared to dominating earlier indexes of their values viewed only in the aspect of the needs of agriculture and forestry, and supplementing the list of the goals of documentation with the prediction of the changes in soils influenced by different factors. All these circumstances cause changes in the ways of the interpretation and understanding of spatial soil data. In methodological sense, the tools of the new approach are: including the fuzzy inference as the proper for the procedures of the classification of soils and visualization of the ranges of their units, the application of knowledge discovery in databases (KDD) and data mining (DM) in the modelling of morphologic and spatial relations useful in predicting changes in soils in new environmental conditions. Nowadays, systems of spatial information, equipped with KDD algorithms make - in the relation to the documentation of soils in technologically advanced countries - systems of the extraction of knowledge and information, allowing environmental risk assessment related to the propagation of pollutants and complex studies of their transformations under the influence of multidirectional anthropogenic influence. In the paper the application of KDD algorithms was presented in the assessment of present and forecasted state of soils.
Access status: Restricted ,
Ocena wybranych algorytmów wykrywania rzadkich zdarzeń
(Data obrony: 2018-10-18) Ziomek, Sebastian
Wydział Zarządzania
Access status: Restricted ,
Odkrywanie wiedzy z danych : wprowadzenie do eksploracji danych
(Wydawnictwo Naukowe PWN, 2006) Larose, Daniel T.
Access status: Restricted ,
Opracowanie kompilatora on-line dla kursu dydaktycznego z zakresu data mining oraz analiza porównawcza przydatności wybranych technik w nauczaniu
(Data obrony: 2021-03-22) Gawlik, Michał
Wydział Inżynierii Metali i Informatyki Przemysłowej
Access status: Restricted ,
Przegląd i analiza istniejących rozwiązań dotyczących Inteligentnych Systemów Wspomagania Decyzji
(Data obrony: 2020-12-07) Jamróz, Damian
Wydział Inżynierii Metali i Informatyki Przemysłowej
Access status: Restricted ,
Przetwarzanie i analiza strumienia rzeczywistych danych typu Big Data do prognozowania produkcji energii elektrycznej przez farmę wiatrową
(Data obrony: 2017-12-18) Nowobilski, Karol
Wydział Elektrotechniki, Automatyki, Informatyki i Inżynierii Biomedycznej
Access status: Restricted ,
Review of recent biclustering methods
(Data obrony: 2019-01-28) Drozd, Kordian
Wydział Elektrotechniki, Automatyki, Informatyki i Inżynierii Biomedycznej
Access status: Open Access ,
Studium wybranych aspektów procesów pozyskiwania i gromadzenia wiedzy w systemach zdalnego nauczania
(Wydawnictwa AGH, 2009) Skowrońska-Kapusta, Agata; Kapusta, Paweł; Goetzen, Piotr
Automatic adaptation of e-learning tools to VLE (Virtual learning environment) users' needs supports teaching/learning process. Adaptation takes place during the process of analysis of data gathered when e-platform user session has been established. Wide range of information must be analyzed. The aim of this paper is to define selected statistic data which, later on, will be treated by analysis algorithms. Collector and Analysator subsystems are introduced. Thanks to gathered data the e-learning system might become more secure and more efficient. The data can reorganize many independent VLE for one user which will lead to more individual teaching/learning. Proposed solutions define fundamental assumption of the project which uses Moodle platform an e-learning VLE.
Access status: Open Access ,
Techniki eksploracji danych w zagadnieniach eksploatacji górniczej złóż węgla kamiennego
(Wydawnictwa AGH, 2009) Brzychczy, Edyta
The paper presents a review of data mining techniques applied to the mining process issues. At the beginning, the need of knowledge discovery is described and the characteristic of data according to the mining process of deposit are given. The importance of information in management of the mining process was emphasized. In the continuation, process of data exploration was described. Attributes of data were characterized as well as the examples of data analysis techniques according to the formulated exploration tasks. The data exploratory model could be created on the basis of the wide know methodologies. In the paper two methodologies were presented: Cross-Industry Standard Process for Data Mining (CRISP-DM) and SEMMA evolved in SAS Institute. In the continuation, examples of the selected exploratory techniques in analysis of the hard coal mining process elements are presented. The following techniques are described: linear regression, neural networks, decision trees, clustering algorithms and association rules. Described techniques were applied to problems such as: methane threat prognosis, longwall gates compression, analysis of longwall equipment, analysis of longwall gate equipment and research on similarity of mining excavations.
Access status: Open Access ,
The use of data mining approach to prediction control strategies for industrial processes
(Wydawnictwa AGH, 2008) Wójcik, Waldemar; Gromaszek, Konrad
This work is intended to give a view on alternative application of data mining techniques. Paper shortly presents business intelligence (BI) solution based on SQL Server 2005 and some data mining tasks and techniques are discussed. The next part of the work focuses on prediction example using Microsoft Decision Trees. The use of discussed techniques for industrial process advisory system is also considered.
Access status: Restricted ,
Tri-klasteryzacja - przegląd metod i zastosowań
(Data obrony: 2019-01-30) Mielczarek, Łukasz
Wydział Elektrotechniki, Automatyki, Informatyki i Inżynierii Biomedycznej
Access status: Open Access ,
Using advanced data mining and integration in environmental prediction scenarios
(Wydawnictwa AGH, 2012) Habala, Ondrej; Hluchý, Ladislav; Tran, Viet; Krammer, Peter; Šeleng, Martin
We present one of the meteorological and hydrological experiments performed in the FP7 project ADMIRE. It serves as an experimental platform for hydrologists, and we have used it also as a testing platform for a suite of advanced data integration and data mining (DMI) tools, developed within ADMIRE. The idea of ADMIRE is to develop an advanced DMI platform accessible even to users who are not familiar with data mining techniques. To this end, we have designed a novel DMI architecture, supported by a set of software tools, managed by DMI process descriptions written in a specialized high-level DMI language called DISPEL, and controlled via several different user interfaces, each performing a different set of tasks and targeting different user group.