Informacja

Drogi użytkowniku, aplikacja do prawidłowego działania wymaga obsługi JavaScript. Proszę włącz obsługę JavaScript w Twojej przeglądarce.

Wyszukujesz frazę "classification model" wg kryterium: Temat


Wyświetlanie 1-4 z 4
Tytuł:
Neural networks as performance improvement models in intelligent CAPP systems
Autorzy:
Rojek, I.
Powiązania:
https://bibliotekanauki.pl/articles/971020.pdf
Data publikacji:
2010
Wydawca:
Polska Akademia Nauk. Instytut Badań Systemowych PAN
Tematy:
classification model
neural network
tool
manufacturing operation
Opis:
The paper presents neural networks as performance improvement models in intelligent computer aided process planning systems (CAPP systems). For construction of these models three types of neural networks were used: linear network, multi-layer network with error backpropagation, and the Radial Basis Function network (RBF). The models were compared. Due to the comparison, we can say which type of neural network is the best for selection of tools for manufacturing operations. Tool selection for manufacturing operation is a classification problem. Hence, neural networks were built as classification models, meant to improve tool selection for manufacturing. The study was done for selected manufacturing operations: turning, milling and grinding. Models for the milling operation were presented in detail.
Źródło:
Control and Cybernetics; 2010, 39, 1; 54-68
0324-8569
Pojawia się w:
Control and Cybernetics
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Single-ended quality measurement of a music content via convolutional recurrent neural networks
Autorzy:
Organiściak, Kamila
Borkowski, Józef
Powiązania:
https://bibliotekanauki.pl/articles/1849158.pdf
Data publikacji:
2020
Wydawca:
Polska Akademia Nauk. Czytelnia Czasopism PAN
Tematy:
audio data analysis
artefacts detection
convolutional neural networks
recurrent neural networks
classification model
Opis:
The paper examines the usage of Convolutional Bidirectional Recurrent Neural Network (CBRNN) for a problem of quality measurement in a music content. The key contribution in this approach, compared to the existing research, is that the examined model is evaluated in terms of detecting acoustic anomalies without the requirement to provide a reference (clean) signal. Since real music content may include some modes of instrumental sounds, speech and singing voice or different audio effects, it is more complex to analyze than clean speech or artificial signals, especially without a comparison to the known reference content. The presented results might be treated as a proof of concept, since some specific types of artefacts are covered in this paper (examples of quantization defect, missing sound, distortion of gain characteristics, extra noise sound). However, the described model can be easily expanded to detect other impairments or used as a pre-trained model for other transfer learning processes. To examine the model efficiency several experiments have been performed and reported in the paper. The raw audio samples were transformed into Mel-scaled spectrograms and transferred as input to the model, first independently, then along with additional features (Zero Crossing Rate, Spectral Contrast). According to the obtained results, there is a significant increase in overall accuracy (by 10.1%), if Spectral Contrast information is provided together with Mel-scaled spectrograms. The paper examines also the influence of recursive layers on effectiveness of the artefact classification task.
Źródło:
Metrology and Measurement Systems; 2020, 27, 4; 721-733
0860-8229
Pojawia się w:
Metrology and Measurement Systems
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Crash data reporting systems in Fourteen Arab countries: challenges and improvement
Autorzy:
Abounoas, Zahira
Raphael, Wassim
Badr, Yarob
Faddoul, Rafic
Guillaume, Anne
Powiązania:
https://bibliotekanauki.pl/articles/1833641.pdf
Data publikacji:
2020
Wydawca:
Polska Akademia Nauk. Czytelnia Czasopism PAN
Tematy:
road accidents
road safety
information system
reporting system
variables selection
classification model
wypadek drogowy
bezpieczeństwo na drogach
system informacyjny
systemy raportowania
dobór zmiennych
model klasyfikacji
Opis:
Traffic crash fatalities and serious injuries still represent a big burden for most Arab countries because the actual policies, strategies, and interventions are based on poorly collected data. Through this paper, we assessed the crash data reporting systems in Fourteen Arab countries via a survey conducted to identify the fundamental dysfunctions at the management and data collection levels. Then, to address some of the dataset problems, we had applied data mining technics to select a minimum of variables (crash, vehicle, and road user) that should be collected for a better understanding of crash circumstances. For this raison, three methods of selection (correlation, information gain, and gain ratio) and seven classifiers (naive Bayes, nearest neighbour, random forest, random tree, J48, reduced error pruning tree, and bagging) were tested and compared to identify the variables that affect significantly the crashes severity. Decision trees family of classifiers showed the best performance based on the analysis of the area under the curve. The explanatory variables obtained from the data mining process were combined with other descriptive variables to maintain traceability. As a result, we produced hybrid lists of variables for the crash, vehicle, and road user, each contains 25 variables. Finally, in order to propose a cost-effective solution to switch from manual to electronic data collection, we got inspired by a tool used to track animals to create and customize a unified e-form for handheld devices, in order to ensure easy entering of the harmonized data for the entire region based on our selected lists of variables. The tool verified the countries requirements especially by enabling data collection and transfer with and without the internet, and by allowing data analysis thought its built-in Geographic Information System (GIS) capabilities.
Źródło:
Archives of Transport; 2020, 56, 4; 73-88
0866-9546
2300-8830
Pojawia się w:
Archives of Transport
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Predykcyjny model dobowej emisji energii sejsmicznej indukowanej eksploatacją górniczą
Predictive model of the daily release of seismic energy induced by mining
Autorzy:
Jakubowski, J.
Lenart, Ł.
Ożóg, Ł.
Powiązania:
https://bibliotekanauki.pl/articles/166220.pdf
Data publikacji:
2014
Wydawca:
Stowarzyszenie Inżynierów i Techników Górnictwa
Tematy:
sejsmiczność indukowana
wstrząsy górnicze
hazard sejsmiczny
zagrożenie tąpaniami
drzewa wzmacniane
sieci neuronowe
regresja logistyczna
modele prognostyczne
modele klasyfikacyjne
induced seismicity
mining tremors
seismic hazard
rockburst hazard
data mining
boosted trees
neural networks
logistic regression
predictive model
classification model
Opis:
W artykule przedstawiono budowę i ocenę predykcyjnego modelu klasyfikacyjnego dobowej emisji energii sejsmicznej indukowanej eksploatacją ścianową węgla. Model jest oparty na danych z katalogu wstrząsów i podstawowych danych o wydobyciu i ścianach eksploatowanych w partii XVI kopalni Piast w okresie od lipca 1987 do marca 2011. Zmienną prognozowaną jest dwustanowa zmienna określająca wystąpienie dobowej sumy energii sejsmicznej wstrząsów w rejonie ściany większej lub równej wartości progowej 10/5 J. Zastosowano trzy metody analityczne w schemacie data mining: regresję logistyczną, sieci neuronowe i drzewa wzmacniane. Jako najlepszy do celów prognozy wybrano model drzew wzmacnianych. Wyniki na zbiorze walidacyjnym pokazały jego dobrą zdolność predykcyjną, co zachęca do dalszych badań.
This paper presents the design and evaluation of the classification predictive model of daily seismic activity induced by longwall mining. The model combines seismic catalog data, output volume and basic characteristics of the longwall faces in sector XVI of the Piast coal mine over the period of July 1987 to March 2011. The predicted variable defines the occurrence of a daily sum of seismic energy released nearby the longwall, that is greater than or equal to the threshold value of 10/5 J. Machine learning and statistical methods were applied, namely neural networks, stochastic gradient boosted trees and logistic regression. The design and evaluation of the classification predictive models were presented. The boosted tree model appeared to meet the prediction quality criteria best. The results of the model evaluation show its promising predictive capability.
Źródło:
Przegląd Górniczy; 2014, 70, 3; 18-25
0033-216X
Pojawia się w:
Przegląd Górniczy
Dostawca treści:
Biblioteka Nauki
Artykuł
    Wyświetlanie 1-4 z 4

    Ta witryna wykorzystuje pliki cookies do przechowywania informacji na Twoim komputerze. Pliki cookies stosujemy w celu świadczenia usług na najwyższym poziomie, w tym w sposób dostosowany do indywidualnych potrzeb. Korzystanie z witryny bez zmiany ustawień dotyczących cookies oznacza, że będą one zamieszczane w Twoim komputerze. W każdym momencie możesz dokonać zmiany ustawień dotyczących cookies