scholarly journals Wykorzystanie technik sztucznych sieci neuronowych do predykcji wybranych parametrów jako uzupełnienia zbioru danych wejściowych w konstrukcji modeli parametrycznych 3D

Nafta-Gaz ◽  
2021 ◽  
Vol 77 (7) ◽  
pp. 429-445
Author(s):  
Weronika Kaczmarczyk ◽  
◽  
Andrzej Brodzicki ◽  
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Effective Porosity ◽  
Learning Technology ◽  
Full Data ◽  
Data Set ◽  
Mean Values ◽  
Hydrocarbon Reservoir ◽  
Artificial Neural ◽  
Hydrocarbon Saturation

The article presents the possibilities of using artificial neural networks for parametric prediction in borehole profiles, the application of which supplemented the set of information in all boreholes located within the analyzed area. The approach presented in the article will be used when there is no possibility of specialized interpretation of the drilling geophysics curves, supplementing the missing data. The set of data used in the study included solutions in the profiles of 10 boreholes, four of which were characterized by the availability of the full data set analyzed in this article, including compressional wave velocity, effective porosity, hydrocarbon saturation, Young’s modulus and Poisson’s ratio. Using the technique of the operation of artificial neural networks, a prediction of missing information was carried out based on the relationships between the analyzed parameters in the wells, where the estimated data was available. In recent years, there has been a dynamic development of machine learning technology and the so-called artificial intelligence. There are very few fields of science in which they find no application. The hydrocarbon saturation parameter, despite the challenges posed by the interpretation of this parameter, was also subjected to an estimation attempt, confirming the low correlation values between the analyzed parameters and requiring much more advanced work of an individual nature. The results of parametric prediction, previously validated by characterizing the R and RMSE parameters, were applied in the next step in the spatial modeling process of all analyzed parameters. Finally, as part of the visualization of the differences between the use of an incomplete and partially estimated data set in spatial analysis, a map of mean values of the selected parameter within the analyzed interval was presented. The set of data prepared in this way allowed for a more reliable spatial reconstruction of the distribution of parameters important in the context of the characteristics of the hydrocarbon reservoir, on the basis of which, in the subsequent stages, it is possible to more fully assess the deposit potential of the analyzed object. The methodology presented in the article, supported by a real case study, is an alternative to geophysical interpretations that require financial and time resources, sometimes large numbers of boreholes, especially for areas characterized by relatively low spatial variability and tectonic complexity. The condition is the availability of the interpretation in at least several boreholes, constituting a pattern for recreating the variability of the tested parameter / parameters in the remaining profiles of the boreholes.

scholarly journals Opportunities and Constraints in Applying Artificial Neural Networks (ANNs) in Food Authentication. Honey—A Case Study

2021 ◽  
Vol 11 (15) ◽  
pp. 6723
Author(s):  
Ariana Raluca Hategan ◽  
Romulus Puscas ◽  
Gabriela Cristea ◽  
Adriana Dehelean ◽  
Francois Guyon ◽  
...  
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Training Sample ◽  
Training Data ◽  
Elemental Content ◽  
Neural Structure ◽  
Food Authentication ◽  
Data Set ◽  
Artificial Neural

The present work aims to test the potential of the application of Artificial Neural Networks (ANNs) for food authentication. For this purpose, honey was chosen as the working matrix. The samples were originated from two countries: Romania (50) and France (53), having as floral origins: acacia, linden, honeydew, colza, galium verum, coriander, sunflower, thyme, raspberry, lavender and chestnut. The ANNs were built on the isotope and elemental content of the investigated honey samples. This approach conducted to the development of a prediction model for geographical recognition with an accuracy of 96%. Alongside this work, distinct models were developed and tested, with the aim of identifying the most suitable configurations for this application. In this regard, improvements have been continuously performed; the most important of them consisted in overcoming the unwanted phenomenon of over-fitting, observed for the training data set. This was achieved by identifying appropriate values for the number of iterations over the training data and for the size and number of the hidden layers and by introducing of a dropout layer in the configuration of the neural structure. As a conclusion, ANNs can be successfully applied in food authenticity control, but with a degree of caution with respect to the “over optimization” of the correct classification percentage for the training sample set, which can lead to an over-fitted model.

Predicting Students Grades Using Artificial Neural Networks and Support Vector Machine

2019 ◽  
pp. 751-766
Author(s):  
Sajid Umair ◽  
Muhammad Majid Sharif
Keyword(s):  
Neural Networks ◽  
Support Vector Machine ◽  
Artificial Neural Networks ◽  
Student Performance ◽  
Semantic Analysis ◽  
Vital Role ◽  
Support Vector ◽  
Data Set ◽  
Important Research Topic ◽  
Artificial Neural

Prediction of student performance on the basis of habits has been a very important research topic in academics. Studies show that selection of the correct data set also plays a vital role in these predictions. In this chapter, the authors took data from different schools that contains student habits and their comments, analyzed it using latent semantic analysis to get semantics, and then used support vector machine to classify the data into two classes, important for prediction and not important. Finally, they used artificial neural networks to predict the grades of students. Regression was also used to predict data coming from support vector machine, while giving only the important data for prediction.

scholarly journals Artificial Neural Networks in Drug Design 11: Influence of Learning Rate and Momentum Factor on the Predictive Ability

2000 ◽  
Vol 68 (1) ◽  
pp. 57-64 ◽  
Author(s):  
D. Kaiser ◽  
C. Tmej ◽  
P. Chiba ◽  
K.-J. Schaper ◽  
G. Ecker
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Predictive Power ◽  
Predictive Ability ◽  
Learning Rate ◽  
Data Set ◽  
Lead Compounds ◽  
Learning Rates ◽  
Artificial Neural ◽  
Nanomolar Range

A data set of 48 propafenone-type modulators of multidrug resistance was used to investigate the influence of learning rate and momentum factor on the predictive power of artificial neural networks of different architecture. Generally, small learning rates and medium sized momentum factors are preferred. Some of the networks showed higher cross validated Q2 values than the corresponding linear model (0.87 vs. 0.83). Screening of a 158 compound virtual library identified several new lead compounds with activities in the nanomolar range.

A simulation-based method using artificial neural networks for solving the inverse kinematic problem of articulated robots

2015 ◽  
Vol 231 (3) ◽  
pp. 470-479 ◽  
Author(s):  
Mustafa Soylak ◽  
Tuğrul Oktay ◽  
İlke Turkmen
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Artificial Neural Network ◽  
Artificial Neural Networks ◽  
Inverse Kinematic ◽  
Plasma Cutting ◽  
Three Dimensional Model ◽  
Inverse Kinematic Problem ◽  
Data Set ◽  
Artificial Neural

In our article, inverse kinematic problem of a plasma cutting robot with three degree of freedom is solved using artificial neural networks. Artificial neural network was trained using joint angle values according to cartesian coordinates ( x, y, z) of end point of a robotic arm. The Levenberg–Marquardt training algorithm was applied to educate artificial neural network. To validate the designed neural network, it was tested using a new test data set which is not applied in training. A simulation was performed on a three-dimensional model of MSC.ADAMS software using angle values obtained from artificial neural network test. It was revealed from this simulation that trajectory of plasma cutting torch obtained using artificial neural network agreed well with desired trajectory.

scholarly journals The Use of Artificial Neural Networks for Forecasting of Air Temperature inside a Heated Foil Tunnel

Sensors ◽  
2020 ◽  
Vol 20 (3) ◽  
pp. 652 ◽  
Author(s):  
Sławomir Francik ◽  
Sławomir Kurpaska
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Mean Square ◽  
Internal Temperature ◽  
Data Set ◽  
External Temperature ◽  
Factors Influencing ◽  
Testing Data ◽  
Artificial Neural ◽  
Hidden Layer

It is important to correctly predict the microclimate of a greenhouse for control and crop management purposes. Accurately forecasting temperatures in greenhouses has been a focus of research because internal temperature is one of the most important factors influencing crop growth. Artificial Neural Networks (ANNs) are a powerful tool for making forecasts. The purpose of our research was elaboration of a model that would allow to forecast changes in temperatures inside the heated foil tunnel using ANNs. Experimental research has been carried out in a heated foil tunnel situated on the property of the Agricultural University of Krakow. Obtained results have served as data for ANNs. Conducted research confirmed the usefulness of ANNs as tools for making internal temperature forecasts. From all tested networks, the best is the three-layer Perceptron type network with 10 neurons in the hidden layer. This network has 40 inputs and one output (the forecasted internal temperature). As the networks input previous historical internal temperature, external temperature, sun radiation intensity, wind speed and the hour of making a forecast were used. These ANNs had the lowest Root Mean Square Error (RMSE) value for the testing data set (RMSE value = 3.7 °C).

Large-scale Groundwater Simulation using Artificial Neural Networks in the Danube River Basin

2020 ◽  
Author(s):  
Illias Landros ◽  
Ioannis Trichakis ◽  
Emmanouil Varouchakis ◽  
George P. Karatzas
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
River Basin ◽  
Danube River ◽  
Bayesian Regularization ◽  
Data Set ◽  
The Danube River ◽  
Precipitation Temperature ◽  
Artificial Neural ◽  
Danube River Basin

<p>In recent years, Artificial Neural Networks (ANNs) have proven their merit in being able to simulate the changes in groundwater levels, using as inputs other parameters of the water budget, e.g. precipitation, temperature, etc.. In this study, ANNs have been used to simulate hydraulic head in a large number of wells throughout the Danube River Basin, taking as inputs, precipitation, temperature, and evapotranspiration data in the region. Different ANN architectures have been examined, to minimize the simulation error of the testing data-set. Among the different training algorithms, Levenberg-Marquardt and Bayesian Regularization are used to train the ANNs, while the different activation functions of the neurons that were deployed include tangent sigmoid, logarithmic sigmoid and linear. The initial application comprised of data from 128 wells between 1 January 2000 and 31 October 2014. The best performance was achieved by the algorithm Bayesian Regularization with a error of the order  based on all observation wells. A second application, compared the results of the first one, with the results of an ANN used to simulate a single well. The pros and cons of the two approaches, and the synergies of using both of them is further discussed in order to distinguish the differences, and guide researchers in the field for further applications.</p>

scholarly journals Evaluation of Gel-Pad Oligonucleotide Microarray Technology by Using Artificial Neural Networks

2005 ◽  
Vol 71 (12) ◽  
pp. 8663-8676 ◽  
Author(s):  
Alex Pozhitkov ◽  
Boris Chernov ◽  
Gennadiy Yershov ◽  
Peter A. Noble
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Thermal Dissociation ◽  
Perfect Match ◽  
Area Under The Curve ◽  
Binding Constants ◽  
Quality Data ◽  
Image Analysis System ◽  
Data Set ◽  
Artificial Neural

ABSTRACT Past studies have suggested that thermal dissociation analysis of nucleic acids hybridized to DNA microarrays would improve discrimination among duplex types by scanning through a broad range of stringency conditions. To more fully constrain the utility of this approach using a previously described gel-pad microarray format, artificial neural networks (NNs) were trained to recognize noisy or low-quality data, as might derive from nonspecific fluorescence, poor hybridization, or compromised data collection. The NNs were trained to classify dissociation profiles (melts) into groups based on selected characteristics (e.g., initial signal intensity, area under the curve) using a data set of 21,044 profiles derived from 186 probes hybridized to a study set of RNA extracted from 32 microbes common to the human oral cavity. Three melt profile groups were identified: one group consisted mostly of ideal melt profiles; another group consisted mostly of poor melt profiles; and, the remainder were difficult to classify. Screening of melting profiles of perfect-match hybrids revealed inconsistencies in the form of melting profiles even for identical probes on the same microarray hybridized to same target rRNA. Approximately 18% of perfect-match duplex types were correctly classified as poor. Experimental variability and deviation from ideal melt behavior were shown to be attributable primarily to a method of local background subtraction that was very sensitive to displacement of the grid frames used for image capture (both determined by the image analysis system) and duplexes with low binding constants. Additional results showed that long RNA fragments limit the discriminating power among duplex types.

Prediction of Fracture Force of Weld Line Based on Artificial Neural Networks

2011 ◽  
Vol 314-316 ◽  
pp. 547-553
Author(s):  
Peng Fei Zhu ◽  
Xiao Fang Sun ◽  
Ying Jun Lu ◽  
Hai Tian Pan
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Process Parameters ◽  
Weld Line ◽  
Percentage Error ◽  
Maximum Relative Error ◽  
Melt Temperature ◽  
Data Set ◽  
Fracture Force ◽  
Artificial Neural

A feed-forward three-layer neural network was proposed to predict the fracture force of injection-molded parts’ weld line. Firstly, the most significant process parameters which affect the fracture force of weld line were analyzed. Secondly, melt temperature, injection pressure, holding pressure and holding time were chosen as import variables and the fracture force of weld line was chosen as output variable to construct artificial neural networks. Furthermore, the performance of ANN was evaluated and tested by its application to verification tests with process parameters randomly selected which all of them were not used in the network training. Results showed that the ANN predictions yield mean absolute percentage error (MAPE) in the range of 0.86％,and maximum relative error (MRE) in the range of 1.84％ for the test data set, and which can comparatively accurately reflect the influence relation of the injection process parameters on part’s quality index under the circumstance of data deficiencies.

scholarly journals Deep Convolutional Spiking Neural Networks for Image Classification

2021 ◽  
Author(s):  
Ruthvik Vaila
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Artificial Neural Networks ◽  
Gradient Descent ◽  
Stochastic Gradient ◽  
Spiking Neural Networks ◽  
Stochastic Gradient Descent ◽  
Data Set ◽  
Learning Capabilities ◽  
Artificial Neural

Spiking neural networks are biologically plausible counterparts of artificial neural networks. Artificial neural networks are usually trained with stochastic gradient descent (SGD) and spiking neural networks are trained with bioinspired spike timing dependent plasticity (STDP). Spiking networks could potentially help in reducing power usage owing to their binary activations. In this work, we use unsupervised STDP in the feature extraction layers of a neural network with instantaneous neurons to extract meaningful features. The extracted binary feature vectors are then classified using classification layers containing neurons with binary activations. Gradient descent (backpropagation) is used only on the output layer to perform training for classification. Surrogate gradients are proposed to perform backpropagation with binary gradients. The accuracies obtained for MNIST and the balanced EMNIST data set compare favorably with other approaches. The effect of the stochastic gradient descent (SGD) approximations on learning capabilities of our network are also explored. We also studied catastrophic forgetting and its effect on spiking neural networks (SNNs). For the experiments regarding catastrophic forgetting, in the classification sections of the network we use a modified synaptic intelligence that we refer to as cost per synapse metric as a regularizer to immunize the network against catastrophic forgetting in a Single-Incremental-Task scenario (SIT). In catastrophic forgetting experiments, we use MNIST and EMNIST handwritten digits datasets that were divided into five and ten incremental subtasks respectively. We also examine behavior of the spiking neural network and empirically study the effect of various hyperparameters on its learning capabilities using the software tool SPYKEFLOW that we developed. We employ MNIST, EMNIST and NMNIST data sets to produce our results.

Sign in / Sign up

Export Citation Format

Share Document