Wyniki wyszukiwania - BazTech

1

Prediction of Tunnel Cross-Sectional Area After Blastin

Nguyen Chi Thanh, Nguyen Nghia Viet

Inżynieria Mineralna

|

2023

|

no. 2, vol. 1

39--47

EN

In this paper, two methods to predict and calculate the area of the tunnel face after the blasting were used. The first one is an artificial intelligence method using an artificial neural network system (ANN) model, and the second one – the support vector regression (SVR). After building predictive models for the area of the tunnel face after blasting by both methods, on the basis of comparing the results obtained in both methods, the performance of these models was assessed through the root mean square error RMSE and the coefficient of determination R2. RMSE and R2 values of the artificial neural network system (ANN) model were obtained as 0.1473 and 0.903 in training datasets, respectively. These values are 0.1497 and 0.9107 in testing datasets. In the SRV model, RMSE and R2 were equaled to 0.1228 and 0.9331 in training datasets, respectively. These values are 0.1708 and 0.9055, respectively in testing datasets. It can be concluded that artificial intelligence using ANN and SVM models can be used to predict the area of the tunnel face after blasting with high accuracy.

2

Fault location of distribution network with distributed generation based on Karrenbauer transform and support vector machine regression

Wang Siming, Zhao Kaikai

Archives of Electrical Engineering

|

2023

|

Vol. 72, nr 2

461--481

EN

As the capacity and scale of distribution networks continue to expand, and distributed generation technology is increasingly mature, the traditional fault location is no longer applicable to an active distribution network and "two-way" power flow structure. In this paper, a fault location method based on Karrenbauer transform and support vector machine regression (SVR) is proposed. Firstly, according to the influence of Karrenbauer transformation on phase angle difference before and after section fault in a low-voltage active distribution network, the fault regions and types are inferred preliminarily. Then, in the feature extraction stage, combined with the characteristics of distribution network fault mechanism, the fault feature sample set is established by using the phase angle difference of the Karrenbauer current. Finally, the fault category prediction model based on SVR was established to solve the problem of a single-phase mode transformation modulus and the indistinct identification of two-phase short circuits, then more accurate fault segments and categories were obtained. The proposed fault location method is simulated and verified by building a distribution network system model. The results show that compared with other methods in the field of fault detection, the fault location accuracy of the proposed method can reach 98.56%, which can enhance the robustness of rapid fault location.

3

Evaluation of the performance of data-driven approaches for filling monthly precipitation gaps in a semi-arid climate conditions

Katipoğlu Okan Mert

Acta Geophysica

|

2023

|

Vol. 71, no. 5

2265--2285

EN

Missing data cause problems in meteorological, hydrological, and climate analysis. The observation data should be complete and cover long periods to make the research more accurate and reliable. Artificial intelligence techniques have attracted interest for completing incomplete meteorological data in recent years. In this study the abilities of machine learning models, artificial neural networks, the nonlinear autoregressive with exogenous input (NARX) model, support vector regression, Gaussian processes regression, boosted tree, bagged tree (BAT), and linear regression to fill in missing precipitation data were investigated. In developing the machine learning model, 70% of the dataset was used for training, 15% for testing, and 15% for validation. The Bayburt, Tercan, and Zara precipitation stations, which are closest to the Erzincan station and have the highest correlation coefficients, were used to fill the data gaps. The accuracy of the constructed models was tested using various statistical criteria, such as root-mean-square error (RMSE), mean absolute error (MAE), Nash–Sutcliffe model efficiency coefficient (NSE), and determination coefficient (R2) and graphical approaches such as scattering, box plots, violin plots, and Taylor diagrams. Based on the comparison of model results, it was concluded that the BAT model with R2: 0.79 and NSE: 0.79 and error (RMSE: 11.42, and MAE: 7.93) was the most successful in the completion of missing monthly precipitation data. The contribution of this research is assist in the choice of the best and most accurate method for estimating precipitation data in semi-arid regions like Erzincan.

4

Comparison of machine learning models for predicting groundwater level, case study: Najafabad region

Zarafshan Pejman, Etezadi Hamed, Javadi Saman, Roozbahani Abbas, Hashemy S. Mehdi, Zarafshan Payam

Acta Geophysica

|

2023

|

Vol. 71, no. 4

1817--1830

EN

Water resources, consisting of surface water and groundwater, are considered to be among the crucial natural resources in most arid and semiarid regions. Groundwater resources as the sustainable yields can be predicted, whereas this is one of the important stages in water resource management. To this end, several models such as mathematical, statistical, empirical, and conceptual can be employed. In this paper, machine learning and deep learning methods as conceptual ones are applied for the simulations. The selected models are support vector regression (SVR), adaptive neuro-fuzzy inference system (ANFIS), and multilayer perceptron (MLP). Next, these models are optimized with the adaptive moment estimation (ADAM) optimization algorithm which results in hybrid models. The hyper-parameters of the stated models are optimized with the ADAM method. The root mean squared error (RMSE), mean absolute error (MAE), mean squared error (MSE), and coefficient of determination (R2) are used to evaluate the accuracy of the simulated groundwater level. To this end, the aquifer hydrograph is used to compare the results with observations data. So, the RMSE and R2 show that the accuracy of the machine learning and deep learning models is better than the numerical model for the given data. Moreover, the MSE is approximately the same in all three cases (ranging from 0.7113 to 0.6504). Also, the total value of R2 and RMSE for the best hybrid model is 0.9617 and 0.7313, respectively, which are obtained from the model output. The results show that all three techniques are useful tools for modeling hydrological processes in agriculture and their computational capabilities and memory are similar.

5

Prediction of the groundwater quality index through machine learning in Western Middle Chelif plain in North Algeria

Elmeddahi Yamina, Ragab Ragab

Acta Geophysica

|

2022

|

Vol. 70, no 4

1797--1814

EN

Water quality monitoring and assessment has been one of the world’s major concerns in recent decades. This study examines the performance of three approaches based on the integration of machine learning and feature extraction techniques to improve water quality prediction in the Western Middle Chelif plain in Algeria during 2014–2018. The most dominant Water Quality Index parameters that were extracted by neuro-sensitivity analysis (NSA) and principal component analysis (PCA) techniques were used in the multilayer perceptron neural network, support vector regression (SVR) and decision tree regression models. Various combinations of input data were studied and evaluated in terms of prediction performance, using statistical criteria and graphical comparisons. According to the results, the MLPNN1 model with eight input parameters gave the highest performance for both training and validation phases (R=0.98/0.95, NSE=0.96/0.88, RMSE=11.20/15.03, MAE=7.89/10.22 and GA=1.34) when compared with the multiple linear regression, TDR and SVR models. Generally, the prediction performance of models integrated with NSA approaches is significantly improved and outperforms models coupled with the PCA dimensionality reduction method.

6

Weather drought index prediction using the support vector regression in the Ansegmir Watershed, Upper Moulouya, Morocco

Bekri My Hachem, El Hmaidi Abdellah, Ousmana Habiba, El Faleh El Mati, Berrada Mohamed, El Aissaoui Kamal, Essahlaoui Ali, El Ouali Abdelhadi

Journal of Water and Land Development

|

2021

|

no. 50

187--194

EN

The purpose of this study is to develop mathematical models based on artificial intelligence: Models based on the support vectors regression (SVR) for drought forecast in the Ansegmir watershed (Upper Moulouya, Morocco). This study focuses on the prediction of the temporal aspect of the two drought indices (standardized precipitation index – SPI and standardized precipitation-evapotranspiration index – SPEI) using six hydro-climatic variables relating to the period 1979–2013. The model SVR3-SPI: RBF, ε = 0.004, C = 20 and γ = 1.7 for the index SPI, and the model SVR3-SPEI: RBF ε = 0.004, C = 40 and γ = 0.167 for the SPEI index are significantly better in comparison to other models SVR1, SVR2 and SVR4. The SVR model for the SPI index gave a correlation coefficient of R = 0.92, MSE = 0.17 and MAE = 0.329 for the learning phase and R = 0.90, MSE = 0.18 and MAE = 0.313 for the testing phase. As for the SPEI index, the overlay is slightly poorer only in the case of the SPI index between the observed values and the predicted ones by the SVR model. It shows a very small gap between the observed and predicted values. The correlation coefficients R = 0.88 for the learning, R = 0.86 for testing remain higher and corresponding to a quadratic error average MSE = 0.21 and MAE = 0.351 for the learning and MSE = 0.21 and MAE = 0.350 for the testing phase. The prediction of drought by SVR model remain useful and would be extremely important for drought risk management.

7

Machine learning for predicting discharge fuctuation of a karst spring in North China

Cheng Shu, Qiao Xiaojuan, Shi Yaolin, Wang Dawei

Acta Geophysica

|

2021

|

Vol. 69, no. 1

257--270

EN

The quantitative analyses of karst spring discharge typically rely on physical-based models, which are inherently uncertain. To improve the understanding of the mechanism of spring discharge fuctuation and the relationship between precipitation and spring discharge, three machine learning methods were developed to reduce the predictive errors of physical-based groundwater models, simulate the discharge of Longzici spring’s karst area, and predict changes in the spring on the basis of long time series precipitation monitoring and spring water fow data from 1987 to 2018. The three machine learning methods included two artifcial neural networks (ANNs), namely multilayer perceptron (MLP) and long short-term memory–recurrent neural network (LSTM–RNN), and support vector regression (SVR). A normalization method was introduced for data preprocessing to make the three methods robust and computationally efcient. To compare and evaluate the capability of the three machine learning methods, the mean squared error (MSE), mean absolute error (MAE), and root-mean-square error (RMSE) were selected as the performance metrics for these methods. Simulations showed that MLP reduced MSE, MAE, and RMSE to 0.0010, 0.0254, and 0.0318, respectively. Meanwhile, LSTM–RNN reduced MSE to 0.0010, MAE to 0.0272, and RMSE to 0.0329. Moreover, the decrease in MSE, MAE, and RMSE was 0.0397, 0.1694, and 0.1991, respectively, for SVR. Results indicated that MLP performed slightly better than LSTM–RNN, and MLP and LSTM–RNN performed considerably better than SVR. Furthermore, ANNs were demonstrated to be prior machine learning methods for simulating and predicting karst spring discharge.

8

Shallow, Deep, Ensemble models for Network Device Workload Forecasting

Liu Cenru

Annals of Computer Science and Information Systems

|

2020

|

Vol. 21

101--104

EN

Reliable prediction of workload-related characteristics of monitored devices is important and helpful for management of infrastructure capacity. This paper presents 3 machine learning models (shallow, deep, ensemble) with different complexity for network device workload forecasting. The performance of these models have been compared using the data provided in FedCSIS'20 Challenge. The R2 scores achieved from the cascade Support Vector Regression (SVR) based shallow model, Long short-term memory (LSTM) based deep model, and hierarchical linear weighted ensemble model are 0.2506, 0.2831, and 0.3059, respectively, and was ranked 3rd place in the preliminary stage of the challenges.

9

Application of gaussian kernel with regard to correlations for image reconstruction in electrical tomography

Rymarczyk Tomasz, Kozłowski Edward, Adamkiewicz Przemysław, Sikora Jan

Przegląd Elektrotechniczny

|

2019

|

R. 95, nr 5

55--58

EN

The article presents the application of support methods Vector Machine for Regression and Support Vector Machine for Regression with a modified correlation kernel in electrical impedance tomography. Statistical methods have been used to reconstruct imaging. In addition, a model was created that analyses similar objects of different sizes. It learns about a smaller object, but we recognize a larger object. The paper shows how to make an analysis for such cases.

PL

W artykule przedstawiono aplikację opartą na metodach maszyna wektorów nośnych do regresji i maszyna wektorów nośnych do regresji z zmodyfikowanym jądrem korelacji w elektrycznej tomografii impedancyjnej. Metody statystyczne zostały wykorzystana do rekonstrukcji obrazuj. Dodatkowo stworzono model, który analizuje podobne obiekty o różnych rozmiarach. Uczy się na obiekcie o mniejszych gabarytach, natomiast rozpoznajemy obiekt o większym rozmiarze. W pracy pokazano w jaki sposób dokonywać analizę dla takich przypadków.

10

Training subset selection for support vector regression

Liu Cenru, Cen Jiahao

Annals of Computer Science and Information Systems

|

2019

|

Vol. 18

11--14

EN

As more and more data are available, training a machine learning model can be extremely intractable, especially for complex models like Support Vector Regression (SVR) train- ing of which requires solving a large quadratic programming optimization problem. Selecting a small data subset that can effectively represent the characteristic features of training data and preserve their distribution is an efficient way to solve this problem. This paper proposes a systematic approach to select the best representative data for SVR training. The distribution of both predictor and response variables are preserved in the selected subset via a 2-layer data clustering strategy. A 2-layer step-wise greedy algorithm is introduced to select best data points for constructing a reduced training set. The proposed method has been applied for predicting deck's win rates in the Clash Royale Challenge, in which 10 subsets containing hundreds of data examples were selected from 100k for training 10 SVR models to maximize their prediction performance evaluated using R-squared metric. Our final submission having a R2 score of 0.225682 won the 3rd place among over 1200 solutions submitted by 115 teams.

11

Efficient support vector regression with reduced training data

Cen Ling, Vu Quang Hieu, Ruta Dymitr

Annals of Computer Science and Information Systems

|

2019

|

Vol. 18

15--18

EN

Support Vector Regression (SVR) as a supervised machine learning algorithm have gained popularity in various fields. However, the quadratic complexity of the SVR in the number of training examples prevents it from many practical applications with large training datasets. This paper aims to explore efficient ways that maximize prediction accuracy of the SVR at the minimum number of training examples. For this purpose, a clustered greedy strategy and a Genetic Algorithm (GA) based approach are proposed for optimal subset selection. The performance of the developed methods has been illustrated in the context of Clash Royale Challenge 2019, concerned with decks' win rate prediction. The training dataset with 100,000 examples were reduced to hundreds, which were fed to SVR training to maximize model prediction performance measured in validation R2 score. Our approach achieved the second highest score among over hundred participating teams in this challenge.

12

Nowa adaptacyjna metoda estymacji stosunku mocy sygnał/szum w środowisku radia programowalnego

Chruściel K., Skrzypiec J., Wszołek J., Sikora M., Ludwin W., Wągrowski M., Gozdecki J., Łoziak K.

Przegląd Telekomunikacyjny + Wiadomości Telekomunikacyjne

|

2016

|

nr 6

613--616, CD

PL

W artykule przedstawiono nową adaptacyjną metodę estymacji wartości stosunku sygnał/szum SNR (Signal-To-Noise Ratio). Zaproponowana metoda, w pierwszej kolejności korzysta z prostego estymatora wartości chwilowej SNR. Następnie, na tej podstawie wybierana jest jedna z czterech metod bardziej dokładnej estymacji wartość SNR. W artykule omówiono elementy składowe oraz algorytm działania zaproponowanej metody, a t akże j ej najważniejsze właściwości. Ponadto zaprezentowano wyniki badań modelu symulacyjnego zaproponowanej metodyw środowisku radia programowalnego – GNU Radio.

EN

The paper presents a new automatic method for estimation of signal-to-noise ratio (SNR). Proposed method first uses a simple algorithm to estimate the instantaneous level of SNR. Then, based on the estimation result, the correct SNR estimator is chosen. The papier describe the proposed method, its operation and basic properties. In addition, the GNU Radio simulation results of the proposed method are also included in the paper.

13

Oil Formation Volume Factor Determination Through a Fused Intelligence

Gholami A.

Acta Geophysica

|

2016

|

Vol. 64, no. 6

2510--2529

EN

Volume change of oil between reservoir condition and standard surface condition is called oil formation volume factor (FVF), which is very time, cost and labor intensive to determine. This study proposes an accurate, rapid and cost-effective approach for determining FVF from reservoir temperature, dissolved gas oil ratio, and specific gravity of both oil and dissolved gas. Firstly, structural risk minimization (SRM) principle of support vector regression (SVR) was employed to construct a robust model for estimating FVF from the aforementioned inputs. Subsequently, an alternating conditional expectation (ACE) was used for approximating optimal transformations of input/output data to a higher correlated data and consequently developing a sophisticated model between transformed data. Eventually, a committee machine with SVR and ACE was constructed through the use of hybrid genetic algorithm-pattern search (GA-PS). Committee machine integrates ACE and SVR models in an optimal linear combination such that makes benefit of both methods. A group of 342 data points was used for model development and a group of 219 data points was used for blind testing the constructed model. Results indicated that the committee machine performed better than individual models.

14

Black-Box system identification by means of Support Vector Regression and Imperialist Competitive Algorithm

Sałat R., Awtoniuk M., Korpysz K.

Przegląd Elektrotechniczny

|

2013

|

R. 89, nr 9

223-226

EN

The paper proposes to use SVR network for system identification by means of the Black-Box method. Selection of the optimal network parameters as well as the selection of optimal set of regressors by the Imperialist Competitive Algorithm have been proposed. The accuracy of models built was compared to ARX model for a linear object and NARX model for a non-linear one. The results show that the use of SVR in Black- Box identification can be an useful and efficient alternative for models based on NARX and ARX structures.

PL

W artykule zaproponowano użycie sieci SVR do identyfikacji systemów metodą Black-Box. Do doboru optymalnych parametrów sieci i wyboru optymalnego zestawu regresorów, zaproponowano użycie algorytmu ewolucyjnego Imperialist Competitive Algorithm. Dokładność zbudowanych modeli porównano z modelem typu ARX, dla obiektu liniowego, oraz NARX, dla nieliniowego. Otrzymane wyniki wskazują, że wykorzystanie SVR w identyfikacji Black-Box może być użyteczną i efektywną alternatywą dla modeli o strukturze ARX oraz NARX.

15

Intelligent sensing and monitoring : respiratory motion prediction for tumor following radiotherapy

Ichiji K., Homma N., Sakai M., Bukovsky I., Zhang X., Osanai M., Abe M., Sugita N., Yoshizawa M.

Journal of Artificial Intelligence and Soft Computing Research

|

2012

|

Vol. 2, No. 4

331--342

EN

This paper presents a medical application of the intelligent sensing and monitoring, a new lung tumor motion prediction method for tumor following radiation therapy. An essential core of the method is accurate estimation of complex fluctuation of time-varying periodical nature of lung tumor motion. Such estimation is achieved by using a novel multiple time-varying seasonal autoregressive (TVSAR) model in which several windows of different time-lengths are used to calculate correlation based fluctuation of periodic nature in the motion. The proposed method provides the prediction as a combination of those based on different window lengths. Multiple regression (MR), multilayer perceptron (MLP) and support vector regression (SVR) are used to combine and the prediction performances are evaluated by using clinical lung tumor motion. The proposed methods with the combined predictions showed high accurate prediction and are superior to the single different predictions. The average errors of MR, MLP, and SVR were 0.8455,0.8507, and 0.7530 mm at 0.5 s ahead, respectively. The results are clinically sufficient and thus clearly demonstrate that the proposed TVSAR with an appropriate combination method is useful for improving the prediction performance.

16

Power quality diagnosis in distribution networks using support vector regression based S-transform technique

Faisal M., Mohamed A., Shareef H.

Przegląd Elektrotechniczny

|

2010

|

R. 86, nr 11a

38-42

EN

This paper presents a novel method for performing automatic power quality diagnosis to identify the causes of short duration voltage disturbances such as voltage sags and swells. Such voltage disturbances can be caused by permanent or non permanent faults. A permanent fault causes permanent damage and power interruption to the customers whereas a non permanent fault can be categorized as either transient or incipient faults. In the proposed power quality diagnosis method, a time frequency analysis technique called as the S-transform is used to analyse and extract features of voltage disturbances recorded from the power quality monitoring system. The support vector regression which is an intelligent technique is then used identify whether the voltage disturbances are caused by permanent, non permanent, transient or incipient faults. Test results proved that the proposed power quality diagnosis method can provide accurate diagnosis on the causes of short duration voltage disturbances.

PL

W artykule przedstawiono nową metodę przeprowadzania automatycznej diagnostyki jakości energii elektrycznej do identyfikacji przyczyn krótkoczasowych zakłóceń napięcia, takich jak zapady napięcia. Zaburzenia napięcia mogą być spowodowane przez długotrwałe lub chwilowe awarie. W proponowanej metodzie diagnozowania jakości zasilania, zastosowano transformatę S do ekstrakcji charakterystyk zarejestrowanych przebiegów z systemu monitoringu. Zastosowano regresję SVR jako technike inteligentna, pozwalajaca na rozróżnienie pomiędzy typami awarii. Wyniki badań wykazały, że proponowana metoda diagnozowania jakości zasilania może zapewnić dokładną diagnozę na temat przyczyn zaburzeń napięcia o krótkim czasie trwania.