scholarly journals Earthfill dam seepage analysis using ensemble artificial intelligence based modeling

2018 ◽  
Vol 20 (5) ◽  
pp. 1071-1084 ◽  
Author(s):  
Elnaz Sharghi ◽  
Vahid Nourani ◽  
Nazanin Behfar
Keyword(s):  
Artificial Intelligence ◽  
Fuzzy Inference ◽  
Support Vector ◽  
Model Ensemble ◽  
Feed Forward Neural Network ◽  
Seepage Analysis ◽  
Inference System ◽  
Neural Ensemble ◽  
Predicting Performance ◽  
Seepage Modeling

Abstract In this paper, an ensemble artificial intelligence (AI) based model is proposed for seepage modeling. For this purpose, firstly several AI models (i.e. Feed Forward Neural Network, Support Vector Regression and Adaptive Neural Fuzzy Inference System) were employed to model seepage through the Sattarkhan earthfill dam located in northwest Iran. Three different scenarios were considered where each scenario employs a specific input combination suitable for different real world conditions. Afterwards, an ensemble method as a post-processing approach was used to improve predicting performance of the water head through the dam and the results of the models were compared and evaluated. For this purpose, three methods of model ensemble (simple linear averaging, weighted linear averaging and non-linear neural ensemble) were employed and compared. The obtained results indicated that the model ensemble could lead to a promising improvement in seepage modeling. The results indicated that the ensembling method could increase the performance of AI modeling by up to 20% in the verification step.

scholarly journals Multi-station artificial intelligence based ensemble modeling of suspended sediment load

2021 ◽  
Author(s):  
Vahid Nourani ◽  
Ali Kheiri ◽  
Nazanin Behfar
Keyword(s):  
Artificial Intelligence ◽  
Fuzzy Inference ◽  
Weighted Averaging ◽  
Support Vector ◽  
Inference System ◽  
Ensemble Technique ◽  
Ensemble Techniques ◽  
Neural Ensemble ◽  
Single Station ◽  
The Individual

Abstract In this study, Artificial Intelligence (AI) models along with ensemble techniques were employed for predicting the SSL via single-station and multi-station scenarios. Feed Forward Neural Networks (FFNNs), Adaptive Neuro-Fuzzy Inference System (ANFIS), and Support Vector Regression (SVR) were the employed AI models, and the simple averaging (SA), weighted averaging (WA), and neural averaging (NA) were the ensemble techniques developed for combining the outputs of the individual AI models to gain more accurate estimations of the SSL. For this purpose, twenty-year observed streamflow and SSL data of three gauging stations, located in Missouri and Upper Mississippi regions were utilized in both daily and monthly scales. The obtained results of both scenarios indicated the supremacy of ensemble techniques to single AI models. The neural ensemble demonstrated more reliable performance comparing to other ensemble techniques. For instance, in the first scenario, the ensemble technique increased the predicted results up to 20% in the verification phase of the daily and monthly modeling and up to 5 and 8% in the verification step of the second scenario.

Thermal Resistance Modeling of Oscillating Heat Pipes for Nanofluids by Artificial Intelligence Approach

2019 ◽  
Vol 141 (7) ◽  
Author(s):  
M. Malekan ◽  
A. Khosravi ◽  
H. R. Goshayeshi ◽  
M. E. H. Assad ◽  
J. J. Garcia Pabon
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Thermal Resistance ◽  
Heat Pipe ◽  
Fuzzy Inference ◽  
Working Fluid ◽  
Group Method ◽  
Feed Forward Neural Network ◽  
Inference System ◽  
Intelligent Models

In this study, thermal resistance of a closed-loop oscillating heat pipe (OHP) is investigated using experimental tests and artificial intelligence methods. For this target, γFe2O3 and Fe3O4 nanoparticles are mixed with the base fluid. Also, intelligent models are developed to predict the thermal resistance of the OHP. These models are developed based on the heat input into evaporator section, the thermal conductivity of working fluids, and the ratio of the inner diameter to length of OHP. The intelligent methods are multilayer feed-forward neural network (MLFFNN), adaptive neuro-fuzzy inference system (ANFIS) and group method of data handling (GMDH) type neural network. Thermal resistance of the heat pipe (as a measure of thermal performance) is considered as the target. The results showed that using the nanofluids as working fluid in the OHP decreased the thermal resistance, where this decrease for Fe3O4/water nanofluid was more than that of γFe2O3/water. The intelligent models also predicted successfully the thermal resistance of OHP with a correlation coefficient close to 1. The root-mean-square error (RMSE) for MLFFNN, ANFIS, and GMDH models was obtained as 0.0508, 0.0556, and 0.0569 (°C/W) (for the test data), respectively.

scholarly journals Development of Hybrid Artificial Intelligence Approaches and a Support Vector Machine Algorithm for Predicting the Marshall Parameters of Stone Matrix Asphalt

2019 ◽  
Vol 9 (15) ◽  
pp. 3172 ◽  
Author(s):  
Hoang-Long Nguyen ◽  
Thanh-Hai Le ◽  
Cao-Thang Pham ◽  
Tien-Thinh Le ◽  
Lanh Si Ho ◽  
...  
Keyword(s):  
Artificial Intelligence ◽  
Support Vector Machine ◽  
Mean Squared Error ◽  
Fuzzy Inference ◽  
Absolute Error ◽  
Support Vector ◽  
Inference System ◽  
Stone Matrix Asphalt ◽  
Hybrid Artificial Intelligence ◽  
Stone Matrix

The main objective of this study is to develop and compare hybrid Artificial Intelligence (AI) approaches, namely Adaptive Network-based Fuzzy Inference System (ANFIS) optimized by Genetic Algorithm (GAANFIS) and Particle Swarm Optimization (PSOANFIS) and Support Vector Machine (SVM) for predicting the Marshall Stability (MS) of Stone Matrix Asphalt (SMA) materials. Other important properties of the SMA, namely Marshall Flow (MF) and Marshall Quotient (MQ) were also predicted using the best model found. With that goal, the SMA samples were fabricated in a local laboratory and used to generate datasets for the modeling. The considered input parameters were coarse and fine aggregates, bitumen content and cellulose. The predicted targets were Marshall Parameters such as MS, MF and MQ. Models performance assessment was evaluated thanks to criteria such as Root Mean Squared Error (RMSE), Mean Absolute Error (MAE) and correlation coefficient (R). A Monte Carlo approach with 1000 simulations was used to deduce the statistical results to assess the performance of the three proposed AI models. The results showed that the SVM is the best predictor regarding the converged statistical criteria and probability density functions of RMSE, MAE and R. The results of this study represent a contribution towards the selection of a suitable AI approach to quickly and accurately determine the Marshall Parameters of SMA mixtures.

scholarly journals Artificial Intelligence Based Ensemble Modeling for Multi-Station Prediction of Precipitation

Atmosphere ◽  
2019 ◽  
Vol 10 (2) ◽  
pp. 80 ◽  
Author(s):  
Vahid Nourani ◽  
Selin Uzelaltinbulat ◽  
Fahreddin Sadikoglu ◽  
Nazanin Behfar
Keyword(s):  
Artificial Intelligence ◽  
Least Square ◽  
Ensemble Method ◽  
Support Vector ◽  
Monthly Precipitation ◽  
Ensemble Modeling ◽  
Inference System ◽  
Ensemble Techniques ◽  
Neural Ensemble ◽  
Non Linear

The aim of ensemble precipitation prediction in this paper was to achieve the best performance via artificial intelligence (AI) based modeling. In this way, ensemble AI based modeling was proposed for prediction of monthly precipitation with three different AI models (feed forward neural network-FFNN, adaptive neural fuzzy inference system-ANFIS and least square support vector machine-LSSVM) for the seven stations located in the Turkish Republic of Northern Cyprus (TRNC). Two scenarios were examined each having specific inputs set. The scenario 1 was developed for predicting each station’s precipitation through its own data at previous time steps while in scenario 2, the central station’s data were imposed into the models, in addition to each station’s data, as exogenous input. Afterwards, the ensemble modeling was generated to improve the performance of the precipitation predictions. To end this aim, two linear and one non-linear ensemble techniques were used and then the obtained outcomes were compared. In terms of efficiency measures, the averaging methods employing scenario 2 and non-linear ensemble method revealed higher prediction efficiency. Also, in terms of Skill score, non-linear neural ensemble method could enhance predicting efficiency up to 44% in the verification step.

scholarly journals Development of a new empirical correlation for predicting formation volume factor of reservoir oil using artificial intelligence

2021 ◽  
Vol 44 (4) ◽  
pp. 408-416
Author(s):  
E. V. Shakirova ◽  
A. A. Aleksandrov ◽  
M. V. Semykin
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Artificial Neural Network ◽  
Fuzzy Inference ◽  
Empirical Correlation ◽  
Support Vector ◽  
Volume Factor ◽  
Inference System ◽  
Study Results ◽  
Artificial Neural

It is known that oil in reservoir conditions is characterized by the content of a certain amount of dissolved gas. As reservoir pressure decreases this gas is released from oil significantly changing its physical properties, primarily its density and viscosity. In addition, the oil volume also reduces, sometimes by 50–60 %. In this regard, when calculating reserves, it is necessary to justify the reduction amount of the reservoir oil volume when oil is extracted to the surface. For this purpose, the concept of formation volume factor of reservoir oil has been introduced. The formation volume factor of oil is considered one of the main characterizing parameters of crude oil. It is also required for modeling and predicting the characteristics of an oil reservoir. The purpose of the present work is to develop a new empirical correlation for predicting the formation volume factor of reservoir oil using artificial intelligence methods based on MATLAB software, such as: an artificial neural network, an adaptive neuro-fuzzy inference system, and a support vector machine. The article presents a new empirical correlation extracted from the artificial neural network based on 503 experimental data points for oils from the Eastern Siberia field, which was able to predict the formation volume factor of oil with the correlation coefficient of 0.969 and average absolute error of less than 1 %. The conducted study shows that the prediction accuracy of the desired parameter in the developed artificial intelligence model exceeds the accuracy of study results obtained by conventional statistical methods. Moreover, the model can be useful in the prospect of process optimization in field planning and development.

scholarly journals Ecological-environmental quality estimation using remote sensing and combined artificial intelligence techniques

2020 ◽  
Author(s):  
Vahid Nourani ◽  
Ehsan Foroumandi ◽  
Elnaz Sharghi ◽  
Dominika Dąbrowska
Keyword(s):  
Artificial Intelligence ◽  
Remote Sensing ◽  
Environmental Quality ◽  
Network Performance ◽  
Fuzzy Inference ◽  
Support Vector ◽  
Inference System ◽  
Climate Conditions ◽  
Environmental Attributes ◽  
Artificial Neural Network Ann

Abstract Ecological-environmental quality was evaluated for Tabriz and Rasht cities (in Iran) with different climate conditions using artificial intelligence (AI) and remote sensing (RS) techniques. Sampling sites were surveyed and ecological experts assigned eco-environment background values (EBVs) of sites. Then, eco-environmental attributes were extracted as RS derived, and meteorological attributes were observed. Three AI-based models, artificial neural network (ANN), support vector regression (SVR), and adaptive neuro-fuzzy inference system (ANFIS) were then applied to learn the relationship between a target set of known EBVs and eco-environmental attributes as inputs. According to the results of the single models, none of the models could evaluate EBV appropriately for all regions and classes. Thereafter, three combining techniques were applied to the outputs of single models to enhance spatial evaluation of EBV. It was observed that the modeling for Tabriz led to more accurate results. It seems that the better network performance for Tabriz may be due to a more heterogeneous dataset in this kind of climate. Furthermore, results indicated that SVR led to better performance than both ANN and ANFIS models, but the models' combining techniques were shown to be superior. Combining techniques enhanced performance of single AI modeling up to 26% in the verification step.

scholarly journals Modelling and Prediction of Water Quality by Using Artificial Intelligence

2021 ◽  
Vol 13 (8) ◽  
pp. 4259
Author(s):  
Mosleh Hmoud Al-Adhaileh ◽  
Fawaz Waselallah Alsaade
Keyword(s):  
Artificial Intelligence ◽  
Water Quality ◽  
Fuzzy Inference ◽  
Feed Forward Neural Network ◽  
Statistical Parameters ◽  
Anfis Model ◽  
K Nearest Neighbors ◽  
Inference System ◽  
Efficient Operation ◽  
Sanitation Systems

Artificial intelligence methods can remarkably reduce costs for water supply and sanitation systems and help ensure compliance with the quality of drinking and wastewater treatment. Therefore, modelling and predicting water quality to control water pollution has been widely researched. The novelty of the proposed system is presented to develop an efficient operation of monitoring drinking water to ensure a sustainable and friendly green environment. In this work, the adaptive neuro-fuzzy inference system (ANFIS) algorithm was developed to predict the water quality index (WQI). Feed-forward neural network (FFNN) and K-nearest neighbors were applied to classify water quality. The dataset has eight significant parameters, but seven parameters were considered to show significant values. The proposed methodology was developed based on these statistical parameters. Prediction results demonstrated that the ANFIS model was superior for the prediction of WQI values. Nevertheless, the FFNN algorithm achieved the highest accuracy (100%) for water quality classification (WQC). Furthermore, the ANFIS model accurately predicted WQI, and the FFNN model showed superior robustness in classifying the WQC. In addition, the ANFIS model showed accuracy during the testing phase, with a regression coefficient of 96.17% for predicting WQI, and the FFNN model achieved the highest accuracy (100%) for WQC. This proposed method, using advanced artificial intelligence, can aid in water treatment and management.

METODE KOMPARASI ARTIFICIAL NEURAL NETWORK PADA PREDIKSI CURAH HUJAN - LITERATURE REVIEW

2020 ◽  
Vol 14 (2) ◽  
pp. 48-53
Author(s):  
Herlina Jayadianti ◽  
Tedy Agung Cahyadi ◽  
Nur Ali Amri ◽  
Muhammad Fathurrahman Pitayandanu
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Fuzzy Inference ◽  
Moving Average ◽  
Ensemble Empirical Mode Decomposition ◽  
Support Vector ◽  
Fast Fourier Transformation ◽  
Feed Forward Neural Network ◽  
Inference System ◽  
Artificial Neural

Abstrak - Penelitian untuk mencari model prediksi curah hujan yang akurat di berbagai bidang sudah banyak dilakukan, maka dilakukan di-review kembali guna membantu proses penyaliran dalam perusahaan tambang. Review dilakukan dengan membandingkan hasil dari setiap model yang telah dilakukan pada beberapa penelitian sebelumnya. Penelitian ini menggunakan metode kuantitatif. Model yang dibandingkan pada penelitian di antaranya yaitu model Fuzzy, Fast Fourier Transformation (FFT), Emotional Artificial Neural Network (EANN), Artificial Neural Network (ANN), Adaptive Ensemble Empirical Mode Decomposition-Artificial Neural Network (AEEMD-ANN), E-SVR-Artificial Neural Network (E-SVR-ANN), Artificial Neural Network Backpropagation (BPNN), Adaptive Splines Threshold (ASTAR), Seasonal First-Order Autoregressive (SAR), Gumbel, Autoregressive Integrated Moving Average (ARIMA), Feed Forward Neural Network (FFNN), Support Vector Machine (SVM), Adaptive Neuro-Fuzzy Inference System (ANFIS), dan Artificial Neural Network-Fuzzy (ANN-Fuzzy). Hasil dari review menyimpulkan bahwa model Artificial Neural Network memiliki beberapa kelebihan dibandingkan dengan metode yang lain, yakni ANN mampu memberikan hasil yang dapat mengenali pola-pola dengan baik dan mudah dikembangkan menjadi bermacam-macam variasi sesuai dengan permasalahan maupun parameter yang ada, sehingga ANN direkomendasikan untuk perhitungan prediksi hujan. Abstract - Various kinds of research have been carried out to find accurate models to predict rainfall in various fields, so the research that has been done previously was reviewed again to help the drainage process in mining companies. The review is done by comparing the results of each model that has been conducted in several previous studies. This research used quantitative methods. Models compared in this study include the Fuzzy model, Fast Fourier Transformation (FFT), Emotional Artificial Neural Network (EANN), Artificial Neural Network (ANN), Adaptive Ensemble Empirical Mode Decomposition-Artificial Neural Network (AEEMD-ANN), E-SVR -Artificial Neural Network (E-SVR-ANN), Artificial Neural Network Backpropagation (BPNN), Adaptive Splines Threshold (ASTAR), Seasonal First-Order Autoregressive (SAR), Gumbel, Autoregressive Integrated Moving Average (ARIMA), Feed Forward Neural Network (FFNN), Support Vector Machine (SVM), Adaptive Neuro-Fuzzy Inference System (ANFIS), and Artificial Neural Network-Fuzzy (ANN-Fuzzy). The results of the review concluded that the Artificial Neural Network model has several advantages compared to other methods, namely ANN is able to provide results that can recognize patterns well and easily developed into a variety of variations in accordance with existing problems and parameters, so ANN is recommended for rain prediction calculation.

scholarly journals Artificial Intelligence Techniques for Cancer Detection and Classification: Review Study

2017 ◽  
Vol 13 (3) ◽  
pp. 342 ◽  
Author(s):  
Alaá Rateb Mahmoud Al-shamasneh ◽  
Unaizah Hanum Binti Obaidellah
Keyword(s):  
Neural Network ◽  
Artificial Intelligence ◽  
Fuzzy Inference ◽  
Human Cancer ◽  
Imaging Techniques ◽  
Detection Methods ◽  
Support Vector ◽  
Inference System ◽  
Mortality And Morbidity ◽  
Artificial Intelligence Techniques

Cancer is the general name for a group of more than 100 diseases. Although cancer includes different types of diseases, they all start because abnormal cells grow out of control. Without treatment, cancer can cause serious health problems and even loss of life. Early detection of cancer may reduce mortality and morbidity. This paper presents a review of the detection methods for lung, breast, and brain cancers. These methods used for diagnosis include artificial intelligence techniques, such as support vector machine neural network, artificial neural network, fuzzy logic, and adaptive neuro-fuzzy inference system, with medical imaging like X-ray, ultrasound, magnetic resonance imaging, and computed tomography scan images. Imaging techniques are the most important approach for precise diagnosis of human cancer. We investigated all these techniques to identify a method that can provide superior accuracy and determine the best medical images for use in each type of cancer.

Sign in / Sign up

Export Citation Format

Share Document