Random forest regression on pullout resistance of a pile

Shaymaa Alsamia; Edina Koch

doi:10.1556/606.2024.01052

Jump to Content

Pollack Periodica

Volume/Issue:: Volume 19: Issue 3

Random forest regression on pullout resistance of a pile

Authors:

Shaymaa Alsamia

Shaymaa Alsamia Department of Structural and Geotechnical Engineering, Faculty of Engineering Sciences, Széchenyi István University, Győr, Hungary
Department of Structures and Water Resources, Faculty of Engineering, University of Kufa, Kufa, Iraq

Search for other papers by Shaymaa Alsamia in
Current site
Google Scholar
PubMed

alsamia.shaymaa.mahmood.badr@sze.hu https://orcid.org/0000-0002-7012-6499

and

Edina Koch

Edina Koch Department of Structural and Geotechnical Engineering, Faculty of Engineering Sciences, Széchenyi István University, Győr, Hungary

Search for other papers by Edina Koch in
Current site
Google Scholar
PubMed

View More View Less

Pages:: 28–33

Online Publication Date:: 15 May 2024

Publication Date:: 16 Oct 2024

Article Category:: Research Article

DOI:: https://doi.org/10.1556/606.2024.01052

Keywords:: helical piles; pull-out resistance; artificial neural network; adaptive neuro-fuzzy inference system; random forest; support vector machine

Open access

Download PDF

Abstract

This research aims to study the pullout resistance of a helical pile using three methods of machine learning techniques, which are: random forest regression, support vector regression, and adaptive neuro-fuzzy inference system, based on experimental results of a helical pile. The performance of these three techniques has been d compared and the results show that random forest algorithm has best performance than neuro-fuzzy inference system and support vector technique. The results show that machine learning considered a good tool in terms of estimating the pullout resistance of helical piles in the soil.

Abstract

1 Introduction

In recent years, significant development and improvement have been observed in engineering fields due to the use of modern computational methods and measurement techniques [1]. One of these fields in which these improvements have been noticed is the field of civil engineering and geotechnical engineering [2, 3]. There are many types of deep foundations; one of these types is helical piles (HPs), as they consist of a central shaft steel column with helix-shaped plates, hence the name helical piles [4]. HPs are used to support building structures, bridges, and other types of infrastructure because they provide bearing capacity and stability for different types of structures and buildings [5]. HPs are also used in cases where traditional deep foundation systems are not practical and feasible, like drilled columns and driven piles for different soil conditions [6] and also used in commercial and residential properties and areas with limited access and space [7]. HPs provide an alternative solution as a foundation that provides good stability and is sufficient to resist horizontal stresses, compression and tension [8]. The helical piles have received great attention from researchers studying their behavior due to their stability and provide good performance in avoiding horizontal pressures, compression and tension. In 2017, G. Spagnoli [8], improved a theoretical model to analyze the bearing capacity and torque of HPs based on cone penetration testing to determine the axial resistance of helical piles and predict the torque required for installation., various methods have been explored [9, 10]. To analyze and understand the behavior of HPs, models of finite elements are widely used for this purpose [11–13]. The researchers discussed different methods and approaches to verify pullout resistance (Pul), as it is one of the important parameters for HPs for both piles and anchors [14–16]. The various soft computing techniques, which represent a set of computational techniques designed to find solutions and deal with incomplete, uncertain, or imprecise data for which it is difficult to find solutions using traditional methods, are vastly used in various engineering fields [17–19]. Fuzzy logic [20], particle swarm optimization [21], neural networks [22], metaheuristic techniques [23] and genetic algorithms [24] are some soft computing techniques commonly used in engineering fields. In geotechnical engineering applications, it is widely used, like designing stabilized earth walls [25], assessing landslide and slope stability [26], predicting soil compression coefficient [27], modeling bearing capacity [28] and among others. Within a mathematical framework, these techniques can optimize the relationship between multiple parameters [29], tailored to a specific problem. By taking a cost function, these algorithms perform intricate computations to maximize/minimize this function. Na et al. [30] in 2016, utilized the Harmony Search Algorithm (HSA) to optimally design the material cost of HPs. The HSA was discovered to be an effective approach for this objective, as it resulted in a cost reduction of 27% [30]. The Adaptive Neuro-Fuzzy Inference System (ANFIS) is a kind of Artificial Neural Network (ANN) that combines the reasoning capabilities of fuzzy logic and the learning abilities of neural networks to create a hybrid intelligent system. ANFIS is used for modeling complex systems where the relationships between inputs and outputs are not well understood. It works by using a set of input variables and a set of output variables to create a fuzzy inference system. This system is then trained using a combination of supervised and unsupervised learning algorithms to adjust the parameters of the fuzzy logic rules to better match the desired outputs [31]. Helical piles are widely used in civil engineering for foundation construction due to their unique properties, including ease of installation and excellent load-bearing capacity. However, predicting the pullout resistance behavior of helical piles is a complex and challenging problem, as it depends on a variety of factors like soil properties, installation method, and pile geometry. In recent years, machine learning techniques have emerged as a promising tool for analyzing and predicting the behavior of complex systems like helical piles. In this study, three machine learning methods - adaptive neuro fuzzy inference system, random forest regression, and support vector regression – have been applied to experimental results of a helical pile, with the aim of evaluating their performance and identifying the most effective approach for predicting the pullout resistance behavior of helical piles. In this paper, a comparative analysis of three machine learning methods - adaptive neuro fuzzy inference system, random forest regression, and support vector regression - is presented for predicting the pullout resistance behavior of a helical pile. The results show that random forest regression outperformed the other two methods in terms of accuracy and error values. This study provides valuable insights into the potential of machine learning techniques for evaluating the actions of helical piles in soil, and offers practical guidance for engineers and researchers in this field.

2 Materials and methods

The pullout resistance of a helical pile, which is a type of deep foundation, can be affected by various factors. These include the type and characteristics of the soil, the geometry and size of the helix plates, the spacing and orientation of the plates [32], the geometry and size of the pile shaft, the installation torque and method [33], the groundwater level [34] and soil moisture content, the loading conditions and magnitude, the depth of embedment, and environmental factors such as temperature and corrosion [35]. All of these factors can impact the performance of the helical pile in terms of its ability to withstand axial or uplift loads and therefore need to be carefully considered during the design and installation process. In intelligent simulations, the effective factors act as inputs for a target parameter, and the network aims to capture their relationship and identify any patterns. The current study utilizes the dataset provided by Nazir et al. [36] for this purpose [36]. The embedment ratio $R_{e m}$ of a helical pile is the depth-to-diameter ratio and is an important design parameter that can affect the performance of the helical pile. The embedment ratio can vary depending on factors like the soil type, the loading conditions, and the required capacity of the pile. A higher embedment ratio generally results in a higher capacity of the pile to resist axial or uplift loads, but may also increase the installation difficulty and cost. The dataset analyzed in this study includes 36 samples that record the $P_{u l}$ of helical piles, as an independent variable, along with the embedment ratio $R_{e m}$ , soil density class $C_{S D}$ , and shaft diameter ratio $(R_{S D} = D_{b} / D_{s})$ as input parameters affecting $P_{u l}$ as it is shown in Fig. 1 where D_s is the central shaft diameter and D_b is the helical plate (flange) diameter.

Fig. 1.

Shaft diameter ratio in helical pile

Citation: Pollack Periodica 19, 3; 10.1556/606.2024.01052

Figures 2 –5 display the changes in $R_{e m}$ , $C_{S D}$ , $R_{S D}$ , and $P_{u l}$ respectively. The embedment ratio ranges from 0 to 5 with a mean value of 2.5. The soil density class has two recorded values of 85 and 35 kN m⁻³ that correspond to dense and loose soils, respectively. The dataset consists of an equal number of samples for both dense and loose soil types. The shaft diameter ratio, follows a repeated pattern with the values 0.3, 0.4, and 0.5, resulting in a total of 36 samples in the dataset 6 × 2 × 3. The corresponding $P_{u l}$ values range from 0 to 1622.47 N with an average of 376.8 N. It is observed that the $P_{u l}$ values for dense soils are higher compared to loose soils.

Fig. 2.

The embedment ratio

Citation: Pollack Periodica 19, 3; 10.1556/606.2024.01052

Fig. 3.

The soil density class

Citation: Pollack Periodica 19, 3; 10.1556/606.2024.01052

Fig. 4.

The shaft diameter ratio

Citation: Pollack Periodica 19, 3; 10.1556/606.2024.01052

Fig. 5.

Pullout resistance

Citation: Pollack Periodica 19, 3; 10.1556/606.2024.01052

3 Methodology

Three models were formulated to analyze the performance of the pullout resistance in this work including an adaptive neuro-fuzzy inference system, random forest regression, and support vector machine.

3.1 Adaptive neuro-fuzzy inference system

White [37] introduced the concepts of Generalized Regression Neural Network (GRNN) and Multi-Layer Perceptron Neural Network (MLPNN) as two popular types of ANNs. ANNs are computational models that mimic the functioning of biological neural systems, as described by McCulloch and Pitts [38] and Anderson and McNeill [39]. The key elements of these networks are the neurons, which are interconnected through synapses to process signals, as it is explained by Hu and Hwang [40]. To establish a non-linear correlation between the inputs and targets, the data undergo a series of operations across multiple layers. A GRNN comprises four layers, specifically, the input layer, pattern layer, summation layer, and output layer, as described by Xie et al. [41]. Conversely, an MLPNN has a minimum of three layers, including the input layer, one or more hidden layer(s), and the output layer, as stated by Hornik et al. [42]. In both the GRNN and MLPNN, the number of neurons in the first and last layers corresponds to the dimensions of the inputs and targets, respectively. The number of neurons in the hidden layer of the MLPNN is flexible and usually determined by the user, whereas in the GRNN, the number of neurons in the pattern layer matches the number of instances. In both models, the primary computations are performed in the middle layers, and the output neurons conduct a linear calculation to produce responses. Further details on these models can be found in various literature sources, such as Seyedashraf et al. [43] and Ge et al. [44]. The ANFIS model, introduced by Jang [45], combines the benefits of neural networks and fuzzy logic, as noted by Moayedi et al. [46]. Fuzzy systems involve operations like fuzzification, a fuzzy inference engine, and defuzzification, which are used to transform crisp values into linguistic fuzzy variables for entry into an inference engine. The fuzzy rules are applied to these variables, and the resulting value is subjected to a defuzzification process to convert the response back into crisp values. The ANFIS is similar to ANNs in that it consists of five layers, each of which performs a specific operation, including The ANFIS comprises five layers, with the first layer, called the fuzzification layer, transforming crisp inputs into fuzzy ones. In the implication layer, the ANN's weight functions are calculated, and the obtained weights are normalized in the normalization layer. The fourth layer carries out defuzzification, and the output is produced by the neurons in the output layer, as explained by Alajmi and Almeshal [47].

3.2 Random forest regression

Random Forest Regression (RFR) is widely utilized in machine learning for regression tasks and can be seen as an advancement of the RFR, which is primarily used for classification tasks. In RFR, numerous decision trees are generated, with each tree trained on a randomly chosen subset of the data and features. Afterwards, the algorithm consolidates the predictions from all the trees to produce the final prediction. By decreasing the model's variance, utilizing RFR instead of a single decision tree can enhance the prediction's accuracy. This is achieved by reducing the overfitting of the model, which can be a common issue with decision trees. RFR also has the ability to handle high-dimensional data and non-linear relationships between the features and the output. RFR is implemented in Python using the scikit-learn library. To achieve the intended level of accuracy, the model's hyper-parameters, including the number of trees and the number of features in each tree, can be adjusted. Once the model has undergone training, it is capable of making predictions on new data.

3.3 Support vector regression

Support Vector Regression (SVR) is a machine learning algorithm used for regression tasks. It is based on the Support Vector Machine (SVM) algorithm, which is primarily used for classification tasks. SVR functions by identifying a hyperplane that best suits the data and maximizes the distance between the hyperplane and the nearest data points. This hyperplane is then used to make predictions on new data. One of the advantages of using SVR is that it can handle non-linear relationships between the features and the output by using a kernel function. The kernel function maps the data to a higher-dimensional feature space where it is easier to find a hyperplane that separates the data points. SVR can also handle outliers in the data by controlling the width of the margin around the hyperplane. SVR is implemented in Python using the scikit-learn library. The hyper-parameters of the model, like the type of kernel function and the regularization parameter, can be tuned to achieve the desired level of accuracy. Once the model is trained, it can be used to make predictions on new data. Overall, SVR is a powerful machine learning algorithm that is well-suited for regression tasks, particularly when the data has non-linear relationships between the features and the output. It can also handle outliers in the data and can tune the level of complexity of the model by controlling the width of the margin around the hyperplane.

4 Results and discussion

The proposed models were implemented and evaluated using two types of data: training data and testing data. The training data comprised 25 samples, while the testing data contained 11 samples. The data were randomly permuted to enable a random selection, and a 70:30 selection ratio was applied, as stated in the text.

4.1 Indices used to evaluate accuracy

To evaluate the accuracy of both data groups, three widely accepted criteria are employed. The first criterion used to measure the prediction error for J samples is the Root Mean Square Error (RMSE), as it is expressed in the following equation,

R M S E = \sqrt{\frac{1}{J} \sum_{i = 1}^{J} {{[(P}_{u l, i_{o b s e r v a t i o n}} - P_{u l, i_{e s t i m a t i o n}})]}^{2}} .

(1)

The values of

P_{u l}

are estimated and expected using

P_{u l, i_{e s t i m a t i o n}}

and

P_{u l, i_{o b s e r v a t i o n}}

, respectively. The second measure used for accuracy assessment is the Mean Absolute Error (MAE) which is calculated on the base of Eq. (2),

M A E = \frac{1}{J} \sum_{i = 1}^{J} | P_{u l, i_{o b s e r v a t i o n}} - P_{u l, i_{e s t i m a t i o n}} | .

(2)

4.2 Training and development

The ANFIS with adjustable parameters of its Membership Functions (MFs) is fed by training data and during the training procedure, the system attempts to optimize the tuning of the MFs to capture the relationship between $P_{u l}$ and the independent variables, $R_{e m}$ , $C_{S D}$ , and $R_{S D}$ . The ANFIS is optimized over a total of 1000 iterations. The pullout resistance patterns obtained in the laboratory and by predictive models is displayed in Fig. 6. It can be observed from the figure that all models could accurately capture most of the $P_{u l}$ behavior. Nevertheless, the random forest model outperformed the others in predicting the maximum and minimum $P_{u l}$ .

Fig. 6.

Predictive models of the pullout resistance behavior

Citation: Pollack Periodica 19, 3; 10.1556/606.2024.01052

4.3 Results of testing and comparison

During the second phase, the pullout was predicted for new pile conditions, and as with the training phase, the performance of each network was evaluated using RMSE, MAE, and PCC by comparing the predicted values to the expected values. Figure 7 displays the difference between the expected and predicted pullout resistance, which is referred to as “Error”. The regression chart shows a high aggregation of data points around the ideal line (i.e., x = 0), and the graph exhibits a higher frequency of small errors. These results demonstrate the satisfactory performance of the models used.

Fig. 7.

Performance of the predictive models

Citation: Pollack Periodica 19, 3; 10.1556/606.2024.01052

Based on Fig. 7, it can be concluded that all predicted outputs have a high level of agreement with the laboratory results over a specific domain of the dataset. However, ANFIS has the worst performance while random regression performed better than others.

5 Conclusions

Three machine learning were utilized to study the behavior of the pullout resistance of a helical pile. Adaptive neuro-fuzzy inference systems, random forest regression, and support vector regression were employed to study and analyze the experimental results of a helical pile. While the adaptive neuro-fuzzy inference system performed well on the training set, it had a deficiency on the test set. The support vector technique has better performance than the adaptive neuro-fuzzy inference system and worse than the random forest algorithm. Overall, random forest machine learning regression outperformed other methods in this study and returns a good prediction state with acceptable error values. Consequently, random forest regression is highly recommended to represent complex data of pile foundation analysis.

References

[1]↑
C. Zhang, H. Kordestani, and M. Shadabfar, “A combined review of vibration control strategies for high-speed trains and railway infrastructures: Challenges and solutions,” J. Low Freq. Noise, Vib. Act. Control, vol. 42, no. 1, pp. 272–291, 2023.
- Search Google Scholar
- Export Citation
[2]↑
Z. Zhang, W. Li, and J. Yang, “Analysis of stochastic process to model safety risk in construction industry,” J. Civ. Eng. Manag., vol. 27, no. 2, pp. 87–99, 2021.
- Search Google Scholar
- Export Citation
[3]↑
S. Alsamia, M. S. Mahmood, and A. Akhtarpour, “Estimation of capillary rise in unsaturated gypseous sand soils,” Pollack Period, vol. 15, no. 2, pp. 118–129, 2020.
- Search Google Scholar
- Export Citation
[4]↑
R. A. Sirsikar, “Study of helical pile behavior in cohesionless soil,” BSc Thesis, National Institute of Technology, Durgapur, India, 2018.
- Search Google Scholar
- Export Citation
[5]↑
M. Shahbazi, A. B. Cerato, E. M. Hassan, and H. Mahmoud, “Seismic risk assessment of a steel building supported on helical pile groups,” Acta Geotech, vol. 17, no. 1, pp. 289–301, 2022.
- Search Google Scholar
- Export Citation
[6]↑
S. P. Clemence and A. J. Lutenegger, “Industry survey of state of practice for helical piles and tiebacks,” DFI Journal-The J. Deep Found. Inst., vol. 9, no. 1, pp. 21–41, 2015.
- Search Google Scholar
- Export Citation
[7]↑
H. A. Perko, Helical Piles: A Practical Guide to Design and Installation. John Wiley & Sons, 2009.
- Search Google Scholar
- Export Citation
[8]↑
F. M. Abdrabbo and A. Z. El Wakil, “Laterally loaded helical piles in sand,” Alexandria Eng. J., vol. 55, no. 4, pp. 3239–3245, 2016.
- Search Google Scholar
- Export Citation
[9]↑
G. Spagnoli, “A CPT-based model to predict the installation torque of helical piles in sand,” Mar. Georesources Geotechnol., vol. 35, no. 4, pp. 578–585, 2017.
- Search Google Scholar
- Export Citation
[10]↑
A. M. A. Fateh, A. Eslami, and A. Fahimifar, “Direct CPT and CPTU methods for determining bearing capacity of helical piles,” Mar. Georesources Geotechnol., vol. 35, no. 2, pp. 193–207, 2017.
- Search Google Scholar
- Export Citation
[11]↑
Z. Liang and Z. Zhu, “Critical helical buckling load assessment of coiled tubing under axial force by use of the explicit finite-element method,” J. Pet. Sci. Eng., vol. 169, pp. 51–57, 2018.
- Search Google Scholar
- Export Citation
[12]
K. Papadopoulou, H. Saroglou, and V. Papadopoulos, “Finite element analyses and experimental investigation of helical micropiles,” Geotech. Geol. Eng., vol. 32, pp. 949–963, 2014.
- Search Google Scholar
- Export Citation
[13]
M. F. Alwalan and M. H. El Naggar, “Finite element analysis of helical piles subjected to axial impact loading,” Comput. Geotech., vol. 123, 2020, Art no. 103597.
- Search Google Scholar
- Export Citation
[14]↑
G. Spagnoli, C. de H. C. Tsuha, P. Oreste, and C. M. o M. Solarte, “Estimation of uplift capacity and installation power of helical piles in sand for offshore structures,” J. Waterw. Port, Coastal, Ocean Eng., vol. 144, no. 6, 2018, Art no. 4018019.
- Search Google Scholar
- Export Citation
[15]
G. Spagnoli and C. de H. C. Tsuha, “A review on the behavior of helical piles as a potential offshore foundation system,” Mar. Georesources Geotechnol., vol. 38, no. 9, pp. 1013–1036, 2020.
- Search Google Scholar
- Export Citation
[16]
P. Cheng, J. Guo, K. Yao, and X. Chen, “Numerical investigation on pullout capacity of helical piles under combined loading in spatially random clay,” Mar. Georesources Geotechnol., pp. 1–14, 2022.
- Search Google Scholar
- Export Citation
[17]↑
K. Kumar, S. Roy, and J. P. Davim, Soft Computing Techniques for Engineering Optimization. CRC Press, 2019.
- Search Google Scholar
- Export Citation
[18]
J. Ghaboussi, Soft Computing in Engineering. CRC Press, 2018.
- Search Google Scholar
- Export Citation
[19]
S. K. Shreyas and A. Dey, “Application of soft computing techniques in tunnelling and underground excavations: state of the art and future prospects,” Innov. Infrastruct. Solut., vol. 4, pp. 1–15, 2019.
- Search Google Scholar
- Export Citation
[20]↑
S. Alsamia, H. Albedran, and M. S. Mahmood, “Contamination depth prediction in sandy soils using fuzzy rule-based expert system,” Int. Rev. Appl. Sci. Eng., vol. 14, no. 1, pp. 87–99, 2023.
- Search Google Scholar
- Export Citation
[21]↑
H. Ghafil and K. Jármai, “Comparative study of particle swarm optimization and artificial bee colony algorithms,” in Multiscience XXXII. MicroCAD International Multidisciplinary Scientific Conference, Miskolc-Egyetemváros, Hungary, September 5–6, 2018, pp. 1–6.
- Search Google Scholar
- Export Citation
[22]↑
M. H. Bhatti, J. Khan, M. U. G. Khan, R. Iqbal, M. Aloqaily, Y. Jararweh, and B. Gupta, “Soft computing-based EEG classification by optimal feature selection and neural networks,” IEEE Trans. Ind. Inform., vol. 15, no. 10, pp. 5747–5754, 2019.
- Search Google Scholar
- Export Citation
[23]↑
H. N. Ghafil, S. Alsamia, and K. Jármai, “Fertilization optimization algorithm on CEC2015 and large scale problems,” Pollack Period, vol. 17, no. 1, pp. 24–29, 2021.
- Search Google Scholar
- Export Citation
[24]↑
H. N. Ghafil and K. Jármai, Optimization for Robot Modelling with MATLAB. Springer Nature, 2020.
- Search Google Scholar
- Export Citation
[25]↑
Y. Yalcin, M. Orhon, and O. Pekcan, “An automated approach for the design of mechanically stabilized earth walls incorporating metaheuristic optimization algorithms,” Appl. Soft Comput., vol. 74, pp. 547–566, 2019.
- Search Google Scholar
- Export Citation
[26]↑
H. Moayedi, M. Mehrabi, M. Mosallanezhad, A. S. A. Rashid, and B. Pradhan, “Modification of landslide susceptibility mapping using optimized PSO-ANN technique,” Eng. Comput., vol. 35, pp. 967–984, 2019.
- Search Google Scholar
- Export Citation
[27]↑
F. Xu, L. K. Foong, and Z. Lyu, “A novel search scheme based on the social behavior of crow flock for feed-forward learning improvement in predicting the soil compression coefficient,” Eng. Comput., pp. 1–14, 2022.
- Search Google Scholar
- Export Citation
[28]↑
N. V. Luat, J. Shin, and K. Lee, “Hybrid BART-based models optimized by nature-inspired metaheuristics to predict ultimate axial capacity of CCFST columns,” Eng. Comput., vol. 38, no. 2, pp. 1421–1450, 2022.
- Search Google Scholar
- Export Citation
[29]↑
A. Hazim, A. A. Habeeb, J. Károly, and K. Endre, “Interpolated spline method for a thermal distribution of a pipe with a turbulent heat flow,” Multidiszcip. Tudományok, vol. 11, no. 5, pp. 353–362, 2021.
- Search Google Scholar
- Export Citation
[30]↑
K. Na, D. Lee, H. Lee, K. Jung, and H. Choi, “Optimum configuration of helical piles with material cost minimized by harmony search algorithm,” in Advances in Intelligent Systems and Computing, vol. 382, Harmony Search Algorithm, J. Kim, and Z. Geem, Eds., Berlin, Heidelberg: Springer, 2016, pp. 329–340.
- Search Google Scholar
- Export Citation
[31]↑
H. Moayedi, D. T. Bui, M. Gör, B. Pradhan, and A. Jaafari, “The feasibility of three prediction techniques of the artificial neural network, adaptive neuro-fuzzy inference system, and hybrid particle swarm optimization for assessing the safety factor of cohesive slopes,” ISPRS Int. J. Geo-Information, vol. 8, no. 9, 2019, Art no. 391.
- Search Google Scholar
- Export Citation
[32]↑
D. Mulyanda, M. M. Iqbal, and R. Dewi, “The effect of helical size on uplift pile capacity,” Int. J. Sci. Technol. Res., vol. 9, no. 2, pp. 4140–4145, 2020.
- Search Google Scholar
- Export Citation
[33]↑
K. Shao, Q. Su, K. Liu, G. Shao, Z. Zhong, Z. Li, and C. Chen, “A new modified approach to evaluating the installation power of large-diameter helical piles in sand validated by centrifuge and field data,” Appl. Ocean Res., vol. 114, 2021, Art no. 102756.
- Search Google Scholar
- Export Citation
[34]↑
A. S. Bradshaw, L. Cullen, and Z. Miller, “Field study of group effects on the pullout capacity of ‘deep’ helical piles in sand,” Can. Geotech. J., vol. 59, no. 4, pp. 538–545, 2022.
- Search Google Scholar
- Export Citation
[35]↑
M. Mosallanezhad and H. Moayedi, “Developing hybrid artificial neural network model for predicting uplift resistance of screw piles,” Arab. J. Geosci., vol. 10, 2017, Art no. 479.
- Search Google Scholar
- Export Citation
[36]↑
R. Nazir, H. S. Chuan, H. Niroumand, and K. A. Kassim, “Performance of single vertical helical anchor embedded in dry sand,” Measurement, vol. 49, pp. 42–51, 2014.
- Search Google Scholar
- Export Citation
[37]↑
H. White, Artificial Neural Networks: Approximation and Learning Theory. Blackwell Publishers, Inc., 1992.
- Search Google Scholar
- Export Citation
[38]↑
W. S. McCulloch and W. Pitts, “A logical calculus of the ideas immanent in nervous activity,” Bull. Math. Biophys., vol. 5, pp. 115–133, 1943.
- Search Google Scholar
- Export Citation
[39]↑
D. Anderson and G. McNeill, “Artificial neural networks technology,” Kaman Sci. Corp., vol. 258, no. 6, pp. 1–83, 1992.
- Search Google Scholar
- Export Citation
[40]↑
Y. H. Hu and J. N. Hwang, Handbook of Neural Network Signal Processing. Acoustical Society of America, 2002.
- Search Google Scholar
- Export Citation
[41]↑
H. Xie, G. Li, X. Zhao, and F. Li, “Prediction of limb joint angles based on multi-source signals by GS-GRNN for exoskeleton wearer,” Sensors, vol. 20, no. 4, 2020, Art no. 1104.
- Search Google Scholar
- Export Citation
[42]↑
K. Hornik, M. Stinchcombe, and H. White, “Multilayer feedforward networks are universal approximators,” Neural Networks, vol. 2, no. 5, pp. 359–366, 1989.
- Search Google Scholar
- Export Citation
[43]↑
O. Seyedashraf, M. Mehrabi, and A. A. Akhtari, “Novel approach for dam break flow modeling using computational intelligence,” J. Hydrol., vol. 559, pp. 1028–1038, 2018.
- Search Google Scholar
- Export Citation
[44]↑
X. Lin, W. Zhang, H. Qiu, and B. Peng, “Research on auxiliary diagnosis of power communication field operation and maintenance based on CBR,” Telecommun. Radio Eng., vol. 79, no. 19, pp. 1761–1771, 2020.
- Search Google Scholar
- Export Citation
[45]↑
J. S. Jang, “ANFIS: adaptive-network-based fuzzy inference system,” IEEE Trans. Syst. Man. Cybern, vol. 23, no. 3, pp. 665–685, 1993.
- Search Google Scholar
- Export Citation
[46]↑
H. Moayedi, M. Mehrabi, B. kalantar, M. A. Muazu, A. S. A. Rashid, L. K. Foong, and H. Nguyen, “Novel hybrids of adaptive neuro-fuzzy inference system (ANFIS) with several metaheuristic algorithms for spatial susceptibility assessment of seismic-induced landslide,” Geomatics, Nat. Hazards Risk, vol. 10, no. 1, pp. 1879–1911, 2019.
- Search Google Scholar
- Export Citation
[47]↑
M. S. Alajmi and A. M. Almeshal, “Prediction and optimization of surface roughness in a turning process using the ANFIS-QPSO method,” Materials, vol. 13, no. 13, 2020, Art no. 2986.
- Search Google Scholar
- Export Citation

ProCite

RefWorks

Reference Manager

BibTeX

Zotero

EndNote

Save
Cite
Email this content

Share Link

Copy this link, or click below to email it to a friend
Email this content
or copy the link directly:

https://akjournals.com/view/journals/606/19/3/article-p28.xml
The link was not copied. Your current browser may not support copying via this button.

Link copied successfully

Collapse
Expand

Pollack Periodica

Print ISSN:: 1788-1994

Online ISSN:: 1788-3911

Editorial Board

Bálint Bachmann (Institute of Architecture, Faculty of Engineering and Information Technology, University of Pécs, Hungary)
Jeno Balogh (Department of Civil Engineering Technology, Metropolitan State University of Denver, Denver, Colorado, USA)
Radu Bancila (Department of Geotechnical Engineering and Terrestrial Communications Ways, Faculty of Civil Engineering and Architecture, “Politehnica” University Timisoara, Romania)
Charalambos C. Baniotopolous (Department of Civil Engineering, Chair of Sustainable Energy Systems, Director of Resilience Centre, School of Engineering, University of Birmingham, U.K.)
Oszkar Biro (Graz University of Technology, Institute of Fundamentals and Theory in Electrical Engineering, Austria)
Ágnes Borsos (Institute of Architecture, Department of Interior, Applied and Creative Design, Faculty of Engineering and Information Technology, University of Pécs, Hungary)
Matteo Bruggi (Dipartimento di Ingegneria Civile e Ambientale, Politecnico di Milano, Italy)
Petra Bujňáková (Department of Structures and Bridges, Faculty of Civil Engineering, University of Žilina, Slovakia)
Anikó Borbála Csébfalvi (Department of Civil Engineering, Institute of Smart Technology and Engineering, Faculty of Engineering and Information Technology, University of Pécs, Hungary)
Mirjana S. Devetaković (Faculty of Architecture, University of Belgrade, Serbia)
Szabolcs Fischer (Department of Transport Infrastructure and Water Resources Engineering, Faculty of Architerture, Civil Engineering and Transport Sciences Széchenyi István University, Győr, Hungary)
Radomir Folic (Department of Civil Engineering, Faculty of Technical Sciences, University of Novi Sad Serbia)
Jana Frankovská (Department of Geotechnics, Faculty of Civil Engineering, Slovak University of Technology in Bratislava, Slovakia)
János Gyergyák (Department of Architecture and Urban Planning, Institute of Architecture, Faculty of Engineering and Information Technology, University of Pécs, Hungary)
Kay Hameyer (Chair in Electromagnetic Energy Conversion, Institute of Electrical Machines, Faculty of Electrical Engineering and Information Technology, RWTH Aachen University, Germany)
Elena Helerea (Dept. of Electrical Engineering and Applied Physics, Faculty of Electrical Engineering and Computer Science, Transilvania University of Brasov, Romania)
Ákos Hutter (Department of Architecture and Urban Planning, Institute of Architecture, Faculty of Engineering and Information Technolgy, University of Pécs, Hungary)
Károly Jármai (Institute of Energy and Chemical Machinery, Faculty of Mechanical Engineering and Informatics, University of Miskolc, Hungary)
Teuta Jashari-Kajtazi (Department of Architecture, Faculty of Civil Engineering and Architecture, University of Prishtina, Kosovo)
Róbert Kersner (Department of Technical Informatics, Institute of Information and Electrical Technology, Faculty of Engineering and Information Technology, University of Pécs, Hungary)
Rita Kiss (Biomechanical Cooperation Center, Faculty of Mechanical Engineering, Budapest University of Technology and Economics, Budapest, Hungary)
István Kistelegdi (Department of Building Structures and Energy Design, Institute of Architecture, Faculty of Engineering and Information Technology, University of Pécs, Hungary)
Stanislav Kmeť (President of University Science Park TECHNICOM, Technical University of Kosice, Slovakia)
Imre Kocsis (Department of Basic Engineering Research, Faculty of Engineering, University of Debrecen, Hungary)
László T. Kóczy (Department of Information Sciences, Faculty of Mechanical Engineering, Informatics and Electrical Engineering, University of Győr, Hungary)
Dražan Kozak (Faculty of Mechanical Engineering, Josip Juraj Strossmayer University of Osijek, Croatia)
György L. Kovács (Department of Technical Informatics, Institute of Information and Electrical Technology, Faculty of Engineering and Information Technology, University of Pécs, Hungary)
Balázs Géza Kövesdi (Department of Structural Engineering, Faculty of Civil Engineering, Budapest University of Engineering and Economics, Budapest, Hungary)
Tomáš Krejčí (Department of Mechanics, Faculty of Civil Engineering, Czech Technical University in Prague, Czech Republic)
Jaroslav Kruis (Department of Mechanics, Faculty of Civil Engineering, Czech Technical University in Prague, Czech Republic)
Miklós Kuczmann (Department of Automations, Faculty of Mechanical Engineering, Informatics and Electrical Engineering, Széchenyi István University, Győr, Hungary)
Tibor Kukai (Department of Engineering Studies, Institute of Smart Technology and Engineering, Faculty of Engineering and Information Technology, University of Pécs, Hungary)
Maria Jesus Lamela-Rey (Departamento de Construcción e Ingeniería de Fabricación, University of Oviedo, Spain)
János Lógó (Department of Structural Mechanics, Faculty of Civil Engineering, Budapest University of Technology and Economics, Hungary)
Carmen Mihaela Lungoci (Faculty of Electrical Engineering and Computer Science, Universitatea Transilvania Brasov, Romania)
Frédéric Magoulés (Department of Mathematics and Informatics for Complex Systems, Centrale Supélec, Université Paris Saclay, France)
Gabriella Medvegy (Department of Interior, Applied and Creative Design, Institute of Architecture, Faculty of Engineering and Information Technology, University of Pécs, Hungary)
Tamás Molnár (Department of Visual Studies, Institute of Architecture, Faculty of Engineering and Information Technology, University of Pécs, Hungary)
Ferenc Orbán (Department of Mechanical Engineering, Institute of Smart Technology and Engineering, Faculty of Engineering and Information Technology, University of Pécs, Hungary)
Zoltán Orbán (Department of Civil Engineering, Institute of Smart Technology and Engineering, Faculty of Engineering and Information Technology, University of Pécs, Hungary)
Dmitrii Rachinskii (Department of Mathematical Sciences, The University of Texas at Dallas, Texas, USA)
Chro Radha (Chro Ali Hamaradha) (Sulaimani Polytechnic University, Technical College of Engineering, Department of City Planning, Kurdistan Region, Iraq)
Maurizio Repetto (Department of Energy “Galileo Ferraris”, Politecnico di Torino, Italy)
Zoltán Sári (Department of Technical Informatics, Institute of Information and Electrical Technology, Faculty of Engineering and Information Technology, University of Pécs, Hungary)
Grzegorz Sierpiński (Department of Transport Systems and Traffic Engineering, Faculty of Transport, Silesian University of Technology, Katowice, Poland)
Zoltán Siménfalvi (Institute of Energy and Chemical Machinery, Faculty of Mechanical Engineering and Informatics, University of Miskolc, Hungary)
Andrej Šoltész (Department of Hydrology, Faculty of Civil Engineering, Slovak University of Technology in Bratislava, Slovakia)
Zsolt Szabó (Faculty of Information Technology and Bionics, Pázmány Péter Catholic University, Hungary)
Mykola Sysyn (Chair of Planning and Design of Railway Infrastructure, Institute of Railway Systems and Public Transport, Technical University of Dresden, Germany)
András Timár (Faculty of Engineering and Information Technology, University of Pécs, Hungary)
Barry H. V. Topping (Heriot-Watt University, UK, Faculty of Engineering and Information Technology, University of Pécs, Hungary)

POLLACK PERIODICA
Pollack Mihály Faculty of Engineering
Institute: University of Pécs
Address: Boszorkány utca 2. H–7624 Pécs, Hungary
Phone/Fax: (36 72) 503 650

E-mail: peter.ivanyi@mik.pte.hu

or amalia.ivanyi@mik.pte.hu

Indexing and Abstracting Services:

SCOPUS
CABELLS Journalytics

2023
Scopus
CiteScore	1.5
CiteScore rank	Q3 (Civil and Structural Engineering)
SNIP	0.849
Scimago
SJR index	0.288
SJR Q rank	Q3

Pollack Periodica
Publication Model	Hybrid
Submission Fee	none
Article Processing Charge	900 EUR/article
Printed Color Illustrations	40 EUR (or 10 000 HUF) + VAT / piece
Regional discounts on country of the funding agency	World Bank Lower-middle-income economies: 50% World Bank Low-income economies: 100%
Further Discounts	Editorial Board / Advisory Board members: 50% Corresponding authors, affiliated to an EISZ member institution subscribing to the journal package of Akadémiai Kiadó: 100%
Subscription fee 2025	Online subsscription: 381 EUR / 420 USD Print + online subscription: 456 EUR / 520 USD
Subscription Information	Online subscribers are entitled access to all back issues published by Akadémiai Kiadó for each title for the duration of the subscription, as well as Online First content for the subscribed content.
Purchase per Title	Individual articles are sold on the displayed price.