@article{RabczukGuoZhuangetal., author = {Rabczuk, Timon and Guo, Hongwei and Zhuang, Xiaoying and Chen, Pengwan and Alajlan, Naif}, title = {Stochastic deep collocation method based on neural architecture search and transfer learning for heterogeneous porous media}, series = {Engineering with Computers}, volume = {2022}, journal = {Engineering with Computers}, publisher = {Springer}, address = {London}, doi = {10.1007/s00366-021-01586-2}, url = {http://nbn-resolving.de/urn:nbn:de:gbv:wim2-20220209-45835}, pages = {1 -- 26}, abstract = {We present a stochastic deep collocation method (DCM) based on neural architecture search (NAS) and transfer learning for heterogeneous porous media. We first carry out a sensitivity analysis to determine the key hyper-parameters of the network to reduce the search space and subsequently employ hyper-parameter optimization to finally obtain the parameter values. The presented NAS based DCM also saves the weights and biases of the most favorable architectures, which is then used in the fine-tuning process. We also employ transfer learning techniques to drastically reduce the computational cost. The presented DCM is then applied to the stochastic analysis of heterogeneous porous material. Therefore, a three dimensional stochastic flow model is built providing a benchmark to the simulation of groundwater flow in highly heterogeneous aquifers. The performance of the presented NAS based DCM is verified in different dimensions using the method of manufactured solutions. We show that it significantly outperforms finite difference methods in both accuracy and computational cost.}, subject = {Maschinelles Lernen}, language = {en} } @article{ChakrabortyAnitescuZhuangetal., author = {Chakraborty, Ayan and Anitescu, Cosmin and Zhuang, Xiaoying and Rabczuk, Timon}, title = {Domain adaptation based transfer learning approach for solving PDEs on complex geometries}, series = {Engineering with Computers}, volume = {2022}, journal = {Engineering with Computers}, doi = {10.1007/s00366-022-01661-2}, url = {http://nbn-resolving.de/urn:nbn:de:gbv:wim2-20220811-46776}, pages = {1 -- 20}, abstract = {In machine learning, if the training data is independently and identically distributed as the test data then a trained model can make an accurate predictions for new samples of data. Conventional machine learning has a strong dependence on massive amounts of training data which are domain specific to understand their latent patterns. In contrast, Domain adaptation and Transfer learning methods are sub-fields within machine learning that are concerned with solving the inescapable problem of insufficient training data by relaxing the domain dependence hypothesis. In this contribution, this issue has been addressed and by making a novel combination of both the methods we develop a computationally efficient and practical algorithm to solve boundary value problems based on nonlinear partial differential equations. We adopt a meshfree analysis framework to integrate the prevailing geometric modelling techniques based on NURBS and present an enhanced deep collocation approach that also plays an important role in the accuracy of solutions. We start with a brief introduction on how these methods expand upon this framework. We observe an excellent agreement between these methods and have shown that how fine-tuning a pre-trained network to a specialized domain may lead to an outstanding performance compare to the existing ones. As proof of concept, we illustrate the performance of our proposed model on several benchmark problems.}, subject = {Maschinelles Lernen}, language = {en} } @article{KumariHarirchianLahmeretal., author = {Kumari, Vandana and Harirchian, Ehsan and Lahmer, Tom and Rasulzade, Shahla}, title = {Evaluation of Machine Learning and Web-Based Process for Damage Score Estimation of Existing Buildings}, series = {Buildings}, volume = {2022}, journal = {Buildings}, number = {Volume 12, issue 5, article 578}, publisher = {MDPI}, address = {Basel}, doi = {10.3390/buildings12050578}, url = {http://nbn-resolving.de/urn:nbn:de:gbv:wim2-20220509-46387}, pages = {1 -- 23}, abstract = {The seismic vulnerability assessment of existing reinforced concrete (RC) buildings is a significant source of disaster mitigation plans and rescue services. Different countries evolved various Rapid Visual Screening (RVS) techniques and methodologies to deal with the devastating consequences of earthquakes on the structural characteristics of buildings and human casualties. Artificial intelligence (AI) methods, such as machine learning (ML) algorithm-based methods, are increasingly used in various scientific and technical applications. The investigation toward using these techniques in civil engineering applications has shown encouraging results and reduced human intervention, including uncertainties and biased judgment. In this study, several known non-parametric algorithms are investigated toward RVS using a dataset employing different earthquakes. Moreover, the methodology encourages the possibility of examining the buildings' vulnerability based on the factors related to the buildings' importance and exposure. In addition, a web-based application built on Django is introduced. The interface is designed with the idea to ease the seismic vulnerability investigation in real-time. The concept was validated using two case studies, and the achieved results showed the proposed approach's potential efficiency}, subject = {Maschinelles Lernen}, language = {en} } @article{BandJanizadehChandraPaletal., author = {Band, Shahab S. and Janizadeh, Saeid and Chandra Pal, Subodh and Saha, Asish and Chakrabortty, Rabbin and Shokri, Manouchehr and Mosavi, Amir Hosein}, title = {Novel Ensemble Approach of Deep Learning Neural Network (DLNN) Model and Particle Swarm Optimization (PSO) Algorithm for Prediction of Gully Erosion Susceptibility}, series = {Sensors}, volume = {2020}, journal = {Sensors}, number = {Volume 20, issue 19, article 5609}, publisher = {MDPI}, address = {Basel}, doi = {10.3390/s20195609}, url = {http://nbn-resolving.de/urn:nbn:de:gbv:wim2-20210122-43341}, pages = {1 -- 27}, abstract = {This study aims to evaluate a new approach in modeling gully erosion susceptibility (GES) based on a deep learning neural network (DLNN) model and an ensemble particle swarm optimization (PSO) algorithm with DLNN (PSO-DLNN), comparing these approaches with common artificial neural network (ANN) and support vector machine (SVM) models in Shirahan watershed, Iran. For this purpose, 13 independent variables affecting GES in the study area, namely, altitude, slope, aspect, plan curvature, profile curvature, drainage density, distance from a river, land use, soil, lithology, rainfall, stream power index (SPI), and topographic wetness index (TWI), were prepared. A total of 132 gully erosion locations were identified during field visits. To implement the proposed model, the dataset was divided into the two categories of training (70\%) and testing (30\%). The results indicate that the area under the curve (AUC) value from receiver operating characteristic (ROC) considering the testing datasets of PSO-DLNN is 0.89, which indicates superb accuracy. The rest of the models are associated with optimal accuracy and have similar results to the PSO-DLNN model; the AUC values from ROC of DLNN, SVM, and ANN for the testing datasets are 0.87, 0.85, and 0.84, respectively. The efficiency of the proposed model in terms of prediction of GES was increased. Therefore, it can be concluded that the DLNN model and its ensemble with the PSO algorithm can be used as a novel and practical method to predict gully erosion susceptibility, which can help planners and managers to manage and reduce the risk of this phenomenon.}, subject = {Geoinformatik}, language = {en} } @article{HarirchianKumariJadhavetal., author = {Harirchian, Ehsan and Kumari, Vandana and Jadhav, Kirti and Rasulzade, Shahla and Lahmer, Tom and Raj Das, Rohan}, title = {A Synthesized Study Based on Machine Learning Approaches for Rapid Classifying Earthquake Damage Grades to RC Buildings}, series = {Applied Sciences}, volume = {2021}, journal = {Applied Sciences}, number = {Volume 11, issue 16, article 7540}, publisher = {MDPI}, address = {Basel}, doi = {10.3390/app11167540}, url = {http://nbn-resolving.de/urn:nbn:de:gbv:wim2-20210818-44853}, pages = {1 -- 33}, abstract = {A vast number of existing buildings were constructed before the development and enforcement of seismic design codes, which run into the risk of being severely damaged under the action of seismic excitations. This poses not only a threat to the life of people but also affects the socio-economic stability in the affected area. Therefore, it is necessary to assess such buildings' present vulnerability to make an educated decision regarding risk mitigation by seismic strengthening techniques such as retrofitting. However, it is economically and timely manner not feasible to inspect, repair, and augment every old building on an urban scale. As a result, a reliable rapid screening methods, namely Rapid Visual Screening (RVS), have garnered increasing interest among researchers and decision-makers alike. In this study, the effectiveness of five different Machine Learning (ML) techniques in vulnerability prediction applications have been investigated. The damage data of four different earthquakes from Ecuador, Haiti, Nepal, and South Korea, have been utilized to train and test the developed models. Eight performance modifiers have been implemented as variables with a supervised ML. The investigations on this paper illustrate that the assessed vulnerability classes by ML techniques were very close to the actual damage levels observed in the buildings.}, subject = {Maschinelles Lernen}, language = {en} } @article{OuaerHosseiniAmaretal., author = {Ouaer, Hocine and Hosseini, Amir Hossein and Amar, Menad Nait and Ben Seghier, Mohamed El Amine and Ghriga, Mohammed Abdelfetah and Nabipour, Narjes and Andersen, P{\aa}l {\O}steb{\o} and Mosavi, Amir and Shamshirband, Shahaboddin}, title = {Rigorous Connectionist Models to Predict Carbon Dioxide Solubility in Various Ionic Liquids}, series = {Applied Sciences}, volume = {2020}, journal = {Applied Sciences}, number = {Volume 10, Issue 1, 304}, publisher = {MDPI}, doi = {https://doi.org/10.3390/app10010304}, url = {http://nbn-resolving.de/urn:nbn:de:gbv:wim2-20200107-40558}, pages = {18}, abstract = {Estimating the solubility of carbon dioxide in ionic liquids, using reliable models, is of paramount importance from both environmental and economic points of view. In this regard, the current research aims at evaluating the performance of two data-driven techniques, namely multilayer perceptron (MLP) and gene expression programming (GEP), for predicting the solubility of carbon dioxide (CO2) in ionic liquids (ILs) as the function of pressure, temperature, and four thermodynamical parameters of the ionic liquid. To develop the above techniques, 744 experimental data points derived from the literature including 13 ILs were used (80\% of the points for training and 20\% for validation). Two backpropagation-based methods, namely Levenberg-Marquardt (LM) and Bayesian Regularization (BR), were applied to optimize the MLP algorithm. Various statistical and graphical assessments were applied to check the credibility of the developed techniques. The results were then compared with those calculated using Peng-Robinson (PR) or Soave-Redlich-Kwong (SRK) equations of state (EoS). The highest coefficient of determination (R2 = 0.9965) and the lowest root mean square error (RMSE = 0.0116) were recorded for the MLP-LMA model on the full dataset (with a negligible difference to the MLP-BR model). The comparison of results from this model with the vastly applied thermodynamic equation of state models revealed slightly better performance, but the EoS approaches also performed well with R2 from 0.984 up to 0.996. Lastly, the newly established correlation based on the GEP model exhibited very satisfactory results with overall values of R2 = 0.9896 and RMSE = 0.0201.}, subject = {Maschinelles Lernen}, language = {en} } @article{ShamshirbandJoloudariGhasemiGoletal., author = {Shamshirband, Shahaboddin and Joloudari, Javad Hassannataj and GhasemiGol, Mohammad and Saadatfar, Hamid and Mosavi, Amir and Nabipour, Narjes}, title = {FCS-MBFLEACH: Designing an Energy-Aware Fault Detection System for Mobile Wireless Sensor Networks}, series = {Mathematics}, volume = {2020}, journal = {Mathematics}, number = {Volume 8, Issue 1, article 28}, publisher = {MDPI}, doi = {10.3390/math8010028}, url = {http://nbn-resolving.de/urn:nbn:de:gbv:wim2-20200107-40541}, pages = {24}, abstract = {Wireless sensor networks (WSNs) include large-scale sensor nodes that are densely distributed over a geographical region that is completely randomized for monitoring, identifying, and analyzing physical events. The crucial challenge in wireless sensor networks is the very high dependence of the sensor nodes on limited battery power to exchange information wirelessly as well as the non-rechargeable battery of the wireless sensor nodes, which makes the management and monitoring of these nodes in terms of abnormal changes very difficult. These anomalies appear under faults, including hardware, software, anomalies, and attacks by raiders, all of which affect the comprehensiveness of the data collected by wireless sensor networks. Hence, a crucial contraption should be taken to detect the early faults in the network, despite the limitations of the sensor nodes. Machine learning methods include solutions that can be used to detect the sensor node faults in the network. The purpose of this study is to use several classification methods to compute the fault detection accuracy with different densities under two scenarios in regions of interest such as MB-FLEACH, one-class support vector machine (SVM), fuzzy one-class, or a combination of SVM and FCS-MBFLEACH methods. It should be noted that in the study so far, no super cluster head (SCH) selection has been performed to detect node faults in the network. The simulation outcomes demonstrate that the FCS-MBFLEACH method has the best performance in terms of the accuracy of fault detection, false-positive rate (FPR), average remaining energy, and network lifetime compared to other classification methods.}, subject = {Vernetzung}, language = {en} } @article{MeiabadiMoradiKaramimoghadametal., author = {Meiabadi, Mohammad Saleh and Moradi, Mahmoud and Karamimoghadam, Mojtaba and Ardabili, Sina and Bodaghi, Mahdi and Shokri, Manouchehr and Mosavi, Amir Hosein}, title = {Modeling the Producibility of 3D Printing in Polylactic Acid Using Artificial Neural Networks and Fused Filament Fabrication}, series = {polymers}, volume = {2021}, journal = {polymers}, number = {Volume 13, issue 19, article 3219}, publisher = {MDPI}, address = {Basel}, doi = {10.3390/polym13193219}, url = {http://nbn-resolving.de/urn:nbn:de:gbv:wim2-20220110-45518}, pages = {1 -- 21}, abstract = {Polylactic acid (PLA) is a highly applicable material that is used in 3D printers due to some significant features such as its deformation property and affordable cost. For improvement of the end-use quality, it is of significant importance to enhance the quality of fused filament fabrication (FFF)-printed objects in PLA. The purpose of this investigation was to boost toughness and to reduce the production cost of the FFF-printed tensile test samples with the desired part thickness. To remove the need for numerous and idle printing samples, the response surface method (RSM) was used. Statistical analysis was performed to deal with this concern by considering extruder temperature (ET), infill percentage (IP), and layer thickness (LT) as controlled factors. The artificial intelligence method of artificial neural network (ANN) and ANN-genetic algorithm (ANN-GA) were further developed to estimate the toughness, part thickness, and production-cost-dependent variables. Results were evaluated by correlation coefficient and RMSE values. According to the modeling results, ANN-GA as a hybrid machine learning (ML) technique could enhance the accuracy of modeling by about 7.5, 11.5, and 4.5\% for toughness, part thickness, and production cost, respectively, in comparison with those for the single ANN method. On the other hand, the optimization results confirm that the optimized specimen is cost-effective and able to comparatively undergo deformation, which enables the usability of printed PLA objects.}, subject = {3D-Druck}, language = {en} } @article{LizarazuHarirchianShaiketal., author = {Lizarazu, Jorge and Harirchian, Ehsan and Shaik, Umar Arif and Shareef, Mohammed and Antoni-Zdziobek, Annie and Lahmer, Tom}, title = {Application of machine learning-based algorithms to predict the stress-strain curves of additively manufactured mild steel out of its microstructural characteristics}, series = {Results in Engineering}, volume = {2023}, journal = {Results in Engineering}, number = {Volume 20 (2023)}, publisher = {Elsevier}, address = {Amsterdam}, doi = {10.1016/j.rineng.2023.101587}, url = {http://nbn-resolving.de/urn:nbn:de:gbv:wim2-20231207-65028}, pages = {1 -- 12}, abstract = {The study presents a Machine Learning (ML)-based framework designed to forecast the stress-strain relationship of arc-direct energy deposited mild steel. Based on microstructural characteristics previously extracted using microscopy and X-ray diffraction, approximately 1000 new parameter sets are generated by applying the Latin Hypercube Sampling Method (LHSM). For each parameter set, a Representative Volume Element (RVE) is synthetically created via Voronoi Tessellation. Input raw data for ML-based algorithms comprises these parameter sets or RVE-images, while output raw data includes their corresponding stress-strain relationships calculated after a Finite Element (FE) procedure. Input data undergoes preprocessing involving standardization, feature selection, and image resizing. Similarly, the stress-strain curves, initially unsuitable for training traditional ML algorithms, are preprocessed using cubic splines and occasionally Principal Component Analysis (PCA). The later part of the study focuses on employing multiple ML algorithms, utilizing two main models. The first model predicts stress-strain curves based on microstructural parameters, while the second model does so solely from RVE images. The most accurate prediction yields a Root Mean Squared Error of around 5 MPa, approximately 1\% of the yield stress. This outcome suggests that ML models offer precise and efficient methods for characterizing dual-phase steels, establishing a framework for accurate results in material analysis.}, subject = {Maschinelles Lernen}, language = {en} } @article{LashkarAraKalantariSheikhKhozanietal., author = {Lashkar-Ara, Babak and Kalantari, Niloofar and Sheikh Khozani, Zohreh and Mosavi, Amir}, title = {Assessing Machine Learning versus a Mathematical Model to Estimate the Transverse Shear Stress Distribution in a Rectangular Channel}, series = {Mathematics}, volume = {2021}, journal = {Mathematics}, number = {Volume 9, Issue 6, Article 596}, publisher = {MDPI}, address = {Basel}, doi = {10.3390/math9060596}, url = {http://nbn-resolving.de/urn:nbn:de:gbv:wim2-20210504-44197}, pages = {15}, abstract = {One of the most important subjects of hydraulic engineering is the reliable estimation of the transverse distribution in the rectangular channel of bed and wall shear stresses. This study makes use of the Tsallis entropy, genetic programming (GP) and adaptive neuro-fuzzy inference system (ANFIS) methods to assess the shear stress distribution (SSD) in the rectangular channel. To evaluate the results of the Tsallis entropy, GP and ANFIS models, laboratory observations were used in which shear stress was measured using an optimized Preston tube. This is then used to measure the SSD in various aspect ratios in the rectangular channel. To investigate the shear stress percentage, 10 data series with a total of 112 different data for were used. The results of the sensitivity analysis show that the most influential parameter for the SSD in smooth rectangular channel is the dimensionless parameter B/H, Where the transverse coordinate is B, and the flow depth is H. With the parameters (b/B), (B/H) for the bed and (z/H), (B/H) for the wall as inputs, the modeling of the GP was better than the other one. Based on the analysis, it can be concluded that the use of GP and ANFIS algorithms is more effective in estimating shear stress in smooth rectangular channels than the Tsallis entropy-based equations.}, subject = {Maschinelles Lernen}, language = {en} }