检索结果-内蒙古大学图书馆

Predictive modeling of Persian walnut (Juglans regia L.) in vitro proliferation media using machine learning approaches: a comparative study of ANN, KNN and GEP models

引用

PLANT METHODS 2022年第1期18卷 48-48页

作者： Sadat-Hosseini, Mohammad Arab, Mohammad M. Soltani, Mohammad Eftekhari, Maliheh Soleimani, Amanollah Vahdati, Kourosh Univ Jiroft Fac Agr Dept Hort Jiroft Iran Univ Tehran Coll Aburaihan Dept Hort Tehran Iran Univ Tehran Coll Aburaihan Dept Irrigat & Draintage Engn Tehran Iran Ta Rbiat Modares Univ TMU Fac Agr Dept Hort Sci Tehran Iran Univ Jiroft Dept Agron & Plant Breeding Fac Agr Jiroft Iran

Background Optimizing plant tissue culture media is a complicated process, which is easily influenced by genotype, mineral nutrients, plant growth regulators (PGRs), vitamins and other factors, leading to undesirable and inefficient medium composition. Facing incidence of different physiological disorders such as callusing, shoot tip necrosis (STN) and vitrification (Vit) in walnut proliferation, it is necessary to develop prediction models for identifying the impact of different factors involving in this process. In the present study, three machine learning (ML) approaches including multi-layer perceptron neural network (MLPNN), k-nearest neighbors (KNN) and gene expression programming (GEP) were implemented and compared to multiple linear regression (MLR) to develop models for prediction of in vitro proliferation of Persian walnut (Juglans regia L.). The accuracy of developed models was evaluated using coefficient of determination (R-2), root mean square error (RMSE) and mean absolute error (MAE). With the aim of optimizing the selected prediction models, multi-objective evolutionary optimization algorithm using particle swarm optimization (PSO) technique was applied. Results Our results indicated that all three ML techniques had higher accuracy of prediction than MLR, for example, calculated R-2 of MLPNN, KNN and GEP vs. MLR was 0.695, 0.672 and 0.802 vs. 0.412 in Chandler and 0.358, 0.377 and 0.428 vs. 0.178 in Rayen, respectively. The GEP models were further selected to be optimized using PSO. The comparison of modeling procedures provides a new insight into in vitro culture medium composition prediction models. Based on the results, hybrid GEP-PSO technique displays good performance for modeling walnut tissue culture media, while MLPNN and KNN have also shown strong estimation capability. Conclusion Here, besides MLPNN and GEP, KNN also is introduced, for the first time, as a simple technique with high accuracy to be used for developing prediction models in op

关键词： Walnut in vitro propagation Artificial neural network gene expression programming k-nearest neighbors Prediction model

来源：评论

学校读者我要写书评

暂无评论

An ensemble genetic programming model for seasonal precipitation forecasting

引用

SN APPLIED SCIENCES 2020年第11期2卷 1-14页

作者： Mehr, Ali Danandeh Antalya Bilim Univ Dept Civil Engn Antalya Turkey

Seasonal precipitation forecasting is one of the most challenging tasks in stochastic hydrology. This article proposes a new ensemble model, called EGP, to a season-ahead forecast of total seasonal precipitation. The EGP integrates evolutionary genetic programming (GP) and gene expression programming (GEP) techniques with multiple linear regression to increase forecasting accuracy of standalone GP and GEP models, while it secures their explicit structure. The EGP model was trained and validated using 88 years (1930-2017) of measured precipitation data from Muratpasa Station, Antalya, Turkey. The model performance was evaluated in terms of different statistical error measures and cross-validated with two other ensemble models as well as the state-of-the-art random forest developed in this study as the benchmark. The results showed that the proposed model can increase the forecasting accuracy of the best standalone GP and GEP models up to 30%. The EGP was also found to be superior to random forest, particularly in predicting low and high seasonal precipitation amount. This model is explicit, easy to evolve, and therefore, motivating to be used in practice.

关键词： Precipitation genetic programming Seasonal forecast gene expression programming Multiple regression Random forest

来源：评论

学校读者我要写书评

暂无评论

Semi-analytical model for compressive arch action capacity of RC frame structures

引用

STRUCTURES 2020年 27卷 1231-1245页

作者： Azim, Iftikhar Yang, Jian Iqbal, Muhammad Farjad Javed, Muhammad Faisal Nazar, Sohaib Wang, Feiliang Liu, Qing-feng Shanghai Jiao Tong Univ State Key Lab Ocean Engn Shanghai 200240 Peoples R China Shanghai Jiao Tong Univ Shanghai Key Lab Digital Maintenance Bldg & Infra Sch Naval Architecture Ocean & Civil Engn Shanghai 200240 Peoples R China Univ Birmingham Sch Civil Engn Birmingham B15 2TT W Midlands England GIK Inst Engn Sci & Technol Dept Civil Engn Topi 23460 Swabi Pakistan COMSATS Univ Islamabad Dept Civil Engn Abbottabad Campus Abbottabad Pakistan

Compressive arch action (CAA) is one of the favorable resistance mechanisms at low deflections against progressive collapse of reinforced concrete (RC) frame buildings. In this study, Park & Gamble model for calculating the CAA capacity of RC frame structures is modified by incorporating a compressive stress block for high strength concrete (HSC). Meanwhile, a comprehensive database of RC specimens is collated and the modified model is applied on the database to determine the peak deflection (delta) values at CAA by using an iterative approach. The S values obtained are then modelled by using distinctive features of gene expression programming (GEP) to develop a relationship for delta as a function of height (h) and net span length of the two beams after the column removal (L). The proposed model is validated against a wide range of published results and compared with other models available in literature. The comparison shows that the proposed modified Park & Gamble model can accurately predict the CAA capacity of the specimens. Moreover, the developed model is easy-to-use and skips the oversimplified assumption proposed in the Park & Gamble model to calculate delta (i.e. delta = 0.5*depth of the specimen).

关键词： Compressive arch action Progressive collapse Reinforced concrete High strength concrete gene expression programming

来源：评论

学校读者我要写书评

暂无评论

Assessing temporal data partitioning scenarios for estimating reference evapotranspiration with machine learning techniques in arid regions

引用

JOURNAL OF HYDROLOGY 2020年 590卷 125252-125252页

作者： Kazemi, Mohammad Hossein Shiri, Jalal Marti, Pau Majnooni-Heris, Abolfazl Univ Tabriz Fac Agr Water Engn Dept Tabriz Iran Univ Tabriz Fac Civil Engn Ctr Excellence Hydroinformat Tabriz Iran Univ Illes Balears Area Engn Agroforestal Carretera Valldemossa Km 7-5 Palma De Mallorca 07022 Spain

Recently, data driven machine learning techniques has been widely applied for modeling reference evapotranspiration (ETo) values under various climatic conditions taking into account the different number of sites and available data length. A major issue with applying those models is the proper selection of training/testing data sets. Although some spatial generalization approaches have been recommended for this purpose, there are no specified recommended local (temporal) data partitioning strategies for machine learning based ETo estimation. The present study evaluates different hold-out and k-fold validation temporal data partitioning strategies when using gene expression programming (GEP) technique to estimate daily ETo in arid regions. The k-fold validation strategies considered annual, monthly and growing season period patterns as test data sets. Although commonly used partitioning of the available patterns into training and testing sets gave accurate results, statistical analysis showed that the results obtained through k-fold validation assessment were more reliable. A two-block partitioning strategy with chronologic data selection for training and testing provided the most accurate results among the hold-out procedures (mean scatter index (SI) value of 0.162). Fixing the extreme ETo values as training data set in hold-out procedures provided the less accurate results with considerable over/underestimation of the ETo values (mean SI value was 0.506). Results on the basis of hold-out approaches can be biased or only partially valid depending on selection of the test data from the time series. K-fold validation yielded the lowest over/underestimations of ETo values. Further, considering monthly patterns as minimum affordable test size produced higher error magnitudes among k-fold validation strategies, while considering the complete patterns of one growing season provided more accurate results among k-fold validation strategies.

关键词： Evapotranspiration gene expression programming Hold out K-fold validation

来源：评论

学校读者我要写书评

暂无评论

Post-fire compressive strength of recycled PET aggregate concrete reinforced with steel fibers: Optimization and prediction via RSM and GEP

引用

CONSTRUCTION AND BUILDING MATERIALS 2020年 252卷 119057-119057页

作者： Nematzadeh, Mahdi Shahmansouri, Amir Ali Fakoor, Maziar Univ Mazandaran Dept Civil Engn Babol Sar Iran

A major environmental challenge facing metropolitan areas is recycling and removing waste plastic materials including PET from the environment. On one hand, using waste materials as a substitution for a portion of natural aggregate in concrete has been an efficient solution for dealing with the environmental problems associated with these materials. On the other hand, despite the degradation of concrete properties due to the presence of waste materials, the incorporation of fibers into concrete can improve its mechanical performance. In this regard, the compressive performance of fiber-reinforced concrete containing recycled PET chips being exposed to high temperatures, was investigated in this experimental effort. A total of 108 specimens, divided into 9 mix designs, were then fabricated in order to perform the compression test. The variables under consideration were the volume percentage of PET chips replacing natural sand (0, 5, and 10%), the volume ratio of steel fibers (0, 0.5, and 1%), and the temperature (25, 200, 400, and 600 degrees C). Further, a comparison was made between the compressive strength values obtained from tests and the associated predictions of ACI 216 and EN 1994-1-2. The findings demonstrated that the presence of PET chips replacing a percentage of sand by volume and steel fibers in the concrete mix lowered the compressive strength of the specimens with and without the thermal loading. Also, the codes overestimated the compressive strength values of all thermally treated concrete specimens. Moreover, the response surface method (RSM) was utilized to optimize the design parameters so as to obtain the maximum compressive strength of concrete with PET chips and steel fibers subjected to high temperatures. Finally, a closed-form formula was developed to predict the compressive strength using the gene expression programming (GEP) approach. The optimization results demonstrated that by replacing 10% of natural sand with recycled PET chips and add

关键词： Recycled PET aggregate Steel fibers Elevated temperatures Compressive strength Multi-objective optimization Response surface method Strength prediction gene expression programming

来源：评论

学校读者我要写书评

暂无评论

Shear strength prediction of short circular reinforced-concrete columns using soft computing methods

引用

ADVANCES IN STRUCTURAL ENGINEERING 2020年第14期23卷 3048-3061页

作者： Ketabdari, Hesam Karimi, Farzad Rasouli, Mahsa Shahid Beheshti Univ Fac Civil Water & Environm Engn Tehran *** Iran Qom Univ Fac Civil Engn Qom Iran

In this article, it has been aimed to predict the shear strength of short circular reinforced-concrete columns using the meta-heuristic algorithms. Based on the studies conducted so far, the parameters dominantly affecting the shear strength include axial force, longitudinal and transverse reinforcement, column dimension ratio, concrete compressive strength and ductility. In this respect, first, 200 numerical models of the short circular reinforced-concrete column incorporating various effective parameters so that a sufficient number of outputs could be provided, are analyzed by ABAQUS software to compute their shear strengths. Then, the gene expression programming and particle swarm optimization algorithms are employed to predict the shear strengths and by means of each algorithm, a relation was proposed accordingly. Then, using the experimental data, these relations are evaluated by comparing with those specified in ACI 318 and ASCE-ACI 426. The results indicate that the percentage of relative error between the experimental data and the values obtained from ACI 318 and ASCE-ACI 426 is respectively equal to 25% and 30%, which have been reduced to 13% and 9% through the gene expression programming and particle swarm optimization algorithms implying the satisfactory performance of these two algorithms. Finally, a comparison of the gene expression programming and particle swarm optimization is investigated in terms of convergence rate, degree of accuracy, and performance mechanism.

关键词： ACI 318 ASCE-ACI 426 finite element model gene expression programming particle swarm optimization algorithm shear strength short circular reinforced-concrete columns

来源：评论

学校读者我要写书评

暂无评论

Predictive modelling of the MR of subgrade cohesive soils incorporating CPT-related parameters through a soft-computing approach

引用

ROAD MATERIALS AND PAVEMENT DESIGN 2020年第3期21卷 701-719页

作者： Sadrossadat, Ehsan Ghorbani, Behnam Zohourian, Behzad Kaboutari, Mahdi Oskooei, Parisa Rahimzadeh Islamic Azad Univ Mashhad Branch Young Researchers & Elite Club Mashhad Razavi Khorasan Iran Ferdowsi Univ Mashhad Fac Engn Civil Engn Dept Mashhad Razavi Khorasan Iran Eqbal Lahoori Inst Higher Educ Dept Civil Engn Mashhad Razavi Khorasan Iran

Performance of pavements is significantly influenced by the characteristics and behaviour, e.g. compaction and deformation, of their underlying layer as subjected to different loadings. This can be experimentally or theoretically estimated through the subgrade soil resilient modulus (M-R) parameter. The M-R found by laboratory tests does not completely describe the actual in situ conditions of subgrade soils. Additionally, almost all of the predictive models proposed in the literature relate the M-R parameter to lab-related soil indices and conditions of stresses applied in laboratory tests. This study explores the feasibility of producing a new M-R equation using key soil lab and in situ related parameters for the pavements subgrade cohesive soils through gene expression programing (GEP) approach. A database comprising several experimental data acquired by conducting cone penetration test and corresponding resilient moduli tests on various cohesive subgrade soils is employed for modelling of the pertinent M-R factor and a new empirical mode is suggested. In order to examine the proposed model from both precision and engineering perspectives, various validation and verification analyses are done. The results present that the strength of GEP approach and the proposed formula for indirect estimation of the M-R of pavements subgrade soils.

关键词： pavements subgrade layer cohesive soils indirect estimation soft computing gene expression programming

来源：评论

学校读者我要写书评

暂无评论

Dimensionally Aware Multi-Objective genetic programming for Automatic Crowd Behavior Modeling

引用

ACM TRANSACTIONS ON MODELING AND COMPUTER SIMULATION 2020年第3期30卷 1–24页

作者： Li, D. Zhong, J. South China Univ Technol B3382 Wai Huan Dong Rd Guangzhou 510006 Peoples R China Sino Singapore Int Joint Res Inst Singapore Singapore

One limitation of current data-driven automatic crowd modeling methods is that the models generated have low interpretability, which limits the practical applications of the models. In this article, we propose a new data-driven crowd modeling approach that can generate universal behavior rules with better interpretability. Higher interpretability helps people better understand and analyze the rules. Furthermore, the proposed approach considers both static and dynamic features during modeling to generate a realistic crowd, based on the assumption that humans tend to consider different features with respect to their states. In the proposed method, the automatic behavior rule generation problem is formulated as a symbolic regression problem. Then, the problem is solved by multi-objective genetic programming. On one hand, to improve the interpretability of the behavior rules found, a new mechanism is proposed to guide the algorithm to find concise and dimensionally consistent solutions. On the other hand, decisions made by considering static and dynamic features respectively are combined to improve the generated crowd realism. To validate the effectiveness of the proposed method, three real-world datasets are utilized for training and testing. The simulation results demonstrate that the proposed method is able to find universal behavior rules that are competitive to previous work in accuracy while having better interpretability.

关键词： Agent-based modeling crowd simulation decision rules evolutionary algorithm gene expression programming

来源：评论

学校读者我要写书评

暂无评论

Application of genetic expression programming and artificial neural network for prediction of CBR

引用

ROAD MATERIALS AND PAVEMENT DESIGN 2020年第5期21卷 1183-1200页

作者： Tenpe, Ashwini R. Patel, Anjan Visvesvaraya Natl Inst Technol Dept Civil Engn Nagpur Maharashtra India

TheCBR(California bearing ratio) value is an important parameter of the subgrade soil required for the design of pavements. The present study deals with the application of genetic expression programming (GEP) and artificial neural network (ANN) for the prediction ofCBR. Various soil properties, such as gravel percentage (G), sand percentage (S), fine content (FC), liquid limit (W-L), plastic limit (W-P), plasticity index (I-P), optimum water content (Wc(opt)) and maximum dry density (gamma(d)(max)), were considered as the variables input parameters in the analyses. Mathematical expressions were developed for the prediction ofCBRand their dependency over different combinations of variables was obtained byGEP. The same combinations of variables were used forANNprediction. It was observed that both theGEPandANNmethods fit well forCBRprediction and the model consisting of variablesG,S,I-P,W(C)(opt)and gamma(dmax)was found to be the best model. It was found that 80 numbers of chromosomes, 3 head length and 3 numbers of fixed genes is the optimal condition for the prediction ofCBRbyGEP. TheGandSwere found to be the most significant parameters with 28.41% and 39.62% contribution in case ofGEPand 26.83% and 23.37% in case ofANN, respectively. The variableW(P)was not used byGEPduring optimal model construction, which may imply poor dependability ofCBRover it.

关键词： gene expression programming artificial neural network California bearing ratio prediction

来源：评论

学校读者我要写书评

暂无评论

Predictive model for stress at ultimate in internally unbonded steel tendons based on genetic expression programming

引用

RESULTS IN ENGINEERING 2022年 13卷

作者： Oukaili, Nazar Peera, Iqbal Univ Baghdad Coll Engn Dept Civil Engn Baghdad Iraq

Predicting the stress increment (delta f(ps)) and in turn, the total stress (f(ps)) in internally unbonded steel tendons at ultimate flexural strength of post-tensioned concrete members is one of the major challenges due to the lack of bond between the steel tendon and surrounding concrete. This article presents the development of a new predictive model to evaluate the stress increment (delta f(ps)) and in turn, the total stress (f(ps)) based on a genetic expression programming (GEP). GEP has the ability to collect all the influential parameters, among all the cross-sectional and the member's geometrical properties, the mechanical properties of materials, and the applied load, in one single closed-form expression for predicting (delta f(ps)). The proposed model was developed based on a comprehensive experimental database of 196 concrete specimens that were collected from literature and the experimental outcomes of 22 beams and one-way post-tensioned concrete slabs which were previously prepared, fabricated, and tested by authors of the present study. A parametric study was conducted to obtain an idea of the relationship between the independent variables and their effect on the stress increment in unbonded tendons at ultimate (i.e., the target parameter (delta f(ps))). To inspect the potentiality of the proposed (GEP) model against 22 analytical models available in the literature, an extensive comparative study was carried out. The performance of the proposed model was checked according to the values of the coefficient of determination (R-2) and different achieved statistical errors. In comparison to the experimental values of (delta f(ps)) and (f(ps)), the proposed model showed the highest coefficient of determination (R-2) of 0.78 and 0.93, respectively, compared to the other 22 analytical models. While the values of mean absolute error, relative absolute error, root mean square error, and root-relative square error to determine (delta f(ps)) and (f(ps)) were found

关键词： Soft computer approaches Predictive model gene expression programming Stress increment Unbonded tendon Post-tensioning Flexural concrete member

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：