Powered by OpenAIRE graph
Found an issue? Give us feedback
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ Journal of Rock Mech...arrow_drop_down
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
Journal of Rock Mechanics and Geotechnical Engineering
Article . 2024 . Peer-reviewed
License: CC BY
Data sources: Crossref
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
https://dx.doi.org/10.60692/77...
Other literature type . 2024
Data sources: Datacite
https://dx.doi.org/10.60692/sh...
Other literature type . 2024
Data sources: Datacite
versions View all 4 versions
addClaim

This Research product is the result of merged Research products in OpenAIRE.

You have already added 0 works in your ORCID record related to the merged Research product.

Predicting the friction angle of clays using a multi-layer perceptron neural network enhanced by yeo-johnson transformation and coral reefs optimization

التنبؤ بزاوية احتكاك الطين باستخدام شبكة عصبية متعددة الطبقات مدركة معززة بتحول يو جونسون وتحسين الشعاب المرجانية
Authors: Yang Li-bing; T. Nguyen-Thoi; Trung Tin Tran;

Predicting the friction angle of clays using a multi-layer perceptron neural network enhanced by yeo-johnson transformation and coral reefs optimization

Abstract

La prédiction précise de l'angle de frottement des argiles est cruciale pour évaluer la stabilité des pentes dans les applications d'ingénierie. Cette étude aborde l'importance d'estimer l'angle de frottement et présente le développement de quatre modèles informatiques souples : YJ-FPA-MLPnet, YJ-CRO-MLPnet, YJ-ACOC-MLPnet et YJ-CSA-MLPnet. Tout d'abord, la technique de transformation Yeo-Johnson (YJ) a été utilisée pour stabiliser la variance des données et la rendre plus adaptée aux modèles statistiques paramétriques qui supposent une normalité et des variances égales. Cette technique devrait améliorer la précision des modèles de prédiction de l'angle de frottement. Les modèles de prédiction de l'angle de frottement ont ensuite utilisé des réseaux neuronaux perceptron multicouches (MLPnet) et des algorithmes d'optimisation métaheuristique pour améliorer davantage les performances, y compris l'algorithme de pollinisation des fleurs (FPA), l'optimisation des récifs coralliens (CRO), l'optimisation continue des colonies de fourmis (ACOC) et l'algorithme de recherche de coucous (CSA). Les modèles de prédiction sans la technique YJ, c'est-à-dire FPA-MLPnet, CRO-MLPnet, ACOC-MLPnet et CSA-MLPnet, ont ensuite été comparés à ceux avec la technique YJ, c'est-à-dire YJ-FPA-MLPnet, YJ-CRO-MLPnet, YJ-ACOC-MLPnet et YJ-CSA-MLPnet. Parmi ceux-ci, le modèle YJ-CRO-MLPnet a démontré une fiabilité supérieure, atteignant une précision allant jusqu'à 83 % dans la prédiction de l'angle de frottement de l'argile dans des scénarios d'ingénierie pratiques. Cette amélioration est significative, car elle représente une augmentation de 1,3% à environ 20% par rapport aux modèles qui n'utilisaient pas la technique de transformation YJ.

La predicción precisa del ángulo de fricción de las arcillas es crucial para evaluar la estabilidad de los taludes en aplicaciones de ingeniería. Este estudio aborda la importancia de estimar el ángulo de fricción y presenta el desarrollo de cuatro modelos de computación blanda: YJ-FPA-MLPnet, YJ-CRO-MLPnet, YJ-ACOC-MLPnet y YJ-CSA-MLPnet. En primer lugar, se utilizó la técnica de transformación de Yeo-Johnson (YJ) para estabilizar la varianza de los datos y hacerla más adecuada para modelos estadísticos paramétricos que asumen normalidad e iguales varianzas. Se espera que esta técnica mejore la precisión de los modelos de predicción del ángulo de fricción. Los modelos de predicción del ángulo de fricción utilizaron redes neuronales de perceptrón multicapa (MLPnet) y algoritmos de optimización metaheurística para mejorar aún más el rendimiento, incluido el algoritmo de polinización de flores (FPA), la optimización de arrecifes de coral (CRO), la optimización continua de colonias de hormigas (ACOC) y el algoritmo de búsqueda de cucos (CSA). Los modelos de predicción sin la técnica YJ, es decir, FPA-MLPnet, CRO-MLPnet, ACOC-MLPnet y CSA-MLPnet, se compararon con los de la técnica YJ, es decir, YJ-FPA-MLPnet, YJ-CRO-MLPnet, YJ-ACOC-MLPnet e YJ-CSA-MLPnet. Entre estos, el modelo YJ-CRO-MLPnet demostró una fiabilidad superior, logrando una precisión de hasta el 83% en la predicción del ángulo de fricción de la arcilla en escenarios prácticos de ingeniería. Esta mejora es significativa, ya que representa un aumento del 1,3% a aproximadamente el 20% en comparación con los modelos que no utilizaron la técnica de transformación YJ.

The accurate prediction of the friction angle of clays is crucial for assessing slope stability in engineering applications. This study addresses the importance of estimating the friction angle and presents the development of four soft computing models: YJ-FPA-MLPnet, YJ-CRO-MLPnet, YJ-ACOC-MLPnet, and YJ-CSA-MLPnet. First of all, the Yeo-Johnson (YJ) transformation technique was used to stabilize the variance of data and make it more suitable for parametric statistical models that assume normality and equal variances. This technique is expected to improve the accuracy of friction angle prediction models. The friction angle prediction models then utilized multi-layer perceptron neural networks (MLPnet) and metaheuristic optimization algorithms to further enhance performance, including flower pollination algorithm (FPA), coral reefs optimization (CRO), ant colony optimization continuous (ACOC), and cuckoo search algorithm (CSA). The prediction models without the YJ technique, i.e. FPA-MLPnet, CRO-MLPnet, ACOC-MLPnet, and CSA-MLPnet, were then compared to those with the YJ technique, i.e. YJ-FPA-MLPnet, YJ-CRO-MLPnet, YJ-ACOC-MLPnet, and YJ-CSA-MLPnet. Among these, the YJ-CRO-MLPnet model demonstrated superior reliability, achieving an accuracy of up to 83% in predicting the friction angle of clay in practical engineering scenarios. This improvement is significant, as it represents an increase from 1.3% to approximately 20% compared to the models that did not utilize the YJ transformation technique.

يعد التنبؤ الدقيق بزاوية احتكاك الطين أمرًا بالغ الأهمية لتقييم استقرار المنحدر في التطبيقات الهندسية. تتناول هذه الدراسة أهمية تقدير زاوية الاحتكاك وتقدم تطوير أربعة نماذج حوسبة ناعمة: YJ - FPA - MLPnet و YJ - CRO - MLPnet و YJ - ACOC - MLPnet و YJ - CSA - MLPnet. بادئ ذي بدء، تم استخدام تقنية التحويل Yeo - Johnson (YJ) لتثبيت تباين البيانات وجعلها أكثر ملاءمة للنماذج الإحصائية البارامترية التي تفترض الحالة الطبيعية والتباينات المتساوية. من المتوقع أن تحسن هذه التقنية دقة نماذج التنبؤ بزاوية الاحتكاك. ثم استخدمت نماذج التنبؤ بزاوية الاحتكاك الشبكات العصبية الإدراكية متعددة الطبقات (MLPnet) وخوارزميات التحسين metaheuristic لزيادة تعزيز الأداء، بما في ذلك خوارزمية تلقيح الزهور (FPA)، وتحسين الشعاب المرجانية (CRO)، وتحسين مستعمرة النمل المستمر (ACOC)، وخوارزمية البحث الوقواق (CSA). ثم تمت مقارنة نماذج التنبؤ بدون تقنية YJ، أي FPA - MLPnet و CRO - MLPnet و ACOC - MLPnet و CSA - MLPnet، مع تلك التي تستخدم تقنية YJ، أي YJ - FPA - MLPnet و YJ - CRO - MLPnet و YJ - ACOC - MLPnet و YJ - CSA - MLPnet. من بين هذه النماذج، أظهر نموذج YJ - CRO - MLPnet موثوقية فائقة، حيث حقق دقة تصل إلى 83 ٪ في التنبؤ بزاوية احتكاك الطين في السيناريوهات الهندسية العملية. هذا التحسن كبير، لأنه يمثل زيادة من 1.3 ٪ إلى ما يقرب من 20 ٪ مقارنة بالنماذج التي لم تستخدم تقنية تحويل YJ.

Related Organizations
Keywords

Artificial neural network, Composite material, Artificial intelligence, Tunnel Grouting Techniques, Reef, Management, Monitoring, Policy and Law, Oceanography, Biochemistry, Gene, Layer (electronics), Engineering, TA703-712, Landslide Hazards and Risk Assessment, Safety, Risk, Reliability and Quality, Biology, Civil and Structural Engineering, Perceptron, Slope stability, Natural hazards, Susceptibility Mapping, Geology, Engineering geology. Rock mechanics. Soil mechanics. Underground construction, FOS: Earth and related environmental sciences, Coral reef, Computer science, Materials science, Geotechnical engineering, Physical Sciences, Environmental Science, Soft computing models, Transformation (genetics), Clay, Factors of Safety and Reliability in Geotechnical Engineering, Friction angle, Coral

  • BIP!
    Impact byBIP!
    selected citations
    These citations are derived from selected sources.
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    7
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Top 10%
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Average
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Top 10%
Powered by OpenAIRE graph
Found an issue? Give us feedback
selected citations
These citations are derived from selected sources.
This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Citations provided by BIP!
popularity
This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
BIP!Popularity provided by BIP!
influence
This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Influence provided by BIP!
impulse
This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
BIP!Impulse provided by BIP!
7
Top 10%
Average
Top 10%
gold