Special Issue “Deep Learning and Hybrid-Metaheuristics: Novel Engineering Applications”

 

 

 

 

 

Mathematics (ISSN 2227-7390) is a peer-reviewed open access journal which provides an advanced forum for studies related to mathematics, and is published monthly online by MDPI. The European Society for Fuzzy Logic and Technology (EUSFLAT) and International Society for the Study of Information (IS4SI) are affiliated with Mathematics and their members receive a discount on article processing charges.

  • Open Access—free for readers, with article processing charges (APC) paid by authors or their institutions.
  • High Visibility: Indexed in the Science Citation Indexed Expanded – SCIE (Web of Science) from Vol. 4 (2016) and Scopus.
  • Rapid Publication: manuscripts are peer-reviewed and a first decision provided to authors approximately 16.4 days after submission; acceptance to publication is undertaken in 4.6 days (median values for papers published in this journal in the first half of 2020).
  • Recognition of Reviewers: reviewers who provide timely, thorough peer-review reports receive vouchers entitling them to a discount on the APC of their next publication in any MDPI journal, in appreciation of the work done.

 

Impact Factor: 1.747 (2019) (First decile JCR)

Special Issue “Deep Learning and Hybrid-Metaheuristics: Novel Engineering Applications”

Deadline for manuscript submissions: 30 April 2021.

Special Issue Editors

Prof. Dr. Víctor Yepes Website SciProfiles
Guest Editor
ICITECH, Universitat Politècnica de València, Valencia, Spain
Interests: multiobjective optimization; structure optimization; lifecycle assessment; social sustainability of infrastructures; reliability-based maintenance optimization; optimization and decision-making under uncertainty
Special Issues and Collections in MDPI journals
Dr. José Antonio García Website
Guest Editor
Pontificia Universidad Católica de Valparaíso, Chile
Interests: optimization; deep learning; operations research; artificial intelligence applications to industrial problems

Special Issue Information

Dear Colleagues,

Hybrid metaheuristic methods have shown very good performances in different combinatorial problems. Additionally, the rise of machine learning techniques has created a space to develop metaheuristic algorithms that use these techniques in order to tackle NP-hard problems and improve the convergence of algorithms. In this Special Issue, we invite researchers to submit papers in this optimization line, applying hybrid algorithms to industrial problems, including but not limited to industrial applications, and challenging problems arising in the fields of big data, construction, sustainability, transportation, and logistics, among others.

Deep learning techniques have also been important tools in extracting features, classifying situations, predicting events, and assisting in decision making. Some of these tools have been applied, for example, to Industry 4.0. Among the main techniques used are feedforward networks (FNN), convolutional networks (CNN), long-term short memory (LSTM), autoencoders (AE), enerative adversarial networks, and deep Q-networks (DQNs). Contributions on practical deep learning applications and cases are invited to this Special Issue, including but not limited to applications to the industry of computational vision, natural language processing, supervised learning applied to industry, unsupervised learning applied to industry, and reinforcement learning, among others.

Prof. Dr. Víctor Yepes
Dr. José Antonio García
Guest Editors

 

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All papers will be peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Mathematics is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 1200 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI’s English editing service prior to publication or during author revisions.

Keywords

  • Construction
  • Smart cities
  • Optimization
  • Deep learning

Optimización de muros de contrafuertes mediante algoritmo híbrido de enjambre de partículas y clustering

Acaban de publicarnos un artículo en la revista Mathematics,  revista indexada en el primer cuartil del JCR. En este artículo se presenta un algoritmo híbrido de enjambre de partículas y clustering para optimizar el coste y las emisiones de CO2 de un muro de contrafuertes. El trabajo se enmarca dentro del proyecto de investigación DIMALIFE que dirijo como investigador principal en la Universitat Politècnica de València.

El diseño de los muros de contrafuertes es un problema de optimización combinatoria de interés debido a las aplicaciones prácticas relativas al ahorro de costos que implica el diseño y la optimización en la cantidad de emisiones de CO2 generadas en su construcción. Por otro lado, este problema presenta importantes retos en cuanto a complejidad computacional, pues involucra 32 variables de diseño, por lo que tenemos en el orden de 10^20 combinaciones posibles. En este artículo proponemos un algoritmo híbrido en el que se integra el método de optimización del enjambre de partículas que resuelve los problemas de optimización en espacios continuos con la técnica de clustering db-scan. Este algoritmo optimiza dos funciones objetivo: las emisiones de carbono y el costo económico de los muros de hormigón armado. Para evaluar la contribución del operador del db-scan en el proceso de optimización, se diseñó un operador aleatorio. Se comparan las mejores soluciones, los promedios y los rangos intercuartílicos de las distribuciones obtenidas. A continuación se comparó el algoritmo db-scan con una versión híbrida que utiliza k-means como método de discretización y con una implementación discreta del algoritmo de búsqueda de armonía. Los resultados indican que el operador db-scan mejora significativamente la calidad de las soluciones y que la metaheurística propuesta muestra resultados competitivos con respecto al algoritmo de búsqueda de armonía.

Abstract:

The design of reinforced earth retaining walls is a combinatorial optimization problem of interest due to practical applications regarding the cost savings involved in the design and the optimization in the amount of CO2 emissions generated in its construction. On the other hand, this problem presents important challenges in computational complexity since it involves 32 design variables; therefore we have in the order of 10^20 possible combinations. In this article, we propose a hybrid algorithm in which the particle swarm optimization method is integrated that solves optimization problems in continuous spaces with the db-scan clustering technique, with the aim of addressing the combinatorial problem of the design of reinforced earth retaining walls. This algorithm optimizes two objective functions: the carbon emissions embedded and the economic cost of reinforced concrete walls. To assess the contribution of the db-scan operator in the optimization process, a random operator was designed. The best solutions, the averages, and the interquartile ranges of the obtained distributions are compared. The db-scan algorithm was then compared with a hybrid version that uses k-means as the discretization method and with a discrete implementation of the harmony search algorithm. The results indicate that the db-scan operator significantly improves the quality of the solutions and that the proposed metaheuristic shows competitive results with respect to the harmony search algorithm.

Keywords:

CO2 emission; earth-retaining walls; optimization; db-scan; particle swarm optimization

Reference:

GARCÍA, J.; MARTÍ, J.V.; YEPES, V. (2020). The buttressed  walls problem: An application of a hybrid clustering particle swarm optimization algorithm. Mathematics, 8(6):862. https://doi.org/10.3390/math8060862

Descargar (PDF, 847KB)

Algoritmo híbrido de búsqueda del cuco para optimizar muros de contrafuertes

Acaban de publicarnos un artículo en la revista Mathematics,  revista indexada en el primer cuartil del JCR. En este artículo se presenta un algoritmo híbrido de búsqueda del cuco y de clasificación no supervisada para optimizar el coste y las emisiones de CO2 de un muro de contrafuertes. El trabajo se enmarca dentro del proyecto de investigación DIMALIFE que dirijo como investigador principal en la Universitat Politècnica de València.

La Búsqueda Cuco se basa en la estrategia de reproducción de algunas especies de pájaros cucos. Éstos pájaros dejan sus huevos en los nidos de otros pájaros de otras especies para que éstas los críen, expulsando incluso los huevos del nido invadido. Si el pájaro anfitrión se percata que el huevo no es el propio, lo sacará del nido o directamente lo abandonará y construirá otro nido.

Por su parte, K-means es un algoritmo de clasificación no supervisada (clusterización) que agrupa objetos en k grupos basándose en sus características. El agrupamiento se realiza minimizando la suma de distancias entre cada objeto y el centroide de su grupo o cluster.

En este artículo se propone un algoritmo híbrido, en el que la metaheurística de búsqueda del cuco se utiliza como mecanismo de optimización en espacios continuos y la técnica de aprendizaje no supervisada k-means para discretizar las soluciones. Se diseña un operador aleatorio para determinar la contribución del operador k-means en el proceso de optimización. Se comparan los mejores valores, los promedios y los rangos intercuartiles de las distribuciones obtenidas. Los resultados muestran que el operador k-means contribuye significativamente a la calidad de las soluciones y que nuestro algoritmo es altamente competitivo.

Abstract

The counterfort retaining wall is one of the most frequent structures used in civil engineering. In this structure, optimization of cost and CO2 emissions are important. The first is relevant in the competitiveness and efficiency of the company, the second in environmental impact. From the point of view of computational complexity, the problem is challenging due to the large number of possible combinations in the solution space. In this article, a k-means cuckoo search hybrid algorithm is proposed where the cuckoo search metaheuristic is used as an optimization mechanism in continuous spaces and the unsupervised k-means learning technique to discretize the solutions. A random operator is designed to determine the contribution of the k-means operator in the optimization process. The best values, the averages, and the interquartile ranges of the obtained distributions are compared. The hybrid algorithm was later compared to a version of harmony search that also solved the problem. The results show that the k-mean operator contributes significantly to the quality of the solutions and that our algorithm is highly competitive, surpassing the results obtained by harmony search.

Keywords

CO2emission; earth-retaining walls; optimization; k-means; cuckoo search

Referencia:

GARCÍA, J.; YEPES, V.; MARTÍ, J.V. (2020). A hybrid k-means cuckoo search algorithm applied to the counterfort retaining walls problem. Mathematics,  8(4), 555. DOI:10.3390/math8040555

Descargar (PDF, 1.24MB)

 

 

Special Issue “Optimization for Decision Making II”

 

 

 

 

 

Mathematics (ISSN 2227-7390) is a peer-reviewed open access journal which provides an advanced forum for studies related to mathematics, and is published monthly online by MDPI.

  • Open Access – free for readers, with article processing charges (APC) paid by authors or their institutions.
  • High visibility: Indexed in the Science Citation Indexed Expanded – SCIE (Web of Science) from Vol. 4 (2016), Scopus, and Zentralblatt MATH from Vol. 3 (2015).
  • Rapid publication: manuscripts are peer-reviewed and a first decision provided to authors approximately 21.7 days after submission; acceptance to publication is undertaken in 5.3 days (median values for papers published in this journal in the second half of 2018).
  • Recognition of reviewers: reviewers who provide timely, thorough peer-review reports receive vouchers entitling them to a discount on the APC of their next publication in any MDPI journal, in appreciation of the work done.

Impact Factor: 1.105 (2018)  (First quartile, JCR)

Special Issue “Optimization for Decision Making II”

Deadline for manuscript submissions: 29 February 2020.

Special Issue Editors

Guest Editor 

Prof. Víctor Yepes
Universitat Politècnica de València, Spain
Website | E-Mail
Interests: multiobjective optimization; structures optimization; lifecycle assessment; social sustainability of infrastructures; reliability-based maintenance optimization; optimization and decision-making under uncertainty

Guest Editor 

Prof. José M. Moreno-Jiménez
Universidad de Zaragoza
Website | E-Mail
Interests: multicriteria decision making; environmental selection; strategic planning; knowledge management; evaluation of systems; logistics and public decision making (e-government, e-participation, e-democracy and e-cognocracy)

Special Issue Information

Dear Colleagues,

In the current context of the electronic governance of society, both administrations and citizens are demanding greater participation of all the actors involved in the decision-making process relative to the governance of society. In addition, the design, planning, and operations management rely on mathematical models, the complexity of which depends on the detail of models and complexity/characteristics of the problem they represent. Unfortunately, decision-making by humans is often suboptimal in ways that can be reliably predicted. Furthermore, the process industry seeks not only to minimize cost, but also to minimize adverse environmental and social impacts. On the other hand, in order to give an appropriate response to the new challenges raised, the decision-making process can be done by applying different methods and tools, as well as using different objectives. In real-life problems, the formulation of decision-making problems and application of optimization techniques to support decisions is particularly complex, and a wide range of optimization techniques and methodologies are used to minimize risks or improve quality in making concomitant decisions. In addition, a sensitivity analysis should be done to validate/analyze the influence of uncertainty regarding decision-making.

Prof. Víctor Yepes
Prof. José Moreno-Jiménez
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All papers will be peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Mathematics is an international peer-reviewed open access monthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 1200 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI’s English editing service prior to publication or during author revisions.

Keywords

  • Multicriteria decision making
  • Optimization techniques
  • Multiobjective optimization

 

Special Issue “Optimization for Decision Making”

 

 

 

 

 

Mathematics (ISSN 2227-7390) is a peer-reviewed open access journal which provides an advanced forum for studies related to mathematics, and is published monthly online by MDPI.

 

 

Special Issue “Optimization for Decision Making”

Deadline for manuscript submissions: 31 May 2019

Special Issue Editors

Guest Editor 

Prof. Víctor Yepes
Universitat Politècnica de València, Spain
Website | E-Mail
Interests: multiobjective optimization; structures optimization; lifecycle assessment; social sustainability of infrastructures; reliability-based maintenance optimization; optimization and decision-making under uncertainty

Guest Editor 

Prof. José M. Moreno-Jiménez
Universidad de Zaragoza
Website | E-Mail
Interests: multicriteria decision making; environmental selection; strategic planning; knowledge management; evaluation of systems; logistics and public decision making (e-government, e-participation, e-democracy and e-cognocracy)

Special Issue Information

Dear Colleagues,

In the current context of the electronic governance of society, both administrations and citizens are demanding greater participation of all the actors involved in the decision-making process relative to the governance of society. In addition, the design, planning, and operations management rely on mathematical models, the complexity of which depends on the detail of models and complexity/characteristics of the problem they represent. Unfortunately, decision-making by humans is often suboptimal in ways that can be reliably predicted. Furthermore, the process industry seeks not only to minimize cost, but also to minimize adverse environmental and social impacts. On the other hand, in order to give an appropriate response to the new challenges raised, the decision-making process can be done by applying different methods and tools, as well as using different objectives. In real-life problems, the formulation of decision-making problems and application of optimization techniques to support decisions are particularly complex and a wide range of optimization techniques and methodologies are used to minimize risks or improve quality in making concomitant decisions. In addition, a sensitivity analysis should be done to validate/analyze the influence of uncertainty regarding decision-making.

Prof. Víctor Yepes
Prof. José M. Moreno-Jiménez
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All papers will be peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Mathematics is an international peer-reviewed open access monthly journal published by MDPI. Please visit the Instructions for Authors page before submitting a manuscript.

Keywords

  • Multicriteria decision making
  • Optimization techniques
  • Multiobjective optimization