Research

Jump to: Review

12 pages, 2213 KiB

Open AccessArticle

Short Text Event Coreference Resolution Based on Context Prediction

by Xinyou Yong, Chongqing Zeng, Lican Dai, Wanli Liu and Shimin Cai

Appl. Sci. 2024, 14(2), 527; https://doi.org/10.3390/app14020527 - 07 Jan 2024

Viewed by 665

Event coreference resolution is the task of clustering event mentions that refer to the same entity or situation in text and performing operations like linking, information completion, and validation. Existing methods model this task as a text similarity problem, focusing solely on semantic [...] Read more.

Event coreference resolution is the task of clustering event mentions that refer to the same entity or situation in text and performing operations like linking, information completion, and validation. Existing methods model this task as a text similarity problem, focusing solely on semantic information, neglecting key features like event trigger words and subject. In this paper, we introduce the event coreference resolution based on context prediction (ECR-CP) as an alternative to traditional methods. ECR-CP treats the task as sentence-level relationship prediction, examining if two event descriptions can create a continuous sentence-level connection to identify coreference. We enhance ECR-CP with a fusion coding model (ECR-CP⁺) to incorporate event-specific structure and semantics. The model identifies key text information such as trigger words, argument roles, event types, and tenses via an event extraction module, integrating them into the encoding process as auxiliary features. Extensive experiments on the benchmark CCKS 2021 dataset demonstrate that ECR-CP and ECR-CP⁺ outperform existing methods in terms of precision, recall, and F1 Score, indicating their superior performance. Full article

(This article belongs to the Special Issue Advances in Natural Computing: Methods and Application)

► Show Figures

Figure 1

18 pages, 3414 KiB

Open AccessArticle

Distributed Genetic Algorithm for Community Detection in Large Graphs with a Parallel Fuzzy Cognitive Map for Focal Node Identification

by Haritha K., Judy M. V., Konstantinos Papageorgiou and Elpiniki Papageorgiou

Appl. Sci. 2023, 13(15), 8735; https://doi.org/10.3390/app13158735 - 28 Jul 2023

Cited by 1 | Viewed by 800

Abstract

This study addresses the importance of focal nodes in understanding the structural composition of networks. To identify these crucial nodes, a novel technique based on parallel Fuzzy Cognitive Maps (FCMs) is proposed. By utilising the focal nodes produced by the parallel FCMs, the [...] Read more.

This study addresses the importance of focal nodes in understanding the structural composition of networks. To identify these crucial nodes, a novel technique based on parallel Fuzzy Cognitive Maps (FCMs) is proposed. By utilising the focal nodes produced by the parallel FCMs, the algorithm efficiently creates initial clusters within the population. The community discovery process is accelerated through a distributed genetic algorithm that leverages the focal nodes obtained from the parallel FCM. This approach mitigates the randomness of the algorithm, addressing the limitations of the random population selection commonly found in genetic algorithms. The proposed algorithm improves the performance of the genetic algorithm by enabling informed decision making and forming a better initial population. This enhancement leads to improved convergence and overall algorithm performance. Furthermore, as graph sizes grow, traditional algorithms struggle to handle the increased complexity. To address this challenge, distributed algorithms are necessary for effectively managing larger data sizes and complexity. The proposed method is evaluated on diverse benchmark networks, encompassing both weighted and unweighted networks. The results demonstrate the superior scalability and performance of the proposed approach compared to the existing state-of-the-art methods. Full article

(This article belongs to the Special Issue Advances in Natural Computing: Methods and Application)

► Show Figures

Figure 1

14 pages, 3811 KiB

Open AccessArticle

Short Words for Writer Identification Using Neural Networks

by Georgia Koukiou

Appl. Sci. 2023, 13(11), 6841; https://doi.org/10.3390/app13116841 - 05 Jun 2023

Viewed by 1096

Abstract

In biometrics, it is desirable to distinguish a person using only a short sample of his handwriting. This problem is treated in the present work using only a short word with three letters. It is shown that short words can contribute to high-performance [...] Read more.

In biometrics, it is desirable to distinguish a person using only a short sample of his handwriting. This problem is treated in the present work using only a short word with three letters. It is shown that short words can contribute to high-performance writer identification if line characteristics are extracted using morphological directional transformations. Thus, directional morphological structuring elements are used as a tool for extracting this kind of information with the morphological opening operation. The line characteristics are organized based on Markov chains so that the elements of the transition matrix are used as feature vectors for identification. The Markov chains describe the alternation in the directional line features along the word. The analysis of the feature space is carried out using the Fisher linear discriminant method. The identification performance is assessed using neural networks, where the simplest neural structures are sought. The capabilities of these simple neural structures are investigated theoretically concerning the achieved separability into the feature space. The identification capabilities of the neural networks are further assessed using the leave-one-out method. It is proved that the neural methods achieve identification performance that approaches 100%. The significance of the proposed method is that it is the only one in the literature that presents high identification performance using only one short word. Furthermore, the features used as well as the classifiers are simple and robust. The method is independent of the language used regardless of the direction of writing. The NIST database is used for extracting short-length words having only three letters each. Full article

(This article belongs to the Special Issue Advances in Natural Computing: Methods and Application)

► Show Figures

Figure 1

14 pages, 3274 KiB

Open AccessArticle

Pharmacophore-Modeling-Based Optimal Placement and Sizing of Large-Scale Energy Storage Stations in a Power System including Wind Farms

by Hady H. Fayek, Fady H. Fayek and Eugen Rusu

Appl. Sci. 2023, 13(10), 6175; https://doi.org/10.3390/app13106175 - 18 May 2023

Cited by 2 | Viewed by 963

Abstract

The world is targeting fully sustainable electricity by 2050. Energy storage systems have the biggest role to play in the 100% renewable energy scenario. This paper presents an optimal method for energy storage sizing and allocation in a power system including a share [...] Read more.

The world is targeting fully sustainable electricity by 2050. Energy storage systems have the biggest role to play in the 100% renewable energy scenario. This paper presents an optimal method for energy storage sizing and allocation in a power system including a share of wind farms. The power system, which is used as a test system, is a modified version of the IEEE 39 bus system. The optimization is applied using novel pharmacophore modeling (PM), which is compared to state-of-the-art techniques. The objective of the optimization is to minimize the costs of power losses, peak demand and voltage deviation. The PM optimization is applied using two methods, namely, weighting factor and normalization. The optimization and simulation are applied in the DIgSILENT power factory software application. The results show that normalization of PM optimization drives the power system to less cost in terms of total power losses by up to 29% and voltage deviation by up to 4% and better covers peak demand than state-of-the-art optimization techniques. Full article

(This article belongs to the Special Issue Advances in Natural Computing: Methods and Application)

► Show Figures

Figure 1

23 pages, 1682 KiB

Open AccessArticle

Transfer Learning Based on Clustering Difference for Dynamic Multi-Objective Optimization

by Fangpei Yao and Gai-Ge Wang

Appl. Sci. 2023, 13(8), 4795; https://doi.org/10.3390/app13084795 - 11 Apr 2023

Cited by 2 | Viewed by 1325

Abstract

Dynamic multi-objective optimization problems (DMOPs) have become a research hotspot in engineering optimization, because their objective functions, constraints, or parameters may change over time, while quickly and accurately tracking the changing Pareto optimal set (POS) during the optimization process. Therefore, solving dynamic multi-objective [...] Read more.

Dynamic multi-objective optimization problems (DMOPs) have become a research hotspot in engineering optimization, because their objective functions, constraints, or parameters may change over time, while quickly and accurately tracking the changing Pareto optimal set (POS) during the optimization process. Therefore, solving dynamic multi-objective optimization problems presents great challenges. In recent years, transfer learning has been proved to be one of the effective means to solve dynamic multi-objective optimization problems. However, this paper proposes a new transfer learning method based on clustering difference to solve DMOPs (TCD-DMOEA). Different from the existing methods, it uses the clustering difference strategy to optimize the population quality and reduce the data difference between the target domain and the source domain. On this basis, transfer learning technology is used to accelerate the construction of initialization population. The advantage of the TCD-DMOEA method is that it reduces the possibility of negative transfer and improves the performance of the algorithm by improving the similarity between the source domain and the target domain. Experimental results show that compared with several advanced dynamic multi-objective optimization algorithms based on different benchmark problems, the proposed TCD-DMOEA method can significantly improve the quality of the solution and the convergence speed. Full article

(This article belongs to the Special Issue Advances in Natural Computing: Methods and Application)

► Show Figures

Figure 1

26 pages, 9152 KiB

Open AccessArticle

A Comparative Study in Forming Behavior of Different Grades of Steel in Cold Forging Backward Extrusion by Integrating Artificial Neural Network (ANN) with Differential Evolution (DE) Algorithm

by Praveenkumar M. Petkar, Vinayak N. Gaitonde, Vinayak N. Kulkarni, Ramesh S. Karnik and João Paulo Davim

Appl. Sci. 2023, 13(3), 1276; https://doi.org/10.3390/app13031276 - 18 Jan 2023

Cited by 2 | Viewed by 970

Abstract

The cold forging backward extrusion is employed to produce parts that are characterized by better mechanical strength. However, in this process, punches are often prone to breakages because of the large forces encountered in deforming the steel billets. The service life of the [...] Read more.

The cold forging backward extrusion is employed to produce parts that are characterized by better mechanical strength. However, in this process, punches are often prone to breakages because of the large forces encountered in deforming the steel billets. The service life of the punches is affected majorly by the geometrical attributes, the type of steel undergoing deformation, and hence the present investigation focuses on the applications of natural computing algorithms such as artificial neural network (ANN) and differential evolution (DE) optimization algorithm to study the differential influence on the forming behavior of different grades steel and enhance the punch service life. The AISI steel grades, such as AISI 1010, 1018, and 1045, employed extensively in the production of automotive components, have been compared in terms of forming behavior, such as effective stress, strain, strain rate, and punch force. The multi-layer feed-forward ANN architecture was utilized for process modeling with forming responses of finite element (FE) simulations that are strategically planned through the design of experiments (DoE) approach. Considerable variations were found for the effective stress and punch force amongst the steels, while marginal deviations were observed for effective strain and strain rates. Confirmatory experiments were conducted to validate the results of optimal combinations obtained through the DE optimization technique, and the deviations were observed to be in the acceptable range. The cold forging backward extruded components have also been examined for better mechanical soundness through microstructure and micro-hardness analysis that clearly revealed the mechanical integrity and strength enhancement within the forged components. The proposed study would assist the industries engaged in the production of cold-forged steel components in determining the appropriate values of variables to minimize the forming responses and, thus, help in enhancing the life of the tooling. Full article

(This article belongs to the Special Issue Advances in Natural Computing: Methods and Application)

► Show Figures

Figure 1

21 pages, 4226 KiB

Open AccessArticle

Natural Computing-Based Designing of Hybrid UHMWPE Composites for Orthopedic Implants

by Vinoth Arulraj, Shubhabrata Datta and João Paulo Davim

Appl. Sci. 2022, 12(20), 10408; https://doi.org/10.3390/app122010408 - 15 Oct 2022

Viewed by 1137

Abstract

The current study deals with the design of ultra-high molecular weight polyethylene (UHMWPE) composites by integrating various micro and nanoparticles as reinforcements for enhanced performance of acetabular cups in hip prostheses. For the design, a data-driven design approach was implemented, exploiting natural computing [...] Read more.

The current study deals with the design of ultra-high molecular weight polyethylene (UHMWPE) composites by integrating various micro and nanoparticles as reinforcements for enhanced performance of acetabular cups in hip prostheses. For the design, a data-driven design approach was implemented, exploiting natural computing techniques such as Artificial Neural Network (ANN) and Genetic Algorithm (GA). Experimental data related to UHMWPE reinforced with carbon nanotube, graphene, carbon fiber, and hydroxyapatite were gathered from the published works of previous researchers. To study the relationship between the volume fraction and the morphology of the particles with the tribological and mechanical properties of the composites, ANN modeling and sensitivity analyses were used. Optimization of the properties was done with the developed ANN models as objective functions in order to find the optimal combinations of reinforcements, which helps to achieve enhanced tribo-mechanical properties of the composites. This natural computing approach of designing the UHMWPE composites paved a way for experimentation. Full article

(This article belongs to the Special Issue Advances in Natural Computing: Methods and Application)

► Show Figures

Figure 1

Review

Jump to: Research

25 pages, 631 KiB

Open AccessReview

A Survey on Search Strategy of Evolutionary Multi-Objective Optimization Algorithms

by Zitong Wang, Yan Pei and Jianqiang Li

Appl. Sci. 2023, 13(7), 4643; https://doi.org/10.3390/app13074643 - 06 Apr 2023

Cited by 10 | Viewed by 2891

Abstract

The multi-objective optimization problem is difficult to solve with conventional optimization methods and algorithms because there are conflicts among several optimization objectives and functions. Through the efforts of researchers and experts from different fields for the last 30 years, the research and application [...] Read more.

The multi-objective optimization problem is difficult to solve with conventional optimization methods and algorithms because there are conflicts among several optimization objectives and functions. Through the efforts of researchers and experts from different fields for the last 30 years, the research and application of multi-objective evolutionary algorithms (MOEA) have made excellent progress in solving such problems. MOEA has become one of the primary used methods and technologies in the realm of multi-objective optimization. It is also a hotspot in the evolutionary computation research community. This survey provides a comprehensive investigation of MOEA algorithms that have emerged in recent decades and summarizes and classifies the classical MOEAs by evolutionary mechanism from the viewpoint of the search strategy. This paper divides them into three categories considering the search strategy of MOEA, i.e., decomposition-based MOEA algorithms, dominant relation-based MOEA algorithms, and evaluation index-based MOEA algorithms. This paper selects the relevant representative algorithms for a detailed summary and analysis. As a prospective research direction, we propose to combine the chaotic evolution algorithm with these representative search strategies for improving the search capability of multi-objective optimization algorithms. The capability of the new multi-objective evolutionary algorithm has been discussed, which further proposes the future research direction of MOEA. It also lays a foundation for the application and development of MOEA with these prospective works in the future. Full article

(This article belongs to the Special Issue Advances in Natural Computing: Methods and Application)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Advances in Natural Computing: Methods and Application

Share This Special Issue

Special Issue Editor

Special Issue Information

Keywords

Published Papers (8 papers)

Research

Review

Planned Papers

Further Information

Guidelines

MDPI Initiatives

Follow MDPI