Modeling of artificial neural networks for silicon prediction in the cast iron production process

Cardoso, Wandercleiton; Felice, Renzo Di; Santos, Bruna Nunes Dos; Schitine, Arthur Nascimento; Machado, Thiago Augusto Pires; Galdino, André Gustavo de Sousa; Dixini, Pedro Vitor Morbach

doi:10.11591/ijai.v11.i2.pp530-538

Cited by 5 publications

(4 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Nevertheless, the resolved questions are only related to some critical Classical Neural Network Architecture, which makes related research be developed more deeply. Moreover, supporting evidence from [29] highlights that the ANN with 30 neurons performs best, but it cannot be visualized using a framework in research. It is emphasized that metaheuristics effectively handle uncertainty by incorporating randomization into the search process.…”

Section: Literature Review and Problem Statementmentioning

confidence: 99%

A novel approach to the development of neural network architecture based on metaheuristic protis approach

Harumy,

Zarlis,

Lydia

et al. 2023

EEJET

View full text Add to dashboard Cite

Determining the best model for the neural network architecture and how to optimize the architecture with the metaheuristic Protis Approach is a subject of the study. A comprehensive investigation and utilization of metaheuristic methods are necessary. These methods aim to solve problems and adapt from the lifestyle of the amoeba protis. In this study, the proposed method modifies the life cycle of the amoeba, which consists of four phases: prophase, metaphase, anaphase, and telophase. These four phases are modified in the neural network architecture to optimize the appropriate number of hidden layers and produce an efficient architecture model. The results show that the protis approach optimized the neural network architecture, especially in generating hidden layers to improve the neural network model. Distinctive features of the results obtained are that the average range of degenerate neurons in the hidden layer is 0 to 35 neurons in each layer. The standard number of neurons makes it possible to solve the problem of determining the best model on the neural network architecture. The protis algorithm embedded in the protis recurrent neural network for categorical data measurements produces an average RMSE value, representing the difference between actual measurements and predictions, equal to 0.066. Consequently, the developed model surpasses the current classical neural network model in terms of performance. Regarding accuracy, the protis algorithm embedded in the neural network for categorical and time series data achieves an average precision of 0.952 and a recall of 0.950. The protis convolutional neural network achieves an accuracy of 95.9 %. Therefore, from the three tested datasets, the protis convolutional neural network exhibits the highest accuracy value

show abstract

Section: Literature Review and Problem Statementmentioning

confidence: 99%

A novel approach to the development of neural network architecture based on metaheuristic protis approach

Harumy,

Zarlis,

Lydia

et al. 2023

EEJET

View full text Add to dashboard Cite

show abstract

“…Since good DM models usually require well-structured data, the data quality must be improved via thorough data cleansing. The data values must be correct and consistent as missing data is a major problem during DM processes, especially when occurring in large amounts; however, it is not all attributes (instances) with missing values can be removed from the sample [1]- [3]. The problem of data loss is particularly apparent in decision-making processes, especially in online applications where data must be used exactly as it was generated.…”

Section: Introductionmentioning

confidence: 99%

“…− Missing data in medical datasets Thinking about how the data points were lost in the first place is the simplest technique to deal with lost data. The three processes of missing data are randomly missing, randomly missing, and unignorable [2], [3], [6], [7]. To begin, the phrase "totally missing completely at random" (MCAR) refers to the fact that the data that is missing is not logged at random.…”

Section: Introductionmentioning

confidence: 99%

A missing data imputation method based on salp swarm algorithm for diabetes disease

Hassan

Ali²,

Abdulsahib

et al. 2023

Bulletin EEI

View full text Add to dashboard Cite

Most of the medical datasets suffer from missing data, due to the expense of some tests or human faults while recording these tests. This issue affects the performance of the machine learning models because the values of some features will be missing. Therefore, there is a need for a specific type of methods for imputing these missing data. In this research, the salp swarm algorithm (SSA) is used for generating and imputing the missing values in the pain in my ass (also known Pima) Indian diabetes disease (PIDD) dataset, the proposed algorithm is called (ISSA). The obtained results showed that the classification performance of three different classifiers which are support vector machine (SVM), K-nearest neighbour (KNN), and Naïve Bayesian classifier (NBC) have been enhanced as compared to the dataset before applying the proposed method. Moreover, the results indicated that issa was performed better than the statistical imputation techniques such as deleting the samples with missing values, replacing the missing values with zeros, mean, or random values.

show abstract

“…These classes of materials have a carbon content of up to 0.30%, which means that their surface properties (tribological properties, oxidation and corrosion resistance) are worse than those of other steel grades. To improve the surface properties of steels, some processes are used, such as heat treatment processes, carburizing, nitriding, nitrocarburizing, boriding and plasma spraying [43][44][45][46][47][48] .…”

Section: Introductionmentioning

confidence: 99%

Deposition of Ti-Based Thin Films on AISI 1020 Steel Substrates Using the Cathodic Cage Plasma Deposition Technique

Silva,

Cardoso,

Gontijo

et al. 2023

Mat. Res.

View full text Add to dashboard Cite

The automotive industry is one of the largest industrial segments in the world market. The exhaust system of motor vehicles is responsible for the emission and treatment of toxic gasses released by the engine. In this sense, the application of titanium on an AISI 1020 steel substrate was carried out by plasma deposition using a cathode cage. The aim of this research was to evaluate the application of this material in the exhaust system of motor vehicles. The samples were characterized by scanning electron microscopy (SEM), confocal microscopy (CM), microhardness tests and corrosion resistance tests. The samples exhibited a thin film with higher titanium content and hardness than the uncoated sample. The corrosion potential also increased and the current density was lower than the uncoated sample. The conclusion is that the deposition of thin titanium films on AISI 1020 steel with CCPD has the potential to produce thin films.

show abstract

Modeling of artificial neural networks for silicon prediction in the cast iron production process

Cited by 5 publications

References 19 publications

A novel approach to the development of neural network architecture based on metaheuristic protis approach

A novel approach to the development of neural network architecture based on metaheuristic protis approach

A missing data imputation method based on salp swarm algorithm for diabetes disease

Deposition of Ti-Based Thin Films on AISI 1020 Steel Substrates Using the Cathodic Cage Plasma Deposition Technique

Contact Info

Product

Resources

About