Detection of geochemical anomalies related to mineralization using the Random Forest model optimized by the Competitive Mechanism and Beetle Antennae Search

Cao, Martine; Yin, Deshun; Zhong, Yu; Liu, Yan; Lu, Laijun

doi:10.1016/j.gexplo.2023.107195

Cited by 13 publications

(6 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The RF is one of the classifiers, which is constructed considering a group of decision trees known as weak learners that are required to be trained, parallelly, that can estimate the output concerning a majority-voting system 51 . In the RF, each decision tree strongly relies on a training dataset that is influenced by residual variation, noise, and particularity as uncertainties of data 52 . Accordingly, a minor variation in the training procedure has a significant effect on the development decision tree.…”

Section: Machine Learning Methodsmentioning

confidence: 99%

Applying feature selection and machine learning techniques to estimate the biomass higher heating value

Abdollahi,

Ranjbar,

Razeghi Jahromi

2023

Sci Rep

View full text Add to dashboard Cite

The biomass higher heating value (HHV) is an important thermal property that determines the amount of recoverable energy from agriculture byproducts. Precise laboratory measurement or accurate prediction of the HHV is essential for designing biomass conversion equipment. The current study combines feature selection scenarios and machine learning tools to establish a general model for estimating biomass HHV. Multiple linear regression and Pearson’s correlation coefficients justified that volatile matter, nitrogen, and oxygen content of biomass samples have a slight effect on the HHV and it is better to ignore them during the HHV modeling. Then, the prediction performance of random forest, multilayer and cascade feedforward neural networks, group method of data handling, and least-squares support vector regressor are compared to determine the intelligent estimator with the highest accuracy toward biomass HHV prediction. The ranking test shows that the multilayer perceptron neural network better predicts the HHV of 532 biomass samples than the other intelligent models. This model presents the outstanding absolute average relative error of 2.75% and 3.12% and regression coefficients of 0.9500 and 0.9418 in the learning and testing stages. The model performance is also superior to a recurrent neural network which was recently developed in the literature using the same databank.

show abstract

Section: Machine Learning Methodsmentioning

confidence: 99%

Applying feature selection and machine learning techniques to estimate the biomass higher heating value

Abdollahi,

Ranjbar,

Razeghi Jahromi

2023

Sci Rep

View full text Add to dashboard Cite

show abstract

“…RF is an ensemble method that uses a random subset of features (from a training set) to train multiple independent decision trees (bootstrap) and predict instance by majority voting of each tree outcome or the average. The model is easy to interpret, runs efficiently on large database, is fast to train and scalable, performs well in complex datasets, and is robust to irrelevant features [53][54][55]. However, it is sensitive to overfitting, which can then be regulated using the numbers of trees.…”

Section: Random Forestmentioning

confidence: 99%

The Use of a Large Language Model for Cyberbullying Detection

Ogunleye,

Dharmaraj

2023

Analytics

View full text Add to dashboard Cite

The dominance of social media has added to the channels of bullying for perpetrators. Unfortunately, cyberbullying (CB) is the most prevalent phenomenon in today’s cyber world, and is a severe threat to the mental and physical health of citizens. This opens the need to develop a robust system to prevent bullying content from online forums, blogs, and social media platforms to manage the impact in our society. Several machine learning (ML) algorithms have been proposed for this purpose. However, their performances are not consistent due to high class imbalance and generalisation issues. In recent years, large language models (LLMs) like BERT and RoBERTa have achieved state-of-the-art (SOTA) results in several natural language processing (NLP) tasks. Unfortunately, the LLMs have not been applied extensively for CB detection. In our paper, we explored the use of these models for cyberbullying (CB) detection. We have prepared a new dataset (D2) from existing studies (Formspring and Twitter). Our experimental results for dataset D1 and D2 showed that RoBERTa outperformed other models.

show abstract

“…After that, models predicting the amount of deformation were learned using the 150 learning data. The learned models were Random Forest [23], SVM (support vector machine) [24], Decision Tree [25], kNN (K-Nearest Neighbor) [26] Linear Regression [27], ANN (artificial neural network) [28], etc. The performance evaluation indicators used were mean square error (MSE), mean square root error (RMSE), mean absolute error (MEA), and R 2 .…”

Section: Machine Learningmentioning

confidence: 99%

Optimization of Plastic Speed Meter Housing for Automobiles: Injection Molding Simulation, Taguchi Method and Machine Learning

Han

2023

Mater. Plast.

View full text Add to dashboard Cite

The plastic speed meter housing for automobiles requires accurate parts and assembly to inform the driver of their exact speed. For accurate assembly, the molded speed meter should have a minimize amount of deformation. In this study, to obtain injection molding conditions that minimize the deformation of the speed meter, the main molding conditions that cause the deformation of the speed meter were identified using the Taguchi method. By combining the confirmed molding conditions, 150 data sets were created, and machine learning was conducted using the data set. The model with the best accuracy learned through machine learning was the Linear Regression model. The results of this Linear Regression model were then validated with test data. The optimal injection molding conditions were derived by inputting 5000 molding conditions data into the learned Linear Regression model. Injection molding analysis was performed using the derived injection molding conditions, and the amount of deformation was reduced by about 6.4% compared to the case where current molding conditions were applied. The optimal molding conditions obtained by machine learning were applied to actcual molding. The amount of deformation of the mold amount of the molded speed meter housing was smaller than the amount of deformation predicted in the machine learning model.

show abstract

Detection of geochemical anomalies related to mineralization using the Random Forest model optimized by the Competitive Mechanism and Beetle Antennae Search

Cited by 13 publications

References 22 publications

Applying feature selection and machine learning techniques to estimate the biomass higher heating value

Applying feature selection and machine learning techniques to estimate the biomass higher heating value

The Use of a Large Language Model for Cyberbullying Detection

Optimization of Plastic Speed Meter Housing for Automobiles: Injection Molding Simulation, Taguchi Method and Machine Learning

Contact Info

Product

Resources

About