Performance Of Multilayer Perceptron Research Articles

Gut metagenome-derived image augmentation and deep learning improve prediction accuracy of metabolic disease classification.

In recent years, statistics and machine learning methods have been widely used to analyze the relationship between human gut microbial metagenome and metabolic diseases, which is of great significance for the functional annotation and development of microbial communities. In this study, we proposed a new and scalable framework for image enhancement and deep learning of gut metagenome, which could be used in the classification of human metabolic diseases. Each data sample in three representative human gut metagenome datasets was transformed into image and enhanced, and put into the machine learning models of logistic regression (LR), support vector machine (SVM), Bayesian network (BN) and random forest (RF), and the deep learning models of multilayer perceptron (MLP) and convolutional neural network (CNN). The accuracy performance of the overall evaluation model for disease prediction was verified by accuracy (A), accuracy (P), recall (R), F1 score (F1), area under ROC curve (AUC) and 10 fold cross-validation. The results showed that the overall performance of MLP model was better than that of CNN, LR, SVM, BN, RF and PopPhy-CNN, and the performance of MLP and CNN models was further improved after data enhancement (random rotation and adding salt-and-pepper noise). The accuracy of MLP model in disease prediction was further improved by 4%-11%, F1 by 1%-6% and AUC by 5%-10%. The above results showed that human gut metagenome image enhancement and deep learning could accurately extract microbial characteristics and effectively predict the host disease phenotype. The source code and datasets used in this study can be publicly accessed in https://github.com/HuaXWu/GM_ML_Classification.git.

Predicting the skin friction’s evolution in a forced turbulent channel flow

The present paper reports on the ability of neural networks (NN) and linear stochastic estimation (LSE) tools to predict the evolution of skin friction in a minimal turbulent channel (Reτ=165) after applying an actuation near the wall that is localized in space and time. Two different NN architectures are compared, namely multilayer perceptrons (MLP) and convolutional neural networks (CNN). The paper describes the effect that the predictive horizon and the type/size/number of wall-based sensors have on the performance of each estimator. The performance of MLPs and LSEs is very similar, and becomes independent of the sensor’s size when they are smaller than 60 wall units. For sufficiently small sensors, the CNN outperforms MLPs and LSEs, suggesting that CNNs are able incorporate some of the non-linearities of the near-wall cycle in their prediction of the skin friction evolution after the actuation. Indeed, the CNN is the only architecture able to achieve reasonable predictive capabilities using pressure sensors only. The predictive horizon has a strong effect on the predictive capacity of both NN and LSE, with a Pearson correlation coefficient that varies from 0.95 for short times (i.e., of the order of the actuation time) to less than 0.4 for times of the order of an eddy turn-over time. The analysis of the weights and filters in the LSE and NNs show that all estimators are targeting wall-signatures consistent with streaks, which is interpreted as the streak being the most causal feature in the near-wall cycle for the present forcing.

Optimized Multilayer Perceptron for Sensorimotor Functional Mapping Based on a Few Minutes of Intracranial Electroencephalogram Data.

Using 6-minute free-running intracranial-electroencephalogram (icEEG) during sleep, an optimized multilayer perceptron (MLP) neural network accurately maps the sensorimotor cortex (SM) and identifies the anterior lip of the central sulcus (CS) in intractable epilepsy patients. We calculated 6 performance metrics to evaluate the MLP's efficacy: accuracy, area under the curve (AUC), recall, precision, F1-scores, and specificity. Each layer had 4 neurons with hyperbolic TanH activation function and 4 with Gaussian distribution function. Conventional 10-fold cross-validation was used. Feature extension (ε) and weighted imbalanced data (w) improved MLP performance. ANN NEUROL 2024;96:187-193.

Mathematical Modelling of the Drying Characteristics of Indian Spinach Using Machine Learning Approach

This study employs machine learning techniques to investigate the drying characteristics of Indian spinach leaves. Drying experiments were conducted at varying air temperatures (50°C, 60°C, 70°C) and velocities (1.2m/s and 1.4m/s) while monitoring drying time, moisture content, and important parameters. Artificial neural networks and support vector machine were used to predict drying rate and final moisture content based on conditions. Higher temperatures and air velocities lead to shorter drying times and lower moisture contents, with higher air velocities enhancing moisture diffusion and reducing energy intensity. Nine drying models were fitted, with the Page and Hii, et al. models showing strong performance. The MultiLayer Perceptron (MLP) 3-8-1 configuration achieves high accuracy, and Support Vector Machine (SVM) models with the Radial Basis Function (RBF) kernel perform well in predicting moisture ratio. These findings offer insights into Indian spinach drying behavior and highlight the effectiveness of machine learning models. The obtained values aid in optimizing drying conditions, and the robust performance of MLP and SVM models holds potential for applications beyond drying, including diabetic retinopathy diagnosis.

Quantitative interpretation of geoelectric inverted data with a robust probabilistic approach

The nonuniqueness of the solution to the geophysical inverse problem can lead to misinterpretation while characterizing the subsurface. To tackle this situation, ground-truth information from excavations and wells can be used to improve, calibrate, and interpret inverted models. We refer to quantitative interpretation as the decision analysis based on probability theory, which is focused on solving a classification problem. First, we present a probabilistic approach to classify the different types of materials or “categories” observed in borehole logs using multiple data sources: inverted 2D electrical resistivity tomography and induced polarization data and the positions ( x, z) of these boreholes. Then, using the Bayes’ rule and permanence of ratios, we compute the joint conditional probabilities of each category, given all data sources in the whole inverted model domain. We validate this approach with synthetic data modeling for a complex anthropogenic-geologic scenario and using real data from an old landfill. Afterward, we assess the performance of the probabilistic approach for classification and compare it with the machine learning algorithm of multilayer perceptron (MLP). In addition, we analyze the effect that the different data sources and the number of boreholes (and their distribution) have on both approaches with the synthetic case. Our results indicate that the MLP performance is better for delineating the different categories where the lateral contrasts in the synthetic resistivity model are small. Nevertheless, the classification obtained with the probabilistic approach using real data seems to provide a more geologically realistic distribution. We conclude that the probabilistic approach is robust for classifying categories when high spatial heterogeneity is expected and when ground-truth data are limited or not sparsely distributed. Finally, this approach can be easily extended to integrate multiple geophysical methods and does not require the optimization of hyperparameters as for MLP.

Mortality prediction among ICU inpatients based on MIMIC-III database results from the conditional medical generative adversarial network

Background and aimsImproved mortality prediction among intensive care unit (ICU) inpatients is a valuable and challenging task. Limited clinical data, especially with appropriate labels, are an important element restricting accurate predictions. Generative adversarial networks (GANs) are excellent generative models and have shown great potential for data simulation. However, there have been no relevant studies using GANs to predict mortality among ICU inpatients. In this study, we aim to evaluate the predictive performance of a variant of GAN called conditional medical GAN (c-med GAN) compared with some baseline models, including simplified acute physiology score II (SAPS II), support vector machine (SVM), and multilayer perceptron (MLP). MethodsData from a publicly available intensive care database, the Medical Information Mart for Intensive Care III (MIMIC-III) database (v1.4), were included in this study. The area under the precision-recall curve (PR-AUC), area under the receiver operating characteristic curve (ROC-AUC), and F1 score were used to evaluate the predictive performance. In addition, the size of the dataset was artificially reduced, and the performance of the c-med GAN was compared in different size datasets. ResultsThe results showed that c-med GAN achieves the best PR-AUC, ROC-AUC, and F1 score compared with SAPS II, SVM, and MLP when training in the full MIMIC-III dataset. When the size of the dataset was reduced, the prediction performances of both MLP and c-med GAN were affected. However, the c-med GAN still outperformed MLP on smaller datasets and had less degradation. ConclusionThe prediction of in-hospital mortality based on the c-med GAN for ICU patients showed better performance than the baseline models. Despite some inadequacies, this model may have a promising future in clinical applications which will be explored by further research.

Modeling and prediction of CO2 partial pressure in methanol solution using artificial neural networks

CO2 capture techniques are being developed faster by developing models that predict the solubility of CO2 in various solvents. Artificial neural network (ANN) model is developed in the current study to predict the solubility of CO2 in CH3OH + H2O system. Correlations can predict CO2 solubility in liquids (in different mole fractions) for the temperatures of 258–390.0 K and pressure of 0–10 MPa, respectively. In this study, prediction data for the pressure essential to dissolve CO2 in methanol solution are reported for temperature of 258–395.0 K. Multi-layer perceptron (MLP) and radial basis functions (RBF) were applied in this study. The predictions of solubility of carbon dioxide in mixtures of water and methanol are more accurate with MLP-ANN (artificial neural network) than RBF-ANN. The proposed models and reports of experimental data on CO2 partial pressure are found to be in good agreement. It has been found that the ANN technique provides high accuracy and good prediction. As a result, the correlation coefficient R2 = 0.99 was highly accurate and the mean square error (MSE) was less than 0.1. Levenberg-Marquardt (trainlm) with the lowest MSE measured at 0.00072863 with the strongest regression coefficient (R2). The best MSE validation performance of MLP and RBF networks was 0.0066566 and 0.2166952 at 30 epochs and 50 epochs, respectively. This study showed that the MLP and RBF model explained in this study are suitable to predicting CO2 solubility in methanol solution.

Multilayer perceptron-based self-care early prediction of children with disabilities.

Early identification of children with self-care impairments is one of the key challenges professional therapists face due to the complex and time-consuming detection process using relevant self-care activities. Due to the complex nature of the problem, machine-learning methods have been widely applied in this area. In this study, a feed-forward artificial neural network (ANN)-based self-care prediction methodology, called multilayer perceptron (MLP)-progressive, has been proposed. The proposed methodology integrates unsupervised instance-based resampling and randomizing preprocessing techniques to MLP for improved early detection of self-care disabilities in children. Preprocessing of the dataset affects the MLP performance; hence, randomization and resampling of the dataset improves the performance of the MLP model. To confirm the usefulness of MLP-progressive, three experiments were conducted, including validating MLP-progressive methodology over multi-class and binary-class datasets, impact analysis of the proposed preprocessing filters on the model performance, and comparing the MLP-progressive results with state-of-the-art studies. The evaluation metrics accuracy, precision, recall, F-measure, TP rate, FP rate, and ROC were used to measure performance of the proposed disability detection model. The proposed MLP-progressive model outperforms existing methods and attains a classification accuracy of 97.14% and 98.57% on multi-class and binary-class datasets, respectively. Additionally, when evaluated on the multi-class dataset, significant improvements in accuracies ranging from 90.00% to 97.14% were observed when compared to state-of-the-art methods.

Automatic Speech Emotion Recognition of Younger School Age Children

This paper introduces the extended description of a database that contains emotional speech in the Russian language of younger school age (8–12-year-old) children and describes the results of validation of the database based on classical machine learning algorithms, such as Support Vector Machine (SVM) and Multi-Layer Perceptron (MLP). The validation is performed using standard procedures and scenarios of the validation similar to other well-known databases of children’s emotional acting speech. Performance evaluation of automatic multiclass recognition on four emotion classes “Neutral (Calm)—Joy—Sadness—Anger” shows the superiority of SVM performance and also MLP performance over the results of perceptual tests. Moreover, the results of automatic recognition on the test dataset which was used in the perceptual test are even better. These results prove that emotions in the database can be reliably recognized both by experts and automatically using classical machine learning algorithms such as SVM and MLP, which can be used as baselines for comparing emotion recognition systems based on more sophisticated modern machine learning methods and deep neural networks. The results also confirm that this database can be a valuable resource for researchers studying affective reactions in speech communication during child-computer interactions in the Russian language and can be used to develop various edutainment, health care, etc. applications.

Cluster Membership of Galaxies Using Multi-Layer Perceptron Neural Network

In this study, we report systematic investigations of the membership of galaxies inside a cluster using a machine learning (ML) neural network. By directly assigning the membership, rather than estimating the galaxy redshift as an intermediate step, we optimize the network structure to determine the membership classification. The cluster membership is determined by the Multi-Layer Perceptron (MLP) neural network trained using various observed photometric and morphological parameters of galaxies measured from I and V band images taken with the Subaru Suprime-Cam of 16 clusters at redshift ∼0.15–0.3. This dataset enables MLP to be applied to cluster galaxies in a wide range of cluster-centric distances, well into a field, and a wide range of galaxy magnitudes, into a regime of dwarf galaxies. We find: (1) With only two bands, our MLP model can achieve relatively high overall performance, obtaining high scores simultaneously in both the purity and the completeness of the classification; (2) The performance of MLP can be improved by including non-SED (Spectral Energy Distribution) parameters; (3) Faint galaxies are harder to assign their memberships even using our MLP model, though the performance is more robust than other photometric methods. ML can effectively combine various conventional methods of finding cluster membership, making it inherit advantages of each method. The overall good performance of the ML membership is vital to cluster studies in the era of faint and data-intensive galaxy survey in which the complete spectroscopic observation is out of reach.

Mercury prediction in groundwater of Naameh Landfill using an Artificial Neural Network (ANN) model

Mercury is a highly poisonous metal which is mostly found in environment. It is considered at the top of the parameters of water quality that requires investigations for planning and management. To understand the status of mercury in the groundwater of Naameh Landfill, Artificial Neural Network (ANN) models were used as indicators of water quality and for the prediction of Mercury. Two types of feed forward networks have been used including multilayer perceptron (MLP) and radial basis function (RBF). A number of different MLP neural networks algorithms and RBF networks trained and developed with reference to pH, EC, TDS, TON, calcium and magnesium to predict Mercury concentration in groundwater. Six scenarios were used to train MLP and RBF networks for choosing the best-fit model for predicting water quality parameters in groundwater of Naameh Landfill. The performances of MLP and RBF models were evaluated by utilizing the coefficient of determination (R2). The results showed that the computed values of R2 for MLP and RBF were 0.791 and 0.881respectively. In addition, the prediction results showed that both types of networks are very good for predicting Mercury concentration in the ground water of our study area. Moreover, the results showed that there are mercury residues for 2 years ahead even if there is no discharge in this place. As a matter of fact, there are no studies that encompass status of heavy metals in municipal solid waste landfills in Lebanon or neighboring countries using ANN models. Thus, this study can be described as unique as it demonstrated a 9 year groundwater data (2011-2019), presented data and projected data for two upcoming years. This is crucial especially in the continual waste crisis that Lebanon is facing and the absence of sustainable disposal practices. This data is a rigid base and a solid reference for developing adequate solutions to prevent future contamination of groundwater with its associated negative impacts on the health and wellbeing of individuals.

Automated Machine Learning: A Case Study of Genomic "Image-Based" Prediction in Maize Hybrids.

Machine learning methods such as multilayer perceptrons (MLP) and Convolutional Neural Networks (CNN) have emerged as promising methods for genomic prediction (GP). In this context, we assess the performance of MLP and CNN on regression and classification tasks in a case study with maize hybrids. The genomic information was provided to the MLP as a relationship matrix and to the CNN as “genomic images.” In the regression task, the machine learning models were compared along with GBLUP. Under the classification task, MLP and CNN were compared. In this case, the traits (plant height and grain yield) were discretized in such a way to create balanced (moderate selection intensity) and unbalanced (extreme selection intensity) datasets for further evaluations. An automatic hyperparameter search for MLP and CNN was performed, and the best models were reported. For both task types, several metrics were calculated under a validation scheme to assess the effect of the prediction method and other variables. Overall, MLP and CNN presented competitive results to GBLUP. Also, we bring new insights on automated machine learning for genomic prediction and its implications to plant breeding.

MLP-PSO Framework with Dynamic Network Tuning for Traffic Flow Forecasting

Traffic flow forecasting is the need of the hour requirement in Intelligent Transportation Systems (ITS). Various Artificial Intelligence Frameworks and Machine Learning Models are incorporated in today’s ITS to enhance forecasting. Tuning the model parameters play a vital role in designing an efficient model to improve the reliability of forecasting. Hence, the primary objective of this research is to propose a novel hybrid framework to tune the parameters of Multilayer Perceptron (MLP) using the Swarm Intelligence technique called Particle Swarm Optimization (PSO). The proposed MLP-PSO framework is designed to adjust the weights and bias parameters of MLP dynamically using PSO in order to optimize the network performance of MLP. PSO continuously monitors the gradient loss of MLP network while forecasting the traffic flow. The loss is reduced gradually using Inertia Weight (denoted as ω) which is the critical parameter of PSO. It is used to set a balance between the local and global search possibilities. The Inertia Weight has been varied in order to dynamically adjusts the network parameters of MLP. A comparison has been carried out among MLP and MLP-PSO models with variants of Inertia Weight Initializations. The results obtained justifies that, the proposed MLP-PSO framework reduces the forecasting error and improves reliability and accuracy than MLP model.

Feature-Enhanced Data Classification Using B-center Function

Linear-kernel Support Vector Machine (SVM) classification algorithm needs to constantly calculate the similarity between the data to be tested and the sample during classification. If samples in the dataset are linearly indivisible, the accuracy of the algorithm will get worse. The feature weight calculation based on category information in Multi-layer Perceptron (MLP) algorithm is not accurate enough to express the relationship between features and categories, i.e. it cannot distinguish categories precisely when the features with the same category frequency. In order to improve the performance of MLP and linear-kernel SVM algorithms in classification, an improved function: the Base function, which is based on clustering, is proposed in this paper. Before running the classification algorithm, a series of possible centers is predicted, after which the Base function is used for data clustering to increase the dimension of data, and then samples with more features are passed to classification models. In the high-position Gaussian data space, the Base function can obviously improve the spatial distribution of samples. Experimental comparison in the thesis also proved that the Base function can improve the performance of MLP or SVM in classification effectively. The proposed feature-enhanced MLP is superior to the baseline with 32.6% accuracy promotion on the Gaussian dataset.

A Study of Creatinine Level among Patients with Dyslipidemia and Type 2 Diabetes Mellitus using Multilayer Perceptron and Multiple Linear Regression.

Background and Objective:Dyslipidemia is one of the most important risk factors for coronary heart disease with diabetes mellitus. Diabetic dyslipidemia is correlated with reduced concentrations of high-density lipoprotein cholesterol, elevated concentrations of plasma triglycerides, and increased concentrations of dense small particles of low-density lipoprotein cholesterol. Furthermore, dyslipidemia is one of the factors that accelerate renal failure in patients with nephropathy that is observed to be higher in these patients. This paper aims to propose the variable selection using the multilayer perceptron (MLP) neural network methodology before performing the multiple linear regression (MLR) modeling. Dataset consists of patient with Dyslipidemia, and Type 2 Diabetes Mellitus was selected to illustrate the design-build methodology. According to clinical expert's opinion and based on their assessment, these variables were chosen, which comprises the level of creatinine, urea, total cholesterol, uric acid, sodium, and HbA1c.Materials and Methods:At the first stage, all the selected variables will be a screen for their clinical important point of view, and it was found that creatinine has a significant relationship to the level of urea reading, a total of cholesterol reading, and the level of uric acid reading. By considering the level of significance, α = 0.05, these three variables are being selected and used for the input of the MLP model. Then, the MLR is being applied according to the best variable obtained through MLP process.Results:Through the testing/out-sample mean squared error (MSE), the performance of MLP was assessed. MSE is an indication of the distance from the actual findings from our estimates. The smallest MSE of the MLP shows the best variable selection combination in the model.Conclusion:In this research paper, we also provide the R syntax for MLP better illustration. The key factors associated with creatinine were urea, total cholesterol, and uric acid in patients with dyslipidemia and type 2 diabetes mellitus.

Enhanced myoelectric control against arm position change with weighted recursive Gaussian process

In the last decade, there has been huge advancement in biomechatronic systems by the integration of pattern recognition and regression algorithms. In many myoelectric control studies, high accuracy in estimating a subject’s wrist movement was reported by measuring electromyography (EMG) signal from subjects’ forearms. However, many algorithms suffer from limited robustness against undesired disturbance in the real-world environment. In particular, arm position change is an inevitable disturbance that results in severe degradation of performance. In this study, the weighted recursive Gaussian process (WRGP) is proposed to overcome this effect. In the algorithm, the noise variance is weighted by covariate shift adaptation, which is able to handle the uncertainties. WRGP is compared with the commonly used linear regression (LR) and multilayer perceptron (MLP). LR, MLP, and WRGP are trained with the EMG dataset acquired at an arm position and tested with the different EMG dataset acquired at another arm position. Also, WRGP with uniform weights and WRGP with the weights estimated from the covariate shift adaptation are compared. The results show that WRGP with uniform weights is more robust than LR and MLP regardless of the arm position (0.16 and 0.16 higher average $$R^2$$ index, respectively). The performance of WRGP with the weights estimated from the covariate shift adaptation is significantly higher ( $$p<0.05$$ ) than the performance of LR and MLP (0.30 and 0.33 higher average $$R^2$$ index, respectively).

Optimizing the performance of MLP and SVR predictors based on logical oring and experimental ranking equation

ABSTRACT Improving conventional prediction systems is widely used to optimize the learning process, achieve higher performance, and avoid overfitting. This paper’s purpose is to propose a new predictor for solar tracking systems applications based on oring operator and ranking equation with a conventional predictor including Multi-Layer Perceptron (MLP) and Support Vector Machine Regression (SVR). The point of using oring and ranking equation is to create a new variable that stores the information of combined attributes. This process aims to increase the accuracy of predictors and increase the efficiency of intelligent solar tracking systems. The experiments used 6 different datasets for solar tracking systems. The results revealed that the proposed predictors performed better than conventional predictors. Using the proposed predictors has improved both Root Mean Square Error (RMSE) and Coefficient of Determination (R 2). The developed MLP models showed lower RMSE and higher R 2 compared to conventional MLP models. The improvement ranges for using MLP are from 1.0013 to 1.4614 degrees for RMSE, and from 1.0019 to 1.4984 times for R 2, while the improvement ranges using SVM are from 1.001 to 1.988 degrees for RMSE and from 1.000 to 2.385 times for R 2.

A multilayer perceptron-based prediction of ammonium adsorption on zeolite from landfill leachate: Batch and column studies

In this study, multilayer perceptron (MLP) artificial neural network was used to predict the adsorption rate of ammonium on zeolite. pH, inlet ammonium concentration, contact time, temperature, dosage of adsorbent, agitation speed, and particle size in the batch experiments were used as independent variables while flow rate and particle size in column mode were investigated. In MLP application, different architecture structures were tried and the architecture structures with the highest predictive performance were determined. To comparatively evaluate the predictive capabilities of MLP based prediction tool, Response Surface Methodology (RSM) was utilized. When the results were evaluated with Root Mean Square Error (RMSE) and Mean Absolute Percentage Error (MAPE) values (<1%) for almost all experiments, it was seen that MLP-based prediction tool produces better predictions than RSM. The scatter plots showed that predictions and actual values were quite compatible. Both regression and determination coefficients were interpreted by creating a regression of the predictions against the actual values and these coefficients were obtained as pretty close to 1. The outstanding performance of MLP in out-of-sample data sets without the need for additional experiment demonstrate that MLP can be effectively and reliably used in cases where experimental setups are difficult or costly.

Developing hybrid time series and artificial intelligence models for estimating air temperatures

Air temperature is a vital meteorological variable required in many applications, such as agricultural and soil sciences, meteorological and climatological studies, etc. Given the importance of this variable, this study seeks to estimate minimum (Tmin), maximum (Tmax), and mean (T) air temperatures by applying a linear autoregressive (AR) time series model and then developing a hybrid model by means of coupling the AR and a non-linear time series model, namely autoregressive conditional heteroscedasticity (ARCH). Hence, the hybrid AR-ARCH model was tested. To that end, the Tmin, Tmax, and T data from 1986 to 2015 at two weather stations located in Northwestern Iran were used for both daily and monthly time scales. The results showed that the hybrid time series model (i.e., AR-ARCH) performed better than the single AR for estimating the air temperature parameters at the study sites. Multi-layer perceptron (MLP) was then employed to estimate the air temperatures using lagged temperature data as input predictors. Next, the single AR and hybrid AR-ARCH time series models were utilized to implement the hybrid MLP-AR and MLP-AR-ARCH models. It is worth noting that developing the hybrid MLP-AR and MLP-AR-ARCH models, as well as AR-ARCH one is the novelty of this study. Three statistical metrics including root mean square error (RMSE), mean absolute error (MAE), and normalized RMSE (NRMSE) were used to investigate the performance of whole the developed models. The hybrid MLP-AR and MLP-AR-ARCH models were found to perform better than the single MLP when estimating the daily and monthly Tmin, Tmax, and T; however, the MLP-AR models outperformed the MLP-AR-ARCH ones. At the end of this study, the performance of MLP was evaluated under an external condition (i.e., estimating the temperature components at any particular site using the temperature data of an adjacent location). The results indicated that the temperature data of a nearby station can be used for estimating the temperatures of a desired station. Most accurate results during the test stage were obtained under a local assessment through the hybrid MLP-AR(1) at the Tabriz station when estimating the monthly Tmax (RMSE = 0.199 °C, MAE = 0.159 °C, NRMSE = 1.012%) and hybrid MLP-AR(12) at the Urmia station when estimating the daily Tmax (RMSE = 0.364 °C, MAE = 0.277 °C, NRMSE = 1.911%).

Detecting hate speech against politicians in Arabic community on social media

Purpose This paper aims to propose an approach for hate speech detection against politicians in Arabic community on social media (e.g. Youtube). In the literature, similar works have been presented for other languages such as English. However, to the best of the authors’ knowledge, not much work has been conducted in the Arabic language. Design/methodology/approach This approach uses both classical algorithms of classification and deep learning algorithms. For the classical algorithms, the authors use Gaussian NB (GNB), Logistic Regression (LR), Random Forest (RF), SGD Classifier (SGD) and Linear SVC (LSVC). For the deep learning classification, four different algorithms (convolutional neural network (CNN), multilayer perceptron (MLP), long- or short-term memory (LSTM) and bi-directional long- or short-term memory (Bi-LSTM) are applied. For extracting features, the authors use both Word2vec and FastText with their two implementations, namely, Skip Gram (SG) and Continuous Bag of Word (CBOW). Findings Simulation results demonstrate the best performance of LSVC, BiLSTM and MLP achieving an accuracy up to 91%, when it is associated to SG model. The results are also shown that the classification that has been done on balanced corpus are more accurate than those done on unbalanced corpus. Originality/value The principal originality of this paper is to construct a new hate speech corpus (Arabic_fr_en) which was annotated by three different annotators. This corpus contains the three languages used by Arabic people being Arabic, French and English. For Arabic, the corpus contains both script Arabic and Arabizi (i.e. Arabic words written with Latin letters). Another originality is to rely on both shallow and deep leaning classification by using different model for extraction features such as Word2vec and FastText with their two implementation SG and CBOW.