Well-known Machine Learning Algorithms Research Articles

Dust Source Susceptibility in the Lower Mesopotamian Floodplain of Iraq

The identification of susceptible dust sources (SDSs) based on the analysis of effective factors (i.e. dust drivers) is considered to be one of the primary and cost-effective solutions to deal with this phenomenon. Accordingly, this study aimed to identify SDSs and delineate their drivers using remote sensing data and machine learning (ML) algorithms in a hotspot area in the Lower Mesopotamian floodplain in southern Iraq. To model SDSs, a total of 15 environmental features based on remote sensing data such as topographic, climatic, land use/cover, and soil properties were considered as dust drivers and fed into the four well-known ML algorithms, including linear discriminant analysis (LDA), logistic model tree (LMT), extreme gradient boosting (XGB)-Linear, and XGB-Tree-based. Dust emission hotspots were identified by visual interpretation of sub-daily MODIS-Terra/Aqua true color composite imagery (2000-2021) to train (70%) and validate (30%) ML algorithms. Considering the variability of the spatial-temporal patterns of SDSs as a result of changes in dust drivers, the modeling process was carried out in four periods, including 2000-2004, 2005-2007, 2008-2012, and 2013-2021. Our results show that dust events in the study area occur most frequently in April, June, July, and August. Overall, all ML algorithms performed well and provided reliable results for identifying SDSs. However, the XGB-Linear provided the most reliable results with an average area under curve (AUC) of 0.79 for the study periods. Precipitation was determined as the most important dust driver. The SDS maps produced can be used as a basis for the development of rehabilitation plans in the study area to mitigate the adverse effects of dust storms.

Determining the Optimal Window Duration to Enhance Emotion Recognition Based on Galvanic Skin Response and Photoplethysmography Signals

Automatic emotion recognition using portable sensors is gaining attention due to its potential use in real-life scenarios. Existing studies have not explored Galvanic Skin Response and Photoplethysmography sensors exclusively for emotion recognition using nonlinear features with machine learning (ML) classifiers such as Random Forest, Support Vector Machine, Gradient Boosting Machine, K-Nearest Neighbor, and Decision Tree. In this study, we proposed a genuine window sensitivity analysis on a continuous annotation dataset to determine the window duration and percentage of overlap that optimize the classification performance using ML algorithms and nonlinear features, namely, Lyapunov Exponent, Approximate Entropy, and Poincaré indices. We found an optimum window duration of 3 s with 50% overlap and achieved accuracies of 0.75 and 0.74 for both arousal and valence, respectively. In addition, we proposed a Strong Labeling Scheme that kept only the extreme values of the labels, which raised the accuracy score to 0.94 for arousal. Under certain conditions mentioned, traditional ML models offer a good compromise between performance and low computational cost. Our results suggest that well-known ML algorithms can still contribute to the field of emotion recognition, provided that window duration, overlap percentage, and nonlinear features are carefully selected.

Evaluating Machine Learning Techniques for Web Robot Detection

A web robot, also known as a web crawler, is an automated script that systematically browses the World Wide Web in a methodical manner. Web robots are commonly used by search engines to index web pages, gather information, and update search engine databases. They follow hyperlinks from one web page to another, collecting data and information for various purposes such as indexing, data mining, and website monitoring. Web robot detection is the process of identifying and distinguishing between human users and web robots on websites, which are a major source of web traffic. This process is vital to prevent malicious web robots from having a negative effect on web servers’ traffic and their users’ privacy. Companies such as Imperva, Inc. use machine learning models to identify malicious bots and prevent them from having unauthorized access to an organization’s server. To understand the benefit that machine learning models bring to web robot detection, we used pre-published server log data to construct machine learning models on Orange (a Data Mining Software) and Python that can distinguish between malicious and benign web robots. We evaluated the performance of three well-known machine learning algorithms: kNN, neural network, and decision tree. Based on our experimental results, the neural network gains the highest precision and the lowest false-positive and false-negative percentage of web robots. However, the neural network requires more time to generate the desired output.

Prerequisites-based course recommendation: recommending learning objects using concept prerequisites and metadata matching

The recommendation is an active area of scientific research; it is also a challenging and fundamental problem in online education. However, classical recommender systems usually suffer from item cold-start issues. Besides, unlike other fields like e-commerce or entertainment, e-learning recommendations must ensure that learners have the adequate background knowledge to cognitively receive the recommended learning objects. For that reason, when designing an efficient e-learning recommendation method, these challenges should be considered. To address those issues, in this paper, we first propose extracting pairs concept prerequisites using Linked Open Data (LOD). Then, we evaluate the proposed list of prerequisite relationships using machine learning predictive models. Then, we present the recommendation approach based on matching concept’s prerequisites relation and courses metadata through a similarity score. The experimental result of prerequisite identification was evaluated using four well-known machine learning algorithms while achieving an accuracy of 90%. Moreover, using three known evaluation metrics, the final prerequisite-based recommendation demonstrates very good results (NDCG@10 = 86%). This solution will enhance recommendations on online learning platforms. Additionally, it will overcome the cold-start issue and accomplish the needed prerequisites and background knowledge for learners to attain their learning objectives.

An Overview on the Advancements of Support Vector Machine Models in Healthcare Applications: A Review

Support vector machines (SVMs) are well-known machine learning algorithms for classification and regression applications. In the healthcare domain, they have been used for a variety of tasks including diagnosis, prognosis, and prediction of disease outcomes. This review is an extensive survey on the current state-of-the-art of SVMs developed and applied in the medical field over the years. Many variants of SVM-based approaches have been developed to enhance their generalisation capabilities. We illustrate the most interesting SVM-based models that have been developed and applied in healthcare to improve performance metrics on benchmark datasets, including hybrid classification methods that combine, for instance, optimization algorithms with SVMs. We even report interesting results found in medical applications related to real-world data. Several issues around SVMs, such as selection of hyperparameters and learning from data of questionable quality, are discussed as well. The several variants developed and introduced over the years could be useful in designing new methods to improve performance in critical fields such as healthcare, where accuracy, specificity, and other metrics are crucial. Finally, current research trends and future directions are underlined.

Potential distribution of Biscogniauxia mediterranea and Obolarina persica causal agents of oak charcoal disease in Iran’s Zagros forests

In Iran, native oak species are under threat from episodes of Charcoal Disease, a decline syndrome driven by abiotic stressors (e.g. drought, elevated temperature) and biotic components, Biscogniauxia mediterranea (De Not.) Kuntze and Obolarina persica (M. Mirabolfathy). The outbreak is still ongoing and the country’s largest ever recorded. Still, the factors driving its’ epidemiology in time and space are poorly known and such knowledge is urgently needed to develop strategies to counteract the adverse effects. In this study, we developed a generic framework based on experimental, machine-learning algorithms and spatial analyses for landscape-level prediction of oak charcoal disease outbreaks. Extensive field surveys were conducted during 2013–2015 in eight provinces (more than 50 unique counties) in the Zagros ecoregion. Pathogenic fungi were isolated and characterized through morphological and molecular approaches, and their pathogenicity was assessed under controlled water stress regimes in the greenhouse. Further, we evaluated a set of 29 bioclimatic, environmental, and host layers in modeling for disease incidence data using four well-known machine learning algorithms including the Generalized Linear Model, Gradient Boosting Model, Random Forest model (RF), and Multivariate Adaptive Regression Splines implemented in MaxEnt software. Model validation statistics [Area Under the Curve (AUC), True Skill Statistics (TSS)], and Kappa index were used to evaluate the accuracy of each model. Models with a TSS above 0.65 were used to prepare an ensemble model. The results showed that among the different climate variables, precipitation and temperature (Bio18, Bio7, Bio8, and bio9) in the case of O. persica and similarly, gsl (growing season length TREELIM, highlighting the warming climate and the endophytic/pathogenic nature of the fungus) and precipitation in case of B. mediterranea are the most important influencing variables in disease modeling, while near-surface wind speed (sfcwind) is the least important variant. The RF algorithm generates the most robust predictions (ROC of 0.95; TSS of 0.77 and 0.79 for MP and OP, respectively). Theoretical analysis shows that the ensemble model (ROC of 0.95 and 0.96; TSS = 0.79 and 0.81 for MP and OP, respectively), can efficiently be used in the prediction of the charcoal disease spatiotemporal distribution. The oak mortality varied ranging from 2 to 14%. Wood-boring beetles association with diseased trees was determined at 20%. Results showed that water deficiency is a crucial component of the oak decline phenomenon in Iran. The Northern Zagros forests (Ilam, Lorestan, and Kermanshah provinces) along with the southern Zagros forests (Fars and Kohgilouyeh va-Boyer Ahmad provinces) among others are the most endangered areas of potential future pandemics of charcoal disease. Our findings will significantly improve our understanding of the current situation of the disease to pave the way against pathogenic agents in Iran.

Modelling of Diabetic Cases for Effective Prevalence Classification

INTRODUCTION: This study compares and contrasts various machine learning algorithms for predicting diabetes. The study of current research work is to analyse the effectiveness of various machine learning algorithms for diabetes prediction.
 OBJECTIVES: To compare the efficacy of various machine learning algorithms for diabetic prediction.
 METHODS: For the same, a diabetic dataset was subjected to the application of various well-known machine learning algorithms. Unbalanced data was handled by pre-processing the dataset. The models were subsequently trained and assessed using different performance metrics namely F1-score, accuracy, sensitivity, and specificity.
 RESULTS: The experimental results show that the Decision Tree and ensemble model outperforms all other comparative models in terms of accuracy and other evaluation metrics.
 CONCLUSION: This study can help healthcare practitioners and researchers to choose the best machine learning model for diabetes prediction based on their specific needs and available data.

A pretrain-finetune approach for improving model generalizability in outcome prediction of acute respiratory distress syndrome patients

BackgroundEarly prediction of acute respiratory distress syndrome (ARDS) of critically ill patients in intensive care units (ICUs) has been intensively studied in the past years. Yet a prediction model trained on data from one hospital might not be well generalized to other hospitals. It is therefore essential to develop an accurate and generalizable ARDS prediction model adaptive to different hospital or medical centers. MethodsWe analyzed electronic medical records of 200,859 and 50,920 hospitalized patients within 24 h after being diagnosed with ARDS from the Philips eICU Institute (eICU-CRD) and the Medical Information Mart for Intensive Care (MIMIC-IV) dataset, respectively. Patients were sorted into three groups, including rapid death, long stay, and recovery, based on their condition or outcome between 24 and 72 h after ARDS diagnosis. To improve prediction performance and generalizability, a “pretrain-finetune” approach was applied, where we pretrained models on the eICU-CRD dataset and performed model finetuning using only a part (35%) of the MIMIC-IV dataset, and then tested the finetuned models on the remaining data from the MIMIC-IV dataset. Well-known machine-learning algorithms, including logistic regression, random forest, extreme gradient boosting, and multilayer perceptron neural networks, were employed to predict ARDS outcomes. Prediction performance was evaluated using the area under the receiver-operating characteristic curve (AUC). ResultsResults show that, in general, multilayer perceptron neural networks outperformed the other models. The use of pretrain-finetune yielded improved performance in predicting ARDS outcomes achieving a micro-AUC of 0.870 for the MIMIC-IV dataset, an improvement of 0.046 over the pretrain model.Conclusions.The proposed pretrain-finetune approach can effectively improve model generalizability from one to another dataset in ARDS prediction.

Unveiling the Impact of Extreme Learning Machine in the Defence and Military Sector

Among the most well-known machine learning algorithms, Extreme Learning Machine (ELM) has seen widespread use across a variety of fields, including the defence and military industries. For problems like sluggish technique and iteratively altering the hidden layer’s parameters to optimise the efficiency of the gradient descent approach, a cutting-edge machine learning algorithm known as the ELM has been developed. Depending on the specific objective and circumstance, the Extreme Learning Machine (ELM) may be more appropriate than Deep Neural Network (DNN) techniques. The models constructed in this manner perform quite well in generalisation. The following three goals are emphasised in its unconventional structure: 1) A great degree of accuracy in learning 2) less need for direct human involvement 3) an extremely rapid rate of learning, and moreover, it provides an optimal response for the whole world. As a result of its quick training, flexibility, and resilience, the Extreme Learning Machine (ELM) has several uses in this field, including target detection and tracking, image and signal processing, cybersecurity and intrusion detection, decision support systems, pattern recognition and classification, etc. According to our findings, the ELM approach was used with low training time and the testing accuracy is excellent. Also, this study presents the contribution of the revolutionary machine learning algorithm ELM to the defence and military sectors.

Слабо-контролируемая групповая классификация

В работе решается задача слабо-контролируемого обучения в постановке групповой бинарной классификации. Предполагается, что каждый объект выборки может включать набор подобъектов, относящихся к разным классам. Предлагаемый метод решения основан на выборе информативного признакового пространства и фильтрации обучающей выборки. Описывается применение разработанного метода для прогнозирования степени поражения участков головного мозга у пациентов с ишемическим инсультом по снимкам компьютерной томографии. Weakly supervised learning implies possible uncertainty or fuzziness of the labelling. Current study addresses this problem using the formulation of group binary classification. It is assumed that each sample object may include a set of sub-objects belonging to one of two classes. Objects are described by a set of features; the predicted feature determines the degree to which an object belongs to the “positive” class. It is required to construct a decision function from the training sample to predict the target feature for new objects. The proposed method is based on the selection of informative feature space and filtering the training sample. Both the selection of informative features and the removal of noise observations are carried out on the basis of analysis of the local environment of objects. The degree of similarity between the object and the class is determined by the k nearest neighbours of the object, taking into account their degree of belonging to the target class. For an experimental study of the developed method, the real problem of analyzing tomography images of the brain to predict the degree of damage to its areas in stroke is solved. The results are compared with a number of known methods. A method for constructing a decision function for predicting the degree of belonging of an object to the target class has been developed. The results of an experimental study and comparison with a number of well-known machine learning algorithms (random forest, support vector machine, kNN) confirmed the efficiency of the method for solving the problem of predicting the degree of damage to brain areas in stroke patients. Unlike other similar algorithms, the proposed method allows establishing a set of the most informative features in order to improve the interpretability of the solution and reduce the effect of overfitting.

Comparative analysis of machine learning algorithms for predicting Dubai property prices

IntroductionPredicting property prices is a crucial task in the real estate market, and machine learning algorithms offer valuable tools for accurate predictions. In this study, we introduce a comprehensive comparison of eight well-known machine learning algorithms, namely, ensemble empirical mode decomposition (EEMD)–stochastic (S) + deterministic (D)–support vector machine (EEMD-SD-SVM), support vector machine (SVM), gradient boosting, random forest, K-nearest neighbors (KNN), linear regression, artificial neural networks (ANN), and decision trees. The focus is on predicting property prices in Dubai, with the primary objective of assessing the predictive performance of these algorithms within this specific market context.MethodsThe evaluation is based on four key performance metrics: R-squared (R2), mean squared error (MSE), root mean squared error (RMSE), and mean absolute percentage error (MAPE). These metrics provide insights into prediction errors, accuracy in percentage terms, and the proportion of variance in property prices explained by independent variables. The study compares the strengths and limitations of each algorithm for predicting property prices in Dubai, highlighting scenarios where certain algorithms excel based on the nature of decision boundaries, handling complex data, capturing localized patterns, and offering interpretability.ResultsFindings from the comparative analysis shed light on the performance of each algorithm in predicting property prices in Dubai. EEMD-SD-SVM and SVM excel in scenarios requiring precise decision boundaries, while gradient boosting and random forests demonstrate robust performance with complex and noisy property price data. KNN captures localized patterns effectively, linear regression is suitable for straightforward regression tasks, ANN excels with extensive datasets, and decision trees offer interpretability in understanding factors influencing property prices.DiscussionThe study emphasizes the significance of model tuning, feature selection, and data pre-processing to enhance predictive power. Additionally, practical aspects such as computational efficiency, model interpretability, and scalability in real-world applications are discussed. The comparative analysis provides valuable guidance for stakeholders, including real estate professionals, data scientists, and stakeholders interested in selecting the most suitable machine learning algorithm for predicting property prices in Dubai, with a focus on the essential evaluation metrics of MSE, RMSE, MAPE, and R2. This study offers insights into the applicability and performance of different machine learning algorithms for predicting property prices in Dubai. Stakeholders such as real estate agents, buyers, sellers, or investors can leverage these insights to make informed decisions in the Dubai real estate market.

Comparative analysis of machine learning algorithms for breast cancer prediction

Breast cancer is a global health concern, and early diagnosis is crucial for successful treatment. The objective of this paper is to conduct a comparative analysis of machine-learning algorithms for the prediction of breast cancer. This study used the Wisconsin Diagnostic Breast Cancer Dataset. Data preparation, technique selection, and performance evaluation are included in the study. The inquiry begins by comparing malignant and benign instances according to input factors and diagnostic outcomes. Finding components having an inverse relationship to the diagnosis is prioritized. Next, a careful approach is used to choose attributes to improve the dataset for model construction. The preprocessed data trains and optimizes four well-known machine learning algorithms: Random Forest, Support Vector Machine, K-Nearest Neighbor, and Logistic Regression. The models are evaluated for accuracy, precision, recall, F1-score, and ROC curve. This study aimed to evaluate numerous breast cancer prediction systems to determine their strengths and weaknesses. To provide openness and replicability, the study uses the Jupyter Notebook platform, Python, and data analytic tools. The logistic regression model has a test accuracy percentage of 99.26%, surpassing all other models examined in this study. Furthermore, it has a minimum false positive rate (FPR) of 1 and a false negative rate (FNR) of 4. The model exhibits a higher level of precision in comparison to the studies examined in the literature review. This study is crucial for early diagnosis and therapy development. The effects include lower healthcare expenses, better patient outcomes, and better diagnostics. Machine learning has shown promise in fighting breast cancer, boosting its relevance in healthcare.

Spatial prediction of winter wheat yield gap: agro-climatic model and machine learning approaches.

This study aimed to identify the most influential soil and environmental factors for predicting wheat yield (WY) in a part of irrigated croplands in southwest Iran, using the FAO-Agro-Climate method and machine learning algorithms (MLAs). A total of 60 soil samples and wheat grain (1m × 1m) in 1200ha of Pasargad plain were collected and analyzed in the laboratory. Attainable WY was assessed using the FAO method for the area. Pearson correlation analysis was used to select the best set of soil properties for modeling. Topographic attributes and vegetation indices were used as proxies of landscape components and cover crop to map actual WY in the study area. Two well-known MLAs, random forest (RF) and artificial neural networks (ANNs), were utilized to prepare an actual continuous WY map. The k-fold method was used to determine the uncertainty of WY prediction and quantify the quality of prediction accuracy. Results showed that soil organic carbon (SOC) and total nitrogen (TN) had a positive and significant correlation with WY. The SOC, TN, normalized different vegetation index (NDVI), and channel network base level (CHN) were recognized as the most important predictors and justifying more than 50% of actual WY. The ANNs outperformed the RF algorithm with an R 2 of 0.75, RMSE of 400 (kg ha-1), and RPD of 2.79, according to statistical indices. The uncertainty analysis showed that the maximum uncertainty of the prediction map [400 (kg ha-1)] was very low compared to the mean value [4937 (kg ha-1)] of WY map. Calculation yield gap using the FAO-agro-climatic model showed that the average yield gap of the region was about 50% of actual yield. The findings of this study demonstrated that integrating simulated attainable crop growth using crop model and a set of soil and environmental covariates with the ANNs algorithm can effectively predict WY gaps in large areas with acceptable and reasonable accuracy. The study emphasizes that the implementation of efficient management practices has the potential to enhance agricultural production in the study area and similar regions. These results represent a significant advancement of sustainable agriculture and provide valuable insights for ensuring global food security.

A Comparative Study of Machine Learning Approaches for the Detection of SARS-CoV-2 and its Variants

The coronavirus disease (COVID-19) caused over 170 million illnesses and over 3 million deaths worldwide. Researchers from all over the world have been using a variety of machine-learning techniques to classify the DNA sequences of the SARS-CoV-2 virus. To classify SARS-CoV-2 (Covid-19) whole genome sequences with other viruses including Dengue, Ebola, Influenza, and also Coronaviruses that may infect humans and are members of the family of Coronaviridae like SARS-CoV, MERS-CoV, we have proposed a multi-dimensional frequency encoding scheme. In the proposed method each genome is converted into four frequency-encoded sequences for each nucleotide. Then each encoded sequence is partitioned into quartiles and fed to the CNN. The findings of the binary classification of SARS-CoV-2 with other viruses and multi-class classification of six different viruses using five well-known machine learning algorithms and the proposed approach using CNN were reported in this study. Furthermore, we applied machine learning methods for the multi-class classification of eight different SARS-CoV-2 variants. The proposed approach performed well among all machine-learning techniques for classifying genome sequences of viruses and SARS-CoV-2 variants with accuracy of 99% and 98% respectively. In addition, we have also compared the performance of our proposed approach with the existing methods from the literature.

An ensemble-based machine learning solution for imbalanced multiclass dataset during lithology log generation

The lithology log, an integral component of the master log, graphically portrays the encountered lithological sequence during drilling operations. In addition to offering real-time cross-sectional insights, lithology logs greatly aid in correlating and evaluating multiple sections efficiently. This paper introduces a novel workflow reliant on an enhanced weighted average ensemble approach for producing high-resolution lithology logs. The research contends with a challenging multiclass imbalanced lithofacies distribution emerging from substantial heterogeneities within subsurface geological structures. Typically, methods to handle imbalanced data, e.g., cost-sensitive learning (CSL), are tailored for issues encountered in binary classification. Error correcting output code (ECOC) originates from decomposition strategies, effectively breaking down multiclass problems into numerous binary subproblems. The database comprises conventional well logs and lithology logs obtained from five proximate wells within a Middle Eastern oilfield. Utilizing well-known machine learning (ML) algorithms, such as support vector machine (SVM), random forest (RF), decision tree (DT), logistic regression (LR), and extreme gradient boosting (XGBoost), as baseline classifiers, this study aims to enhance the accurate prediction of underground lithofacies. Upon recognizing a blind well, the data from the remaining four wells are utilized to train the ML algorithms. After integrating ECOC and CSL techniques with the baseline classifiers, they undergo evaluation. In the initial assessment, both RF and SVM demonstrated superior performance, prompting the development of an enhanced weighted average ensemble based on them. The comprehensive numerical and visual analysis corroborates the outstanding performance of the developed ensemble. The average Kappa statistic of 84.50%, signifying almost-perfect agreement, and mean F-measures of 91.04% emphasize the robustness of the designed ensemble-based workflow during the evaluation of blind well data.

Detection of Hateful Social Media Content for Arabic Language

Social media is a common medium for expression of views, discussion, sharing of content, and promotion of products and ideas. These views are either polite or obscene. The growth of hate speech is one of the negative aspects of the medium and its emergence poses risk factors for society at various levels. Although there are rules and laws for these platforms, they cannot oversee and control all types of content. Thus, there is an urgent need to develop modern algorithms to automatically detect hateful content on social media. Arab society is not isolated from the world, and the usage of social media by its members has highlighted the importance of automated systems that help build an electronic society free of hate and aggression. This article aims to detect hate speech based on Arabic context over the Twitter platform by proposing different novel deep learning architectures in order to provide a thorough analytical study. Also, a comparative study is presented with a different well-known machine learning algorithm, as well as other state-of-the-art algorithms from the literature to be used as a beacon for interested researchers. These models have been applied to the Arabic tweets dataset, which included 15K tweets and 14 features. After training these models, the results obtained for the top two models included an improved bidirectional long short-term memory with an accuracy of 92.20% and a macro F1-score of 92% and a modified convolutional neural network with an accuracy of 92.10% and a macro F1-score of 91%. The results also showed the superiority of the performance of the deep learning models over other models in terms of accuracy.

TIPred: a novel stacked ensemble approach for the accelerated discovery of tyrosinase inhibitory peptides

BackgroundTyrosinase is an enzyme involved in melanin production in the skin. Several hyperpigmentation disorders involve the overproduction of melanin and instability of tyrosinase activity resulting in darker, discolored patches on the skin. Therefore, discovering tyrosinase inhibitory peptides (TIPs) is of great significance for basic research and clinical treatments. However, the identification of TIPs using experimental methods is generally cost-ineffective and time-consuming.ResultsHerein, a stacked ensemble learning approach, called TIPred, is proposed for the accurate and quick identification of TIPs by using sequence information. TIPred explored a comprehensive set of various baseline models derived from well-known machine learning (ML) algorithms and heterogeneous feature encoding schemes from multiple perspectives, such as chemical structure properties, physicochemical properties, and composition information. Subsequently, 130 baseline models were trained and optimized to create new probabilistic features. Finally, the feature selection approach was utilized to determine the optimal feature vector for developing TIPred. Both tenfold cross-validation and independent test methods were employed to assess the predictive capability of TIPred by using the stacking strategy. Experimental results showed that TIPred significantly outperformed the state-of-the-art method in terms of the independent test, with an accuracy of 0.923, MCC of 0.757 and an AUC of 0.977.ConclusionsThe proposed TIPred approach could be a valuable tool for rapidly discovering novel TIPs and effectively identifying potential TIP candidates for follow-up experimental validation. Moreover, an online webserver of TIPred is publicly available at http://pmlabstack.pythonanywhere.com/TIPred.

Predictive modeling on the surface tension and viscosity of ionic liquid-organic solvent mixtures via machine learning

Backgrounda comprehensive collection of reliable open-source data was compiled, encompassing 3454 data points for surface tension and 28,548 data points for viscosity of IL-organic solvent mixtures. Methodspredictive modeling was conducted for these two crucial properties using a combination of the GC method and three well-known machine learning algorithms: Artificial Neural Network (ANN), eXtreme Gradient Boosting (XGBoost), and Light Gradient Boosting Machine (LightGBM). The modeling results demonstrate that the GC models, employing all three machine learning algorithms, offer dependable predictions. Significant FindingsThe XGBoost-based model exhibits the most superior performance in surface tension predictions, achieving a square correlation coefficient (R2) of 0.9829 and a mean absolute error (MAE) of 0.0007 N/m for the randomly generated test dataset. In contrast, the ANN-based model with optimized neurons delivers the best predictive performance in viscosity, achieving an R2 of 0.9582 and an MAE of 0.0975 Pa·s. Furthermore, the Shapley Additive Explanations (SHAP) analysis is performed to evaluate the impact of each feature on the prediction of surface tension and viscosity in IL-organic solvent binary mixtures. The results reveal that the mole fraction of IL has the greatest positive effect on the prediction for both surface tension and viscosity.

Machine learning-based white-box prediction and correlation analysis of air pollutants in proximity to industrial zones

The adverse health effects caused by long-term exposure to high pollution volumes from industries near urban areas are a growing concern. Determining accurate distribution models of pollutants is crucial for establishing safe distances between sectors and urban regions and continuously monitoring pollutant levels. This study was conducted in Siraf City, situated in the Pars special energy zone in southern Iran, to improve the accuracy of simulation results and identify the correlation between emission models and pollutant concentrations. To achieve this goal, concentrations of seven pollutants (CO, CO2, NO2, SO2, O3, PM2.5, PM10) were determined seasonally at 45 points within the study area using field sampling and numerical simulation with AERMOD software. Subsequently, the obtained results were seamlessly transferred into new domains with the primary objective of feature engineering. These engineered features were then fed into an XGBoost model for regression analysis to obtain coefficients, deriving seven equations to enhance pollutant concentration simulations' accuracy significantly. The developed equations improved the simulation accuracy for CO (12.54%), CO2 (12.91%), NO2 (0.94%), SO2 (6.7%), O3 (3.05%), PM2.5 (12.47%), and PM10 (4.62%). The findings demonstrate varying improved accuracy levels depending on the pollutant and simulation accuracy with well-known machine learning algorithms. The machine learning model effectively reveals the relationship between emission models and pollutant concentrations, offering valuable insights to enhance the accuracy of air pollutant emission predictions.

Classification and prediction of deformed steel and concrete bond-slip failure modes based on SSA-ELM model

Bond-slip failure modes between reinforcement and concrete can seriously affect the load-bearing performance and safety of reinforced concrete (RC) structures. The pull-out test is widely used to analyze RC bond-slip and failure modes because of its simplicity. Therefore, a prediction model based on Sparrow Search Algorithm (SSA) Optimized Extreme Learning Machine (SSA-ELM) is proposed in this study to quickly and effectively evaluate the failure forms of RC structures. The bond-slip test samples containing 399 sets of deformed bar and concrete deformation pull-out tests were first collected as a database, and the various characteristic parameters were preprocessed. Then, the features significantly influencing the failure pattern were screened out using random forest, and the plausibility tests were performed using the Pearson correlation coefficient and mutual information. Subsequently, a classification prediction model of the pull-out failure pattern was developed based on standard machine learning (ML) algorithms. In addition, nine well-known ML algorithms (LR, K-NN, DT, SVC, BPNN, NB, RF, AdaBoost, and XGBoost) are considered. This model's accuracy and generalization ability are compared based on the Precision and Recall confusion matrix. Finally, the optimized ELM was trained by SSA using the training set data with optimized ELM weights and thresholds. The results showed that the concrete protective layer thickness ratio to reinforcement diameter had the highest sensitivity to the failure pattern of RC-drawn specimens. The accuracy of the prediction results of the SSA-ELM model was better than other ML algorithms (Accuracy = 95.8%), such as BP Neural Network. In addition, SSA has better stability and higher accuracy than Gray Wolf Optimization (GWO) Algorithm, Particle Swarm Optimization (PSO) Algorithm, Genetic Algorithm (GA), Ant Colony Optimization (ACO), and other ML classification algorithms.