Hybrid Machine Learning Model Research Articles

Mapping seagrass habitats of potential suitability using a hybrid machine learning model

Seagrass meadows provide essential ecosystem services globally in the context of climate change. However, seagrass is being degraded at an accelerated rate globally due to ocean warming, ocean acidification, aquaculture, and human activities. The need for more information on seagrasses’ spatial distribution and health status is a serious impediment to their conservation and management. Therefore, we propose a new hybrid machine learning model (RF-SWOA) that integrates the sinusoidal chaos map whale optimization algorithm (SWOA) with a random forest (RF) model to accurately model the suitable habitat of potential seagrasses. This study combines in situ sampling data with multivariate remote sensing data to train and validate hybrid machine learning models. It shows that RF-SWOA can predict potential seagrass habitat suitability more accurately and efficiently than RF. It also shows that the two most important factors affecting the potential seagrass habitat suitability on Hainan Island in China are distance to land (38.2%) and depth to sea (25.9%). This paper not only demonstrates the effectiveness of a hybrid machine learning model but also provides a more accurate machine learning model approach for predicting the potential suitability distribution of seagrasses. This research can help identify seagrass suitability distribution areas and thus develop conservation strategies to restore healthy seagrass ecosystems.

Physics-Based and Data-Driven Polymer Rheology Model

Summary Polymer flooding is a common enhanced oil recovery (EOR) method used to increase aqueous phase sweep efficiency by increasing viscosity. Estimating polymer viscosity for given reservoir conditions (i.e., oil viscosity, temperature, and brine composition) requires intensive laboratory work. There are existing empirical models to estimate polymer bulk rheology without prior laboratory work; however, they have many coefficients, simple brine composition, and lack physics-based regression boundaries. This study benchmarks the existing polymer empirical and machine learning (ML) models against a new data-driven model with some physics basis for common synthetic polymers. We cover a broad range of polymer concentrations, temperature, salinity, and hardness with an upper limit of 5,000 ppm, 120℃, 290,000 ppm, and 33,000 ppm, respectively. The data were preprocessed through data analytics techniques, and a model was developed with some physics basis by fitting Martin’s equation for Carreau model coefficients. Our regression boundaries obey flexible polymers’ physical and laboratory behavior. We benchmarked the bulk rheological model with existing models in the literature. We used the published models’ coefficients and then tuned their coefficients for our data set for a fair comparison. We then investigated ML as a predictive tool without compromising overfitting the data using the simplest ML model (linear regression) all the way to artificial neural network (ANN) and hybrid ML models. This is the first study that comprehensively benchmarks polymer rheology models and proposes a simple, least number of coefficients, and tunable polymer-rheology model. We provide a predictive bulk rheology model that enables the user to accurately predict polymer viscosity without laboratory measurements and for a wide range of temperatures and brine compositions. Moreover, our study includes the recently common polymer SAV-10 that was not previously studied. We present a simple water viscosity model for a broad brine salinity and temperature range. Our study shows that ML techniques might provide deceptively high accuracy for small data sets, unless due diligence is done to avoid a high-variance model.

Evaluation of the success of the hybrid wavelet-based ANFIS approach in the estimation of monthly stream flows of the Bitlis River, Turkey

Abstract This study aimed to predict monthly flows using an adaptive neuro-fuzzy inference system (ANFIS) and wavelet-ANFIS (W-ANFIS) and to determine the effect of wavelet transformation on the success of the machine learning model. For this purpose, the model inputs are divided into three subcomponents with Daubechies 10 mother wavelets. Subcomponents with the highest correlation were chosen as inputs. The most suitable models were selected by dividing the inputs into 3–7 sub-sets, using 11 different lagged input combinations, and testing various membership functions. In establishing the ANFIS model, 75% of the data were used for training and 25% for testing. The performance of ANFIS models was evaluated with root mean square error, Pearson correlation coefficient, determination coefficients, and Taylor diagram. A model with two sub-sets, a hybrid learning algorithm, a Gbellmf membership function, and 400 iterations was selected as the most suitable. It was concluded that the W-ANFIS model used with the wavelet transform method increased the success of the established ANFIS model. Moreover, it was suggested that the W-ANFIS hybrid machine learning model established in the study can be used effectively in similar climatic regions fed by snowmelt and dominated by a semi-arid climate.

Coupling machine learning with signal process techniques and particle swarm optimization for forecasting flood routing calculations in the Eastern Black Sea Basin, Türkiye.

With the effect of global warming, the frequency of floods, one of the most important natural disasters, increases, and this increases the damage it causes to people and the environment. Flood routing models play an important role in predicting floods so that all necessary precautions are taken before floods reach the region, loss of life and property in the region is prevented, and agricultural lands are protected. This research aims to compare the performance of hybrid machine learning models such as least-squares support vector machine technique hybridized with particle swarm optimization, empirical mode decomposition, variational mode decomposition, and discrete wavelet transform processes for flood routing estimation models in Ordu, Eastern Black Sea Basin, Türkiye. In addition, it is aimed to examine the effect of data division in flood forecasting. Accordingly, 70%, 80%, and 90% of the data were used for training, respectively. For this purpose, the flood data of 2009 and 2013 in Ordu were used. The performance of the established models was evaluated with the help of statistical indicators such as mean bias error, mean absolute percentage error, determination coefficient, Nash-Sutcliffe efficiency, Taylor Diagrams, and boxplot. As a result of the study, the particle swarm optimization least-squares support vector machine technique was chosen as the most successful model in predicting flood routing results. In addition, the optimum data partition ratio was found to be Train:70:Test:30 in the flood routing calculation. The findings are essential regarding flood management and taking necessary precautions before the flood occurs.

Spatial Prediction of Wildfire Susceptibility Using Hybrid Machine Learning Models Based on Support Vector Regression in Sydney, Australia

Australia has suffered devastating wildfires recently, and is predisposed to them due to several factors, including topography, meteorology, vegetation, and ignition sources. This study utilized a geographic information system (GIS) technique to analyze and understand the factors that regulate the spatial distribution of wildfire incidents and machine learning to predict wildfire susceptibility in Sydney. Wildfire inventory data were constructed by combining the fire perimeter through field surveys and fire occurrence data gathered from the visible infrared imaging radiometer suite (VIIRS)-Suomi thermal anomalies product between 2011 and 2020 for the Sydney area. Sixteen wildfire-related factors were acquired to assess the potential of machine learning based on support vector regression (SVR) and various metaheuristic approaches (GWO and PSO) for wildfire susceptibility mapping in Sydney. In addition, the 2019–2020 “Black Summer” fire acted as a validation dataset to assess the predictive capability of the developed model. Furthermore, the information gain ratio (IGR) method showed that driving factors such as land use, forest type, and slope degree have a large impact on wildfire susceptibility in the study area, and the frequency ratio (FR) method represented how the factors influence wildfire occurrence. Model evaluation based on area under the curve (AUC) and root average square error (RMSE) were used, and the outputs showed that the hybrid-based SVR-PSO (AUC = 0.882, RMSE = 0.006) model performed better than the standalone SVR (AUC = 0.837, RMSE = 0.097) and SVR-GWO (AUC = 0.873, RMSE = 0.080) models. Thus, optimizing SVR with metaheuristics improved the accuracy of wildfire susceptibility modeling in the study area. The proposed framework can be an alternative to the modeling approach and can be adapted for any research related to the susceptibility of different disturbances.

A hybrid intelligent model for early validation of infectious diseases: An explorative study of machine learning approaches.

Literature reports several infectious diseases news validation approaches, but none is economically effective for collecting and classifying information on different infectious diseases. This work presents a hybrid machine-learning model that could predict the validity of the infectious disease's news spread on the media. The proposed hybrid machine learning (ML) model uses the Dynamic Classifier Selection (DCS) process to validate news. Several machine learning models, such as K-Neighbors-Neighbor (KNN), AdaBoost (AB), Decision Tree (DT), Random Forest (RF), SVC, Gaussian Naïve Base (GNB), and Logistic Regression (LR) are tested in the simulation process on benchmark dataset. The simulation employs three DCS process methods: overall Local Accuracy (OLA), Meta Dynamic ensemble selection (META-DES), and Bagging. From seven ML classifiers, the AdaBoost with Bagging DCS method got a 97.45% high accuracy rate for training samples and a 97.56% high accuracy rate for testing samples. The second high accuracy was obtained at 96.12% for training and 96.45% for testing samples from AdaBoost with the Meta-DES method. Overall, the AdaBoost with Bagging model obtained higher accuracy, AUC, sensitivity, and specificity rate with minimum FPR and FNR for validation.

RETRACTED ARTICLE: AHI: a hybrid machine learning model for complex industrial information systems

RETRACTED ARTICLE: AHI: a hybrid machine learning model for complex industrial information systems

A hybrid machine learning model for predicting crater width formed by explosions of natural gas pipelines

Despite the existence of industry models for estimating the crater width formed by the explosion of natural gas pipelines, their applicability is still limited since the complex formation mechanisms. In this work, a novel hybrid model was developed to predict crater width formed by explosions of natural gas pipelines, using artificial neural networks (ANN) as the fundamental predictor. Based on the historical accident records, the proposed hybrid model was trained by the pipeline parameter, the operating condition, the installation parameter, and the crater width. A novel nature-inspired optimization algorithm, i.e., the Lévy-Weighted Quantum particle swarm optimization (LWQPSO) algorithm, was proposed to optimize the ANN model's parameters. Three machine learning models were developed for comparative reasons to predict the crater width. The use of precision and error analysis indicators assesses prediction performance. The results show that the proposed hybrid model (LWQPSO-ANN) has high prediction accuracy and stability, which outperforms QPSO-ANN-based benchmark hybrid models and the model without an optimizer (Support Vector Machine, SVM). The parameter sensitivities of the proposed algorithm, including the maximum number of iterations, population size and contraction-expansion coefficient, were determined. The proposed hybrid model is expected to support the quantitative risk assessment (QRA), Right-of-Way (ROW) definition and the inherently safer design of the underground parallel pipelines.

HM-SMF: An Efficient Strategy Optimization using a Hybrid Machine Learning Model for Stock Market Prediction

Stock market forecasting is a significant task, and investing in the stock marketplace is a significant part of monetary research due to its high risk. Therefore, accurate forecasting of stock market analysis is still a challenge. Due to stable and volatile data, stock market forecasting remains a major challenge for investors. Recent machine learning (ML) models have been able to reduce the risk of stock market forecasting. However, diversity remains a key challenge in developing better erudition models and extracts more intellectually priceless qualities to auxiliary advanced predictability. In this paper, we propose an efficient strategy optimization using a hybrid ML model for stock market prediction (HM-SMP). The first contribution of the proposed HM-SMP model is to introduce chaos-enhanced firefly bowerbird optimization (CEFBO) algorithm for optimal feature selection among multiple features which reduce the data dimensionality. Second, we develop a hybrid multi-objective capuchin with a recurrent neural network (HC-RNN) for the prediction of the stock market which enhances the prediction accuracy. We use supervised RNN to predict the closing price. Finally, to estimate the presence of the proposed HM-SMP model through the benchmark, stock market datasets and the performance can be compared with the existing state-of-the-art models in terms of accuracy, precision, recall, and F-measure.

Prediction of fracture density in a gas reservoir using robust computational approaches

One of the challenges that reservoir engineers, drilling engineers, and geoscientists face in the oil and gas industry is determining the fracture density (FVDC) of reservoir rock. This critical parameter is valuable because its presence in oil and gas reservoirs boosts productivity and is pivotal for reservoir management, operation, and ultimately energy management. This valuable parameter is determined by some expensive operations such as FMI logs and core analysis techniques. As a result, this paper attempts to predict this important parameter using petrophysics logs routinely collected at oil and gas wells and by applying four robust computational algorithms and artificial intelligence hybrids. A total of 6067 data points were collected from three gas wells (#W1, #W2, and #W3) in one gas reservoir in Southwest Asia. Following feature selection, the input variables include spectral gamma ray (SGR); sonic porosity (PHIS); potassium (POTA); photoelectric absorption factor (PEF); neutron porosity (NPHI); sonic transition time (DT); bulk density (RHOB); and corrected gamma ray (CGR). In this study, four hybrids of two networks were used, including least squares support vector machine (LSSVM) and multi-layer perceptron (MLP) with two optimizers particle swarm optimizer (PSO) and genetic algorithm (GA). Four robust hybrid machine learning models were applied, and these are LSSVM-PSO/GA and MLP-PSO/GA, which had not previously used for prediction of FVDC. In addition, the k-fold cross validation method with k equal to 8 was used in this article. When the performance accuracy of the hybrid algorithms for the FVDC prediction is compared, the revealed result is LSSVM-PSO > LSSVM-GA > MLP-PSO > MLP-GA. The study revealed that the best algorithm for predicting FVDC among the four algorithms is LSSVM-PSO (for total dataset RMSE = 0.0463 1/m; R2 = 0.9995). This algorithm has several advantages, including: 1) lower adjustment parameters, 2) high search efficiency, 3) fast convergence speed, 4) increased global search capability, and 5) preventing the local optimum from falling. When compared to other models, this model has the lowest error.

Machine Learning Assisted Hybrid Electromagnetic Modeling Framework and Its Applications to UWB MIMO Antennas

Machine learning (ML) has gained recognition as an efficient and robust technique to realize the solution of electromagnetic forward and inverse problems. This article introduces a hybrid ML framework that simultaneously acts as a forward and inverse model based on a mode input. Multivariate relevance vector regression (MVRVR) is adopted for implementing the hybrid ML model. MVRVR models for forward and inverse modeling are also presented. In addition, three hybrid ML models based on support vector regression (SVR), Gaussian process regression (GPR), and artificial neural network (ANN) are also implemented and a thorough comparative analysis between these ML models with the proposed MVRVR model is investigated to verify its accuracy. The proposed hybrid framework can be used to replace the requirements of the two separate models for solving forward and inverse problems. Two examples of ultra-wideband (UWB) MIMO antennas are employed to validate the effectiveness of the proposed modeling framework.

Average variance portfolio optimization using machine learning-based stock price prediction case of renewable energy investments

With the progress of time series prediction, several recent developments in machine learning have shown that the integration of prediction methods into portfolio selection is a great opportunity to structure investment decisions in the renewable energy industry. In this paper, we propose a novel approach to portfolio formation strategy based on a hybrid machine learning model that combines a convolutional neural network (CNN) and long-term bidirectional memory (BiLSTM) with robust input characteristics obtained from Huber’s location for stock prediction and the mean-variance (MV) Markowitz model for optimal portfolio construction. Specifically, this study first applies a prediction method for stock pre-selection to ensure high-quality stock inflows for portfolio formation. Then, the predicted results are integrated into the MV model. To comprehensively demonstrate the superiority of the proposed model, we used two portfolio models, the MV model and the equal-weighted (1/N) portfolio model, with LSTM, BiLSTM and CNN-BiLSTM, and used them as references. Between January 2016 and December 2021, historical data from the Stock Exchange of Thailand 50 Index (SET50) was collected for the study. Experience shows that integrating stock pre-selection can improve VM performance, and the results of the proposed method show that they outperform comparison models in terms of Sharpe ratio, average return and risk.

Prediction of blast-induced air overpressure using a hybrid machine learning model and gene expression programming (GEP): A case study from an iron ore mine

<abstract> <p>Mine blasting can have a destructive effect on the environment. Among these effects, air overpressure (AOp) is a major concern. Therefore, a careful assessment of the AOp intensity should be conducted before any blasting operation in order to minimize the associated environmental detriment. Several empirical models have been established to predict and control AOp. However, the current empirical methods have many limitations, including low accuracy, poor generalizability, consideration only of linear relationships among influencing parameters, and investigation of only a few influencing parameters. Thus, the current research presents a hybrid model which combines an extreme gradient boosting algorithm (XGB) with grey wolf optimization (GWO) for accurately predicting AOp. Furthermore, an empirical model and gene expression programming (GEP) were used to assess the validity of the hybrid model (XGB-GWO). An analysis of 66 blastings with their corresponding AOp values and influential parameters was conducted to achieve the goals of this research. The efficiency of AOp prediction methods was evaluated in terms of mean absolute error (MAE), coefficient of determination (R<sup>2</sup>), and root mean square error (RMSE). Based on the calculations, the XGB-GWO model has performed as well as the empirical and GEP models. Next, the most significant parameters for predicting AOp were determined using a sensitivity analysis. Based on the analysis results, stemming length and rock quality designation (RQD) were identified as two variables with the greatest influence. This study showed that the proposed XGB-GWO method was robust and applicable for predicting AOp driven by blasting operations.</p> </abstract>

ПРОГНОЗИРОВАНИЕ РЕГИОНАЛЬНОЙ ИНФЛЯЦИИ НА ОСНОВЕ ГИБРИДНОЙ МОДЕЛИ МАШИННОГО ОБУЧЕНИЯ: ГРАДИЕНТНЫЙ БУСТИНГ И СЛУЧАЙНЫЙ ЛЕС

In this paper, a hybrid machine learning model was developed for predicting regional inflation based on gradient boosting and random forest. The consumer price index was used as a method of measuring inflation, which measures the ratio of the basket value in the reporting and base periods. One of the key features and scientific novelty of the work is the use of a hybrid model that combines the predictions of two machine learning models (gradient boosting and random forest) and gives the overall result. This approach is a modern trend in the field of inflation forecasting and allows you to get a more objective forecast picture. When choosing gradient boosting and random forest as the main algorithms for building the model, the authors were guided by several reasons. Firstly, these methods are widely used to solve forecasting problems both in Russia and abroad. Secondly, they demonstrated effectiveness in previous studies of the authors, allowing them to work with a large amount of input data and build a ranked scheme based on the influence of each factor on the result. Consideration of the degree of influence of variables is important for the interpretation of the simulation result. Evaluation of the importance of variables is necessary for a more complete interpretation of the simulation results. Thirdly, the data processing process for these models is identical, which significantly reduces the time for data processing. Fourth, despite the similarity of these models as ensembles of decision trees, they differ in the learning process and how they combine the results of individual trees.

Balancing Security and Information Management in the Digital Workplace

As the digital workplace becomes more prevalent, organizations are faced with the challenge of balancing security and information management. On one hand, there is a need to protect sensitive data and prevent cyberattacks, while on the other hand, organizations must enable employees to collaborate and share information effectively. Machine learning (ML) is a promising technology that can help organizations address this challenge. By analyzing data patterns and identifying potential security threats, ML algorithms can enhance security measures and mitigate risks. At the same time, ML can also facilitate information management by automating routine tasks and improving the accuracy of data analysis. In this paper, we explore the role of ML in balancing security and information management in the digital workplace. We propose a hybrid ML model that integrates autoencoder and convolutional subnetworks in unified architecture to help capturing and security threats in the digital workplace, without compromising the information management tasks. We also present a case study of a real-world implementation of ML in a digital workplace setting, highlighting the benefits and limitations of this approach. Our findings suggest that ML can be a valuable tool for achieving a balance between security and information management in the digital workplace, but its successful implementation requires careful consideration of organizational context and stakeholder needs.

A Hybrid Approach for Android Malicious Software Classification

Android operating systems have grown in popularity and are currently being increasingly used on smartphone devices. Because of the quickly expanding quantity of Android malware and the potential safeguard of vast amounts of data kept on Android devices, the identification and categorization of Android malware is regarded as a big data challenge. Researchers started using deep learning (DL) techniques for malware detection, according to the most recent state-of-the-art studies. Nevertheless, researchers and practitioners face challenges such as the choice of DL architecture, extracting and processing features and evaluating results. In this paper, several traditional and hybrid machine learning (ML) models were developed and analyzed in detail to classify Android malware. First, some state-of-the-art DL model has been developed like multi-layer perceptron (MLP), deep neural network (DNN), recurrent neural network (RNN), long short-term memory (LSTM), convolutional neural network (CNN) and later several hybrid models have been developed by combining DNNs with support vector machine (SVM). Second, we have focused on maximizing achievement by fine-tuning a variety of configurations to guarantee the best possible combination of the hyper-parameters and attain the maximum statistical metric value. Finally, we have accomplished performance analysis between these hybrid models and a model based on VGG-16-CNN-1D along with SVM has been proposed to enhance the accuracy and efficacy of large-scale Android malware detection which outperforms all the other developed models using Drebin Dataset. Among the DL methods, DNN achieved the highest F1 score 99.07%. After doing a comparison between hybrid models, it was found that DNN-SVM achieved 99.12% while VGG16-CNN-1D-SVM achieved 98.56% precision, 98.78% recall and 99.20% F1 score, respectively.

A Hybrid Machine Learning Model for Solar Power Forecasting

The paper presents a near investigation of different AI procedures for solar power forecasting. The objective of the research is to identify the most accurate and efficient machine learning algorithms for solar power forecasting. The paper also considers different parameters such as weather conditions, solar radiation, and time of day in the forecasting model. This paper proposes a hybrid machine learning model for solar power forecasting that consolidates the strengths of multiple algorithms, including support vector regression, random forest regression, and artificial neural network. However, the study also highlights the importance of incorporating domain knowledge and feature engineering in machine learning models for better forecasting accuracy.

Hybrid Machine Learning Model for Load Prediction in Cloud Environment

Hybrid Machine Learning Model for Load Prediction in Cloud Environment

Predicting stock prices with LSTM: A hybrid machine learning model for financial forecasting

This article discusses the challenges of accurately predicting the direction of the stock market and proposes a new approach using machine learning and manual forecasting. The article explores the use of technical analysis and machine learning to predict current stock market indices’ values by training on historical data. The authors demonstrate how these methods can be used to influence investor judgments at different levels of consideration, including unrestricted, near, medium, high, and volumic. The article also explores the use of social media platforms like Twitter and the correlation between stock prices and local weather patterns to improve forecasting accuracy. The authors present their research in three phases, demonstrating the potential of machine learning and technical analysis to provide accurate and reliable predictions for investors seeking to protect themselves from market volatility.

Parameter Optimisation-Based Hybrid Reference Evapotranspiration Prediction Models: A Systematic Review of Current Implementations and Future Research Directions

A hybrid machine learning (ML) model is becoming a common trend in predicting reference evapotranspiration (ETo) research. This study aims to systematically review ML models that are integrated with meta-heuristic algorithms (i.e., parameter optimisation-based hybrid models, OBH) for predicting ETo data. Over five years, from 2018–2022, the articles published in three reliable databases, including Web of Science, ScienceDirect, and IEEE Xplore, were considered. According to the protocol search, 1485 papers were selected. After three filters were applied, the final set contained 33 papers related to the nominated topic. The final set of papers was categorised into five groups. The first group, swarm intelligence-based algorithms, had the highest proportion of papers, (23/33) and was superior to all other algorithms. The second group (evolution computation-based algorithms), third group (physics-based algorithms), fourth group (hybrid-based algorithms), and fifth group (reviews and surveys) had (4/33), (1/33), (2/33), and (3/33), respectively. However, researchers have not treated OBH models in much detail, and there is still room for improvement by investigating both newly single and hybrid meta-heuristic algorithms. Finally, this study hopes to assist researchers in understanding the options and gaps in this line of research.