Hybrid Machine Learning Approach Research Articles

Rigorous hybrid machine learning approaches for interfacial tension modeling in brine-hydrogen/cushion gas systems: Implication for hydrogen geo-storage in the presence of cushion gas

In light of the environmental consequences linked to the burning of fossil fuels, there is a mounting push to devise cleaner means of energy generation. The production of hydrogen is gaining momentum as a favored avenue for enabling the shift toward sustainable energy. Effective hydrogen storage is crucial for sustainable energy solutions, and the inclusion of cushion gas in geological storage could aid in maintaining formation pressure during hydrogen reproduction while expanding pore volumes for gas by preventing water presence in pores. Accurately controlling hydrogen behavior and interactions in porous media is crucial for successful storage, with interfacial tension between gas and water playing a significant role in the trapping and mobilizing the phases. Thus, developing a predictive tool to simulate interfacial tension measurements is essential. This study employs various intelligent modeling techniques, including Adaptive Neuro-Fuzzy Inference System, Multilayer Perceptron optimized with Bayesian Regularization, Levenberg-Marquardt, and Scaled Conjugate Gradient algorithm, Grey Wolf Optimizer-based Least Squares Boosting (GWO-LSBOOST), GWO-based Radial Basis Function, GWO-based Least Squares Support Vector Machine, and Extreme Learning Machine (ELM), to develop interfacial tension models for brine-hydrogen/cushion gas systems. Applying these models developed based on diverse theories, structures, and performance characteristics helps identify the optimal predictor for the target parameter. The evaluation of the models was carried out using 2868 experimental data points. The achieved results demonstrated the satisfactory performance of different modeling techniques (with R2 falling within the range of 0.8979 to 0.9960), however, GWO-LSBOOST outperformed others (improving R2 from 0.8979 to 0.9960 and AARE% from 5.5714 % to 0.8060 %, compared to ELM). Leverage outlier identification and trend estimation analysis confirmed the statistical reliability of the dataset and the GWO-LSBOOST model. The formulated strategies offer a promising framework applicable for incorporating the gas-water interfacial tension in simulating various stages of gas injection/ reproduction in underground hydrogen storage.

Predict the compressive strength of ultra high-performance concrete by a hybrid method of machine learning

Ultra-high performance concrete (UHPC) benefits the construction industry due to its improved flexibility, high workability, durability, and performance compared to normal concrete. Some investigators have conducted observed papers on the UHPC’s mechanical properties for establishing a reliable analytical approach for calculating the compressive strength, tensile strength, slump, etc. However, most of these studies were performed with limited samples because of the UHPC’s high cost. This study aims to predict the compressive strength (CS) of UHPC through hybrid machine-learning approaches. The model is included Adaptive-Network Fuzzy Inference System (ANFIS). Moreover, three meta-heuristic algorithms were employed to improve the developed model's accuracy, including the Generalized Normal Distribution Optimization, the COOT optimization algorithm, and the Honey Badger Algorithm. Several metrics were used to compare and assess the performance of the hybrid models in the framework of ANGN, ANCO, and ANHB. A comparison of the predicted and measured results generally shows that the proposed developed models can reasonably estimate the mechanical properties of UHPC. The results indicated that the ANHB model could estimate the CS of UHPC with the most suitable accuracy.

Type-2 Diabetes prediction with cuttlefish search optimization and hybrid model

In India, there are over 30 million individuals with diabetes and many more who are at risk. Diabetes and related health issues must be detected and treated early to be prevented. This study looks at a person's lifestyle and family history to determine their risk of having diabetes. The suggested hybrid machine learning approach, which combines the Support Vector Machine (SVM) classifier and Naive Bayes (NB) classifier, was used to forecast the probability of Type 2 diabetes. We incorporate Cuttlefish Search Optimization (CFSO) to increase prediction accuracy. After the model has been successfully trained, individuals may evaluate their own risk of developing diabetes. 952 times the information required for the question using an online and offline survey along with 18 questions about your habits, health, and family history. Preprocessing was done using min-max normalization, and feature extraction was done using linear discriminant analysis (LDA). The recommended approach was also examined using the Pima Indian Diabetes database. The performance of the provided approach is proved to be the most accurate for both datasets. The term "Type 2 Diabetes prediction with Cuttlefish Search optimization and a hybrid model" refers to the employment of a particular optimization technique called Cuttlefish Search in conjunction with a hybrid model to forecast a person's chance of getting Type 2 Diabetes.

Hybrid Machine Learning Approach for Evapotranspiration Estimation of Fruit Tree in Agricultural Cyber-Physical Systems.

The flourish of the Internet of Things (IoT) and data-driven techniques provide new ideas for enhancing agricultural production, where evapotranspiration estimation is a crucial issue in crop irrigation systems. However, tremendous and unsynchronized data from agricultural cyber-physical systems bring large computational costs as well as complicate performing conventional machine learning methods. To precisely estimate evapotranspiration with acceptable computational costs under the background of IoT, we combine time granulation computing techniques and gradient boosting decision tree (GBDT) with Bayesian optimization (BO) to propose a hybrid machine learning approach. In the combination, a fuzzy granulation method and a time calibration technique are introduced to break voluminous and unsynchronized data into small-scale and synchronized granules with high representativeness. Subsequently, GBDT is implemented to predict evapotranspiration, and BO is utilized to find the optimal hyperparameter values from the reduced granules. IoT data from Xi'an Fruit Technology Promotion Center in Shaanxi Province, China, verify that the proposed granular-GBDT-BO is effective for cherry tree evapotranspiration estimation with reduced computational time, and acceptable and robust predictive accuracy. Consequently, the precise estimation of crop evapotranspiration could provide operational guidance for plant irrigation, plant conservations, and pest control in the agricultural greenhouse.

Hybrid Machine Learning Approach for Attack Classification and Clustering in Network Security

Hybrid Machine Learning Approach for Attack Classification and Clustering in Network Security

A hybrid machine learning approach for the load prediction in the sustainable transition of district heating networks

Current district heating networks are undergoing a sustainable transition towards the 4th and 5th generation of district heating networks, characterized by the integration of different types of renewable energy sources (RES) and low operational temperatures, i.e., 55 °C or lower. Due to the lower temperature difference between supply and return, it is necessary to develop novel methods to understand the loads accurately and provide operation scenarios to anticipate demand peaks and increase flexibility in the energy network, both for long- and short-term horizons. In this study, a hybrid machine-learning (ML) method is developed, combining a clustering pre-processing step with a multi-input artificial neural network (ANN) model to predict heat loads in buildings cluster-wise. Specifically, the impact of time-series data clustering, as a pre-processing step, on the performance of ML models was investigated. It was found that data clustering contributes effectively to the reduction of data training costs by limiting the training processes to representative clusters only instead of all datasets. Additionally, low-quality data, including outliers and large measurement gaps, are excluded from the training to enhance the overall prediction performance of the models.

Intelligent multiobjective optimization for high-performance concrete mix proportion design: A hybrid machine learning approach

The concrete mix proportion design process is complex but important, especially in cold, ocean, underground and other complex engineering environments. In this study, a hybrid intelligent optimization method based on the random forest (RF), recursive feature elimination (RFE), Bayesian optimization (BO), least squares support vector machine (LSSVM) and nondominated sorting genetic algorithm (NGSA)-III was proposed to optimize the concrete mix proportion and rapidly and accurately predict the frost resistance, chloride ion penetration resistance and concrete strength (CS). Adopting a key project in Jilin Province as an example, the RF-RFE-BO-LSSVM-NSGA-III algorithm achieved a significant optimization effect in terms of the chloride ion permeability coefficient (CIPC), relative dynamic elastic modulus (RDEM) and 28-day CS. After optimization, the chloride ion penetration resistance, frost resistance and CS increased by 34.6%, 4.1% and 3.7%, respectively, over the average levels of the sample data. This study can provide basis for concrete mix proportion design in complex environment.

Unlocking Drone Potential in the Pharma Supply Chain: A Hybrid Machine Learning and GIS Approach

In major metropolitan areas, the growing levels of congestion pose a significant risk of supply chain disruptions by hindering surface transportation of commodities. To address this challenge, cargo drones are emerging as a potential mode of transport that could improve the reliability of the pharmaceutical supply chain and enhance healthcare. This study proposes a novel hybrid workflow that combines machine learning and a geographic information system to identify the fewest locations where providers can initiate cargo drone services to yield the greatest initial benefits. The results show that by starting a service in only nine metropolitan areas across four regions of the contiguous United States, drones with a robust 400-mile range can initially move more than 28% of the weight of all pharmaceuticals. The medical community, supply chain managers, and policymakers worldwide can use this workflow to make data-driven decisions about where to access the largest opportunities for pharmaceutical transport by drones. The proposed approach can inform policies and standards such as Advanced Air Mobility to help address supply chain disruptions, reduce transportation costs, and improve healthcare outcomes.

Hybrid Machine Learning Approach to Predict the Site Selectivity of Iridium-Catalyzed Arene Borylation.

The borylation of aryl and heteroaryl C-H bonds is valuable for the site-selective functionalization of C-H bonds in complex molecules. Iridium catalysts ligated by bipyridine ligands catalyze the borylation of the C-H bond that is most acidic and least sterically hindered in an arene, but predicting the site of borylation in molecules containing multiple arenes is difficult. To address this challenge, we report a hybrid computational model that predicts the Site of Borylation (SoBo) in complex molecules. The SoBo model combines density functional theory, semiempirical quantum mechanics, cheminformatics, linear regression, and machine learning to predict site selectivity and to extrapolate these predictions to new chemical space. Experimental validation of SoBo showed that the model predicts the major site of borylation of pharmaceutical intermediates with higher accuracy than prior machine-learning models or human experts, demonstrating that SoBo will be useful to guide experiments for the borylation of specific C(sp2)-H bonds during pharmaceutical development.

A chemistry-informed hybrid machine learning approach to predict metal adsorption onto mineral surfaces

Historically, surface complexation model (SCM) constants and distribution coefficients (Kd) have been employed to quantify mineral-based retardation effects controlling the fate of metals in subsurface geologic systems. Our recent SCM development workflow, based on the Lawrence Livermore National Laboratory Surface Complexation/Ion Exchange (L-SCIE) database, illustrated a community FAIR data approach to SCM development by predicting uranium(VI)-quartz adsorption for a large number of literature-mined data. Here, we present an alternative hybrid machine learning (ML) approach that shows promise in achieving equivalent high-quality predictions compared to traditional surface complexation models. At its core, the hybrid random forest (RF) ML approach is motivated by the proliferation of incongruent SCMs in the literature that limit their applicability in reactive transport models. Our hybrid ML approach implements PHREEQC-based aqueous speciation calculations; values from these simulations are automatically used as input features for a random forest (RF) algorithm to quantify adsorption and avoid SCM modeling constraints entirely. Named the LLNL Speciation Updated Random Forest (L-SURF) model, this hybrid approach is shown to have applicability to U(VI) sorption cases driven by both ion-exchange and surface complexation, as is shown for quartz and montmorillonite cases. The approach can be applied to reactive transport modeling and may provide an alternative to the costly development of self-consistent SCM reaction databases.

Improving Heart Disease Prediction Accuracy Using a Hybrid Machine Learning Approach: A Comparative study of SVM and KNN Algorithms

The largest cause of mortality worldwide is heart disease, and early identification is critical in limiting disease development. Early approaches for detecting cardiovascular illnesses assisted in determining the progressions that should have happened in high-risk persons, reducing their risks. The major goal is to save lives by recognising anomalies in cardiac circumstances, which will be performed by identifying and analysing raw data produced from cardiac information. Machine learning can provide an efficient method for making decisions and creating accurate forecasts. Machine learning techniques are being used extensively in the medical business. A unique machine learning technique is provided in the proposed study to predict cardiac disease. The planned study made advantage of open source heart disease dataset from kaggle. Hybrid algorithms for machine learning prediction are the logical mixture of many previous methodologies designed to improve efficiency and produce improved outcomes. The presented work introduces a hybrid method that employs the notion of categorization for prediction analysis. We used real patient data to build a hybrid technique to predicting cardiac disease. KNN and SVM classification techniques were utilized in this paper. Jupyter Notebook is used to implement this hybrid method. A hybrid technique outperforms other algorithms in the prediction analysis of heart disease.

Development of hybrid ANFIS-GAN-XGBOOST models for accurate prediction of material removal rates from PCB-polluted concrete surfaces using laser technology for sustainable energy generation

This study presents a hybrid machine learning approach for predicting material removal rates from polychlorinated biphenyl (PCB)-polluted concrete surfaces using laser technology. An adaptive neural fuzzy inference system (ANFIS) with XGBoost and generative adversarial networks (GANs) was employed as a hybrid model (ANFISGAN- XGBoost) to classify the numerous input variables for material removal rates based on process factors. Four input parameters, including annealing temperature, scanning speed, frequency, and laser power, were evaluated to calculate the ablation effectiveness and material removal rates. The study demonstrated that the hybrid ANFIS-GAN-XGBoost model applied to laser ablation on concrete surfaces polluted with PCBs accurately predicts the ablation depth. The experimental findings revealed that 96.66% of the PCBs were removed from the concrete surface, and 88.43% of them were decomposed during the laser decontamination procedure. A surface ablation ratio of roughly 7.2 m2/h was achieved, indicating the potential of using laser technology for sustainable energy generation by removing pollutants from concrete surfaces. The findings of this study contribute to the development of sustainable energy generation strategies and could be used in the cleanup of concrete surfaces polluted with PCBs in various settings, including nuclear power plants and polluted buildings. The hybrid ANFIS-GAN-XGBoost model is a valuable tool for predicting material removal rates based on process factors and can be used in the optimization of the laser-based decontamination process for PCB-polluted concrete surfaces. This study highlights the potential of using advanced machine learning models in environmental cleanup efforts, paving the way for future research in this field.

A hybrid machine learning approach for early cost estimation of pile foundations

Purpose This study aims at proposing a hybrid model for early cost prediction of a construction project. Early cost prediction for a construction project is the basic approach to procure a project within a predefined budget. However, most of the projects routinely face the impact of cost overruns. Furthermore, conventional and manual cost computing techniques are hectic, time-consuming and error-prone. To deal with such challenges, soft computing techniques such as artificial neural networks (ANNs), fuzzy logic and genetic algorithms are applied in construction management. Each technique has its own constraints not only in terms of efficiency but also in terms of feasibility, practicability, reliability and environmental impacts. However, appropriate combination of the techniques improves the model owing to their inherent nature. Design/methodology/approach This paper proposes a hybrid model by combining machine learning (ML) techniques with ANN to accurately predict the cost of pile foundations. The parameters contributing toward the cost of pile foundations were collected from five different projects in India. Out of 180 collected data entries, 176 entries were finally used after data cleaning. About 70% of the final data were used for building the model and the remaining 30% were used for validation. Findings The proposed model is capable of predicting the pile foundation costs with an accuracy of 97.42%. Originality/value Although various cost estimation techniques are available, appropriate use and combination of various ML techniques aid in improving the prediction accuracy. The proposed model will be a value addition to cost estimation of pile foundations.

A hybrid machine learning approach based study of production forecasting and factors influencing the multiphase flow through surface chokes

Surface chokes are widely utilized equipment installed on wellheads to control hydrocarbon flow rates. Several correlations have been suggested to model the multiphase flow of oil and gas via surface chokes. However, substantial errors have been reported in empirical fitting models and correlations to estimate hydrocarbon flow because of the reservoir's heterogeneity, anisotropism, variance in reservoir fluid characteristics at diverse subsurface depths, which introduces complexity in production data. Therefore, the estimation of daily oil and gas production rates is still challenging for the petroleum industry. Recently, hybrid data-driven techniques have been reported to be effective for estimation problems in various aspects of the petroleum domain. This paper investigates hybrid ensemble data-driven approaches to forecast multiphase flow rates through the surface choke (viz. stacked generalization and voting architectures), followed by an assessment of the impact of input production control variables. Otherwise, machine learning models are also trained and tested individually on the production data of hydrocarbon wells located in North Sea. Feature engineering has been properly applied to select the most suitable contributing control variables for daily production rate forecasting. This study provides a chronological explanation of the data analytics required for the interpretation of production data. The test results reveal the estimation performance of the stacked generalization architecture has outperformed other significant paradigms considered for production forecasting.

Prediction of seasonal infectious diseases based on hybrid machine learning approach

Prediction of seasonal infectious diseases based on hybrid machine learning approach

Compressive strength prediction of high-strength concrete using hybrid machine learning approaches by incorporating SHAP analysis

Compressive strength prediction of high-strength concrete using hybrid machine learning approaches by incorporating SHAP analysis

A hybrid machine learning approach for forecasting residential electricity consumption: A case study in Singapore

Ensuring effective forecasting of buildings' energy consumption is crucial in establishing a greater understanding and improvement of buildings' energy efficiency. In Singapore, domestic electricity usage in public residential buildings takes up a significant portion of the country's annual energy consumption. Having effective forecasting approaches is thus important in supporting relevant strategies and policy making. In this research, we proposed a hybrid approach that was based on a combination of building characteristics and urban landscape variables to predict residential housing electricity usage in Singapore. XGboost was also incorporated inside the hybrid approach as the preferred machine learning approach for energy consumption predictions. To demonstrate our proposed approach's predictive strength, the performance of our proposed hybrid machine learning approach was compared with two other models, Geographically Weighted Regression (GWR) model and the Random Forest (RF) model. Results showed that our proposed hybrid model had outperformed these abovementioned approaches with higher accuracy (r2 value of 0.9). The proposed approach had thus been effective in forecasting electricity consumption for public housing in Singapore, and it could also be utilised in other similar urban areas for future electricity consumption forecasting.

Soil type identification model using a hybrid computer vision and machine learning approach

Soil type identification model using a hybrid computer vision and machine learning approach

Implementation of Hybrid Prediction Model: An Unsupervised and Supervised Learning Perspective

Using raw data to make inferences is the core of data science. This might be accomplished by closely examining the complex trends and patterns in the data. Machine Learning based forecasting methods have shown useful in predicting perioperative outcomes to improve the quality of future event planning decisions. In many application sectors where machine learning models were used, it has long been necessary to identify and prioritise the negative characteristics of a threat. Wish to provide precise predictions about a certain set of data, for example, use machine learning techniques in data science. Numerous prediction algorithms are now in use to address forecasting issues. Numerous epidemiological models are being employed internationally to forecast pandemic mortality rates and the number of affected people. Making the right decisions depends on the development of reliable prediction models.
 Epidemiological models have had trouble making longer-term forecasts with a higher degree of accuracy due to a lack of significant data and ambiguity. This research suggests a hybrid machine learning approach to anticipate the pandemic in contrast to Susceptible-Infected-Resistant based models, and we demonstrate its potential using COVID-19 data from India. Order to improve the identification of epidemics early, The model can also be updated using data from sources like search engine searches. Results from two well-known machine learning methods were compared to those from the improved SIR and SEIQR models.

Efficiency Management of Women Poultry Farmers Using Hybrid DEA and Machine Learning Approach: A Case of SHG-based Production in Sub-Himalayan North Bengal

Data envelopment analysis (DEA) offers a linear programming approach to evaluate the efficiency in diverse fields of production and service sectors with wide utilization for effective performance measurement operations. DEA has found its useful applications in agriculture to examine optimal resource use for sustainable consumption. The popularly used two-step process where DEA is employed along with a regression model to explain the impact of exogenous factors on efficiency has been employed in past studies. This article aims to combine the conventional DEA approach with machine learning (ML) models for establishing a novel alternative method for performance measurement as well as the prediction of key exogenous factors affecting the efficiency of the women self-help groups (SHGs) led poultry farmers in sub-Himalayan North Bengal surrounding the Siliguri region of Darjeeling district. For this purpose, in the first step, DEA was employed to measure the efficiency of 80 women poultry farmers belonging to 20 SHGs and in the second step, the state-of-the-art random forest (RF) technique has been employed to predict the most important efficiency influencing variables. The results suggested inefficiencies among the SHG women with wide variation between the efficient and inefficient units. The use of the RF model predicted important factors such as the role of non-governmental organizations, educational level, financial inclusion, landholding and poultry rearing experience in years to impact the efficiency of these women farmers. As a result, the hybrid DEA-ML approach is useful to tackle ill adversities in poultry production that may help the women SHGs to develop agriculture-based income.