Hybrid Machine Learning Technique Research Articles

A Novel Approaches to Crop Variety Development for Sustainable Agriculture using Hybrid Machine Learning Model

The growing global population and changing climate need sustainable agriculture practices and new crop varieties. This study proposes a hybrid machine learning technique that combines linear regression and logistic regression to identify and extract unique traits from a broad range of crop species. The system integrates these qualities to create new crop types with a variety of benefits. The system begins by collecting detailed data on multiple crop species, including production potential, drought resilience, disease tolerance, nutritional content, and adaptation to different climates. Preprocessing ensures data quality. The hybrid machine learning algorithm uses the revised dataset. Linear regression identifies variables with strong connections with the required attributes, making it easier to find good candidates for the new crop variety. Logistic regression analyzes categorical data, including disease resistance genes and nutritional variables that affect crop quality. The method efficiently identifies and ranks the best characteristics across varied crop species by combining regression model findings. The traits have been strategically combined to create a pioneering cultivar that optimizes crop productivity, robustness, nutritional composition, and versatility while reducing vulnerability to pathogenic diseases and ecological challenges. The innovative crop variety is tested in various agricultural situations to determine the system's effectiveness. The topic under inquiry is compared to current kinds in terms of yield, quality, and sustainability. This unique hybrid machine learning technology may combine the best qualities from multiple sources to develop cutting-edge agricultural cultivars. The system's speed and accuracy in identifying beneficial traits promotes sustainable agriculture by reducing monospecific breeding and increasing crop resilience to environmental challenges. This work advances global food security and resource-efficient crop varieties.

Automatic non-destructive estimation of polyphenol oxidase and peroxidase enzyme activity levels in three bell pepper varieties by Vis/NIR spectroscopy imaging data based on machine learning methods

The browning process of food products if often formed upon cutting and damage during their processing, transport, and storage, amongst other potential sources and reasons. Enzymic browning can be mainly due to polyphenol peroxidase (PPO) and peroxidase (POD) enzymes. Visible/near-infrared (Vis/NIR) imaging spectroscopy in the range of 350-1150 nm was used in this study for automatic and non-destructive evaluation of PPO and POD activity levels in three bell pepper varieties (red, yellow, orange; N=30), with a total of 30 inputs samples in each variety. The spectral data were then modeled by the partial least square regression (PLSR) throughout the whole spectral range, without using any subset of the most effective wavelength (EW) values. Regression determination coefficient (R2) values for the estimation (prediction) of POD enzyme activity levels were 0.794, 0.772, and 0.726 for red, yellow, and orange bell peppers, respectively, all over the validation set. At the same time, the activity levels of PPO enzyme over bell peppers showed R2 values of 0.901, 0.810, and 0.859, for red, yellow, and orange bell peppers, respectively, all over the validation set. In addition, a combination of Support vector machine (SVM) with either genetic algorithms (GA), particle swarm optimization (PSO), ant colony optimization (ACO), or imperialistic competitive algorithms (ICA) hybrid machine learning (ML) techniques were used to select the optimal (discriminant) spectral EW wavelength values, and regression performance was consistently improved, to judge from higher regression fit R2 values. Either 14 or 15 EWs were computed and selected in order of their discriminative power using previously mentioned ML techniques. The SVM-PSO method resulted the best one in the process of selecting the most effective wavelength values (nm). On the other hand, three regression methods comprising PLSR, multiple least regression (MLR), and neural network (NN), were employed to model the SVM-PSO selected EWs. The ratio of performance to deviation (RPD), the R2 and the root mean square error (RMSE), over the test set, for the non-linear NN regression method exhibited better results as compared to the other two regression methods, being closely followed by PLSR, and therefore NN regression method was selected as the best approach for modeling the most effective spectral wavelength values in this study.

Physicochemical properties-based hybrid machine learning technique for the prediction of SARS-CoV-2 T-cell epitopes as vaccine targets.

Majority of the existing SARS-CoV-2 vaccines work by presenting the whole pathogen in the attenuated form to immune system to invoke an immune response. On the other hand, the concept of a peptide based vaccine (PBV) is based on the identification and chemical synthesis of only immunodominant peptides known as T-cell epitopes (TCEs) to induce a specific immune response against a particular pathogen. However PBVs have received less attention despite holding huge untapped potential for boosting vaccine safety and immunogenicity. To identify these TCEs for designing PBV, wet-lab experiments are difficult, expensive, and time-consuming. Machine learning (ML) techniques can accurately predict TCEs, saving time and cost for speedy vaccine development. This work proposes novel hybrid ML techniques based on the physicochemical properties of peptides to predict SARS-CoV-2 TCEs. The proposed hybrid ML technique was evaluated using various ML model evaluation metrics and demonstrated promising results. The hybrid technique of decision tree classifier with chi-squared feature weighting technique and forward search optimal feature searching algorithm has been identified as the best model with an accuracy of 98.19%. Furthermore, K-fold cross-validation (KFCV) was performed to ensure that the model is reliable and the results indicate that the hybrid random forest model performs consistently well in terms of accuracy with respect to other hybrid approaches. The predicted TCEs are highly likely to serve as promising vaccine targets, subject to evaluations both in-vivo and in-vitro. This development could potentially save countless lives globally, prevent future epidemic-scale outbreaks, and reduce the risk of mutation escape.

Computer-aided urban energy systems cyber attach detection and mitigation: Intelligence hybrid machine learning technique for security enhancement of smart cities

This paper introduces a sophisticated computer-aided system for enhancing the security of smart cities through urban cyber attack detection and mitigation. The proposed system employs a comprehensive mathematical framework that models the dynamics of cyber attacks, detection, and mitigation, capturing the intricate relationships within a smart city environment. Leveraging a hybrid approach combining Transfer Learning and Meta-Learning, the system adapts to evolving threats and tasks, showcasing superior performance in comparison to standalone methods. Simulation results demonstrate the system’s robustness, with low False Positive and False Negative Rates, high System Security, and effective Mitigation Strategies. This research contributes a state-of-the-art solution for securing smart cities, leveraging intelligent hybrid machine learning techniques.

Evolutionary Hybrid Machine Learning Techniques for DNA Cancer Data Classification

Evolutionary Hybrid Machine Learning Techniques for DNA Cancer Data Classification

Predicting the web crippling capacity of cold-formed steel lipped channels using hybrid machine learning techniques

Cold-Formed Steel Lipped (CFSL) channels are susceptible to a localized failure mechanism known as web crippling, triggered by concentrated loads or reactions applied to the web of the section. These loads induce buckling and distortion in the web, ultimately leading to the member's collapse. It is a challenging task to accurately determine the web crippling capacity of a CFSL channel due to its complexity and various influencing factors. This paper presents hybrid soft computing techniques for accurately predicting the web crippling capacity of CFSL channels subjected to two flange load cases. The developed soft computing techniques combine Artificial Neural Networks (ANN) with either Genetic Algorithms (GA) or Particle Swarm Optimization (PSO) to improve computational efficiency and accuracy. The finite element models of CFSL channels are developed and validated by experimental results and then employed to generate a database, which is used to train machine learning models, including ANN, GA-ANN, and PSO-ANN. Analysis is undertaken on the reliability of existing design formulas for determining the web crippling capacity of CFSL channels. It is shown that the PSO-ANN model outperforms the other models in terms of prediction accuracy. The existing design codes and formulas are not reliable in estimating the web crippling capacity of CFSL channels. However, the proposed model yields good correlation with finite element analysis results. A user- friendly graphical interface tool is developed for the practical design of cold-formed steel lipped channels.

An integrated approach combining randomized kernel PCA, Gaussian mixture modeling and ICA for fault detection in non-linear processes

Principal component analysis (PCA) and independent component analysis (ICA), as well as their kernel extensions, have been widely applied in the past for industrial fault detection with Gaussian or non-Gaussian process data with linear or non-linear characteristics. Kernel-based techniques lead to computational complexity due to the high dimensionality of the dataset in the feature space. In this work, a randomization approach is used to obtain a low-rank approximation of the high-dimensional kernel matrix. A hybrid machine learning technique is proposed that integrates randomized kernel PCA (RKPCA) with ICA and Gaussian mixture modeling (GMM). The proposed approach, ICA-RKPCA-GMM, addresses the Gaussian and non-Gaussian characteristics of non-linear process data. Another hybrid algorithm combining three basic techniques of ICA, PCA and GMM is also developed (ICA-PCA-GMM). The fault detection performances of the proposed techniques (ICA-RKPCA-GMM and ICA-PCA-GMM) are compared with PCA, ICA, KPCA and combined ICA-PCA techniques by applying the techniques to two benchmark systems. Monitoring performances were evaluated by determining the false alarm rate and fault detection rate for different types of process and sensor faults. The simulation results show that the proposed ICA-RKPCA-GMM approach yields better results than individual ICA, PCA and KPCA techniques, the combined ICA-PCA and the proposed ICA-PCA-GMM technique.

An Effective Heart Disease Detection and Classification using Machine Learning

About 20.5 million people die yearly due to cardiovascular disease (CVD). Early prediction of heart disease and accurate heart severity identification can save the induvial life with timely medications. In many cases, most deaths occur due to inaccurate diagnosis of the heart. In computer science, various existing researchers have dealt with the classification of heart disease on synthetic as well as real-time datasets. But still, those systems have a challenge such as low classification accuracy, high error rate and inaccurate heart severity detection. After identifying all these challenges, we proposed an effective heart disease detection and classification using hybrid machine learning techniques. In this article, we describe how various feature extraction and hybrid machine learning classifiers produce accurate severity of heart disease on real-time datasets. In the first phase, we collected a Cleveland dataset from Kaggle and then applied preprocessing and normalization for data balancing. Various feature extraction and selection methods, such as TF-IDF, Co-relation coefficient, N-Gram, and bi-Gram features, are used for practical module training. The different machine learning we used on normalized datasets for classification. The five supervised machine learning algorithms are used, such as Support Vector Machine (SVM), Naïve Bayes (NB), Artificial Neural Network (ANN) and Hybrid Machine Learning (HML) etc. The HML achieves 99.30% accuracy on the Cleveland dataset using Weka 3.8 machine learning framework. As a result, the proposed system compares with various heart disease predictions using machine learning techniques.

Utilizing Hybrid Machine Learning Techniques and Gridded Precipitation Data for Advanced Discharge Simulation in Under-Monitored River Basins

This study addresses the challenge of utilizing incomplete long-term discharge data when using gridded precipitation datasets and data-driven modeling in Iran’s Karkheh basin. The Multilayer Perceptron Neural Network (MLPNN), a rainfall-runoff (R-R) model, was applied, leveraging precipitation data from the Asian Precipitation—Highly Resolved Observational Data Integration Toward Evaluation (APHRODITE), Global Precipitation Climatology Center (GPCC), and Climatic Research Unit (CRU). The MLPNN was trained using the Levenberg–Marquardt algorithm and optimized with the Non-dominated Sorting Genetic Algorithm-II (NSGA-II). Input data were pre-processed through principal component analysis (PCA) and singular value decomposition (SVD). This study explored two scenarios: Scenario 1 (S1) used in situ data for calibration and gridded dataset data for testing, while Scenario 2 (S2) involved separate calibrations and tests for each dataset. The findings reveal that APHRODITE outperformed in S1, with all datasets showing improved results in S2. The best results were achieved with hybrid applications of the S2-PCA-NSGA-II for APHRODITE and S2-SVD-NSGA-II for GPCC and CRU. This study concludes that gridded precipitation datasets, when properly calibrated, significantly enhance runoff simulation accuracy, highlighting the importance of bias correction in rainfall-runoff modeling. It is important to emphasize that this modeling approach may not be suitable in situations where a catchment is undergoing significant changes, whether due to development interventions or the impacts of anthropogenic climate change. This limitation highlights the need for dynamic modeling approaches that can adapt to changing catchment conditions.

Blockchain security enhancement: an approach towards hybrid consensus algorithms and machine learning techniques

In this paper, we propose hybrid consensus algorithms that combine machine learning (ML) techniques to address the challenges and vulnerabilities in blockchain networks. Consensus Protocols make ensuring agreement among the applicants in the distributed systems difficult. However, existing mechanisms are more vulnerable to cyber-attacks. Previous studies extensively explore the influence of cyber attacks and highlight the necessity for effective preventive measures. This research presents the integration of ML techniques with the proposed hybrid consensus algorithms and advantages over predicting cyber-attacks, anomaly detection, and feature extraction. Our hybrid approaches leverage and optimize the proposed consensus protocols' security, trust, and robustness. However, this research also explores the various ML techniques with hybrid consensus algorithms, such as Delegated Proof of Stake Work (DPoSW), Proof of Stake and Work (PoSW), Proof of CASBFT (PoCASBFT), Delegated Byzantine Proof of Stake (DBPoS) for security enhancement and intelligent decision making in consensus protocols. Here, we also demonstrate the effectiveness of the proposed methodology within the decentralized networks using the ProximaX blockchain platform. This study shows that the proposed research framework is an energy-efficient mechanism that maintains security and adapts to dynamic conditions. It also integrates privacy-enhancing features, robust consensus mechanisms, and ML approaches to detect and prevent security threats. Furthermore, the practical implementation of these ML-based hybrid consensus models faces significant challenges, such as scalability, latency, throughput, resource requirements, and potential adversarial attacks. These challenges must be addressed to ensure the successful implementation of the blockchain network for real-world scenarios.

Secure and efficient storage approach for cloud environment using hybrid machine learning techniques

Cloud computing is a new way to organize things. Cloud users can store their files that are far away and linked to the web. As a result, personal and critical data are stored in an easily accessible and transferable manner. Hence, its demand is expanding daily. Due to the fact that the user accesses data over the internet, issues about the secrecy and confidentiality have arisen. To address this issue, hybridization employs an encryption technology known as the RSA with 3- DES approach. This article primarily addressed two aspects: data security and storage. The encryption strategy is used to secure cloud data, while the MBFD with WOA & ANN approach is used to store it. Also the utilization of neural network along with the whale optimization model ensures the controlled storage of cloud has been done. The experiment demonstrates that the suggested cloud system outperforms the present one in terms of energy usage, latency, and SLA breach.

A Novel Predictive Analysis and Classification of Land Subsidence Vulnerability Mapping based on GIS using Hybrid Optimized Machine Learning Techniques and Computer Vision

Land subsidence is a natural disaster caused by the extraction of the earth's material strength on the surface that causes the earth's surface to settle and sink. Land subsidence can also result in significant financial losses since it causes structural damage and expensive maintenance costs for roads, trains, barriers, pipelines, ground water, oil, natural gas, mines, and buildings. The Geographic Information System (GIS) and Google Earth Platform (GEP) can be used to map this land subsidence. This provides a comprehensive view of land pattern subsidence and its interactions with other geographical elements. It applies to both progressive subsidence caused by fluid extraction (groundwater, oil, or natural gas) and rapid surface subsidence caused by the collapse of an underground mine. Risk mitigation is the most effective way to deal with the experimental model. This research study focuses on the use of Predictive Data Analysis (PDA), a powerful environment in data analytics that provides a set of tools that make it easier to evaluate optimal models. The proposed model makes use of a dataset that includes specific land subsidence circumstances as input. The prediction result is achieved using a hybrid machine learning technique that combines Stochastic Gradient Descent (SGD) with Long Short-Term Memory (LSTM) and is compared to K-Nearest Neighbor (KNN), Generative Adversarial Network (GAN), and Artificial Neural Network (ANN). The proposed system employs LSTM and SGD as optimizers, resulting in a hybrid model that improves accuracy. Among the four algorithms investigated the LSTM-SGD network has the highest accuracy (97%), followed by KNN (96%), GAN (90%), and ANN (89%). Due to their ability to capture complicated nonlinear correlations in data and manage temporal dependencies, optimized hybrid ML models LSTM-SGD and KNN models appear to be particularly well-suited for land subsidence prediction.

Advancing Bankruptcy Forecasting With Hybrid Machine Learning Techniques: Insights From an Unbalanced Polish Dataset

Advancing Bankruptcy Forecasting With Hybrid Machine Learning Techniques: Insights From an Unbalanced Polish Dataset

Alert Correlation Model Based on Hybrid Machine Learning Techniques to Enhance the Performance of NIDS

Alert Correlation Model Based on Hybrid Machine Learning Techniques to Enhance the Performance of NIDS

Permeation Flux Prediction of Vacuum Membrane Distillation Using Hybrid Machine Learning Techniques.

Vacuum membrane distillation (VMD) has attracted increasing interest for various applications besides seawater desalination. Experimental testing of membrane technologies such as VMD on a pilot or large scale can be laborious and costly. Machine learning techniques can be a valuable tool for predicting membrane performance on such scales. In this work, a novel hybrid model was developed based on incorporating a spotted hyena optimizer (SHO) with support vector machine (SVR) to predict the flux pressure in VMD. The SVR-SHO hybrid model was validated with experimental data and benchmarked against other machine learning tools such as artificial neural networks (ANNs), classical SVR, and multiple linear regression (MLR). The results show that the SVR-SHO predicted flux pressure with high accuracy with a correlation coefficient (R) of 0.94. However, other models showed a lower prediction accuracy than SVR-SHO with R-values ranging from 0.801 to 0.902. Global sensitivity analysis was applied to interpret the obtained result, revealing that feed temperature was the most influential operating parameter on flux, with a relative importance score of 52.71 compared to 17.69, 17.16, and 14.44 for feed flowrate, vacuum pressure intensity, and feed concentration, respectively.

Bump and Run

Banks use ridiculous amounts of computational resources on computing various risk measures. We discuss how this can be avoided using a cocktail of a big hybrid simulation model, adjoint differentiation and machine learning techniques, aka differential machine learning.

Review of deep learning techniques for power generation prediction of industrial solar photovoltaic plants

Varying power generation by industrial solar photovoltaic plants impacts the steadiness of the electric grid which necessitates the prediction of solar power generation accurately. In this study, a comprehensive updated review of standalone and hybrid machine learning techniques for PV power forecasting is presented. Forecasting solar generation is of importance for the sustainability of grid power and also to achieve the UN sustainable development targets by 2030. The comparison of techniques shows that grouping datasets based on input feature similarity, results in higher accuracy. Long-Short Term Memory (LSTM) is found to perform better than other deep learning networks for all time horizons. The Gate Recurrent Unit (GRU), with few trainings, is found to be better for small datasets than LSTM. Based on the more complicated data patterns, a novel architecture of the Deep Learning Network model, with the capability to analyze and forecast is presented considering factors influencing industrial solar power generation. The study is of importance to researchers, solar industry, and electricity distribution companies for sustainable development worldwide.

Prediction by a hybrid machine learning model for high-mobility amorphous In2O3: Sn films fabricated by RF plasma sputtering deposition using a nitrogen-mediated amorphization method

In this study, we developed a hybrid machine learning technique by combining appropriate classification and regression models to address challenges in producing high-mobility amorphous In2O3:Sn (a-ITO) films, which were fabricated by radio-frequency magnetron sputtering with a nitrogen-mediated amorphization method. To overcome this challenge, this hybrid model that was consisted of a support vector machine as a classification model and a gradient boosting regression tree as a regression model predicted the boundary conditions of crystallinity and experimental conditions with high mobility for a-ITO films. Based on this model, we were able to identify the boundary conditions between amorphous and crystalline crystallinity and thin film deposition conditions that resulted in a-ITO films with 27% higher mobility near the boundary than previous research results. Thus, this prediction model identified key parameters and optimal sputtering conditions necessary for producing high-mobility a-ITO films. The identification of such boundary conditions through machine learning is crucial in the exploration of thin film properties and enables the development of high-throughput experimental designs.

Empirical Model for the Retained Stability Index of Asphalt Mixtures Using Hybrid Machine Learning Approach

Moisture susceptibility is a complex phenomenon that induces various distresses in asphalt pavements and can be assessed by the Retained Stability Index (RSI). This study proposes a robust model to predict the RSI using a hybrid machine learning technique, including Artificial Neural Network (ANN) and Gene Expression Programming. The model is expressed as a simple and direct mathematical function with input variables of mineral filler proportion (F%), water absorption rate of combined aggregate (Ab%), asphalt content (AC%), and air void content (Va%). A relative importance analysis ranked AC% as the most influential variable on RSI, followed by Va%, F%, and Ab%. The experimental RSI results of 150 testing samples of various mixes were utilized along with other data points generated by the ANN to train and validate the proposed model. The model promotes a high level of accuracy for predicting the RSI with a 96.6% coefficient of determination (R2) and very low errors. In addition, the sensitivity of the model has been verified by considering the effect of the variables, which is in line with the results of network connection weight and previous studies in the literature. F%, Ab%, and Va% have an inverse relationship with the RSI values, whereas AC% has the opposite. The model helps forecast the water susceptibility of asphalt mixes by which the experimental effort is minimized and the mixes’ performance can be improved.

Hybrid Machine Learning Technique to Detect Active Botnet Attacks for Network Security and Privacy

A botnet is a malware application controlled from a distance by a programmer with the assistance of a botmaster. Botnets can launch enormous cyber-attacks like Denial-of-Service (DOS), phishing, spam, data stealing, and identity theft. The botnet can also affect the security and privacy of the systems. The conventional approach to detecting botnets is made by signature-based analysis, which cannot discover botnets that are not visible. The behavior-based analysis appears to be an appropriate solution to the current botnet characteristics that are constantly developing. This paper aims to develop an efficient botnet detection algorithm using machine learning with traffic reduction to increase accuracy. Based on behavioural analysis, a traffic reduction strategy is applied to reduce network traffic to improve overall system performance. Several network devices are typically used to retrieve network traffic information. With a detection accuracy of 98.4%, the known and unknown botnet activities are measured using the supplied datasets. The machine learning-based traffic reduction system has achieved a high rate of traffic reduction, about 82%, and false-positive rates range between 0% to 2%. Both findings demonstrate that the suggested technique is efficient and accurate.