Genetic Algorithm Support Vector Machine Research Articles

Prediction of building cooling load: an innovative design for GA-SVM and IG-SVM system for the estimation of hourly precision and computational fluctuation range

ABSTRACT Anticipating the loads that buildings will bear is a crucial strategy in the pursuit of energy efficiency and the reduction of emissions. In this paper, we introduce an interactive and comprehensive joint prediction model, specifically crafted to elevate the precision of forecasts related to building loads. The resultant Genetic Algorithm-Support Vector Machine (GA-SVM) prediction model is put into action to provide hourly predictions of cooling loads for buildings. In scenarios where the prediction of building cooling load (BCL) fluctuations becomes imperative, especially in the face of extreme weather conditions, the information granulation (IG) method is employed. The findings of this validation process unveil significant improvements. The coefficient of variation of root mean square error (CV-RMSE) and mean absolute percentage error (MAPE) for the GA-SVM model are reduced by 58.85% and 68.04%, respectively, when compared to the conventional SVM model. Furthermore, in a comparative analysis against three widely utilized prediction models, the SVM model demonstrates a reduction in CV-RMSE and MAPE ranging from 2.04% to 68.04%. The application of the joint prediction model showcases impressive results, with R 2 values ranging from 97.27% to 99.68%, MAPE ranging from 2.59% to 2.84%, and CV-RMSE ranging from only 0.0249 to 0.0319.

Multi-Objective Optimization Technology for Building Energy-Saving Renovation Strategy Based on Genetic Algorithm

Building energy-saving design is significant for the industry to achieve carbon reduction and sustainable development. Firstly, a multi-objective model for energy consumption, cost, and carbon emissions is established based on the three-dimensional perspectives of society, nature, and economy. Then, a polynomial operator is used to improve the non dominated sorting genetic algorithm to calculate the optimal solution set. The low computational efficiency caused by direct coupling of algorithms in traditional optimization processes is expected to be addressed. According to the results, for the Square1 dataset and Iris dataset, the algorithm proposed in this study improved the reverse distance and convergence metrics by more than 70% compared to support vector machine-genetic algorithm and multi-objective clustering algorithm, with values closer to 0. The solution solved by this algorithm had lower building costs, energy consumption, and carbon emissions, with values of 345200 yuan, 2374 KWh/year, and 26 tons, respectively. This validates the effectiveness of the multi-objective model and solving algorithm established in the study, which helps to obtain the optimal energy-saving design scheme and provides reference for low-carbon optimization of building.

An Improved Internet of Thing-based Optimized SVM Approach for ECG-founded Cardiac Arrhythmia Classification

Cardiovascular diseases (CVD) stand as the leading cause of global mortality, claiming millions of lives annually. An electrocardiogram (ECG) records the heart's electrical activity based on the Internet of Things (IoT), crucial in detecting cardiac arrhythmias (CA), characterized by irregular heart rates and rhythms. Signals from the MIT-BIH Arrhythmia Physio net database are analyzed. This chapter aims to propose a hybrid approach merging Genetic Algorithm-Support Vector Machine (GSVM) and Particle Swarm Optimization-Support Vector Machine (PSVM) for CA classification. The study introduces an algorithm for categorizing ECG beats into six groups using Independent Component Analysis (ICA)-derived features. Optimal SVM settings are determined using Genetic Algorithm (GA) and Particle Swarm Optimization (PSO) on ICA features computed via non-parametric power spectral estimation. The research delves into the origins and methodologies of GA and PSO. Simulation results comparing GSVM and PSVM are presented, emphasizing PSVM's superior performance in accuracy, sensitivity, specificity, and positive predictivity. Detailed performance metrics, including Sensitivity, Specificity, Positive Predictivity, and Accuracy percentages, are scrutinized and compared against the top classifier. The findings endorse PSVM's superiority over GSVM, indicating enhanced performance across multiple evaluation criteria.

Improve the capability of physical model for runoff and sediment yield modelling with a hybrid artificial intelligence-based error updating system

Uncertainty of physical models is caused by the model's complexity as well as the accuracy of input variables. In present study, an error update model was developed based on artificial intelligence, namely Wavelet Multilayer Perceptron (WMLP), Wavelet Support Vector Machine (WSVM), Wavelet Multilayer Perceptron-Genetic Algorithm (WMLP-GA), and Wavelet Support Vector Machine-Genetic Algorithm (WSVM-GA). Sensitivity findings demonstrate that groundwater recession factor (ALPHA_BF), plant uptake compensation factor (EPCO), and curve number were the most sensitive for runoff in the Shivnath River basin, India, as well as four distinctparameters were shown to be highly sensitive to sediment yield at the Sigma station. During the calibration and validation phase, the SWAT model overpredicts runoff at the Simga and Pathardhi stations while underpredicting it at the Kotni station. SWAT model performance for runoff modelling is enhanced via the use of statistical indicators like as Percent of Bias (PBIAS) decreased from −35.355 to −20.503, Root Mean Square Error (RMSE) decreased from 319.905 to 25.191 m3/sec, and coefficient of determination increase from 0.712 to 0.904. At Simga station, the Nash–Sutcliffe efficiency (NSE) increase from 0.315 to 0.745, the PBIAS decreased from −39.502 to –22.946, the RMSE decreased from 186.711 to 24.432 m3/sec, and the coefficient of determination increased from 0.733 to 0.996. Further, NSE increased from 0.305 to 0.985 at Kotni station and PBIAS reduced from −114.026 to −9.214, RMSE reduced from 82.205 to 31.082 m3/sec, coefficient of determination increased from 0.779 to 0.976, NSE increased from 0.523 to 0.927 at Pathardhi station after applying an error update model. For sediment yield prediction, similar outcomes to runoff were obtained. The WSVM-GA model was reported to be the optimum error update model both for runoff and sediment yield modelling. It was recommended that the SWAT model might be applied for runoff and sediment yield simulation in the future.

Bankruptcy Prediction Using Genetic Algorithm-Support Vector Machine (GA-SVM) Feature Selection and Stacking

Bankruptcy is an impact caused by a company's financial failure. Financial failure in the company must be avoided so as not to cause losses to the company. In the research that was carried out utilizing a data set from the Taiwan Economic Journal as many as 6,819 to be trained using machine learning algorithms using classification techniques. The goal obtained from the research conducted is to obtain a classification technique with the best accuracy results. The method used in this research is preprocessing using the synthetic minority over-sampling technique to handling unbalanced data sets. Then, the results of the balanced data set will be processed using a genetic algorithm-support vector machine feature selection algorithm to reduce the attributes of the data set. Data sets that have experienced reduced attributes will be trained using the stacking method with a single classifier base learner in the form of k-nearest neighbors, naïve bayes, decision trees with classification and regression tree models, gradient boosting decision trees, and light gradient boosting. The meta-learner used in the stacking method is extreme gradient boosting. The results of the accuracy obtained from the research conducted were 99.22%.

An examination of the hybrid meta-heuristic machine learning algorithms for early diagnosis of type II diabetes using big data feature selection

People are increasingly getting type II diabetes mellitus (T2DM) due to unhealthy food styles, decreased outdoor activities caused by the COVID-19 pandemic, and unawareness of type II diabetes risk factors. This disease is hidden in the early stages and causes many comorbidities like fatty liver, heart disease, and peripheral artery disease. This study presents several hybrid algorithms to diagnose T2DM in its early stages without requiring expensive and time-consuming medical tests. We first apply feature selection using the Particle Swarm Optimization (PSO) algorithm to reduce the required computations. Meta-heuristics are used in developed hierarchical algorithms to optimize the hyperparameters of machine learning algorithms for classification. A comparative analysis of the algorithms with performance metrics shows Genetic Algorithm-Support Vector Machine (GA-SVM) has the largest area under the Receiver Operating Characteristic (ROC) curve (0.934) and better performance in most metrics (Accuracy of 0.934 and F1-Measure of 0.945) and reasonable metaheuristic computational time. Therefore, the GA-SVM algorithm is recommended for clinical decision support systems. This algorithm diagnoses T2DM at early stages by responding to several questions with about 93% accuracy, which can help patients to survive future complications through lifestyle intervention therapy.

Evaluation of Corporate Social Responsibility and Core Competitiveness Based on GA-SVM Model

Abstract The author proposes a model evaluation based on the GA-SVM model to better understand the evaluation of the company’s relationship and core competitiveness. The system index is reduced by relative gray analysis, the support vector machine model is optimized by a genetic algorithm, and the specific algorithm steps are introduced. Select models from the top 100 enterprises in China’s construction industry in 2020 published by China Construction Industry Market, using relative gray to reduce the measure, and then use the genetic algorithm support vector machine (GA-SVM) model for the training model to achieve the evaluation of the core competencies of the target construction technique business. The experimental results show that the relative error of prediction of the GA-SVM(Genetic algorithm-support vector machine) model for the evaluation of the competitive core of the business is not more than 5, which meets the should be made of accurate predictions. Therefore, choosing the Gaussian radial basis kernel function (RBF) as the kernel function of the GA-SVM intelligent evaluation model is good. It proves that the GA-SVM model can analyze the relationship between the role and the important competition.

Research on SVM-Based Bearing Fault Diagnosis Modeling and Multiple Swarm Genetic Algorithm Parameter Identification Method

The bearing fault diagnosis of petrochemical rotating machinery faces the problems of large data volume, weak fault feature signal strength and susceptibility to noise interference. To solve these problems, current research presents a combined ICEEMDAN-wavelet threshold joint noise reduction, mutual dimensionless metrics and MPGA-SVM approach for rotating machinery bearing fault diagnosis. Firstly, we propose an improved joint noise-reduction method of an Improved Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (ICEEMDAN) and wavelet thresholding. Moreover, the noise-reduced data are processed by mutual dimensionless processing to construct a mutual dimensionless index sensitive to bearing fault features and complete the fault feature extraction of the bearing signals. Furthermore, we design experiments on faulty bearings of multistage centrifugal fans in petrochemical rotating machinery and processed the input data set according to ICEEMDAN-wavelet threshold joint noise reduction and mutual dimensionless indexes for later validation of the model and algorithm. Finally, a support vector machine model used to effectively identify the bearing failures, and a multi-population genetic algorithm, is studied to optimize the relevant parameters of the support vector machine. The powerful global parallel search capability of the multigroup genetic algorithm is used to search for the penalty factor c and kernel parameter r that affect the classification performance of the support vector machine. The global optimal solutions of c and r are found in a short time to construct a multigroup genetic algorithm-support vector machine bearing fault diagnosis and identification model. The proposed model is verified to have 95.3% accuracy for the bearing fault diagnosis, and the training time is 11.1608 s, while the traditional GA-SVM has only 89.875% accuracy and the training time is 17.4612 s. Meanwhile, to exclude the influence of experimental data on the specificity of our method, the experimental validation of the Western Reserve University bearing failure open-source dataset was added, and the results showed that the accuracy could reach 97.1% with a training time of 14.2735 s, thus proving that the method proposed in our paper can achieve good results in practical applications.

Multi-Response Optimization of Milling Process of Hardened S50C Steel Using SVM-GA Based Method

This study aims to find the optimized parameters for surveying the milling process of S50C steel in a minimum quantity lubrication (MQL) environment using a support vector machine-genetic algorithm (SVM-GA). Based on the experimental matrix designed by the Taguchi method, surface roughness and cutting force data were collected corresponding to each experiment with changes in input parameters such as cutting speed, tooth feed rate, and axial depth of cut, along with changes in two parameters of the minimum lubrication system: flow rates and injection pressure. Through analysis by the SVR-NSGAII method, the study obtained the optimal parameters of cutting and lubricating conditions when prioritizing either surface roughness or focusing on the cutting force; however, the most comprehensive result is believed to be achieved by balancing these two factors. So, when striving for the neutral value of both output parameters, which are surface roughness (µm) and cutting force (N), the optimum parameters including injection pressure (MPa), flow rates (mL/h), cutting speed (m/min), feed rate (mm/tooth), and axial depth of cut (mm) are proposed.

A fault diagnosis method for building electrical systems based on the combination of variational modal decomposition and new mutual dimensionless

The fault diagnosis of building electrical systems are of great significance to the safe and stable operation of modern intelligent buildings. In this paper, it has many problems, such as various fault types, inconspicuous fault characteristics, uncertainty of fault type and mode, irregularity, unstable signal, large gap between fault data classes, small gap between classes and nonlinearity, etc. A method of building electrical system fault diagnosis based on the combination of variational mode decomposition and mutual dimensionless indictor (VMD-MDI) and quantum genetic algorithm-support vector machine (QGA-SVM) is proposed. Firstly, the method decomposes the original signal through variational modal decomposition to obtain the optimal number of Intrinsic Mode Function(IMF) containing fault feature information. Secondly, extracts the mutual dimensionless indicator for each IMF. Thirdly, the optimal penalty coefficient C of the support vector machine and the parameter gamma (gamma) in the radial basis kernel function are selected by the quantum genetic algorithm. Finally, SVM optimized by the QGA is used to identify and classify the faults. By applying the proposed method to the experimental platform data of building electrical system, and compared with the traditional feature extraction method Empirical Mode Decomposition (EMD), Singular Value Decomposition(SVD), Local Mean Decomposition(LMD). And compared with traditional SVM, Genetic Algorithm optimized Support Vector Machine (GA-SVM), One-Dimensional Convolutional Neural Network (1DCNN) for fault classification methods. The experimental results show that the method has better effect and higher accuracy in fault diagnosis and classification of building electrical system. Its average test accuracy can reach 91.67%.

Research on Multi-Fault Identification of Marine Vertical Centrifugal Pump Based on Multi-Domain Characteristic Parameters

The marine vertical centrifugal pump is an important piece of auxiliary equipment for ships. Due to the complex operating conditions of marine equipment and the frequent swaying of the hull, typical pump failures such as rotor misalignment, rotor unbalance and mechanical loosening occur frequently, which seriously affect the service life of the marine vertical centrifugal pump. Based on multi-domain characteristic parameters, a fault identification method combining weighted kernel principal component analysis (WKPCA) and particle swarm optimization support vector machine (PSO-SVM) is proposed in this paper. It can effectively solve the problem of multi-fault classification of the centrifugal pump and provide reference for efficient maintenance of equipment. Firstly, a vertical centrifugal pump test bench is set up to simulate typical faults. The collected original fault data are denoised by Kalman filtering. Then, a multi-domain feature set composed of 20 feature parameters was constructed. However, due to high dimension, data redundancy and calculation time were increased. After dimensionality reduction, a fault feature set with 9 feature indexes was established by combining with the WKPCA method. Finally, the PSO-SVM model is used to realize multi-fault identification, and the recognition results of the traditional support vector machine and the genetic algorithm support vector machine (GA-SVM) are compared to verify the diagnosis results and classification performance of PSO-SVM. The results show that the accuracy of WKPCA and PSO-SVM fault recognition methods based on multi-domain characteristic parameters is 1, and it has good convergence.

KLASIFIKASI PENYAKIT HIPERTENSI MENGGUNAKAN METODE SVM GRID SEARCH DAN SVM GENETIC ALGORITHM (GA)

Hypertension is an abnormally high pressure that occurs inside the arteries. Hypertension increased by 8.3% from 2013 based on health research in 2018. Some of the factors that cause hypertension include gender, age, salt consumption, cigarette consumption, cholesterol levels and a family history of hypertension. The data in this study are data on normal and hypertensive patients at the Padangsari Health Center for the period of July – December 2021. This study will classify blood pressure with the aim of obtaining the results of the accuracy of the classification of the methods used. The method used in this study is a support vector machine (SVM). SVM is a well-known algorithm, producing optimal solutions to classification problems. SVM uses kernel functions for separable nonlinear data. The displacement kernels used in this study are linear and RBF. SVM has the disadvantage of determining the best parameters, to overcome these weaknesses developed the method of finding the best parameters. The search for the parameters of this study used grid search and genetic algorithm (GA). Grid search has the advantage of producing parameters that are close to the optimal value, while GA has the advantage of being easy to find global optimum values. This study will compare the classification results of the SVM grid search and SVM GA methods. The results of this study obtained the method that has the best accuracy, namely SVM grid search using a radial base function (RBF) kernel with an accuracy of 89.22%.

Combination of Metaheuristic Optimization Algorithms and Machine Learning Methods for Groundwater Potential Mapping

The groundwater contained in aquifers is among the most important water supply resources, especially in semi-arid and arid regions worldwide. This study aims to evaluate and compare the prediction capability of two well–known models, support vector machine (SVM) and adaptive neuro-fuzzy inference system (ANFIS), combined with a genetic algorithm (GA), invasive weed optimization (IWO), and teaching–learning-based optimization (TLBO) algorithms in groundwater potential mapping (GPM) the Azraq Basin in Jordan. The hybridization of the SVM and ANFIS models with the GA, IWO, and TLBO algorithms results in six models: SVM–GA, SVM–IWO, SVM–TLBO, ANFIS–GA, ANFIS–IWO, and ANFIS–TLBO. A database consisting of well data containing 464 wells with 12 predictive factors was developed for the groundwater potential mapping (GPM) of the study area. Of the 464 well locations, 70% (325 locations) were assigned for the training set and the rest (139 locations) for the validation set. The correlation between the 12 predictive factors and the well locations is analyzed using the frequency ratio (FR) statistical model. An area under receiver operating characteristic (AUROC) curve was used to evaluate and compare the models. According to the results, the SVM-based hybrid models outperformed other ANFIS hybrid models in the learning (training) and validation phases. The SVM–GA and SVM–TLBO hybrid models showed AUROC values of 0.984 and 0.971, respectively, in the training and validation phases. Moreover, the ANFIS–GA and ANFIS–TLBO hybrid models showed an AUROC of 0.979 and 0.984 in the training phase and an AUROC of 0.973 and 0.984 in the validation phase, respectively. The SVM–IWO and ANFIS–IWO hybrid models showed the lowest AUROC. This study demonstrated the more efficient results of the SVM-based hybrid models in comparison with the ANFIS-based hybrid models in terms of accuracy and modeling speed.

An Ensemble Stacking Algorithm to Improve Model Accuracy in Bankruptcy Prediction

Bankruptcy analysis is needed to anticipate bankruptcy. Errors in predicting bankruptcy often cause bankruptcy. Machine learning with high accuracy to analyze reversal must continuously improve its accuracy. Many machine learning models have been applied to predict bankruptcy. However, model improvisation is still needed to improve prediction accuracy. We propose a combination model to improve the accuracy of bankruptcy prediction based on a genetic algorithm-support vector machine (GA-SVM) and stacking ensemble method. This study uses the Taiwanese Bankruptcy dataset from the Taiwan Economic Journal. Then we implement a synthetic minority over-sampling technique for handling imbalanced datasets. We select the best feature using GA-SVM, adopt a new strategy by stacking the classifier, and use extreme gradient boosting as a meta-learner. The results show superior accuracy obtained by the stacking model-based GA-SVM with an accuracy of 99.58%. The accuracy obtained is higher than just applying a single classifier. Thus, this study shows that the proposed method can predict bankruptcy with superior accuracy.

Hole-Finding Learning Strategy for a Robot Assembly With Keyed Circular Peg

Taking the gear assembly of the reducer assembly line as a research background, the hole-finding strategy for robot assembly with keyed circular pegs is proposed to solve the problem of low hole-finding efficiency and success rate. in the circular hole-finding task, deviation domains were divided based on a static mechanism, position vector trajectory optimization in the step distance and direction was designed, and a deviation domain-force mapping relationship was established using a genetic algorithm-support vector machine (GA-SVM) classification algorithm; the accuracy of this algorithm is approximately 90.00%. Thirty groups completed the circular hole-finding task in an average time of 5.4 s. For the square hole-finding task, dual monocular cameras were integrated to identify corner points of the flat key and keyway. Image semantic segmentation based on deep learning was used for the corner-point recognition of the flat key to suppress the effect of changes in light intensity; the recognition has an average error of 0.39 mm. Coarse and fine adjustment circumferential deflection strategies were adopted sequentially. The 30 groups of square hole-finding tasks exhibited a 96.70% success rate in an average time of 10.2 s. The proposed hole-finding strategy improves the efficiency and success rate of the gear assembly.

Firefly-SVM predictive model for breast cancer subgroup classification with clinicopathological parameters.

Breast cancer is a highly predominant destructive disease among women characterised with varied tumour biology, molecular subgroups and diverse clinicopathological specifications. The potentiality of machine learning to transform complex medical data into meaningful knowledge has led to its application in breast cancer detection and prognostic evaluation. The emergence of data-driven diagnostic model for assisting clinicians in diagnostic decision making has gained an increasing curiosity in breast cancer identification and analysis. This motivated us to develop a breast cancer data-driven model for subtype classification more accurately. In this article, we proposed a firefly-support vector machine (SVM) breast cancer predictive model that uses clinicopathological and demographic data gathered from various tertiary care cancer hospitals or oncological centres to distinguish between patients with triple-negative breast cancer (TNBC) and non-triple-negative breast cancer (non-TNBC). The results of the firefly-support vector machine (firefly-SVM) predictive model were distinguished from the traditional grid search-support vector machine (Grid-SVM) model, particle swarm optimisation-support vector machine (PSO-SVM) and genetic algorithm-support vector machine (GA-SVM) hybrid models through hyperparameter tuning. The findings show that the recommended firefly-SVM classification model outperformed other existing models in terms of prediction accuracy (93.4%, 86.6%, 69.6%) for automated SVM parameter selection. The effectiveness of the prediction model was also evaluated using well-known metrics, such as the F1-score, mean square error, area under the ROC curve, logarithmic loss and precision-recall curve. Firefly-SVM predictive model may be treated as an alternate tool for breast cancer subgroup classification that would benefit the clinicians for managing the patient with proper treatment and diagnostic outcome.

QSAR Study of Larvicidal Phytocompounds as Anti-Aedes Aegypti by using GA-SVM Method

Aedes aegypti is one of the most dangerous mosquitoes that can cause several deadly diseases, such as dengue fever, Chikungunya, Zika, and jaundice with high mortality rate. For now, no specific drug has been found that can cure the disease caused by Aedes Aegypti. One possible solution for handling this problem is to inhibit the growth and development of Aedes aegypti larvae. This study aims to implement Genetic Algorithm-Support Vector Machine to develop Quantitative Structure-Activity Relationship model for identification larvicidal phytocompounds as anti-aedes-aegypti. Hyperparameter tuning was performed to improve the performance of the models. Based on the result, we found that the best model was developed by the RBF kernel with the value of and score are 0.64 and 0.64, respectively.

Assessing stroke rehabilitation degree based on quantitative EEG index and nonlinear parameters.

The assessment of motor function is critical to the rehabilitation of stroke patients. However, commonly used evaluation methods are based on behavior scoring, which lacks neurological indicators that directly reflect the motor function of the brain. The objective of this study was to investigate whether resting-state EEG indicators could improve stroke rehabilitation evaluation. We recruited 68 participants and recorded their resting-state EEG data. According to Brunnstrom stage, the participants were divided into three groups: severe, moderate, and mild. Ten quantitative electroencephalographic (QEEG) and five non-linear parameters of resting-state EEG were calculated for further analysis. Statistical tests were performed, and the genetic algorithm-support vector machine was used to select the best feature combination for classification. We found the QEEG parameters show significant differences in Delta, Alpha1, Alpha2, DAR, and DTABR (P < 0.05) among the three groups. Regarding nonlinear parameters, ApEn, SampEn, Lz, and C0 showed significant differences (P < 0.05). The optimal feature classification combination accuracy rate reached 85.3%. Our research shows that resting-state EEG indicators could be used for stroke rehabilitation evaluation.

Phytochemical analysis and antioxidant activity of eight cultivars of tea (Camellia sinensis) and rapid discrimination with FTIR spectroscopy and pattern recognition techniques

Background: Tea (Camellia sinensis L.O. Kuntze) is one of the most commonly consumed beverages globally, with several beneficial health effects. The composition of leaves is affected by different factors such as climate and tea cultivar. Methods: In this study, the total phenolic, flavonoid, and tannin contents, and antioxidant activities of eight cultivars of tea growing in Iran were determined. The epigallocatechin gallate (EGCG) contents were measured by high-performance liquid chromatography (HPLC) analysis. The Fourier-transform infrared (FT-IR) spectra were used to construct a supervised pattern recognition model using a genetic algorithm-support vector machine (GA-SVM) for the classification of cultivars. Results: The results indicated a wide variation of total phenolic content (178.04 to 316.09 mg gallic acid equivalents (GAE)/g extract). Also, the flavonoid contents ranged from 25.54 to 41.1 mg quercetin equivalents )QE(/g extract. All the samples had close tannin amounts (ranging from 40.32 to 45.90 mg as tannic acid equivalent (TAE)/g extract). There was a significant linear relationship among total phenolic and flavonoid contents and antioxidant properties. The cultivars DN, PK2, and C.Y.9 had the highest content of phenolic and flavonoid content as well as the best antioxidant activity. The EGCG contents were from 2.66 to 4.12%. The highest amount of EGCG was found in cultivars 282, PK2, and C.Y.9. The discriminative region of FT-IR spectra (1350-1650 cm-1) were selected using a GA-SVM. This model showed 100% sensitivity and specificity for training and test sets. Conclusion: The leaves phytochemical compositions and antioxidant effect are deeply dependent on the type of tea cultivars. The cultivars PK2 and C.Y.9 can be considered richer sources of polyphenols, especially EGCG. The eight different cultivars can be classified based on chemical components using the recorded FT-IR spectra.

QSAR Study on Aromatic Disulfide Compounds as SARS-CoV Mpro Inhibitor Using Genetic Algorithm-Support Vector Machine

COVID-19 is a type of pneumonia caused by the Severe Acute Respiratory Syndrome Coronavirus-2 (SARS-CoV-2). This virus causes severe acute respiratory syndrome and 2 million active cases of COVID-19 have been found worldwide. A new strain of the SARS-CoV-2 virus emerged that proved to be more virulent than its predecessor. Regarding the design of a new inhibitor for this strain, SARS-CoV Main Protease (Mpro) was used as the target inhibitor. In the in silico development, the Quantitative Structure-Activity Relationship (QSAR) method is commonly used to predict the biological activity of unknown compounds to improve the process of drug design of a disease, including COVID-19. In this study, we aim to develop a QSAR model to predict the activity of aromatic disulfide compounds as SARS-CoV Mpro inhibitors using Genetic Algorithm (GA) – Support Vector Machine (SVM). GA was used for feature selection, while SVM was used for model prediction. The used dataset is set of features of aromatic disulfide compounds, along with information on the toxicity activity. We found that the best SVM model was obtained through the implementation of the polynomial kernel with the value of R2­­train and R2test­ scores are 0.952 and 0.676, respectively.