GA-SVM Algorithm Research Articles

A new hybrid approach for grapevine leaves recognition based on ESRGAN data augmentation and GASVM feature selection

Grapevine leaf is a commodity that is collected only once a year and has a high return on investment due to its export. However, only certain types of grapevine leaves are consumed. Therefore, it is extremely important to distinguish the types of grapevine leaves. In particular, performing this process automatically on industrial machines will reduce human errors, workload, and thus cost. In this study, a new hybrid approach based on a convolutional neural network is proposed that can automatically distinguish the types of grapevine leaves. In the proposed approach, firstly, the overfitting of network models is prevented by applying data augmentation techniques. Second, new synthetic images were created with the ESRGAN technique to obtain detailed texture information. Third, the top blocks of the MobileNetV2 and VGG19 CNN models were replaced with the newly designed top block, effectively extracting features with the data. Fourthly, the GASVM algorithm was adapted and used to create a subset of the features to eliminate the ineffective and unimportant ones from the obtained features. Finally, SVM classification was performed with the feature subset consisting of 314 features, and approximately 2% higher accuracy and MCC score were obtained compared to the approaches in the literature.

Analysis of Network Security Countermeasures From the Perspective of Improved FS Algorithm and ICT Convergence

In this paper, the forward selection (FS) algorithm is introduced on the basis of information and communication technology, and the design of intrusion detection method for communication network is carried out. By studying the classification and detection pattern matching of communication network intrusion behavior, extracting the intrusion behavior features of communication network based on FS algorithm, and optimizing the intrusion detection and learning effect based on the limit learning machine, the intrusion behavior attributes of communication network are clarified, and a new detection method is proposed to solve the problems of low detection accuracy and low recall in the current intrusion behavior detection of complex communication network environments. Compared with the intrusion detection method based on GA-SVM algorithm, the accuracy of the detection results reaches 94.23%, and the recall rate exceeds 97%, which is obviously better than the 85% accuracy and 75% recall rate of the traditional detection method, which can ensure the security of the communication network environment. In addition, this paper proposes the APDR dynamic comprehensive information security assurance system model, which has considerable flexibility and can respond to current network security requirements.

Evaluation and analysis of teaching quality of university teachers using machine learning algorithms

Abstract In order to better improve the teaching quality of university teachers, an effective method should be adopted for evaluation and analysis. This work studied the machine learning algorithms and selected the support vector machine (SVM) algorithm to evaluate teaching quality. First, the principles of selecting evaluation indexes were briefly introduced, and 16 evaluation indexes were selected from different aspects. Then, the SVM algorithm was used for evaluation. A genetic algorithm (GA)-SVM algorithm was designed and experimentally analyzed. It was found that the training time and testing time of the GA-SVM algorithm were 23.21 and 7.25 ms, both of which were shorter than the SVM algorithm. In the evaluation of teaching quality, the evaluation value of the GA-SVM algorithm was closer to the actual value, indicating that the evaluation result was more accurate. The average accuracy of the GA-SVM algorithm was 11.64% higher than that of the SVM algorithm (98.36 vs 86.72%). The experimental results verify that the GA-SVM algorithm can have a good application in evaluating and analyzing teaching quality in universities with its advantages in efficiency and accuracy.

A genetic algorithm-based support vector machine to estimate the transverse mixing coefficient in streams

Abstract Transverse mixing coefficient (TMC) is known as one of the most effective parameters in the two-dimensional simulation of water pollution, and increasing the accuracy of estimating this coefficient will improve the modeling process. In the present study, genetic algorithm (GA)-based support vector machine (SVM) was used to estimate TMC in streams. There are three principal parameters in SVM which need to be adjusted during the estimating procedure. GA helps SVM and optimizes these three parameters automatically in the best way. The accuracy of the SVM and GA-SVM algorithms along with previous models were discussed in TMC estimation by using a wide range of hydraulic and geometrical data from field and laboratory experiments. According to statistical analysis, the performance of the mentioned models in both straight and meandering streams was more accurate than the regression-based models. Sensitivity analysis showed that the accuracy of the GA-SVM algorithm in TMC estimation significantly correlated with the number of input parameters. Eliminating the uncorrelated parameters and reducing the number of input parameters will reduce the complexity of the problem and improve the TMC estimation by GA-SVM.

Geographical traceability of Eucommia ulmoides leaves using attenuated total reflection Fourier transform infrared and ultraviolet-visible spectroscopy combined with chemometrics and data fusion

Eucommia ulmoides is one of valuable cash crops and its leaves are a high-quality raw industrial material with great development potential. Geographical variation is the main factor leading to differences in chemical composition of Eucommia ulmoides leaves (EULs). In this study, a total of 159 samples from 13 provinces in China including male and female individuals as well as various elevation ranges were systematically conducted using fusion data, attenuated total reflection Fourier transformation mid-infrared (ATR-FTIR) and ultraviolet-visible (UV–vis) spectra, coupled to chemometrics. Two classification models, partial least squares discrimination analysis (PLS-DA) and support vector machine (SVM), were established based on individual spectra and multi-spectral fused information, respectively. Comparatively, the SVM model based on genetic algorithm (GA) searching for optimal parameters had the best performance for distinguishing different origin samples with 100 % accuracy rates in calibration and validation sets. Furthermore, hierarchical cluster analysis (HCA) was used for investigating the influence caused by the difference in gender and altitude based on low-level fusion data. The result showed that the effect of individual gender on chemical information of EULs was less than the influence of geographical factors. Meanwhile, an interesting focus was that the PLS-DA scores plot and dendrogram suggested that the chemical profiles of these samples in Jiangxi Province (region 8) was significantly different from other regions because of the green circular economy mode. This study indicated that the PLS-DA and GA-SVM algorithm could be developed as an excellent model in geographical traceability on the basis of mid-level (latent variables, LVs) data fusion with two spectral datasets. Such comprehensive utilization model under the circular industry economy should be recommended.

Competition prediction and fitness behavior based on GA-SVM algorithm and PCA model

Competition prediction and fitness behavior based on GA-SVM algorithm and PCA model

Stability Analysis of Power System Based on GA-SVM

Aiming at the problems of long calculation time and stable stability of power system stability analysis, a GA-SVM algorithm is proposed to analyze the stability of power system. Firstly, the mathematical model is used to describe the power system. The GA algorithm is used to optimize the nonlinear regression SVM parameters. The stability of the power system is simulated and the accuracy and speed under different load levels are verified. The simulation results show that the proposed algorithm has good efficiency, good reliability and high engineering practicability.

GA-SVM Algorithm for Improving Land-Cover Classification Using SAR and Optical Remote Sensing Data

Multisource remote sensing data have been widely used to improve land-cover classifications. The combination of synthetic aperture radar (SAR) and optical imagery can detect different land-cover types, and the use of genetic algorithms (GAs) and support vector machines (SVMs) can lead to improved classifications. Moreover, SVM kernel parameters and feature selection affect the classification accuracy. Thus, a GA was implemented for feature selection and parameter optimization. In this letter, a GA-SVM algorithm was proposed as a method of classifying multifrequency RADARSAT-2 (RS2) SAR images and Thaichote (THEOS) multispectral images. The results of the GA-SVM algorithm were compared with those of the grid search algorithm, a traditional method of parameter searching. The results showed that the GA-SVM algorithm outperformed the grid search approach and provided higher classification accuracy using fewer input features. The images obtained by fusing RS2 data and THEOS data provided high classification accuracy at over 95%. The results showed improved classification accuracy and demonstrated the advantages of using the GA-SVM algorithm, which provided the best accuracy using fewer features.

Prediction of Postpartum Hemorrhage Volume of Pregnant Women Based on GA-SVM Algorithm

To take most advantage of the medical data resources from maternal and child health information platform and to improve the medical level, the team bring up a method based on support vector machine (SVM) algorithm which is aimed at predicting blood flow and blood pressure within 2-24 hours after parturition. We cleaned up the extracted data, determine the linear correlation via Pearson correlation coefficient, and utilize the significance to test and justify the relevance of data. Also, genetic algorithm is used to optimize the parameters. Then, we filter out the data with strong correlation coefficient and make predictions through the SVM algorithm. Finally, we determine the effectiveness of the prediction by doing the comparison between predicted results and the real data. The experiments show that, SVM is valid and feasible for the prediction of postpartum hemorrhage and the blood pressure.

Detection of moldy core in apples and its symptom types using transmittance spectroscopy

Abstract: A detection method based on transmittance spectroscopy and support vector machine (SVM) was proposed to achieve rapid nondestructive detection of moldy core in apples. A visible to near-infrared (Vis/NIR) spectroradiometer was used for scanning transmittance spectra of 215 apple samples in the wavelength range of 200-1025 nm. Wavelet transform was used to reduce the dimensionality of the spectra and extract wavelet coefficients. Two classification algorithms including artificial neural network (ANN) and SVM were used to develop models whose parameters were optimized by genetic algorithms (GA) for determination of the presence and types of moldy core in apples. Comparisons results of the models showed that the GA-SVM model obtained the optimal result with an accuracy of 96.92% for detecting the presence of moldy core and 81.48% for distinguishing symptom types of the disease. These results indicate that it is feasible to detect moldy core in apples nondestructively and rapidly based on transmittance spectroscopy and that wavelet transform is an effective method for extraction of characteristics from spectra. Moreover, the GA-SVM algorithm in conjunction with Vis/NIR transmittance spectroscopy can accurately achieve fast and nondestructive detection of the presence and types of moldy core in apples. Keywords: moldy core of apples, transmittance spectrum, wavelet transform, support vector machine, genetic algorithm, symptom types DOI: 10.3965/j.ijabe.20160906.2235 Citation: Zhou Z Y, Lei Y, Su D, Zhang H H, He D J, Yang C H. Detection of moldy core in apples and its symptom types using transmittance spectroscopy. Int J Agric & Biol Eng, 2016; 9(6): 148－155.

Application of Teaching Quality Assessment Based on Parallel Genetic Support Vector Algorithm in the Cloud Computing Teaching System

With the rapid development of China's economy in recent years, the scale of students has expanded gradually, which has led to many new problems, including the problems of the quality and the quantity of teachers, and the teaching facilities being insufficient. The assessment of teaching quality is one of the most important aspects of teaching management, which come to the attention of every university. Therefore, it has become the current focus in the research of university teaching. At the same time, the traditional method of teaching quality assessment has not been able to deal with the phenomenon of big data in the field of education. As a new technology, cloud computing provides a broad space for the development of a new model in the aspects of hardware environment construction, software resource development, network teaching implementation and personal knowledge management. In order to effectively deal with the challenges of big data processing in the field of education, this paper proposes a GA-SVM teaching quality assessment algorithm which is based on MapReduce. Through the design of a map function and reduce function, this paper realizes the parallelization of the GA-SVM algorithm and the selection of the main parameters. Secondly, this paper uses a genetic algorithm to optimize the penalty coefficient and kernel parameters of SVM, and then solves the problem of difficulty in determining the parameters of support vectors. In addition, we improve the sensitivity of the search through the method of logarithmic transformation, and speed up the convergence rate of the GA model. Finally, we compare the parallel algorithm and the serial algorithm on the Hadoop platform. The results of experiments show that the GA-SVM based on MapReduce is suitable for teaching quality assessment under the environment of big data.

A GASVM Algorithm for Predicting Protein Structure Classes

The research methods of protein structure prediction mainly focus on finding effective features of protein sequences and developing suitable machine learning algorithms. But few people consider the importance of weights of features in classification. We propose the GASVM algorithm (classification accuracy of support vector machine is regarded as the fitness value of genetic algorithm) to optimize the coefficients of these 16 features (5 features are proposed first time) in the classification, and further develop a new feature vector. Finally, based on the new feature vector, this paper uses support vector machine and 10-fold cross-validation to classify the protein structure of 3 low similarity datasets (25PDB, 1189, FC699). Experimental results show that the overall classification accuracy of the new method is better than other methods.