As a place with extremely high safety protection factor,substations are often *** the current substations are equipped with various technical defense systems,the lack of correlation between the various systems results...
详细信息
As a place with extremely high safety protection factor,substations are often *** the current substations are equipped with various technical defense systems,the lack of correlation between the various systems results in a high rate of false alarms and false *** the safety of substations can be achieved by accurately identifying the attributes of objects in the alarm area,reducing the rate of false alarms and false *** identifying the attributes of objects is of great significance for the safety protection of *** response to such problems,this paper proposes a substation alarm area property recognition based on the svm algorithm,which integrates multiple independent information of video,sound,radar and thermal imaging to obtain multi-dimensional information of the object,and adopts a combination of feature engineering and machine learning *** intrusion object recognition classification algorithm realizes the object recognition in the alarm area of the *** experimental analysis,it is verified that the method proposed in this paper can accurately identify the attributes of objects and provide strong support and guarantee for the safety protection of substations..
INTRODUCTION: With the rapid development of virtual reality (VR) technology, digital displays have become increasingly important in various fields. This study aims to improve the application of virtual reality technol...
详细信息
INTRODUCTION: With the rapid development of virtual reality (VR) technology, digital displays have become increasingly important in various fields. This study aims to improve the application of virtual reality technology in the visual design of digital displays by improving the support vector machine (svm) algorithm. The visual design of digital displays is crucial for attracting users, enhancing experience and conveying information, so an accurate and reliable algorithm is needed to support relevant decisions. OBJECTIVES: The purpose of this study is to improve the svm algorithm to more accurately identify features related to the visual design of digital displays. By exploiting the nonlinear mapping and parameter optimization of the svm algorithm, it aims to improve the performance of the model so that it can better adapt to complex visual design scenarios. METHODS: In the process of achieving the objective, multimedia data related to digital displays, including images and videos, were first collected. Through feature engineering, features closely related to visual design were selected, and deep learning techniques were applied to extract higher-level feature representations. Subsequently, the svm algorithm was improved to use the kernel function for nonlinear mapping, and the penalty parameters and the parameters of the kernel function were adjusted. Cross-validation was used in the training and testing phases of the model to ensure its generalization performance. RESULTS: The improved svm algorithm demonstrated higher accuracy, recall and precision compared to the traditional method by evaluating it on the test set. This suggests that the model is able to capture visual design features in digital displays more accurately and provide more reliable support for relevant decisions. CONCLUSION: This study demonstrates that by improving the svm algorithm, more accurate visual design can be achieved in digital displays of virtual reality technology. This improvement pro
In this paper, a new sustainable development model of new culture in rural community based on svm intelligent algorithm is provided. Through nonlinear mapping, economic and cultural factors are grouped together, compr...
详细信息
ISBN:
(纸本)9781509048687
In this paper, a new sustainable development model of new culture in rural community based on svm intelligent algorithm is provided. Through nonlinear mapping, economic and cultural factors are grouped together, comprehensive consideration of various factors, vegetation selection and cultural infrastructure construction site, the results show the model is more effective.
In track and field sports, footwork can greatly affect the effect and performance of sports. Accurate footwork can effectively improve the performance of professional athletes, and for ordinary trainers, it can reduce...
详细信息
In track and field sports, footwork can greatly affect the effect and performance of sports. Accurate footwork can effectively improve the performance of professional athletes, and for ordinary trainers, it can reduce the probability of training injuries. To solve the problem that traditional footwork is inaccurate and not well accepted by people, this paper has used an image processing method based on support vector machine (svm) algorithm to identify and track the footwork. In this paper, a 13-s video image was extracted frame by frame from the athletes' videos in Olympic sports competitions, and the athletes' footwork was used as a benchmark to track their motion trajectories, extracting the corresponding feature points and categorizing them. 10 school athletes, 6 males and 4 females, were selected to track their movement pace and trajectory with a camera. The behaviors were standardized according to the extracted features, and the behaviors before and after standardization were compared. The results showed that the svm algorithm had the most stable classification accuracy, higher recognition accuracy and better performance compared with other classification algorithms. Image processing of standardized track and field movements was effective in improving athletes' performance, with all 10 athletes tested improving their performance between 0.4 and 0.6. The svm algorithm-based image processing method is more acceptable after validation of its effectiveness, and the method can be extended more easily.
This paper suggests extended algorithms for multilevel trans-Z-source inverter. These algorithms are based on space vector modulation (svm), which works with high switching frequency and does not generate the mean val...
详细信息
This paper suggests extended algorithms for multilevel trans-Z-source inverter. These algorithms are based on space vector modulation (svm), which works with high switching frequency and does not generate the mean value of the desired load voltage in every switching interval. In this topology the output voltage is not limited to dc voltage source similar to traditional cascaded multilevel inverter and can be increased with trans-Z-network shoot-through state control. Besides, it is more reliable against short circuit, and due to several number of dc sources in each phase of this topology, it is possible to use it in hybrid renewable energy. Proposed svm algorithms include the following: Combined modulation algorithm (SVPWM) and shoot-through implementation in dwell times of voltage vectors algorithm. These algorithms are compared from viewpoint of simplicity, accuracy, number of switching, and THD. Simulation and experimental results are presented to demonstrate the expected representations. (C) 2015 Faculty of Engineering, Ain Shams University. Production and hosting by Elsevier B.V. This is an open access article under the CC BY-NC-ND license (http://***/licenses/by-nc-nd/4.0/).
In order to improve the recognition rate and stability of dynamic hand gesture recognition, for the low accuracy rate of the classical HMM algorithm in train the B parameter, this paper proposed an improved HMM/svm dy...
详细信息
ISBN:
(纸本)9781628418972
In order to improve the recognition rate and stability of dynamic hand gesture recognition, for the low accuracy rate of the classical HMM algorithm in train the B parameter, this paper proposed an improved HMM/svm dynamic gesture recognition algorithm. In the calculation of the B parameter of HMM model, this paper introduced the svm algorithm which has the strong ability of classification. Through the sigmoid function converted the state output of the svm into the probability and treat this probability as the observation state transition probability of the HMM model. After this, it optimized the B parameter of HMM model and improved the recognition rate of the system. At the same time, it also enhanced the accuracy and the real-time performance of the human-computer interaction. Experiments show that this algorithm has a strong robustness under the complex background environment and the varying illumination environment. The average recognition rate increased from 86.4% to 97.55%.
In this paper we suggest the self-tuning multiobjective genetic algorithm (STMGA) based on the NSGA-II. This new algorithm is aimed to improve the svm classification quality. The quality classification indicators such...
详细信息
In this paper we suggest the self-tuning multiobjective genetic algorithm (STMGA) based on the NSGA-II. This new algorithm is aimed to improve the svm classification quality. The quality classification indicators such as overall accuracy, specificity, sensitivity and a number of support vectors represent the objective functions in the STMGA. The ways for realizing the self-tuning of the such STMGA parameters as the crossover probability, the crossover distribution index and the mutation distribution index have been proposed and investigated. The considered STMGA is more flexible in the context of selecting its parameters' values and allows to refuse from the use of the parameters' values which are set manually. In the case of the radial basis kernel function used for the svm classifier development, the STMGA finds the Pareto-front of such parameters values as the regularization parameter value and the Gaussian kernel parameter value which give the best values in the chosen set of the classification quality indicators. The experimental results obtained on the basis of the model and real datasets of loan scoring, medical and technical diagnostics, etc. confirm the efficiency of the proposed STMGA. (C) 2019 The Authors. Published by Elsevier B.V.
The aim of this work is to improve the results of the svm classification (Support Vector Machine) by hybridizing the svm classifier with the random forest classifier (Random Forest, RF) used as the auxiliary. Specific...
详细信息
The aim of this work is to improve the results of the svm classification (Support Vector Machine) by hybridizing the svm classifier with the random forest classifier (Random Forest, RF) used as the auxiliary. Specification of the classification decisions obtained on the basis of the svm classifier is performed for the objects located in the experimentally determined subareas near the hyperplane separating the classes and including both correctly and erroneously classified objects. In the case of improving the quality of the objects classification from the initial dataset, the proposed hybrid approach to the objects classification can be recommended for classification of new objects. When developing the svm classifier, the fixed default parameters values are used. A comparative analysis of the classification results obtained during the computational experiments in the hybridization of the svm classifier with two auxiliary classifiers the random forest classifier (RF classifier) and the k nearest neighbor classifier (kNN classifier), for which the parameters values are determined randomly, confirms the expediency of using of these classifiers to increase the svm classification quality. It was found that in most cases, the random forest classifier works better in terms of improving the svm classification quality in comparison with the kNN classifier. (C) 2019 The Authors. Published by Elsevier B.V.
Based on the principle that the same class is adjacent, an anomaly intrusion detection method based on K-means and Support Vector Machine (svm) is presented. In order to overcome the disadvantage that k-means algorith...
详细信息
ISBN:
(纸本)9783037852828
Based on the principle that the same class is adjacent, an anomaly intrusion detection method based on K-means and Support Vector Machine (svm) is presented. In order to overcome the disadvantage that k-means algorithm requires initializing parameters, this paper proposes an improved K-means algorithm with a strategy of adjustable parameters. According to the location of wireless sensor networks (WSN), we can obtain clustering results by applying improved K-means algorithm to WSN, and then svm algorithm is applied to different clusters for anomaly intrusion detection. Simulation results show that the proposed method can detect abnormal behaviors efficiently and has high detection rate and low false positive rate than the current typical intrusion detection schemes of WSN.
The aim of this work is to improve the results of the svm classification (Support Vector Machine) by hybridizing the svm classifier with the random forest classifier (Random Forest, RF) used as the auxiliary. Specific...
详细信息
The aim of this work is to improve the results of the svm classification (Support Vector Machine) by hybridizing the svm classifier with the random forest classifier (Random Forest, RF) used as the auxiliary. Specification of the classification decisions obtained on the basis of the svm classifier is performed for the objects located in the experimentally determined subareas near the hyperplane separating the classes and including both correctly and erroneously classified objects. In the case of improving the quality of the objects classification from the initial dataset, the proposed hybrid approach to the objects classification can be recommended for classification of new objects. When developing the svm classifier, the fixed default parameters values are used. A comparative analysis of the classification results obtained during the computational experiments in the hybridization of the svm classifier with two auxiliary classifiers – the random forest classifier (RF classifier) and the k nearest neighbor classifier ( k NN classifier), for which the parameters values are determined randomly, confirms the expediency of using of these classifiers to increase the svm classification quality. It was found that in most cases, the random forest classifier works better in terms of improving the svm classification quality in comparison with the k NN classifier.
暂无评论