Analysis of dissolved gases content in power transformer oil is very important to monitor transformer latent fault and ensure normal operation of entire power *** of dissolved gases content in power transformer oil is...
详细信息
Analysis of dissolved gases content in power transformer oil is very important to monitor transformer latent fault and ensure normal operation of entire power *** of dissolved gases content in power transformer oil is a complicated problem due to its nonlinearity and the small quantity of training *** vector machine (SVM) has been successfully employed to solve classification problem of nonlinearity and small ***,SVM has rarely been applied to diagnosis transformer fault by analysis the dissolved gases content in power *** this study,support vector machine is proposed to analysis dissolved gases content in power transformer oil,among which cross-validation is used to determine free parameters of support vector *** experimental data from the electric power company in Sichuan are used to illustrate the performance of proposed SVM *** experimental results indicate that the proposed SVM model can achieve very good diagnosis accuracy under the circumstances of small ***,the SVM model is a proper alternative for diagnosing power transformer fault.
Floating bottles is one of the most common pollutant of our water. As automatic monitoring is the basis of prompt and effective waste management, a new method of automatic machine image monitoring is proposed. The ori...
详细信息
Floating bottles is one of the most common pollutant of our water. As automatic monitoring is the basis of prompt and effective waste management, a new method of automatic machine image monitoring is proposed. The original image on the surface of the water is firstly segmented, then the segmented image is processed with 5 morphological operations including dilation, closing, skeleton, skeleton after dilation and skeleton after closing. Then 6 areas characteristics are extracted from the segmented images and the 5 morphological images. Finally, the need for the salvage of the floating bottles is identified with the 6 areas characteristics based on the KNN algorithm. There are 80 images used as training samples and 50 images used as test samples in the experiments. The results of the experiments show that compared with manual identification, the accuracy rates of the training samples and test samples are always 90% higher with different KNN algorithm parameters. This means that the method is effective for the automatic monitoring of floating bottles on the water surfaces and should be helpful for the automatic salvage of waste floating bottles.
According to a large number of studies, the internode length is sensitive to environmental stress. In the quality testing of tomato seedlings, optimization algorithm is proposed to extract tomato seedling stem node, u...
详细信息
According to a large number of studies, the internode length is sensitive to environmental stress. In the quality testing of tomato seedlings, optimization algorithm is proposed to extract tomato seedling stem node, using line scan algorithm to extract the main stem area, improve the accuracy of the main stem region selection, and finally through the bag of words model extract main stem node, this method has good robustness. Through the test, it is found that the accuracy of main stem node detection is lowest at fourth nodes, which is 81%.These results demonstrate that our method has the ability to evaluate the vigor of tomato seedlings quickly and accurately.
In the Philippines, according to Philippine Authority of Statistics, there is an imbalance between the student enrollment and student graduation. Almost half of the first-time freshmen full time students who began see...
详细信息
ISBN:
(纸本)9781450371803
In the Philippines, according to Philippine Authority of Statistics, there is an imbalance between the student enrollment and student graduation. Almost half of the first-time freshmen full time students who began seeking a bachelor's degree do not graduate on time. The study aims to utilize how Naïve Bayes algorithm - a data classification algorithm that is based on probabilistic analysis - can be used in educational data mining specifically in student graduation. The study is focused on the application of the Naïve Bayes algorithm in predicting student graduation by generating a model that could early predict and identify students who are prone of not having graduation on time, so proper remediation and retention policies can be formulated and implemented by institutions.
In a variety of text classification algorithm, KNN is a competitive one with simple implementation and high efficiency. However, with the expansion of the size of the text, the runtime of KNN will grow rapidly that ca...
详细信息
ISBN:
(纸本)9781424458219
In a variety of text classification algorithm, KNN is a competitive one with simple implementation and high efficiency. However, with the expansion of the size of the text, the runtime of KNN will grow rapidly that cannot be afford. In this paper, we improve the KNN by introducing the kd-tree storage structure and reducing the sample space through the sample clestering methods. And experiment shows that the runtime of improved KNN algorithm reduce apparently.
BackgroundAfter the World Health Organization declared the COVID-19 pandemic, the role of Vitamin D has become even more critical for people worldwide. The most accurate way to define vitamin D level is 25-hydroxy vit...
详细信息
BackgroundAfter the World Health Organization declared the COVID-19 pandemic, the role of Vitamin D has become even more critical for people worldwide. The most accurate way to define vitamin D level is 25-hydroxy vitamin D(25-OH-D) blood test. However, this blood test is not always feasible. Most data sets used in health science research usually contain highly correlated features, which is referred to as multicollinearity problem. This problem can lead to misleading results and overfitting problems in the ML training process. Therefore, the proposed study aims to determine a clinically acceptable ML model for the detection of the vitamin D status of the North Cyprus adult participants accurately, without the need to determine 25-OH-D level, taking into account the multicollinearity *** study was conducted with 481 observations who applied voluntarily to Internal Medicine Department at NEU Hospital. The classification performance of four conventional supervised ML models, namely, Ordinal logistic regression(OLR), Elastic-net ordinal regression(ENOR), Support Vector Machine(SVM), and Random Forest (RF) was compared. The comparative analysis is performed regarding the model's sensitivity to the participant's metabolic syndrome(MtS)'positive status, hyper-parameter tuning, sensitivities to the size of training data, and the classification performance of the *** to the presence of multicollinearity, the findings showed that the performance of the SVM(RBF) is obviously negatively affected when the test is examined. Moreover, it can be obviously detected that RF is more robust than other models when the variations in the size of training data are examined. This experiment's result showed that the selected RF and ENOR showed better performances than the other two models when the size of training samples was reduced. Since the multicollinearity is more severe in the small samples, it can be concluded that RF and ENOR are not affected by the prese
With the popularization of smart devices, the demand for mobile communication is increasing. The pursuit of stronger signals and faster transmission rates make effective value assessment and rational allocation of res...
详细信息
With the popularization of smart devices, the demand for mobile communication is increasing. The pursuit of stronger signals and faster transmission rates make effective value assessment and rational allocation of resources more important. In this paper, mobile communication value assessment problem is converted into base station classification problem with data, the high-value base station densely distributed area is the high-value mobile communication area. We have given a new value partitioning solution based on machine learning classification model, and on the real test set has achieved far better than the traditional method.
Control chart,the most representative statistical process control technique,can be considered to share a common goal with classification algorithms in that both of them aim at estimating the decision boundaries that c...
详细信息
Control chart,the most representative statistical process control technique,can be considered to share a common goal with classification algorithms in that both of them aim at estimating the decision boundaries that classify the observations into either in-control or the out-of-control *** main limitation that conventional control chart cannot take advantage of using out-of-control information can be eased by integrating classification algorithms with existing monitoring *** the present study,we proposed a hybrid scheme that combines T2 control chart and binary class classification algorithms by eliciting the nature of class *** and real case studies demonstrated that the proposed method can be effectively used for monitoring multivariate processes when their distributions are nonnormally distributed or unknown.
Decision tree is an important learning method in machine learning and data mining,this paper discusses the method of choosing the best attribute based on information *** analyzes the process and the characters of clas...
详细信息
Decision tree is an important learning method in machine learning and data mining,this paper discusses the method of choosing the best attribute based on information *** analyzes the process and the characters of classification and the discovery knowledge based on decision tree about the application of decision tree on data *** an instance, the paper shows the procedure of selecting the decision attribute in detail,finally it pointes out the developing trends of decision tree.
With the development of the global economy and customization,the manufacturing scheduling problem is increasingly *** job shops(FJSs) have to be more flexible and dynamic to handle these complex and various manufactur...
详细信息
With the development of the global economy and customization,the manufacturing scheduling problem is increasingly *** job shops(FJSs) have to be more flexible and dynamic to handle these complex and various manufacturing *** at the dynamic scheduling problem of FJS,a method of mining scheduling rules from scheduling related historical data with industrial big data characteristics is *** the mining of scheduling rules,an improved random forest algorithm is proposed,which is suitable for mining scheduling rules from historical data related to large-scale,high-dimensional,and noisy *** results show that the scheduling rules obtained by the mining method have good performance in terms of scheduling performance and computational efficiency.
暂无评论