Leak Detection in Water Pipes Based on Maximum Entropy Version of Least Square Twin K-Class Support Vector Machine

Numerous novel improved support vector machine (SVM) methods are used in leak detection of water pipelines at present. The least square twin K-class support vector machine (LST-KSVC) is a novel simple and fast multi-classification method. However, LST-KSVC has a non-negligible drawback that it assigns the same classification weights to leak samples, including outliers that affect classification, these outliers are often situated away from the main leak samples. To overcome this shortcoming, the maximum entropy (MaxEnt) version of the LST-KSVC is proposed in this paper, called the MLT-KSVC algorithm. In this classification approach, classification weights of leak samples are calculated based on the MaxEnt model. Different sample points are assigned different weights: large weights are assigned to primary leak samples and outliers are assigned small weights, hence the outliers can be ignored in the classification process. Leak recognition experiments prove that the proposed MLT-KSVC algorithm can reduce the impact of outliers on the classification process and avoid the misclassification color block drawback in linear LST-KSVC. MLT-KSVC is more accurate compared with LST-KSVC, TwinSVC, TwinKSVC, and classic Multi-SVM.

Improved support vector machine algorithm based on the influence of Gestational Diabetes Mellitus on the outcome of perinatal outcome by ultrasound imaging

Objectives: In order to understand the incidence and epidemiological characteristics of gestational diabetes mellitus, the ultrasound imaging of support vector machine processing algorithm was used to clarify the outcome of maternal and neonatal gestational diabetes mellitus. Methods: This study selected clinical data of 12,190 pregnant women who were hospitalized for delivery, and were divided into diabetic group (1268 cases) and control group (10922 cases) according to the diagnosis of gestational diabetes. The study was conducted from January 1, 2012 to December 31, 2019. Colour Doppler ultrasound was performed to record fatal umbilical artery and brain the middle arteries and uterine arteries which are effective indicators of measuring fatal intrauterine conditions. Chi-square test was used to compare the rates between groups, and multivariate logistic regression was used for labour outcomes. Results: The incidence of diabetes during pregnancy is about 10.4% (1268/12190). Senior citizens and women suffering from obesity increase the risk of gestational diabetes, maternal hypertension disorders in pregnancy, premature rupture of membranes, oligohydramnios, fatal distress, multiple births, malpresentation risk increased significantly (P<0.05) than the control group. In gestational diabetes caesarean section rate was significantly higher (61.0% vs46.4%). Caesarean new born 5-minute Apgar score was significantly lower than the control group (P<0.05). Conclusion: In maternal gestational diabetes in high risk pregnancies, complications of pregnancy significantly increase the importance of enhancing weight management and blood glucose monitoring to reduce complications. doi: https://doi.org/10.12669/pjms.37.6-WIT.4855 How to cite this:Liu H, Liu J. Improved support vector machine algorithm based on the influence of Gestational Diabetes Mellitus on the outcome of perinatal outcome by ultrasound imaging. Pak J Med Sci. 2021;37(6):1625-1629. doi: https://doi.org/10.12669/pjms.37.6-WIT.4855 This is an Open Access article distributed under the terms of the Creative Commons Attribution License (http://creativecommons.org/licenses/by/3.0), which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

Research on Abnormal Behavior Recognition of Buses Based on Improved Support Vector Machine

The abnormal driving behavior of buses brings about greater security threat. How to effectively identify the abnormal driving behavior of buses has become one of the problems of cracking public transportation safety. This paper constructs an abnormal behavior recognition model of buses based on improved support vector machine. Through the verification, the model has a high recognition rate, which provides an important means for further improving the safety of public transportation operations.

Stability Evaluation of Rock Slope in Hydraulic Engineering Based on Improved Support Vector Machine Algorithm

The safety problem of the slope has always been an important subject in engineering geology, which has a wide range of application background and practical significance in reality. How to correctly evaluate the stability of the slope and obtain the parameters of the slope has always been the focus of research and production personnel at home and abroad. In recent years, various artificial intelligence calculation methods have been applied to the field of rock engineering and engineering geology, providing some new ideas for the solution of slope stability analysis and parameter back analysis. Support vector machine (SVM) algorithm has unique advantages and generalization in dealing with finite samples and highly complex and nonlinear problems. At present, it has become a research hotspot of intelligent methods and has been widely paid attention to in various application fields of slope engineering. In this paper, a cuckoo search algorithm-improved support vector machine (CS-SVM) method is applied to slope stability analysis and parameter inversion. Aiming at the problem of selecting kernel function parameters and penalty number of SVM, a method of using cuckoo search algorithm to improve support vector machine was proposed, and the global optimization ability of cuckoo search algorithm was used to improve the algorithm. Aiming at the slope samples collected, the classification algorithm of support vector machine (SVM) was used to identify the stable state of the test samples, and the improved SVM algorithm was used to analyze the safety factor of the test samples. The results show that the proposed method is reasonable and reliable. Based on the inversion of the permeability coefficient of the test samples by the improved support vector machine, the comparison between the inversion value and the theoretical value shows that it is basically feasible to invert the permeability coefficient of the dam slope by the improved support vector machine.

Improved support vector machine model in the prediction of tuberculosis incidence

Tuberculosis, as a more common infectious disease with serious physical damage to humans, has been relatively vacant in predictive model research. In order to improve the accuracy of pulmonary tuberculosis, this study combined the incidence of tuberculosis, collected data using data collection methods, used a single data model for predictive analysis, and compared with the actual situation. At the same time, through the comparative analysis, the paper draws the shortcomings of the traditional single model algorithm, constructs a combined model for the prediction of tuberculosis, and collects the incidence of tuberculosis. In addition, this paper draws it into a statistical chart, and analyzes its pathological characteristics and the dynamic trend of the onset. Through experimental research, it can be seen that the prediction accuracy of the combined model of this study is high, which can provide theoretical reference for subsequent related research.