Bing Xia Li

Bio: Bing Xia Li is an academic researcher from North China Electric Power University. The author has contributed to research in topics: Environmental chemistry & Support vector machine. The author has an hindex of 1, co-authored 1 publications receiving 3 citations.

The Application of an Improved Integration Algorithm of Support Vector Machine to the Prediction of Network Security Situation

Abstract: In order to grasp the security situation of the network accurately and provide effective information for managers of network.GeesePSOSEN-SVM algorithm is proposed in this paper. It can produce and train multiple independent SVM through Bootstrap method and increase the degree of difference among SVM based on learning theories of negative correlation to construct the fitness function.GeesePSO algorithm is used to calculate the optimal weights of SVM.The algorithm chooses the high weights of SVM to integrate. At last, through the experiment on MATLAB for network security situational prediction,the results show that the absolute prediction error is smaller ,and the right trend rate is higher.

Distribution and Ecological Risk Assessment of Pharmaceuticals and Personal Care Products in Sediments of North Canal, China

Abstract: The pollution of water bodies by pharmaceuticals and personal care products (PPCPs) has attracted widespread concern due to their widespread use and pseudo-persistence, but their effects on sediments are less known. In this study, solid-phase extraction-high performance liquid chromatography–tandem mass spectrometry (SPE-LC/MSMS) was used to investigate the occurrence and ecological risks of five typical pharmaceuticals and personal care products (PPCPs) in thirteen key reservoirs, sluices, dams, and estuaries in the Haihe River Basin. At the same time, the PPCP exchanges of surface water, groundwater, and sediments in three typical sections were studied. Finally, the PPCP’s environmental risk is evaluated through the environmental risk quotient. The results showed that the five PPCPs were tri-methoprazine (TMP), sinolamine (SMX), ibuprofen (IBU), triclosan (TCS), and caffeine (CAF). The average concentration of these PPCPs ranged from 0 to 481.19 μg/kg, with relatively high concentrations of TCS and CAF. The relationship between PPCPs in the surface sediments was analyzed to reveal correlations between SMX and TMP, CAF and IBU, CAF and TCS. The risk quotients (RQ) method was used to evaluate the ecological risk of the five detected PPCPs. The major contributors of potential environmental risks were IBU, TCS and CAF, among which all the potential environmental risks at the TCS samples were high risk. This study supplemented the research on the ecological risk of PPCPs in sediments of important reaches of the North Canal to reveal the importance of PPCP control in the North Canal and provided a scientific basis for pollution control and risk prevention of PPCPs.

Algorithm of Support Vector Machine Ensemble Based on Negative Correlation Learning

Abstract: This paper presents a constructive algorithm for training negative correlation support vector machines (SVMs) ensembles. This approach can produce individual SVMs whose errors tend to be negatively correlated, so the diversity is emphasized among individual SVMs in an ensemble. Kernel function and its parameters of individual SVMs can be selected automatically with evolutionary strategy. Simulation shows that this method can not only solve model selection problem of SVM, but also improve SVM generalization performance effectively with small cost.

Herbicides in Water Sources: Communicating Potential Risks to the Population of Mangaung Metropolitan Municipality, South Africa

Abstract: Pesticides are an important tool for maintaining and improving the global population’s standard of living. However, their presence in water resources is concerning due to their potential consequences. Twelve water samples from rivers, dams/reservoirs, and treated drinking water were collected from Mangaung Metropolitan Municipality in South Africa. The collected samples were analysed using high-performance liquid chromatography linked to a QTRAP hybrid triple quadrupole ion trap mass spectrometer. The ecological and human health risks were assessed by risk quotient and human health risk assessment methods, respectively. Herbicides, such as atrazine, metolachlor, simazine and terbuthylazine, were analysed in water sources. The average concentrations of simazine in rivers (1.82 mg/L), dams/reservoirs (0.12 mg/L), and treated drinking water (0.03 mg/L) were remarkable among all four herbicides detected. Simazine, atrazine, and terbuthylazine posed high ecological risks for both acute and chronic toxicity in all water sources. Moreover, simazine is the only contaminant in the river water that poses a medium carcinogenic risk to adult. It can be concluded that the level of herbicide detected in water sources may affect aquatic life and human beings negatively. This study may aid in the development of pesticide pollution management and risk reduction strategies within the municipality.

A Network Security Situation Awareness Method Based on GRU in Big Data Environment

Abstract: Aiming at the “bottleneck” problems of the traditional network security situation awareness model, such as large equipment limitations, single data source and poor integration ability, weak level of autonomous learning and data mining, a network security situation awareness framework suitable for big data is constructed. A gate recurrent unit (GRU) model is established to effectively extract features from the situation data set through the deep learning algorithm of big data. It is a method to automatically mine and analyze the hidden relationship and change trend of network security situation, realize the high-speed acquisition and fusion of massive multi-source heterogeneous data, and perceive the network security situation from an all-round perspective. The experimental results show that this method has a good awareness effect on network threats, and has strong representation ability in the face of network threats. It can effectively perceive the network threat situation without relying on data labels, which verifies that this method can effectively improve the efficiency and accuracy of security situation awareness.