The production and use of organochlorine pesticides (OCPs) for agricultural and industrial applications result in high levels of their residues, posing a significant risk to environmental and human health. At present, there are many techniques for OCP-contaminated soil remediation. However, the remediation of contaminated sites may suffer from a series of problems, such as a long recovery cycle, high costs, and secondary pollution, all of which could affect land redevelopment and reuse. Therefore, the selection of an appropriate technology is crucial for contaminated sites. In order to improve and support decision-making for the selection of remediation techniques, we provide a decision-making strategy for the screening of remediation techniques of OCP-contaminated sites. The screening procedure is proposed based on combining the analytic hierarchy process (AHP) and the technique for order preference by similarity to ideal solution (TOPSIS). The screening indexes include economic indicator, environmental indicator, and technical indicator. The assessment results show that co-processing in cement kiln obtained the highest overall score and was thus considered to be the most sustainable option. This suggested remediation technology was similar to the practical remediation project, indicating that the screening method could be applied for the selection of remediation technologies for sites contaminated with persistent organic pollutants.
Soil pollution has become one of the most important environmental issues in China. It is very important to evaluate soil environmental quality comprehensively and objectively. This paper proposes a soil environment quality assessment model based on the Driving Force-Pressure-State-Impact-Response (DPSIR) model and data fusion. At first, 18 evaluation indicators are selected, including complex indexes, such as the industrialization index, heavy metal pollution index, organic pollution index, potential ecological risk index, and human health risk index, and single indexes such as population density, fertilizer/pesticide application intensity, annual average air quality index, etc. Then, hierarchical analysis model is constructed, and the weight of each indicator is calculated based on Analytic Hierarchy Process (AHP) method. According to the quartile of indicator values of 32 provincial administrative divisions on the Chinese mainland, the values of each indicator are standardized and graded. Finally, the soil environmental quality index (SEQI) is calculated by the weighted average of the standard values of the 18 indicators. The assessment model is then applied in evaluating soil quality of Hebei Province, China. The results show that the soil environmental quality of Hebei’s agricultural land is in a medium state, and the industrial land is approaching the alert state. The pressure of soil pollution mainly comes from the discharge of industrial pollutants and the application of pesticides and fertilizers. Soil pollutants, such as lead, copper, zinc, benzo[a]pyrene, and benzo[a] should be especially controlled.
Supervised topic modeling has been successfully applied in the fields of document classification and tag recommendation in recent years. However, most existing models neglect the fact that topic terms have the ability to distinguish topics. In this paper, we propose a term frequency-inverse topic frequency (TF-ITF) method for constructing a supervised topic model, in which the weight of each topic term indicates the ability to distinguish topics. We conduct a series of experiments with not only the symmetric Dirichlet prior parameters but also the asymmetric Dirichlet prior parameters. Experimental results demonstrate that the result of introducing TF-ITF into a supervised topic model outperforms several state-of-the-art supervised topic models.
In this paper, we focus on training a support vector machine (SVM) online with a single pass over streaming data.Traditional batch-mode SVMs require previously prepared training data; these models may be unsuitable for streaming data circumstances. Online SVMs are effective tools for solving this problem by receiving data streams consistently and updating model weights accordingly. However, most online SVMs require multiple data passes before the updated weights converge to stable solutions, and may be unable to address high-rate data streams. This paper presents OSVM_SP, a new online SVM with a single pass over streaming data, and three budgeted versions to bound the space requirement with support vector removal principles. The experimental results obtained with five public datasets show that OSVM_SP outperforms most state-of-the-art single-pass online algorithms in terms of accuracy and is comparable to batch-mode SVMs. Furthermore, the proposed budgeted algorithms achieve comparable predictive performance with only 1/3 of the space requirement.
User profiles constructed using vast network behaviour data are widely used in various fields. However, data island and central server capacity problems limit the implementation of centralised big data training. This paper proposes a user profile construction method, Fed-UserPro, based on federated learning, which uses non-independent and identically distributed unstructured user text to jointly construct user profiles. Latent Dirichlet allocation model and softmax multi-classification regression method are introduced into the federated learning structure to train data. The results show that the accuracy of the Fed-UserPro method is 8.69%–19.71% higher than that of single-party machine learning methods.