No abstract

Consumer product safety closely relates to consumer health. In this paper, a knowledge engineering framework is proposed for data mining to identify key safety factors from a large number of consumer product safety cases. Data mining in the framework is performed in three steps. The first step is to collect consumer product safety cases, a case can be semistructured or unstructured, and cases can be collected either manually or automatically by a web spider crawling certain websites. The second step is to extract all safety factors from a number of consumer product safety cases. A new method based on linear chain conditional random field is developed to extract safety factors. The effectiveness of the method has been validated on product cases. The third step is to identify a set of key factors from all safety factors by knowledge reasoning. To illustrate the process of knowledge reasoning, a set of 3192 safety cases of electric products with electric shock accidents is chosen as the case study; a Bayesian network based model is developed to retrieve key safety factors relating to electric shock accidents. The performance of the reasoning model has been verified by a combination of experts' evaluation and experiments, and it has shown the proposed reasoning model can help identify key safety factors of electric shock accidents successfully. Overall, the proposed framework is capable of identifying key safety factors from a large number of consumer product safety cases. Copyright © 2014 John Wiley & Sons, Ltd.

Abstract. Disease spot segmentation from crop leaf images is a key prerequisite for disease early warning and diagnosis. To improve the accuracy and stability of disease spot segmentation, an adaptive segmentation method for crop disease images based on K-means clustering is proposed. The approach is based on three stages. First, the excess green feature and the a* component of the CIE (L*a*b*) color space were combined to adaptively learn the initial cluster centers. Second, iterative color clustering of two clusters was conducted using the squared Euclidian distance as the similarity distance. Finally, the distance of a* components between two clusters as the clustering criterion function was used to correct the clustering results. To verify the effectiveness of the proposed method, segmentation experiments were performed on images of three kinds of cucumber diseases and one kind of soybean disease. The results of the experiments were compared with the results obtained using a fixed threshold method, the Otsu method, the traditional K-means clustering method, and the Renyi entropy method, which showed that our adaptive segmentation method was accurate and robust for segmentation of crop disease images. Keywords: Adaptive, CIE L*a*b*, Disease spot, Image segmentation, K-means clustering.

Heavy metal pollution in farmlands is a serious threat to sustainable agricultural development and has become a major agro-ecological problem that has attracted public concern in China. This study proposes a soil-crop collaborative risk assessment model that aims to assess the potential safety risks of heavy metal pollution in farmland soils by considering the concentrations of heavy metals in soils and the accumulation effects of heavy metals in crops. Based on these effects, a decision support system for risk assessment of heavy metal pollution in farmland soil is established, in which technologies such as web-based geographic information system, quick response code, radio frequency identification, and web service are introduced as the bases. The proposed system is composed of a mobile data acquisition terminal (MDAT) and a web-based information system (WIS). The MDAT, which is a portable computerized device running on the Android platform, is used for data acquisition or query, and the WIS is used for risk assessment, data management, and information visualization. The system is employed in some county-level cities in China for risk assessment and supervision of heavy metal pollution in farmlands. The practical application results show that the system provides highly efficient decision support for risk assessment of heavy metal pollution in farmland soils.