Search

In this paper, we leverage predictive uncertainty of deep neural networks to answer challenging questions material scientists usually encounter in machine learning based materials applications workflows. First, we show that by leveraging predictive uncertainty, a user can determine the required training data set size necessary to achieve a certain classification accuracy. Next, we propose uncertainty guided decision referral to detect and refrain from making decisions on confusing samples. Finally, we show that predictive uncertainty can also be used to detect out-of-distribution test samples. We find that this scheme is accurate enough to detect a wide range of real-world shifts in data, e.g., changes in the image acquisition conditions or changes in the synthesis conditions. Using microstructure information from scanning electron microscope (SEM) images as an example use case, we show that leveraging uncertainty-aware deep learning can significantly improve the performance and dependability of classification models.

In the present study, the inhibitory effect of neem leaf extract (NLE) on lipopolysaccaride (LPS)-induced nitric oxide (NO) and tumor necrosis factor-α (TNF-α) production was examined both in vitro and in vivo. In vitro study revealed that NLE treatment (100 μg/ml) inhibits LPS (100 ng/ml)-induced NO production by 96% and TNF-α production by 32%. The reduction in NO production is probably conferred by the complete suppression of inducible nitric oxide synthase (iNOS) expression. Interestingly, in vivo NLE significantly improved the survival rate of mice in an experimental sepsis model. Administration of NLE (100 mg/kg) 24 h before LPS treatment (20 mg/kg) improved the survival rate of mice by 60%. The inhibition of plasma NO and TNF-α production by NLE is likely to account for the improved survival of mice. Our results suggest that NLE may present a promising avenue in the development of therapeutic agents for the treatment of inflammatory diseases.

Consumer-to-Consumer (C2C) E-commerce has been growing at a very high speed in recent years. Since identical or nearly-same kinds of products compete one another by relying on keyword search in C2C E-commerce, some sellers describe their products with spam keywords that are popular but are not related to their products. Though such products get more chances to be retrieved and selected by consumers than those without spam keywords, the spam keywords mislead the consumers and waste their time. This problem has been reported in many commercial services like ebay and taobao, but there have been little research to solve this problem. As a solution to this problem, this paper proposes a method to classify whether keywords of a product are spam or not. The proposed method assumes that a keyword for a given product is more reliable if the keyword is observed commonly in specifications of products which are the same or the same kind as the given product. This is because that a hierarchical category of a product in general determined precisely by a seller of the product and so is the specification of the product. Since higher layers of the hierarchical category represent more general kinds of products, a reliable degree is differently determined according to the layers. Hence, reliable degrees from different layers of a hierarchical category become features for keywords and they are used together with features only from specifications for classification of the keywords. Support Vector Machines are adopted as a basic classifier using the features, since it is powerful, and widely used in many classification tasks. In the experiments, the proposed method is evaluated with a golden standard dataset from Yi-han-wang, a Chinese C2C E-commerce, and is compared with a baseline method that does not consider the hierarchical category. The experimental results show that the proposed method outperforms the baseline in F1-measure, which proves that spam keywords are effectively identified by a hierarchical category in C2C E-commerce., {"references":["camino3x2, \"Keyword spam busting.\" (Online).\nAvailable: http://www.ebay.com/gds/ Keyword-Spam-Busting-/\n10000000001612568/g.html","fransgems, \"Beware misleading item headers on ebay auctions!\"\n(Online). Available: http://www.ebay.com/gds/Beware-Misleading\n-Item-Headers-on-eBay-Auctions- /10000000003890459/g.html","jandbcannon, \"You might be keyword spamming too.\" (Online).\nAvailable: http://www.ebay.com/gds/\nBeware-You-Might-Be-Keyword-Spamming-Too-\n/10000000001620833/g.html","E. Blanzieri and A. Bryl, \"A survey of learning-based techniques of\nemail spam filtering,\" Artificial Intelligence Review, vol. 29, no. 1, pp.\n63–92, 2008.","G. Cormack, \"Email spam filtering: A systematic review,\" Foundations\nand Trends in Information Retrieval, vol. 1, no. 4, pp. 335–455, 2007.","G. Koutrika, F. Effendi, Z. Gy¨ongyi, P. Heymann, and H. Garcia-Molina,\n\"Combating spam in tagging systems,\" in Proceedings of the 3rd\ninternational workshop on Adversarial information retrieval on the web,\n2007, pp. 57–64.","A. Ntoulas, M. Najork, M. Manasse, and D. Fetterly, \"Detecting spam\nweb pages through content analysis,\" in Proceedings of WWW, 2006,\npp. 83–92.","A. Khorsi, \"An overview of content-based spam filtering techniques.\"\nInformatica, vol. 31, no. 3, 2007.","A. Hearst, J. Dumais, and S. .B, \"Support vector machines,\" Intelligent\nSystems and their Applications, IEEE, vol. 13, no. 4, pp. 18–28, 1998.\n[10] C. Chang and C. Lin, \"Libsvm: a library for support vector machines,\"\nACM TIST, vol. 2, no. 3, p. 27, 2011.\n[11] \"jcseg.\" (Online). Available: http://code.google.com/p/jcseg/"]}