Search

H9N2 avian influenza viruses are widely prevalent in birds and pose an increasing threat to humans because of their enhanced virulence and transmissibility in mammals. Active surveillance on the prevalence and evolution of H9N2 viruses in different avian hosts will help develop eradication measures. We isolated 16 H9N2 viruses from chickens, green peafowls, and wild birds in eastern China from 2017 to 2019 and characterized their comparative genetic evolution, receptor-binding specificity, antigenic diversity, replication, and transmission in chickens and mice. The phylogenetic analysis indicated that the green peafowl viruses and swan reassortant shared the same ancestor with the poultry H9N2 viruses prevalent in eastern China, while the seven wild bird viruses belonged to wild bird lineage. The chicken, peafowl, and swan H9N2 viruses that belonged to the poultry lineage preferentially recognized α-2, 6-linked sialic acids (human-like receptor), but the wild bird lineage viruses can bind both α-2, 3 (avian-like receptor) and human-like receptor similarly. Interestingly, the H9N2 viruses of poultry lineage replicated well and transmitted efficiently, but the viruses of wild bird lineage replicated and transmitted with low efficiency. Importantly, the H9N2 viruses of poultry lineage replicated in higher titer in mammal cells and mice than the viruses of wild birds lineage. Altogether, our study indicates that co-circulation of the H9N2 viruses in poultry, wild birds, and ornamental birds increased their cross-transmission risk in different birds because of their widespread dissemination.

Knowledge graphs represent information in the form of entities and relation-ships between them. A knowledge graph consists of multi-relational data, having entities as nodes and relations as edges. The relation indicates a relationship between these two entities. Relation extraction is the key step to construct a knowledge graph. Conventional relation extraction methods usually need large scale labeled samples for each website. It’s difficult to deal with the large number of relations and the various representations of each relation. This paper proposed a novel semi-automatic method that builds knowledge graph by extracting relation patterns and finding new relations. The proposed method models the relation pattern as a tag sequence and learns the pattern similarity metric using the existing relation instances. The pattern similarity is adopted to extract new patterns for existing relations. The new relations are detected by using the pattern similarity and clustering technique. The experimental results on large scale web pages show the effectiveness and efficiency of the proposed method.

Combination of Multiple Classifier has been consider as the approach of improving the classification performance. The popular diversification approach named local specialization is based on the simultaneous partitioning of the feature space and an assignment of a compound classifier to each of the sub-space. This paper presents a novel feature space partitioning algorithm for the combination of multiple classifier. The proposed method uses pairwise measure to get the diversity between classifiers and selects the complementary classifiers to get the pseudo labels. Based on the pseudo labels, it splits the feature space into constituents and selects the best classifier committee from the pool of available classifiers. The partitioning and selection are taken place simultaneously as part of a compound optimization process aimed at maximizing system performance. Evolutionary methods are used to find the optimal solution. The experimental results show the effectiveness and efficiency of the proposed method.

PACLIC 23 / City University of Hong Kong / 3-5 December 2009

In the real world, there are a huge amount of advertisement (ad) boards to make customers have a visual awareness of the products or services easily. However, information appearing in the ad boards is so limited that customers always want to know more ad details in a convenient way. In this paper, we present an mobile-based prototype system to automatically extract web ad information from images and websites. After capturing ad images by smartphones and sending them to a remote server, ad image text is recognized by OCR engine, from where ad phrases and keywords are extracted and combined together as queries. Ad web page candidates are then obtained by specific search engines and clustered to remove noises. OCR results are further used to estimate valid ad topic web pages which are pushed back to end users for searching more detailed ad information. Based on the experiments on a real-world ad image dataset collected by ourselves, true ad topic web pages can be found from top-one and top-ten returned pages in about 51.85% and 83.33% query images respectively, which illustrates the effectiveness of the proposed system.

Short term load forecasting (STLF), which aims to predict system load over an internal of one day or one week, plays a crucial role in the control and scheduling operations of a power system. Most existing techniques on short term load forecasting try to improve the performance by selecting ferent prediction models. However, the performance also rely heavily on the quality of training data. This paper focuses on training data selection which is rarely considered in the previous studies. A novel approach is proposed to filter out abnormal data by analyzing historical load curves. Experiments conducted on the real load data show significant improvement over the baseline method using the same data for training. Furthermore, the approach is feasible and thus can be applied in different situations. On one hand, the approach achieves promising results by using only historical load data which is shown in this study. On the other hand, more information can be easily integrated in the approach to select more appropriate training data for further performance improvement.