Search

Recognition of handwritten mathematical expressions (MEs) is an important problem that has wide applications in practice. Handwritten ME recognition is challenging due to the variety of writing styles and ME formats. As a result, recognizers trained by optimizing the traditional supervision loss do not perform satisfactorily. To improve the robustness of the recognizer with respect to writing styles, in this work, we propose a novel paired adversarial learning method to learn semantic-invariant features. Specifically, our proposed model, named PAL-v2, consists of an attention-based recognizer and a discriminator. During training, handwritten MEs and their printed templates are fed into PAL-v2 simultaneously. The attention-based recognizer is trained to learn semantic-invariant features with the guide of the discriminator. Moreover, we adopt a convolutional decoder to alleviate the vanishing and exploding gradient problems of RNN-based decoder, and further, improve the coverage of decoding with a novel attention method. We conducted extensive experiments on the CROHME dataset to demonstrate the effectiveness of each part of the method and achieved state-of-the-art performance. [ABSTRACT FROM AUTHOR]

The conversion of monoculture rubber (Hevea brasiliensis) plantations into rubber-based agroforestry systems has become a common trend in forestry management in the past few decades. Rubber-Flemingia macrophylla (a leguminous shrub) systems are popular in southwestern China’s Xishuangbanna region. The biogeochemical cycles of soil carbon and nitrogen in forests are mainly affected by their fractions. This study investigated the effect of introducing Flemingia macrophylla to rubber plantations of different ages on soil carbon and nitrogen fractions. The experimental treatments included R1 (young rubber plantation), RF1 (young rubber-Flemingia macrophylla system), R2 (mature rubber plantation) and RF2 (mature rubber-Flemingia macrophylla system). The results showed that the introduction of Flemingia macrophylla to rubber plantations of different ages significantly changed soil carbon and nitrogen fractions, improved soil labile organic carbon and nitrogen contents, and ameliorated soil environments. The average soil microbial biomass organic carbon, nitrogen and nitrate-nitrogen in the 0-10 cm soil layer during the experimental period was 38.9%, 55.5%, and 214.7% higher in RF1 than R1, respectively, and 22.1%, 22.2%, and 652.2% higher in RF2 than R2, respectively. Therefore, Flemingia macrophylla can be used as an alternative interplanted tree species within rubber plantations in similar environments of southeastern Asia. [ABSTRACT FROM AUTHOR]