No abstract

No abstract

No abstract

Abstract:The uniformity of wheat seed emergence is an important characteristic used to evaluate cultivars, cultivation mode and field management. Currently, researchers typically investigated the uniformity of seed emergence by manual measurement, a time-consuming and laborious process. This study employed field RGB images from unmanned aerial vehicles (UAVs) to obtain information related to the uniformity of wheat seed emergence and missing seedlings. The calculation of the length of areas with missing seedlings in both drill and broadcast sowing can be achieved by using an area localization algorithm, which facilitated the comprehensive evaluation of uniformity of seed emergence. Through a comparison between UAV images and the results of manual surveys used to gather data on the uniformity of seed emergence, the root-mean-square error (RMSE) was 0.44 for broadcast sowing and 0.64 for drill sowing. The RMSEs of the numbers of missing seedling regions for broadcast and drill sowing were 1.39 and 3.99, respectively. The RMSEs of the lengths of the missing seedling regions were 12.39 cm for drill sowing and 0.20 cm 2 for broadcast sowing. The UAV image-based method provided a new and greatly improved method for efficiently measuring the uniformity of wheat seed emergence. The proposed method could provide a guideline for the intelligent evaluation of the uniformity of wheat seed emergence.

No abstract

We present a novel inversion approach using a neural network to locate subsurface targets and evaluate their backscattering properties from ground penetrating radar (GPR) data. The presented inversion strategy constructs an adaptive linear element (ADALINE) neural network, whose configuration is related to the unknown properties of the targets. The GPR data is reconstructed (compression) to fit the structure of the neural network. The constructed neural network works with a supervised training mode, where a series of primary functions derived from the GPR signal model are used as the input, and the reconstructed GPR data is the expected/target output. In this way, inverting the GPR data is the equivalent of training the network. The back-propagation (BP) algorithm is employed for the training of the neural network. The numerical experiments show that the proposed approach can return an exact estimation for the target's location. Under sparse conditions, an inverted backscattering intensity with a relative error lower than 3% was achieved, whereas for the multi-dominating point scenario, a higher error rate was observed. Finally, the limitations and further developments for the inverting GPR data with the neural network are discussed.

No abstract

The multi-label text classification task aims to tag a document with a series of labels. Previous studies usually treated labels as symbols without semantics and ignored the relation among labels, which caused information loss. In this paper, we show that explicitly modeling label semantics can improve multilabel text classification. We propose a hybrid neural network model to simultaneously take advantage of both label semantics and fine-grained text information. Specifically, we utilize the pre-trained BERT model to compute context-aware representation of documents. Furthermore, we incorporate the label semantics in two stages. First, a novel label graph construction approach is proposed to capture the label structures and correlations. Second, we propose a neoteric attention mechanism-adjustive attention to establish the semantic connections between labels and words and to obtain the label-specific word representation. The hybrid representation that combines context-aware feature and label-special word feature is fed into a document encoder to classify. Experimental results on two publicly available datasets show that our model is superior to other state-of-the-art classification methods.