Search

Simple Summary: Metagenomic binning is a part of the metagenomic analysis process that can classify the genomes in complex microbial communities into possible source species. It is dedicated to restoring more complete genomes and is conducive to studying microbial community structure and function. Obtaining more effective feature representations of genome sequences to improve binning is still a major challenge. This study proposes a new metagenomic binning method called CedtBin, which uses an improved BERT model to obtain the embedded representation of contigs and splices it with the decomposed tetranucleotide frequencies into a new feature representation. Then, the Annoy-DBSCAN clustering algorithm is proposed, which can adaptively determine the parameters of the DBSCAN clustering algorithm for binning. The results show that CedtBin can achieve good binning effects on both simulated and real datasets, and can reconstruct more genomes. Metagenomic binning is a crucial step in metagenomic research. It can aggregate the genome sequences belonging to the same microbial species into independent bins. Most existing methods ignore the semantic information of contigs and lack effective processing of tetranucleotide frequency, resulting in insufficient and complex feature information extracted for binning and poor binning results. To address the above problems, we propose CedtBin, a metagenomic binning method based on contig embedding and decomposed tetranucleotide frequency. First, the improved BERT model is used to learn the contigs to obtain their embedding representation. Secondly, the tetranucleotide frequencies are decomposed using a non-negative matrix factorization (NMF) algorithm. After that, the two features are spliced and input into the clustering algorithm for binning. Considering the sensitivity of the DBSCAN clustering algorithm to input parameters, in order to solve the drawbacks of manual parameter input, we also propose an Annoy-DBSCAN algorithm that can adaptively determine the parameters of the DBSCAN algorithm. This algorithm uses Approximate Nearest Neighbors Oh Yeah (Annoy) and combines it with a grid search strategy to find the optimal parameters of the DBSCAN algorithm. On simulated and real datasets, CedtBin achieves better binning results than mainstream methods and can reconstruct more genomes, indicating that the proposed method is effective. [ABSTRACT FROM AUTHOR]

To detect text from electronic seals that have significant background interference, blurring, text overlapping, and curving, an improved YOLOv8 model named RA-YOLOv8 was developed. The model is primarily based on YOLOv8, with optimized structures in its backbone and neck. The receptive-field attention and efficient multi-scale attention (RFEMA) module is introduced in the backbone. The model's ability to extract and integrate local and global features is enhanced by combining the attention on the receptive-field spatial feature of the receptive-field attention and coordinate attention (RFCA) module and the cross-spatial learning of the efficient multi-scale attention (EMA) module. The Alterable Kernel Convolution (AKConv) module is incorporated in the neck, enhancing the model's detection accuracy of curved text by dynamically adjusting the sampling position. Furthermore, to boost the model's detection performance, the original loss function is replaced with the bounding box regression loss function of Minimum Point Distance Intersection over Union (MPDIoU). Experimental results demonstrate that RA-YOLOv8 surpasses YOLOv8 in terms of precision, recall, and F1 value, with improvements of 0.4%, 1.6%, and 1.03%, respectively, validating its effectiveness and utility in seal text detection. [ABSTRACT FROM AUTHOR]

Recognition of the key text of the Chinese seal can speed up the approval of documents, and improve the office efficiency of enterprises or government administrative departments. Due to image blurring and occlusion, the accuracy of Chinese seal recognition is low. In addition, the real dataset is very limited. In order to solve these problems, we improve the differentiable binarization detection algorithm (DBnet) to construct a model DB-ECA for text region detection, and propose a model named LSTR (Lightweight Seal Text Recognition) for text recognition. The efficient channel attention module is added to the differentiable binarization network to solve the feature pyramid conflict, and the convolutional layer network structure is improved to delay downsampling for reducing semantic feature loss. LSTR uses a lightweight CNN more suitable for small-sample generalization, and dynamically fuses positional and visual information through a self-attention-based inference layer to predict the label distribution of feature sequences in parallel. The inference layer not only solves the weak discriminative power of CNN in the shallow layer, but also facilitates CTC (Connectionist Temporal Classification) to accurately align the feature region with the target character. Experiments on the homemade dataset in this paper, DB-ECA compared with the other five commonly used detection models, the precision, recall, F-measure are the best effect of 90.29, 85.17, 87.65, respectively. LSTR compared with the other five kinds of recognition models in the last three years, to achieve the highest effect of accuracy 91.29%, and has the advantages of a small number of parameters and fast inference. The experimental results fully prove the innovation and effectiveness of our model. [ABSTRACT FROM AUTHOR]

Named entity recognition of government audit text is a key task of intelligent auditing. Aiming at the problems of scarcity of corpus in the field of governmental auditing, insufficient utilization of traditional character vector word-level information features, and insufficient capturing of auditing entity features, this study builds its own dataset in the field of auditing and proposes the model CW-CBGC for recognizing named entities in governmental auditing text based on ChineseBERT and character-word fusion. First, the ChineseBERT pre-training model is used to extract the character vector that integrates the features of glyph and pinyin, combining with word vectors dynamically constructed by the BERT pre-training model; then, the sequences of character-word fusion vectors are input into the bi-directional gated recurrent neural network (BiGRU) to learn the textual features. Finally, the global optimal sequence label is generated by Conditional Random Field (CRF), and the GHM classification loss function is used in the model training to solve the problem of error evaluation under the conditions of noisy entities and unbalanced number of entities. The F1 value of this study's model on the audit dataset is 97.23%, which is 3.64% higher than the baseline model's F1 value; the F1 value of the model on the public dataset Resume is 96.26%, which is 0.73–2.78% higher than the mainstream model. The experimental results show that the model proposed in this paper can effectively recognize the entities in government audit texts and has certain generalization ability. [ABSTRACT FROM AUTHOR]