Search

Natural scene text detection is a significant challenge in computer vision, with tremendous potential applications in multilingual, diverse, and complex text scenarios. A multilingual text detection model based on the Cascade Mask R-CNN is proposed to address the challenges of low accuracy and high difficulty in detecting multilingual text in natural scenes. In response to the challenges posed by multilingual text images with multiple character sets and various font styles, the SFM Swin Transformer feature extraction network is introduced to increase the robustness of character and font detection across different languages. To address the considerable variation in text scales and complex arrangements in natural scene text images, the AS-HRFPN feature fusion network is constructed by incorporating an adaptive spatial feature fusion module and a spatial pyramid pooling module. The feature fusion network improvements enhance the model’s ability to detect text sizes and orientations. Furthermore, to address the complexity of high background diversity and variations in font letter morphology across different languages in multilingual natural scene text images, existing methods often need better detection performance because of the need for global information caused by limited local receptive fields. To mitigate this, a global semantic segmentation branch is introduced to extract and preserve global features to guide text detection. This study collected and constructed a real-world, multilingual, natural scene text image dataset, and comprehensive experiments and analyses were conducted. The experimental results demonstrate that the proposed algorithm achieves an F-measure of 85.02%, which is 4.71% higher than that of the baseline model. Extensive cross-dataset validations on the MSRA-TD500, ICDAR2017MLT, and ICDAR2015 datasets were also conducted to verify the generality of our approach. [ABSTRACT FROM AUTHOR]

Soil salinization has been considered as a major environmental threat to plant growth. Different types of salt in saline soil have different effects on germination and seedling growth. Effect of NaCl on germination and seedling establishment in Suaeda liaotungensis have been reported, but its response to alkali stress remains unclear. Our results showed that brown seeds had higher germination rate, however, black seeds had higher germination recovery percentage under alkali stress. Na2CO3 had stronger inhibitory effect on germination and seedling growth than NaHCO3. As the concentration of alkali stress increased, the ROS level of brown seeds gradually ascended, while that of black seeds decreased first and then ascended. MDA content of dimorphic seeds significantly increased under alkali stress. The trend of SOD, POD and CAT activity between dimorphic seeds was similar under the same type of alkali stress. Alkali stress enhanced proline content of dimorphic seeds, and dimorphic seeds in NaHCO3 solution had higher proline content than Na2CO3 solution. Moreover, radicle and shoot tolerance indexes of seedlings in NaHCO3 solution were significantly higher than that of Na2CO3 solution. Under strong alkali stress, seedlings in NaHCO3 solution had significantly lower ROS level and MDA content as well as higher antioxidant enzyme activity than Na2CO3 solution. This study comprehensively compared the morphological and physiological characteristics in germination and seedlings to better reveal the saline-alkali tolerance mechanisms in S. liaotungensis. [ABSTRACT FROM AUTHOR]

Many lines of evidence indicate that red jungle fowl (RJF) is the primary ancestor of domestic chickens. Although multiple versions of RJF (galgal2-galgal5 and GRCg6a) and commercial chickens (GRCg7b/w and Huxu) genomes have been assembled since 2004, no high-quality indigenous chicken genomes have been assembled, hampering the understanding of chicken domestication and evolution. To fill the gap, we sequenced the genomes of four indigenous chickens with distinct morphological traits in southwest China, using a combination of short, long and Hi-C reads. We assembled each genome (~1.0 Gb) into 42 chromosomes with chromosome N50 90.5–90.9 Mb, amongst the highest quality of chicken genome assemblies. To provide resources for gene annotation and functional analysis, we also sequenced transcriptomes of 10 tissues for each of the four chickens. Moreover, we corrected many mis-assemblies and assembled missing micro-chromosomes 29 and 34–39 for GRCg6a. Our assemblies, sequencing data and the correction of GRCg6a can be valuable resources for studying chicken domestication and evolution. [ABSTRACT FROM AUTHOR]

Purpose: To identify the relevant factors affecting the prognosis and survival time of colon cancer and construct a survival prediction model. Methods: Data on postoperative stage I–III colon cancer patients were obtained from the Surveillance, Epidemiology, and End Results database. We used R project to analyze the data. Univariate and multivariate Cox regression analyses were performed for independent factors correlated with overall survival from colon cancer. The C-index was used to screen the factors that had the greatest influence in overall survival after surgery in colon cancer patients. Receiver operating characteristic (ROC) curve was made according to the Risk score and calculated to validate the predictive accuracy of the model. In addition, we used decision curve analysis (DCA) to evaluate the clinical benefits and utility of the nomogram. We created a model survival curve to determine the difference in prognosis between patients in the low-risk group and those in the high-risk group. Results: Univariate and multifactor COX analyses showed that the race, Grade, tumor size, N-stage and T-stage were independent risk factors affecting survival time of patients. The analysis of ROC and DCA showed the nomogram prediction model constructed based on the above indicators has good predictive effects. Conclusion: Overall, the nomogram constructed in this study has good predictive effects. It can provide a reference for future clinicians to evaluate the prognosis of colon cancer patients. [ABSTRACT FROM AUTHOR]

The outbreak of the 2022 Russia-Ukraine conflict exacerbated the natural gas supply shortage in European countries. European countries restarted coal-fired power plants to maintain economic and social operations. The uneven distribution of coal resources in the world makes coal international trade inevitable. The intricate trade relations between trading countries have formed a coal trade network. When a country's coal exports are limited due to geopolitical factors, it will cause coal supply risks. The risk will spread to more countries along the trade network, eventually leading to the collapse of the trade network. This paper builds a crisis propagation model of the coal supply under the Russia-Ukraine conflict using the cascading failure model. The results showed that the Czech Republic, Ireland, Portugal, and Bulgaria become abnormal as the proportion of coal exports β increases. When the Russian Federation reduced its coal exports by 80% and countries maintained only 10% coal exports against crisis, 23 European countries were the worst. Iceland, Ireland, Turkey and other countries were spread by the indirect risk and became abnormal countries. The Czech Republic and Bulgaria were spread by multiple risk and became abnormal countries. [ABSTRACT FROM AUTHOR]

Handwriting recognition is an important application in pattern recognition. Because handwritten Tai Le has similar characters and the proportion of characters with similar shapes is relatively high, this paper proposes a wavelet deep convolution (WDC) feature combined with an ensemble deep variational sparse Gaussian process (EDVSGP) offline handwritten Tai Le recognition method. A Tai Le recognition sample database is constructed, 2 and 3 levels of wavelet decomposition prior features are extracted, and then, the wavelet a priori feature is transformed into a WDC feature. To avoid the dimensional disaster caused by feature fusion, a dimensionality reduction method combining LDA and PCA is used to reducing the dimensionality of the fused features without reducing the accuracy rate. Moreover, to better recognize handwritten Tai Le characters, 6 deep variationally sparse Gaussian process (DVSGP) models are integrated as an EDVSGP classification model. Using the handwritten Tai Le character database, the proposed method is superior to the existing methods, with an accuracy, recall and F1-score of 94.15%, 94.15%, and 94.15%, respectively. The universality of the method is verified on a dataset of handwritten Chinese characters with similar shapes (HCFC2021.4) and the Devanagari dataset. [ABSTRACT FROM AUTHOR]

Automatic classification of ancient books is an important component of the digital platform of ancient books, while automatic classification of ancient books is more challenging. In view of the ancient books script identification task of different ethnic minorities in China, this paper proposes a deep convolutional neural network (CNN) ancient books script identification method with multi-branch structure and spatial pyramid pooling (SPP), called MbSPPVGG. We build a dataset of Chinese ethnic ancient handwritten books, and crop and standardize preprocessing images of ancient books. In order to improve the identification accuracy of ancient books and ability of CNN to perceive multi-scale changes in image, bottom-level and high-level features of CNN are merged by multi-branch structure to enhance the networks expression ability, and then use SPP to multi-scale de-dimensionality of convolutional features, increase the spatial scale invariance of CNN. The introduction of multi-branch structure and SPP in the CNN model constitutes a new ancient books identification model. The experimental results show that the precision, recall and F1-score of MbSPPVGG model are all 99.94%. As demonstrated by comparison experiments, the classification accuracy of MbSPPVGG model is better than that of state-of-the-art GhostNet, CSPDenseNet, MixNet and other deep learning methods, and its effectiveness is verified on multiple datasets. [ABSTRACT FROM AUTHOR]

Fluorescein-functionalized fluorescent polymer dots (F-PDs) were prepared by a facile one-pot method by magnetic stirring under mild conditions based on carboxymethylcellulose (CMC) and fluorescein as the precursors. The obtained F-PDs exhibited a nanoscale size of 3.2 ± 1.1 nm, excellent water solubility, and bright yellow fluorescence emission with a fluorescence quantum yield of 12.0%. The fluorescent probe displays rapid and sensitive chiral discrimination for lysine focused on different complexation abilities between lysine enantiomers and Cu2+. The concentration of L-lysine in the range 4 to 14 mM (R2 = 0.997) was measured by the fluorescence intensity ratio (I513/I429); the exitation wavelength was set to λex = 365 nm. The detection limit was 0.28 mM (3σ/slope). Importantly, this sensor accurately predicted the enantiomeric excess (ee) of lysine enantiomers at the designed concentration (lysine: 20 mM; Cu2+: 10 mM) ranges. The proposed sensor was successfully applied to determine L-lys (recovery: 95.8–101%; RSD: 0.465–3.34%) and ee values (recovery: 98.5–102%; RSD: 2.61–3.21%) in human urine samples using the standard addition method. [ABSTRACT FROM AUTHOR]

Handwriting recognition is an important area in pattern recognition. For many years, Tai Le has been widely used in Southwest China and Southeast Asia, which makes it of great interest for recognition research. The characteristics of the highly similar characters in Tai Le, such as its large proportion of similar characters and the randomness of its writing, bring great challenges to the task of recognition. In this paper, a method based on ensemble deep learning for offline handwritten Tai Le characters is proposed. First, the handwritten Tai Le character dataset SDH2019.2 was constructed and preprocessed. Then, an ensemble deep convolutional neural network (EDCNN) model was constructed by using a stacking strategy. Thirty deep neural network (DNN) and logistic regression algorithms were integrated into a strong Tai Le classifier by stacking. Experiments showed that the proposed model is competitive with the base DNN model and other ensemble models. The results indicate that the performance of Tai Le recognition by the stacking ensemble-based deep neural network model is high, with an accuracy of 98.85%. Additionally, its precision, recall and F1-score of 98.87%, 98.85% and 98.85%, respectively, are superior to those of other classic neural network models. To verify the general applicability of EDCNN, its effectiveness was also verified by recognizing MNIST handwritten digits and Devanagari handwritten characters. [ABSTRACT FROM AUTHOR]

This document is a correction notice for an article titled "High quality assemblies of four indigenous chicken genomes and related functional data resources" published in Scientific Data. The correction addresses an error in the affiliations of the authors. Specifically, the affiliations of Siwen Wu and Kun Wang were inadvertently swapped, and Siwen Wu's affiliation was missing. The correction provides the correct affiliations for all authors involved in the study. [Extracted from the article]

China has abundant shale gas resource, but its geological conditions are complicated. This work sought to find the shale breaking mechanism with the polycrystalline diamond compact (PDC) bit when drilling the shale that is rich in stratification. Therefore, a laboratory-scale drilling device based on a drilling machine is developed. The influences of Longmaxi shale stratification on drilling parameters in the drilling process with micro-PDC bit are investigated. Six groups of drilling experiments with six inclination angles ( β = 0°, 15°, 30°, 45°, 60° and 90°), total thirty-six groups, are carried out. The weight on bit reaches the maximum value at β = 30° and reaches the minimum value at β = 0°. The biggest torque value is at β = 30°, and the smaller torque values are at β = 15°, β = 45° and β = 60°. When the inclination angle is between 30° and 60°, the shale fragmentation volume is larger. The inclination angle β = 0° is beneficial, and β = 15° and β = 60° are detrimental to controlling the drilling direction in the Longmaxi shale gas formation. [ABSTRACT FROM AUTHOR]