Search

Abstract The leaves of Cyclocarya paliurus (Batalin) Iljinskaja, an endemic tree with a scattered distribution in subtropical China, are rich in flavonoids with beneficial, health-promoting properties. To understand the impact of environment and genetic similarity on the variation pattern of flavonoids in this species, we analyzed C. paliurus germplasm resources from 26 different populations previously sampled from the main distribution area. Environmental, genetic and biochemical data was associated by genetic structure analysis, non-parametric tests, correlation analysis and principal component analysis. We found that populations with higher flavonoid contents were distributed at higher elevations and latitudes and fell into two groups with similar genetic diversities. Significant accumulations of isoquercitrin and kaempferol 3-O-glucoside were detected in the higher flavonoid-content resources. In addition, the genetic clusters with higher flavonoid contents exhibited broader environmental-adaptive capacities. Even in the presence of environmental factors promoting C. paliurus flavonoid accumulation, only those populations having a specific level of genetic similarity were able to exploit such environments.

The high performance of deep learning networks relies on large datasets and powerful computational resources. However, collecting enough diseased training samples is a daunting challenge. In addition, existing few-shot learning models tend to suffer from large size, which makes their deployment on edge devices difficult. To address these issues, this study proposes a pruning-based lightweight few-shot learning (Prune-FSL) approach, which aims to utilize a very small number of labeled samples to identify unknown classes of crop diseases and achieve lightweighting of the model. First, the disease few-shot learning model was built through a metric-based meta-learning framework to address the problem of sample scarcity. Second, a slimming pruning method was used to trim the network channels by the γ coefficients of the BN layer to achieve efficient network compression. Finally, a meta-learning pruning strategy was designed to enhance the generalization ability of the model. The experimental results show that with 80% parameter reduction, the Prune-FSL method reduces the Macs computation from 3.52 G to 0.14 G, and the model achieved an accuracy of 77.97% and 90.70% in 5-way 1-shot and 5-way 5-shot, respectively. The performance of the pruned model was also compared with other representative lightweight models, yielding a result that outperforms those of five mainstream lightweight networks, such as Shufflenet. It also achieves 18-year model performance with one-fifth the number of parameters. In addition, this study demonstrated that pruning after sparse pre-training was superior to the strategy of pruning after meta-learning, and this advantage becomes more significant as the network parameters are reduced. In addition, the experiments also showed that the performance of the model decreases as the number of ways increases and increases as the number of shots increases. Overall, this study presents a few-shot learning method for crop disease recognition for edge devices. The method not only has a lower number of parameters and higher performance but also outperforms existing related studies. It provides a feasible technical route for future small-sample disease recognition under edge device conditions.

The knowledge within wheat production chain data has multiple levels and complex semantic relationships, making it difficult to extract knowledge from them. Therefore, this paper proposes a fine-grained knowledge extraction method for the wheat production chain based on ontology. For the first time, the conceptual layers of ploughing, planting, managing, and harvesting were defined around the main agricultural activities of the wheat production chain. Based on this, the entities, relationships, and attributes in the conceptual layers were defined at a fine-grained level, and a spatial–temporal association pattern layer with four conceptual layers, twenty-eight entities, and forty-two relationships was constructed. Then, based on the characteristics of the self-constructed dataset, the Word2vec-BiLSTM-CRF model was designed for extracting the knowledge within it, i.e., the entity–relationship–attribute model and the Word2vec-BiLSTM-CRF model in this paper were compared with the four SOTA models. The results show that the accuracy and F1 value improved by 8.44% and 8.89%, respectively, compared with the BiLSTM-CRF model. Furthermore, the entities of the pest and disease dataset were divided into two different granularities for the comparison experiment; the results show that for entities with “disease names” and “pest names”, the recognition accuracy at the fine-grained level is improved by 32.71% and 31.58%, respectively, compared to the coarse-grained level, and the recognition performance of various fine-grained entities has been improved.

Cyclocarya paliurus is a relict plant species that survived the last glacial period and shows a population expansion recently. Its leaves have been traditionally used to treat obesity and diabetes with the well-known active ingredient cyclocaric acid B. Here, we presented three C. paliurus genomes from two diploids with different flower morphs and one haplotype-resolved tetraploid assembly. Comparative genomic analysis revealed two rounds of recent whole-genome duplication events and identified 691 genes with dosage effects that likely contribute to adaptive evolution through enhanced photosynthesis and increased accumulation of triterpenoids. Resequencing analysis of 45 C. paliurus individuals uncovered two bottlenecks, consistent with the known events of environmental changes, and many selectively swept genes involved in critical biological functions, including plant defense and secondary metabolite biosynthesis. We also proposed the biosynthesis pathway of cyclocaric acid B based on multi-omics data and identified key genes, in particular gibberellin-related genes, associated with the heterodichogamy in C. paliurus species. Our study sheds light on evolutionary history of C. paliurus and provides genomic resources to study the medicinal herbs.

The extraction of entities and relationships is a crucial task in the field of natural language processing (NLP). However, existing models for this task often rely heavily on a substantial amount of labeled data, which not only consumes time and labor but also hinders the development of downstream tasks. Therefore, with a focus on enhancing the model’s ability to learn from small samples, this paper proposes an entity and relationship extraction method based on the Universal Information Extraction (UIE) model. The core of the approach is the design of a specialized prompt template and schema on cotton pests and diseases as one of the main inputs to the UIE, which, under its guided fine-tuning, enables the model to subdivide the entity and relationship in the corpus. As a result, the UIE-base model achieves an accuracy of 86.5% with only 40 labeled training samples, which really solves the problem of the existing models that require a large amount of manually labeled training data for knowledge extraction. To verify the generalization ability of the model in this paper, experiments are designed to compare the model with four classical models, such as the Bert-BiLSTM-CRF. The experimental results show that the F1 value on the self-built cotton data set is 1.4% higher than that of the Bert-BiLSTM-CRF model, and the F1 value on the public data set is 2.5% higher than that of the Bert-BiLSTM-CRF model. Furthermore, experiments are designed to verify that the UIE-base model has the best small-sample learning performance when the number of samples is 40. This paper provides an effective method for small-sample knowledge extraction.

Adventitious root (AR) formation is vital for successful cutting propagation in plants, while the dynamic regulation of phytohormones is viewed as one of the most important factors affecting AR formation. Cyclocarya paliurus, a hard-to-root plant, is faced with the bottleneck of cloning its superior varieties in practice. In this study, ten treatments were designed to figure out the best hormone-based formula for promoting AR formation in softwood cuttings and explore their hormone-regulating mechanisms. Both the rooting process and the rooting parameters of the softwood cuttings were significantly affected by different hormone-based formulas (p < 0.05), while the greatest rooting rate (93%) and root quality index were achieved in the H3 formula (SR3:IR3 = 1:1). Significant differences in the measured phytohormone concentrations, as well as in their ratios, were detected among the cuttings sampled at various AR formation stages (p < 0.05), whereas the dynamics for each phytohormone varied greatly during AR formation. The transcriptome analysis showed 12,028 differentially expressed genes (DEGs) identified during the rooting process of C. paliurus cuttings, while the KEGG enrichment analysis indicated that a total of 20 KEGG terms were significantly enriched in all the comparison samples, with 253 DEGs detected in signal transduction. Furthermore, 19 genes with vital functions in regulating the hormone signaling pathway were identified by means of a WGCNA analysis. Our results not only optimize a hormone-based formula for improving the rooting of C. paliurus cuttings but also provide an insight into the hormonal regulatory network during AR formation in softwood C. paliurus cuttings.

Potato diseases and pests have a serious impact on the quality and yield of potatoes, and timely prevention and control of potato diseases and pests is essential. A rich knowledge reserve of potato diseases and pests is one of the most important prevention and control measures; however, valuable knowledge is buried in the massive data of potato diseases and pests, making it difficult for potato growers and managers to obtain and use it in a timely manner and to develop the potential of knowledge. Therefore, this paper explores the construction method of a knowledge graph for automatic knowledge extraction, which extracts the knowledge of potato diseases and pests scattered in heterogeneous data from multiple sources, organises it into a semantically related knowledge base, and provides potato growers with professional knowledge and timely guidance to effectively prevent and control potato diseases and pests. In this paper, a data corpus on potato diseases and pests, called PotatoRE, is first constructed. Then, a model of ALBert-BiLSTM-Self_Att-CRF is designed to extract knowledge from the corpus to form a triplet structure, which is imported into the Neo4j graph database for storage and visualisation. Furthermore, the performance of the model constructed in this paper is compared and verified using the datasets PotatoRE and People’s Daily. The results show that compared to the SOTA models of ALBert BiLSTM-CRF and ALBert BiGRU-CRF, the accuracy of our model has been improved by 2.92% and 3.12%, respectively, using PotatoRE. Compared to the Bert BiLSTM-CRF model on two datasets, our model not only improves the accuracy, recall, and F1 values, but also has a higher efficiency. The model in this paper solves the problem of the difficult recognition of nested entities. On this basis, through comparative experiments, the TransH model is used to effectively represent the constructed knowledge graph, which lays the foundation for achieving inference, extension, and automatic updating of the knowledge base. The achievements of the thesis have made certain contributions to the automatic construction of large-scale knowledge bases.

The high performance of deep learning networks relies mainly on massive data. However, collecting enough samples of crop disease is impractical, which significantly limits the intelligent diagnosis of diseases. In this study, we propose Heterogeneous Metric Fusion Network-based Few-Shot Learning (HMFN-FSL), which aims to recognize crop diseases with unseen categories using only a small number of labeled samples. Specifically, CBAM (Convolutional Block Attention Module) was embedded in the feature encoders to improve the feature representation capability. Second, an improved few-shot learning network, namely HMFN-FSL, was built by fusing three metric networks (Prototypical Network, Matching Network, and DeepEMD (Differentiable Earth Mover’s Distance)) under the framework of meta-learning, which solves the problem of the insufficient accuracy of a single metric model. Finally, pre-training and meta-training strategies were optimized to improve the ability to generalize to new tasks in meta-testing. In this study, two datasets named Plantvillage and Field-PV (covering 38 categories of 14 crops and containing 50,403 and 665 images, respectively) are used for extensive comparison and ablation experiments. The results show that the HMFN-FSL proposed in this study outperforms the original metric networks and other state-of-the-art FSL methods. HMFN-FSL achieves 91.21% and 98.29% accuracy for crop disease recognition on 5way-1shot, 5way-5shot tasks on the Plantvillage dataset. The accuracy is improved by 14.86% and 3.96%, respectively, compared to the state-of-the-art method (DeepEMD) in past work. Furthermore, HMFN-FSL was still robust on the field scenes dataset (Field-PV), with average recognition accuracies of 73.80% and 85.86% on 5way-1shot, 5way-5shot tasks, respectively. In addition, domain variation and fine granularity directly affect the performance of the model. In conclusion, the few-shot method proposed in this study for crop disease recognition not only has superior performance in laboratory scenes but is also still effective in field scenes. Our results outperform the existing related works. This study provided technical references for subsequent few-shot disease recognition in complex environments in field environments.

Deep convolutional neural networks (DCNN) have shown promising performance in plant disease recognition. However, these networks cannot be deployed on resource-limited smart devices due to their vast parameters and computations. To address the issue of deployability when developing cotton disease identification applications for mobile/smart devices, we compress the disease recognition models employing the pruning algorithm. The algorithm uses the γ coefficient in the Batch Normalization layer to prune the channels to realize the compression of DCNN. To further improve the accuracy of the model, we suggest two strategies in combination with transfer learning: compression after transfer learning or transfer learning after compression. In our experiments, the source dataset is famous PlantVillage while the target dataset is the cotton disease image set which contains images collected from the Internet and taken from the fields. We select VGG16, ResNet164 and DenseNet40 as compressed models for comparison. The experimental results show that transfer learning after compression overall surpass its counterpart. When compression rate is set to 80% the accuracies of compressed version of VGG16, ResNet164 and DenseNet40 are 90.77%, 96.31% and 97.23%, respectively, and the parameters are only 0.30M, 0.43M and 0.26M, respectively. Among the compressed models, DenseNet40 has the highest accuracy and the smallest parameters. The best model (DenseNet40-80%-T) is pruned 75.70% of the parameters and cut off 65.52% of the computations, with the model size being only 2.2 MB. Compared with the version of compression after transfer learning, the accuracy of the model is improved by 0.74%. We further develop a cotton disease recognition APP on the Android platform based on the model and on the test phone, the average time to identify a single image is just 87ms.

Potato canopy nitrogen content (CNC) is an imperative metric for assessing potato growth status and guiding field management. While the spectral index can be utilized to estimate CNC, its efficacy is influenced by the environment and crop type. To address this issue, we utilized hyperspectral indices (HIs) optimization for CNC estimation. Using the inverse and first-order differential (FD) transformations of the original data (OD), HIs comprising two-band combinations in 400–1000 nm, such as RSI, DSI, NDSI, SASI, and PSI, were constructed to analyze the correlation between CNC and HIs. Based on this analysis, prediction models for potato CNC were created using the most optimal HIs. The results showed that FD transformation significantly improved the correlations between CNC and HIs, among which FD−PSI(R654, R565) had the highest correlation with CNC. We further employed the optimal HIs as variables to establish univariate and multivariate regression models to estimate the potato CNC. Among the univariate models, the accuracy of the OD−DSI model was the highest, with an R2 of 0.79 and RMSE of 0.22. Meanwhile, the FD−MLR model demonstrated the highest accuracy compared to the other multivariate models, with an R2 of 0.84, an RMSE of 0.20 during validation, and a greater prediction accuracy than the OD−DSI model. FD−MLR can be used to map the CNC distribution map of monitored potato planting plots to guide precision fertilization.

Cyclocarya paliurus is mainly distributed in subtropical areas of China. Its leaves are rich in beneficial triterpenoids that have bioactivities against human diseases, including hyperlipemia, diabetes, and hypertension. In this study, data on the genetic diversity, distributing environment, and triterpenoids of C. paliurus samples were collected from a wide area in China. The data covered 316 C. paliurus germplasms collected from 26 distinct populations. Association analysis between genotype and triterpenoids was carried out to describe triterpenoids accumulation pattern. Based on our analyses, we identified the important trend that genotypes with higher triterpenoid contents belonged to a unique genotype subgroup. The results showed that pterocaryoside B and pterocaryoside A significantly vary among the genotypic subgroups. In addition, the different genotypic subgroups showed distinct geographical distributing areas. These findings provide information about the relationship between genetic and environmental factors and how this affects triterpenoids accumulation. This information will be valuable for targeted breeding and for further germplasm selection of C. paliurus resources.

The widespread use of petroleum-based products has led to increasing environmental and ecological problems, while the extraction and application of various natural cellulose fibers have received increasing attention. This research focuses on the extraction of cellulose fibers from cow dung using different treatments: hot water, hydrogen peroxide (H2O2), sodium hydroxide (NaOH) and potassium hydroxide (KOH) boilings, as well as a selection of the best quality cow dung fibers for papermaking with quality control. The study’s objective is to find a sustainable method to extract as much material as possible from renewable biomass feedstock. The results show that the best extraction rate is obtained by KOH boiling with 42% cellulose fibers extracted. Corresponding handmade paper has a burst index of 2.48 KPam2/g, a tear index of 4.83 mNm2/g and a tensile index of 26.72 Nm/g. This project expands the sources of natural cellulose fibers to an eco-friendly and sustainable one and opens up new applications for cow dung.

To reveal the strengthening mechanism and re-failure mechanism of grouting on fractured rock, the variable-angle shear tests, real-time acoustic emission (AE) tests and VIC-3D (non-contact full field strain measurement system) tests were carried out on intact red sandstone (IRS) and grouting-reinforced body of fractured red sandstone (GRBFRS). The results show that the peak shear strength of IRS and GRBFRS decreases with the increase of shear angle. Grouting reinforcement mainly increases the cohesion of GRBFRS to improve its shear strength, but its reconstructability decreases with the increase of shear angle. In the whole process of shear deformation, the shear micro damage and shear fracture of GRBFRS are more than those of IRS. Although the shear re-failure before and after the peak stress stage is the most notable, its intensity or degree is reduced. When the shear angle is 45°, both IRS and GRBFRS undergo shear-splitting failure. However, when the shear angle is large, the IRS and GRBFRS only occurs shear failure. Moreover, the larger the shear angle, the more likely IRS and GRBFRS is to produce secondary shear cracks. The low strength of the rock–grout interface in GRBFRS is the main inducer of shear re-failure.

To explore the bolt-grouting method of the deep roadway under three-dimensional unequal ground stress, a unidirectional coupling model of surrounding rock plastic failure and grouting diffusion considering the influence of excavation disturbance stress was established. Spatial evolution characteristics of plastic failure and grouting diffusion, and the impact of the spacing and row spacing of grouting bolts/cables on grout diffusion, were simulated by using the numerical method. The results revealed that the horizontal ground stress perpendicular to the axial direction of the roadway was the main factor inducing roadway damage. Moreover, the more significant the difference of the ground stress in three directions, the larger the plastic zone of the roof corner and floor corner of the roadway. Under different lateral pressure coefficients, the grout diffused can be approximate ellipsoid and cylinders. Furthermore, the larger the ratio of lateral pressure coefficients perpendicular to and parallel to the axial direction of roadway, the larger the diffusion length of grout in each spatial direction in the surrounding rock. In bolt-grouting support, the length of the grouting bolts/cables should be greater than the plastic zone of the surrounding rock, and the optimal relationship between their spacing and row spacing and diffusion length of grout is determined. The research results were applied in the bolt-grouting engineering for the three-level main roadway in the Haizi Coal Mine, and a good support effect was achieved. This can provide technical guidance and a method of reference for the design and parameter optimization of bolt-grouting support for roadways under deep high ground stress.

Cyclocarya paliurus (Batal.) Iljinskaja, as a woody tree species, has various health-promoting phytochemicals and is commonly used in tea production in China. A field trial for C. paliurus was conducted at two typical sites to evaluate genotype × environmental interaction (GEI) effects and identify the stability and adaptability of 13 families. The genotype main effects and genotype × environment interaction effects (GGE) were used to analyze the GEI effects for tree height, diameter at breast height (DBH), and leaf flavonoid and triterpenoid contents. Two-way analysis of variance indicated that the tree growth and leaf phytochemical contents were mainly affected by genotype and GEI. Based on the results of GGE, the JH1 family had high mean values and high stability in total flavonoid and total triterpenoid accumulations, while the KM4 family exhibited high means and high stability in tree height and DBH growth, as well as high means and medium stability in total triterpenoid content. Pearson’s correlation analysis indicated that the annual mean DBH was significantly and positively correlated with leaf phytochemical content in C. paliurus when all data for the 13 families at the two sites were used. Our results suggest that JH1 should be mainly extended as a superior genotype for the production of flavonoids and triterpenoids in the leaves, while KM4 could be spread for timber production or leaf triterpenoid production. This study provides useful information on the selection of C. paliurus genotypes in target sites and cultivation strategies for establishing oriented plantations.

Cyclocarya paliurus (Batal.) Iljinskaja is a plant with nutraceutical importance since its leaves have been used historically as folk medicines for hundreds of years. The content of 10 phenolic compounds was determined throughout the growing season by high-performance liquid chromatography (HPLC) with UV detector, while the antioxidant activities of C. paliurus leaf extracts were evaluated by 1,1-diphenyl-2-picrylhydrazyl (DPPH), 2,2′-azino-bis (3-ethylbenzothiazoline-6-sulfonic acid) diammonium salt radical cation (ABTS), and ferric reducing antioxidant power (FRAP) methods. Seasonal variations in phenolic concentration and antioxidant activity as well as linkage between the phenolic composition and antioxidant activity were assessed. A significant seasonal variation of phenolic compounds was observed in the leaves and the highest content appeared in May, July, and November. Seventy percent ethanol extract of C. paliurus leaves possessed a good radical scavenging potency. Meanwhile, a significant correlation between antioxidant activities and contents of phenolics was detected. Results of the relationship between molecular structures and their antioxidant activities showed that both the number and configuration of H-donating hydroxyl groups are the main structural features influencing the antioxidant capacity of phenolics, while glycosylation may reduce the antioxidant capacity. The information provided by this study not only revealed the accumulative dynamics of phenolic compounds, but also established a basis for determining the optimal time for harvesting to improve the content of beneficial compounds in the leaves of C. paliurus in the future.

Cyclocarya paliurus has been used commonly to treat diabetes in China. However, the effective components and the effect of plant origin remain unclear. In this study, C. paliurus leaves with different chemical compositions were selected from five geographical locations, and their effects on streptozotocin (STZ)-induced diabetic mice were evaluated with both ethanol and aqueous extracts. Glucose levels, lipid levels, and biomarkers of liver and kidney function were measured. The principal components of both C. paliurus ethanol and aqueous extracts from different geographical locations differed quantitatively and qualitatively. Results showed that C. paliurus extracts with better antihyperglycemic effects were characterized by higher contents of total flavonoids, especially quercetin-3-O-glucuronide and kaempferol-3-O-glucuronide. Furthermore, significantly negative correlations were found between triterpenoids contents and lipid levels. These results revealed the potential antihyperglycemic capacity of C. paliurus flavonoids and the antihyperlipidemic effect of C. paliurus triterpenoids. Thus, we suggest that the composition of C. paliurus compounds might help to design therapeutic alternatives for the treatment of diabetes mellitus. However, geographic origins and the extraction solvents can also affect the effectiveness of the treatment as these factors influence the chemical compositions and thereby the biological activities.

Cyclocarya paliurus is an edible and medicinal plant containing various bioactive components with significant health benefits. A combinative method using high-performance liquid chromatography (HPLC) fingerprint and quantitative analysis was developed and successfully applied for characterization and quality evaluation of C. paliurus leaves collected from 18 geographical locations of China. For the fingerprint analysis, 21 common peaks were observed among the 18 samples, and these peaks were identified by high-performance liquid chromatography coupled with quadrupole time-of-flight mass spectrometry (HPLC–Q–TOF–MS), while a simultaneous quantification of 16 markers was conducted to interpret the variations of contents of these bioactive compounds among the C. paliurus leaves from different geographical locations. Quantification results showed that the contents of these sixteen investigated compounds varied greatly among the leaves from different locations. The developed new method would be a valuable reference for further study and development of this bioactive plant.

As a multiple function tree species, Cyclocarya paliurus (Batal) Iljinskaja is mainly planted and managed for timber production and medical use. To improve the seed use efficiency and outplanting performance of C. paliurus, the effects of container types and growth medium on the seedling growth and root morphology of C. paliurus were investigated by using a completely randomized block experimental design with a 4 × 3 factorial arrangement during nursery culture. Both container type and growth medium significantly affected the growth, biomass, and root morphological indexes of C. paliurus seedlings, but container size had a greater effect on the seedling quality of C. paliurus than the growth medium formula. The root-collar diameter and height of the seedlings were positively and significantly correlated with the biomass variables and root morphological variables, and could be considered essential attributes for evaluating seedling quality. Based on the results from this study, the management regime used here in C. paliurus seedling production is suggested to ensure good quality seedling delivery. Our study provides not only valuable insights into the container seedling culture of C. paliurus, it also enables nursery managers to optimize seedling production.

To increase the yield of secondary metabolites, Arbuscular mycorrhiza fungi were used to improve cyclocarya paliurus. The experiment measured growth indicators, biomass, mineral nutrients, etc. The results showed that after inoculation with mycorrhizal fungi the nitrogen content in the leaves of the experimental group was 27.87 mg/g, K content was 7.48 mg/g, Ca content was 26.63 mg/g, and Mg content was 2.82 mg/g. Compared with the control group (Cg), mycorrhizal fungi can promote the absorption of mineral nutrients by C. paliurus seedlings. A. mycorrhizal fungi had a certain influence on the proportion of root, stem, leaf, and total biomass of C. paliurus seedlings, and their biomass distribution in various parts was relatively balanced. A. mycorrhizal fungi can significantly increase the biomass of willow seedlings’ stems and significantly increase their proportion in the total biomass (p < 0.05). After mycorrhizal inoculation, the secondary metabolic yields of quinic acid, quercetin, and kaempferol in C. paliurus leaves were 0.87 mg/g, 0.32 mg/g, and 0.65 mg/g, respectively, higher than those in the Cg. It is concluded that the use of A. mycorrhizal to improve the survival rate of medicinal materials and ensure the quality of medicinal materials is a new idea for the industrial production of C. paliurus. [ABSTRACT FROM AUTHOR]

To address the difficulty of detecting low embedding rate and high-concealment CNV-QIM (complementary neighbor vertices-quantization index modulation) steganography in low bit-rate speech codec, the code-word correlation model based on a BiLSTM (bi-directional long short-term memory) neural network is built to obtain the correlation features of the LPC codewords in speech codec in this paper. Then, softmax is used to classify and effectively detect low embedding rate CNV-QIM steganography in VoIP streams. The experimental results show that for speech steganography of short samples with low embedding rate, the BiLSTM method in this paper has a superior detection accuracy than state-of-the-art methods of the RNN-SM(recurrent neural network-steganalysis model) and SS-QCCN (simplest strong quantization codeword correlation network). At an embedding rate of 20% and a duration of 3 s, the detection accuracy of BiLSTM method reaches 75.7%, which is higher than that of RNNSM by 11.7%. Furthermore, the average testing time of samples (100% embedding) is 0.3 s, which shows that the method can realize real-time steganography detection of VoIP streams. [ABSTRACT FROM AUTHOR]

Identifying event-specific opinion leaders is essential for understanding event developments and influencing public opinion. News articles are informative and formal in expression, and include valuable information on specific events. In this paper, we propose an improved variant of LeaderRank, called local weighted LeaderRank, to measure the event-specific influence of person nodes in a weighted and undirected person cooccurrence network constructed using news articles related to a specific event. Our proposed method measures the influence of person nodes by considering both the cooccurrence strength between persons, and additional local link weight information for each local person node. To evaluate the performance of our method, we use the weighted susceptible infected (WSI) model to simulate the influence-spreading process in real-person cooccurrence networks. The experiment results obtained after measuring the rank correlations between the rank list generated by the simulation results and those generated by the influence measures show that our method identifies event-specific opinion leaders effectively and performs better than other state-of-the-art influence measures, such as weighted K-shell decomposition and the weighted local centrality. [ABSTRACT FROM AUTHOR]