Co-occurrence Relationships Research Articles

Unraveling minnan imagery: a comprehensive analysis of traditional and modern minnan nursery rhymes through complex networks

Nursery rhymes provide insights into the traditions, beliefs, and values of a culture, thereby making it an integral part of a community’s heritage. As representative linguistic resources within the intangible cultural heritage of the Hoklo people, Minnan nursery rhymes (MNRs) play a crucial role in connecting the Chinese mainland, Taiwan Strait, and overseas Chinese communities. This study delves into features of 617 traditional and 289 modern pieces through text mining techniques, including text segmentation, the TF-IDF (term frequency-inverse document frequency) method, and the complex network analysis. We examine the frequency and emotional purity of lyrics at a larger scale than previous studies using a small set of manually annotated samples. Furthermore, we analyze the patterns of MNRs by assessing the overall, individual, core-periphery structures of the constructed MNR networks, considering key terms as nodes and co-occurrence relationships between nodes as links. Our investigation reveals the heterogeneous nature of terms in both traditional and modern MNR networks. Moreover, through the community detection method, we identify five primary imagery features presented in MNRs. Traditional MNRs place emphasis on family relationships, folk culture, and food culture, reflecting enduring aspects of Minnan cultural heritage. In contrast, modern MNRs pivot towards themes of children’s emotions and natural scenery, indicative of evolving societal values. This study represents the first large-scale complex network analysis of MNRs, providing valuable insights into the embedded Minnan culture and serving as a foundation for further research into the societal dynamics reflected in these cherished MNRs resources.

A global bibliometric and visual analysis of research on premature ovarian failure: Based on the perspective of stem cells.

Premature ovarian failure (POF), a condition influenced by genetic and immune factors, remains incurable despite years of intensive research and significant efforts. This persisting challenge underscores the urgency to address this escalating health concern. Fortunately, stem cell regenerative medicine has emerged as a promising avenue for developing therapeutic strategies and innovative treatments for POF. Bibliometric analysis, renowned for its objectivity, systematic approach, and comprehensive coverage of a given field, has yet to be applied to the study of stem cell research in POF. This study used CiteSpace software to assess contributions and co-occurrence relationships among various countries/regions, institutes, journals, and authors. This approach also allowed us to identify research hotspots and promising future trends within this field. Additionally, we generated visualizing maps utilizing the Web of Science Core Collection (WOSCC) and PubMed publications. By providing valuable information and references, we aim to enhance the understanding of the challenges involved in translating stem cell regeneration into clinical therapeutic potential for POF. Furthermore, our analysis and findings guide researchers and clinicians, facilitating future collaborative research and clinical intervention efforts.

Comparative Analysis of Bacterial Information of Biofilms and Activated Sludge in Full-Scale MBBR-IFAS Systems.

This study extensively analyzed the bacterial information of biofilms and activated sludge in oxic reactors of full-scale moving bed biofilm reactor-integrated fixed-film activated sludge (MBBR-IFAS) systems. The bacterial communities of biofilms and activated sludge differed statistically (R = 0.624, p < 0.01). The denitrifying genera Ignavibacterium, Phaeodactylibacter, Terrimonas, and Arcobacter were more abundant in activated sludge (p < 0.05), while comammox Nitrospira was more abundant in biofilms (p < 0.05), with an average relative abundance of 8.13%. Nitrospira and Nitrosomonas had weak co-occurrence relationships with other genera in the MBBR-IFAS systems. Potential function analysis revealed no differences in pathways at levels 1 and 2 based on the Kyoto Encyclopedia of Genes and Genomes (KEGG) between biofilms and activated sludge. However, in terms of pathways at level 3, biofilms had more potential in 26 pathways, including various organic biodegradation and membrane and signal transportation pathways. In comparison, activated sludge had more potential in only five pathways, including glycan biosynthesis and metabolism. With respect to nitrogen metabolism, biofilms had greater potential for nitrification (ammonia oxidation) (M00528), and complete nitrification (comammox) (M00804) concretely accounted for methane/ammonia monooxygenase (K10944, K10945, and K10946) and hydroxylamine dehydrogenase (K10535). This study provides a theoretical basis for MBBR-IFAS systems from the perspective of microorganisms.

Multi-perspective learning for enhanced user preferences for session-based recommendation

Due to the sparsity and anonymity of interactions within sessions, capturing user preferences by modeling item relationships poses a significant challenge. Previous methods have attempted to utilize collaborative information from adjacent sessions or item attribute knowledge as supplements. However, these methods are prone to introducing interfering information through their session similarity measurement strategies and attribute embedding learning processes, both requiring optimization. Moreover, they often fail to fully model global item relationships. To address these issues, we propose a novel method called Multi-perspective Learning for Enhanced User Preferences (MLEUP) for session-based recommendations. Specifically, we first construct reliable session groups by measuring the overlap and incompatibility of items across sessions to calculate session similarity. Then, by modeling attribute–item and attribute–attribute relationships, along with employing a neighbor-based contrastive self-supervised attribute learning task, we learn high-quality attribute embeddings that capture the user’s stable preferences. Next, leveraging the session groups, we model global item multi-granularity co-occurrence and high-order sequential relationships through designed attention layers, enabling us to learn informative item embeddings that represent the user’s dynamic preferences. Finally, we further model the correlated relationship between the two user preference representations. Our approach ensures that effective attribute knowledge and global collaborative information are learned to mitigate the data sparsity issue, while comprehensively modeling global item relationships to capture the user’s complex dynamic preferences. Experimental results demonstrate that MLEUP achieves state-of-the-art performance in terms of precision, MRR, and NDCG. The experimental datasets and source code of MLEUP are publicly available at https://github.com/lean030/MLEUP.

Spotlight on macrophage pyroptosis: A bibliometric and visual analysis from 2001 to 2023

Macrophage pyroptosis plays a significant role in the pathogenesis of various diseases, especially acute lung injury, atherosclerosis, and sepsis. Despite its importance, analysis of the existing literature has been limited. Therefore, we conducted a bibliometric analysis to provide a comprehensive overview of research on macrophage pyroptosis and identify the current research foci and trends in this field. We collected articles related to macrophage pyroptosis published between 2001 and 2022 from the Web of Science Core Collection and PubMed. Citespace, VOSviewer, bibliometrix R package, and Microsoft Excel 2019 were used to analyze co-occurrence relationships and the contribution of countries/regions, institutions, journals, authors, references, and keywords. In total, 1321 papers were included. China and the United States of America published the most articles in this field. TD Kanneganti had the most publications; BT Cookson was the most cited. Although China contributed the most publications, it had a relatively low ratio of multiple-country collaborations (0.132). Among journals, Frontiers in Immunology and Cell Death Disease published the most papers; Nature and the Journal of Immunology were frequently co-cited. Frequently occurring keywords included “inflammation,” “NLRP3 inflammasome,” “apoptosis,” “caspase-1,” and “cell death.” Moreover, with the advancement of gene editing technology and the integration of clinical applications, novel molecules (“caspases,” “GSDMD,” “ASC”), programmed cell death topics (“pyroptosis,” “ferroptosis,” “necrosis”), and clinical applications (“alveolar macrophage,” “atherosclerosis,” “prognosis”) emerged as frontiers. The macrophage pyroptosis field is rapidly evolving and holds promise as a potential target for treating macrophage pyroptosis-related diseases.

Knowledge framework of intravenous immunoglobulin resistance in the field of Kawasakidisease: A bibliometric analysis (1997-2023).

Kawasaki disease (KD) is an autoimmune disease with cardiovascular disease as its main complication, mainly affecting children under 5 years old. KD treatment has made tremendous progress in recent years, but intravenous immunoglobulin (IVIG) resistance remains a major dilemma. Bibliometric analysis had not been used previously to summarize and analyze publications related to IVIG resistance in KD. This study aimed to provide an overview of the knowledge framework and research hotspots in this field through bibliometrics, and provide references for future basic and clinical research. Through bibliometric analysis of relevant literature published on the Web of Science Core Collection (WoSCC) database between 1997 and 2023, we investigated the cooccurrence and collaboration relationships among countries, institutions, journals, and authors and summarized key research topics and hotspots. Following screening, a total of 364 publications were downloaded, comprising 328 articles and 36 reviews. The number of articles on IVIG resistance increased year on year and the top three most productive countries were China, Japan, and the United States. Frontiers in Pediatrics had the most published articles, and theJournal of Pediatricshad the most citations. IVIG resistance had been studied by 1889 authors, of whom Kuo Ho Chang had published the most papers. Research in the field was focused on risk factors, therapy (atorvastatin, tumor necrosis factor-alpha inhibitors), pathogenesis (gene expression), and similar diseases (multisystem inflammatory syndrome in children, MIS-C). "Treatment," "risk factor," and "prediction" were important keywords, providing a valuable reference for scholars studying this field. We suggest that, in the future, more active international collaborations are carried out to study the pathogenesis of IVIG insensitivity, using high-throughput sequencing technology. We also recommend that machine learning techniques are applied to explore the predictive variables of IVIG resistance.

의미 운율의 정도성 연구

This paper aims to explore the need for expanding the scope and methodology of semantic prosody analysis. First, the scope of the co-occurrence relation of the node was expanded to include not only adverbs, but also subjects and words that modify them. The ‘category’ of the evaluative meaning of co-occurring words was analyzed by considering the context, and the ‘degree’ was measured using the KNU Korean Sentiment Lexicon. And the realization type of semantic prosody in the node was compared and analyzed by dividing it into type and co-occurrence relation. The results of the categorical and degree-based approaches to semantic prosody were compared. As a result of the analysis, first, the type of semantic prosody realization and usage patterns of co-occurring words were different depending on the node. Second, the usage patterns of subjects and adverbs were most similar to ‘giinhada-birotada’ and ‘birotada-oda’. Third, nodes with the same semantic prosody category could be compared more precisely by analyzing the degree of semantic prosody. This showed that there is a need to expand the scope of co-occurrence relation and methodology of analysis when analyzing semantic prosody.

Financial Education: Bibliometic Analysis from 1989 to 2023

This study applies a comprehensive bibliometric analysis to financial education research published between 1989 and 2023 with the aim of exploring trends, patterns, and key themes in the field. By collecting data from various Scopus databases, totaling 280 documents, the analysis involves the distribution of publications, identification of influential articles and authors, and exploration of citation and co-occurrence relationships. Visualizing the results using mapping techniques helps depict the structure and dynamics of financial education research during the specified period. Key findings include limited collaboration among authors, uneven contributions across countries, and the emergence of various subfields in the literature. The research implications encompass the necessity for increased collaboration among researchers to address collaboration gaps, providing in-depth insights into the global distribution of research contributions, and offering insights for future research and policy in financial education.

Abstract LB414: Novel ALK/PIK3CA cooperativity in head and neck squamous cell carcinoma (HNSCC) progression

Abstract Recent genomic characterization studies have demonstrated the genetic heterogeneity of head and neck squamous cell carcinoma (HNSCC). Yet, most of these genetic aberrations remain undruggable. Anaplastic Lymphoma Kinase (ALK) is somatically mutated in ~3.6% of HNSCC (18/504 cases, TCGA-HNSCC Firehose cohort, USA), and the majority of these ALK-mutated HNSCC cases are of advanced stage diseases. Here, we hypothesized that ALK mutations might plausibly contribute to HNSCC progression and could be potentially druggable. Unexpectedly, analysis of HNSCC genomic events revealed a novel co-occurrence relationship between ALK and PIK3CA genomic aberrations in TCGA-HNSCC Firehose cohort (Odds Ratio=2.41; N=522 samples with CNV data), with subsequent validation in an independent metastatic MSK-MetTropism HNSCC cohort (Odds Ratio=5.12; N=412). Consistent with this newly identified co-occurrence relationship, we showed that all 7 HNSCC-relevant ALK point mutations were potent drivers for HNSCC invasiveness and clonogenic growth only in corroboration with PIK3CA aberrations in HNSCC cell models, highlighting the functional importance of this novel ALK/PIK3CA cooperativity in HNSCC, likely reminiscent of ALK/MYCN cooperativity in neuroblastoma. Further, by clonogenic assay, we demonstrated pharmacologic vulnerabilities of all 7 ALK point mutations (including extracellular domain mutations) to ALK targeting by ceritinib in FaDu cell background with endogenous PIK3CA amplification. Strikingly, we were able to capture, for the first time, spontaneous emergence of a druggable ALK somatic mutation directly from a PIK3CA-altered HNSCC patient-derived culture (PDC) upon forced acquisition of anoikis-resistance ex vivo (PDC-25-AR), demonstrating co-evolution of ALK/PIK3CA aberrations in HNSCC likely associated with cancer progression. Patient-derived culture-xenograft (PDCx) of PDC-25-AR displayed remarkable sensitivity to ALK targeting, PI3K targeting, as well as their combination, with induction of apoptosis in these tumors compared to vehicle control. In conclusion, ALK aberrations corroborate with PIK3CA aberrations to promote HNSCC progression, yet, these events are potentially druggable in advanced HNSCC. Citation Format: Lan Wang, Helen Hoi-Yin Chan, Angel Yee Lok Fung, Yuen-Keng Ng, Patrick Kwok-Shing Ng, Yuxiong Su, Jason Ying Kuen Chan, Peony Hiu Yan Poon, Thomas Chun Kit Yeung, Chi Man Tsang, Hoi-Lam Ngan, Wenying Piao, Yuchen Liu, Jack Nimitz Smith, Tin Yu Samuel Law, Ee Ling Kong, Melissa Sue Ann Chan, Chun Ho Law, Sze-Man Chan, Zoey Wing Yee Liu, Joshua Chung-Hymn Ng, Gordon B. Mills, Vivian W.Y. Lui. Novel ALK/PIK3CA cooperativity in head and neck squamous cell carcinoma (HNSCC) progression [abstract]. In: Proceedings of the American Association for Cancer Research Annual Meeting 2024; Part 2 (Late-Breaking, Clinical Trial, and Invited Abstracts); 2024 Apr 5-10; San Diego, CA. Philadelphia (PA): AACR; Cancer Res 2024;84(7_Suppl):Abstract nr LB414.

Genetic and Functional Diversity Help Explain Pathogenic, Weakly Pathogenic, and Commensal Lifestyles in the Genus Xanthomonas.

The genus Xanthomonas has been primarily studied for pathogenic interactions with plants. However, besides host and tissue-specific pathogenic strains, this genus also comprises nonpathogenic strains isolated from a broad range of hosts, sometimes in association with pathogenic strains, and other environments, including rainwater. Based on their incapacity or limited capacity to cause symptoms on the host of isolation, nonpathogenic xanthomonads can be further characterized as commensal and weakly pathogenic. This study aimed to understand the diversity and evolution of nonpathogenic xanthomonads compared to their pathogenic counterparts based on their cooccurrence and phylogenetic relationship and to identify genomic traits that form the basis of a life history framework that groups xanthomonads by ecological strategies. We sequenced genomes of 83 strains spanning the genus phylogeny and identified eight novel species, indicating unexplored diversity. While some nonpathogenic species have experienced a recent loss of a type III secretion system, specifically the hrp2 cluster, we observed an apparent lack of association of the hrp2 cluster with lifestyles of diverse species. We performed association analysis on a large data set of 337 Xanthomonas strains to explain how xanthomonads may have established association with the plants across the continuum of lifestyles from commensals to weak pathogens to pathogens. Presence of distinct transcriptional regulators, distinct nutrient utilization and assimilation genes, transcriptional regulators, and chemotaxis genes may explain lifestyle-specific adaptations of xanthomonads.

Knowledge mapping and global trends of drug hypersensitivity from 2013 to 2023: A bibliometric analysis.

Drug hypersensitivity is a major global public health issue with a significant increase in prevalence in populations. Here, we provide a deep insight into the frontier hotspot and future direction in the field of drug hypersensitivity. A knowledge map is portrayed based on publications related to drug hypersensitivity from Web of Science Core Collection using CiteSpace. Co-occurrence relationships of countries, institutes, authors, journals, references, and keywords are constructed. According to the co-occurrence relationships, hotspots and future trends are overviewed. The United States ranked first in the world and China with the second highest publications was the only developing country. Torres, Mayorga, and Blanca were highly productive authors. Harvard University was the institution with the most research publications. Keywords co-occurrence analysis suggested applications in emerging causes, potential mechanisms, and clinical diagnosis as the research hotspots and development frontiers. Research on drug hypersensitivity is in a rapid development stage and an emerging trend in reports of anaphylaxis to polyethylene glycols is identified. Developing algorithms for understanding the standardization process of culprit drugs, clinical manifestations, and diagnostic methods will be the focus of future direction. In addition, a better understanding of the mechanisms to culprit drugs with immunological precise phenotypic definitions and high-throughput platforms is needed.

Blood microbial signatures associated with mortality in patients with sepsis: A pilot study

Sepsis is a life-threatening illness caused by the dysregulated host response to infection. Nevertheless, our current knowledge of the microbial landscape in the blood of septic patients is still limited. Next-generation sequencing (NGS) is a sensitive method to quantitatively characterize microbiomes at various sites of the human body. In this study, we analyzed the blood microbial DNA of 22 adult patients with sepsis and 3 healthy subjects. The presence of non-human DNA was identified in both healthy and septic subjects. Septic patients had a markedly altered microbial DNA profile compared to healthy subjects over α- and β-diversity. Unexpectedly, the patients could be further divided into two subgroups (C1 and C2) based on β-diversity analysis. C1 patients showed much higher bacteria, viruses, fungi, and archaea abundance, and a higher level of α-diversity (Chao1, Observed and Shannon index) than both C2 patients and healthy subjects. The most striking difference was seen in the case of Streptomyces violaceusniger, Phenylobacterium sp. HYN0004, Caulobacter flavus, Streptomyces sp. 11-1-2, and Phenylobacterium zucineum, the abundance of which was the highest in the C1 group. Notably, C1 patients had a significantly poorer outcome than C2 patients. Moreover, by analyzing the patterns of microbe-microbe interactions in healthy and septic subjects, we revealed that C1 and C2 patients exhibited distinct co-occurrence and co-exclusion relationships. Together, our study uncovered two distinct microbial signatures in the blood of septic patients. Compositional and ecological analysis of blood microbial DNA may thus be useful in predicting mortality of septic patients.

Examining the structure of MPs in the UK-China relationship using speech-word pair bipartite networks

PurposeThis study proposes a novel method utilising a speech-word pair bipartite network to examine the correlation structure between members of parliament (MPs) in the context of the UK- China relationship.Design/methodology/approachWe construct MP-word pair bipartite networks based on the co-occurrence relationship between MPs and words in their speech content. These networks are then mapped into monopartite MPs correlation networks. Additionally, the study calculates correlation network indicators and identifies MP communities and factions to determine the characteristics of MPs and their interrelation in the UK-China relationship. This includes insights into the distribution of key MPs, their correlation structure and the evolution and development trends of MP factions.FindingsAnalysis of the parliamentary speeches on China-related affairs in the British Parliament from 2011 to 2020 reveals that the distribution and interrelationship of MPs engaged in UK-China affairs are centralised and discrete, with a few core MPs playing an integral role in the UK-China relationship. Among them, MPs such as Lord Ahmad of Wimbledon, David Cameron, Lord Hunt of Chesterton and Lord Howell of Guildford formed factions with significant differences; however, the continuity of their evolution exhibits unstableness. The core MP factions, such as those led by Lord Ahmad of Wimbledon and David Cameron, have achieved a level of maturity and exert significant influence.Research limitations/implicationsThe research has several limitations that warrant acknowledgement. First, we mapped the MP-word pair bipartite network into the MP correlation network for analysis without directly analysing the structure of MPs based on the bipartite network. In future studies, we aim to explore various types of analysis based on the proposed bipartite networks to provide more comprehensive and accurate references for studying UK-China relations. In addition, we seek to incorporate semantic-level analyses, such as sentiment analysis of MPs, into the MP-word -pair bipartite networks for in-depth analysis. Second, the interpretations of MP structures in the UK-China relationship in this study are limited. Consequently, expertise in UK-China relations should be incorporated to enhance the study and provide more practical recommendations.Practical implicationsFirstly, the findings can contribute to an objective understanding of the characteristics and connotations of UK-China relations, thereby informing adjustments of focus accordingly. The identification of the main factions in the UK-China relationship emphasises the imperative for governments to pay greater attention to these MPs’ speeches and social relationships. Secondly, examining the evolution and development of MP factions aids in identifying a country’s diplomatic focus during different periods. This can assist governments in responding promptly to relevant issues and contribute to the formulation of effective foreign policies.Social implicationsFirst, this study expands the research methodology of parliamentary debates analysis in previous studies. To the best of our knowledge, we are the first to study the UK-China relationship through the MP-word-pair bipartite network. This outcome inspires future researchers to apply various knowledge networks in the LIS field to elucidate deeper characteristics and connotations of UK-China relations. Second, this study provides a novel perspective for UK-China relationship analysis, which deepens the research object from keywords to MPs. This finding may offer important implications for researchers to further study the role of MPs in the UK-China relationship.Originality/valueThis study proposes a novel scheme for analysing the correlation structure between MPs based on bipartite networks. This approach offers insights into the development and evolving dynamics of MPs.

Event type induction using latent variables with hierarchical relationship analysis

The conventional approach to event extraction requires predefined event types and their corresponding annotations to train event extractors. However, these prerequisites are often difficult to satisfy in real-world applications. To automatically induct event types, most work has been devoted to clustering event triggers, where a cluster of event triggers is represented as an event type. Some works use trigger semantics, while others use co-occurrence relationships to cluster triggers. However, the clustering results of event triggers obtained by the above work are not sufficiently detailed in describing event types, making it difficult to accurately determine the corresponding event types manually. This paper proposes an open-domain event type induction framework that automatically discovers a set of event types from a given corpus. Unlike previous work on event trigger clustering, this paper takes into consideration the hierarchical relationship of event types to partition the event trigger clusters into event mains and subtypes. The framework employs a latent variable-based neural generation module and a semantic-based clustering module, the former of which obtains event trigger clusters representing the main types of events by jointly projecting the co-occurrence and semantic information of event triggers into a latent space for event type latent variable mining, and the latter of which further divides these event trigger clusters into event subtypes based on semantic information. Finally, experiment results show that, compared with the benchmark model, the ETGen-Clus can improve event type quality scores of 6.23% and 3.11% on the two datasets, respectively.

Scenery deconstruction: a new approach to understanding the historical characteristics of Nanjing cultural landscape

The “Eight Scenic Views Paintings” represent crucial visual materials for investigating the history of cultural landscapes. However, traditional methods of interpreting materials struggle to discern the inherent connections between different landscape elements. This study proposes an approach for deconstructing historical images, taking the example of the Forty Scenic Views in the Late Ming Dynasty in Nanjing, China. To explore the co-occurrence structure, hierarchical clustering, and correlation features among various elements, various digital humanities quantification methods were applied, including spatial analysis of ArcGIS, co-occurrence and clustering of KH Coder, and correlation analysis of SPSS. This study reveals the characteristics of the landscape construction of Nanjing in the Late Ming: natural landscape as the foundation, artificial landscape as the core, and advocating tradition as the fashion. It also uncovers the landscape order: mountains, waters, and scenic views interweaved and coexisted, as well as nature and culture intertwined and clustered. In addition, multiple information graphs of the subordinate and co-occurrence relationships of 20 landscape elements were constructed, 5 landscape paradigms were extracted, and 36 pairs of related relationships were discovered, deepening the historical understanding of the urban landscape construction of Nanjing in the Late Ming. This paper puts forward the idea of analyzing historical images by digital method, which provides some essential and detailed historical basis for explaining the value of cultural landscape heritage and shaping contemporary urban landscape.

Self-supervised hypergraph neural network for session-based recommendation supported by user continuous topic intent

Session-based recommendation aims to predict the next item an anonymous user is most likely to click based on its limited historical behaviors. However, in session-based recommendation, the anonymity and short sequences often lead to the issue of data sparsity, which can affect the performance of recommendation models. Existing recommendation methods mostly focus on individual items in the session sequence, without considering the implicit user continuous intent underlying multiple continuous items. Moreover, current graph-based recommendation models do not fully take into account the direction of information transfer among shared items when calculating their similarities. This paper proposes, TCAUIS, a topic classification augmented user intend self-supervised hypergraph neural network for session-based recommendation, which contains continuous topic intent of users within a session and the information of co-occurrence items. The TCAUIS models a individual session sequence as a topic intent hypergraph and co-occurrence graph respectively, and employs latent Dirichlet allocation to classify the topic of the dataset and fuses the topic hyperedges into the hypergraph to alleviate the sparsity of the data and enhance the session information. Additionally, the hypergraph attention networks and attention mechanisms are leveraged to capture the complex high-order information between nodes in both the hypergraphs and co-occurrence graphs. The continuous topic intent of users and information of co-occurrence relationship are effectively integrated using a self-supervised mechanism that maximizes the mutual information between the representations of two sessions. Extensive experimental results show that the proposed TCAUIS model outperforms the state-of-the-art models on three real datasets Diginetica, Yoochoose1/64 and Nowplaying.

CKTN: Commonsense knowledge transfer network for human activity understanding

In most human activity understanding research, various deep learning networks are well designed to fit the character distribution of different human activities in images. After being fed with enough training data, the networks can perceive related patterns passively. Such abilities originate from the stimulation of training data, but these networks lack the ability to perform subjective judgment. When lacking sufficient training data, networks have difficulty perceiving valuable information, which leads to poor performance. However, human beings can infer human activities in complex situations through subjective judgment with their knowledge. On this point, we propose the commonsense knowledge transfer network (CKTN), which is empowered with human cognitive mechanisms and is able to understand human activities by using prior commonsense knowledge. More specifically, we study the structural combination rules of human bodies and explore the co-occurrence relationship between different body parts and objects. Then, we construct the part action cooccurrence probability matrix and human skeleton knowledge matrix, which work as prior knowledge, guiding our network to absorb and reason what the human activities in images are. Compared with traditional deep learning methods, our network realizes the unification of both subjective cognition and passive perception abilities. Experiments show the effectiveness of this method.

Metagenomics reveals differences in the composition of bacterial antimicrobial resistance and antibiotic resistance genes in pasteurized yogurt and probiotic bacteria yogurt from China

Antimicrobial resistance has become a global public health concern, and antibiotic resistance genes (ARG) in food are a research focus. In China, probiotics and pasteurized yogurts are the 2 main types of commercially available yogurt, but the distribution and differences of antibiotic-resistant bacteria and gene types in these products are not well known. This study used a shotgun metagenomic approach to analyze 22 different types of yogurt collected from 9 main yogurt-producing areas in China; each type of yogurt included 8 different batches of samples. The abundance and diversity of bacteria identified in probiotic yogurt were significantly higher than those in pasteurized yogurt, with Acetobacter, Raoultella, and Burkholderia identified as unique and highly abundant genera in probiotic yogurt. Similarly, the abundance of Enterococcus faecium, Staphylococcus aureus, Klebsiella pneumoniae, Acinetobacter baumannii, Pseudomonas aeruginosa, and Enterobacter spp. was higher than that in pasteurized yogurt. A total of 1,149 ARG subtypes belonging to 16 ARG types were identified, with the highest abundance of rifampicin, multidrug efflux pumps, and quinolone resistance genes detected. Network analysis revealed significant nonrandom co-occurrence relationships between different types and subtypes of ARG in yogurt samples. A total of 44 ARG subtypes in pasteurized yogurt were potentially hosted by 36 bacterial genera, and in probiotic yogurt, 63 ARG were expected to be hosted by 86 bacterial species from 37 genera. These findings indicate potential safety issues in fermented dairy products and emphasize the need for a more hygienic environment when processing probiotic yogurt.

Multi-Label Text Classification Model Based on Multi-Level Constraint Augmentation and Label Association Attention

In the multi-label text classification task, a text usually corresponds to multiple label categories, and the labels have correlation and hierarchical structure. However, when the label hierarchy is unknown, the number of various labels is not balanced, which makes it difficult for the model to classify low-frequency labels. In addition, labels have semantic similarities that make it difficult for the model to distinguish between them. In this article, we propose a multi-label text classification model based on multi-level constraint augmentation and label association attention. Compared with traditional methods, our method has two contributions: (1) In order to alleviate the problem of unbalanced number of different label categories and ensure the rationality of sample generation, we propose a data augmentation method based on multi-level constraints. In the process of sample generation, this method uses historical generation information, sample original text information, and sample topic to constrain the generated text. (2) In order to make the model recognize the associated labels accurately, we propose an interaction mechanism based on label association attention and filter gate. This method combines text information and label weight information. At the same time, our classification model considers the important weights of text sentences and effectively utilizes the co-occurrence relationship between labels. Experimental results on three benchmark datasets show that our model outperforms state-of-the-art methods on all main evaluation metrics, especially on low-frequency label prediction with sparse samples.

Semantic interleaving global channel attention for multilabel remote sensing image classification

ABSTRACT Multilabel remote sensing image classification (MLRSIC) has received increasing research interest. Taking the co-occurrence relationship of multiple labels as additional information helps to improve the overall performance. However, current methods only focus on using it to constrain the final feature which is output from a convolutional neural network (CNN). On the one hand, these methods need to exploit the potential of label correlation in feature representation fully. On the other hand, they increase the label noise sensitivity of the system, resulting in poor robustness. In this paper, a novel method called ‘Semantic Interleaving Global chaNnel Attention’ (SIGNA) is proposed for MLRSIC. First, the label co-occurrence graph is obtained according to the statistical information of the training set and fed into a graph neural network (GNN) to generate optimal semantic feature representations of each label. Next, the semantic features are interleaved with visual features which are extracted by CNNs to guide the overall features of the input image transform from the original feature space to the semantic feature space with embedded label relations. Then, global attention triggered by semantic interleaving is used to emphasize visual features in important channels. Finally, to make SIGNA easier to use and more optimized, multihead SIGNA-based feature adaptive weighting networks are proposed as plug-in blocks to plug into any layers of a CNN. For remote sensing images, better classification performance can be achieved by inserting the plug-in blocks into the shallow layers of CNNs. We conducted extensive experimental comparisons on three data sets: UCM, AID and DFC15. Experimental results demonstrate that the proposed SIGNA achieves superior classification performance compared to state-of-the-art (SOTA) methods. Notes that the codes of this paper will be open to the community for reproducibility research.