Search

The k-Nearest Neighbors (kNN) method, established in 1951, has since evolved into a pivotal tool in data mining, recommendation systems, and Internet of Things (IoT), among other areas. This paper presents a comprehensive review and performance analysis of modifications made to enhance the exact kNN techniques, particularly focusing on kNN Search and kNN Join for high-dimensional data. We delve deep into 31 kNN search methods and 12 kNN join methods, providing a methodological overview and analytical insight into each, emphasizing their strengths, limitations, and applicability. An important feature of our study is the provision of the source code for each of the kNN methods discussed, fostering ease of experimentation and comparative analysis for readers. Motivated by the rising significance of kNN in high-dimensional spaces and a recognized gap in comprehensive surveys on exact kNN techniques, our work seeks to bridge this gap. Additionally, we outline existing challenges and present potential directions for future research in the domain of kNN techniques, offering a holistic guide that amalgamates, compares, and dissects existing methodologies in a coherent manner. [ABSTRACT FROM AUTHOR]

Cryogenic electron microscopy (cryo-EM) has emerged as a powerful method for the determination of structures of complex biological molecules. The accurate characterisation of the dynamics of such systems, however, remains a challenge. To address this problem, we introduce cryoENsemble, a method that applies Bayesian reweighting to conformational ensembles derived from molecular dynamics simulations to improve their agreement with cryo-EM data, thus enabling the extraction of dynamics information. We illustrate the use of cryoENsemble to determine the dynamics of the ribosome-bound state of the co-translational chaperone trigger factor (TF). We also show that cryoENsemble can assist with the interpretation of low-resolution, noisy or unaccounted regions of cryo-EM maps. Notably, we are able to link an unaccounted part of the cryo-EM map to the presence of another protein (methionine aminopeptidase, or MetAP), rather than to the dynamics of TF, and model its TF-bound state. Based on these results, we anticipate that cryoENsemble will find use for challenging heterogeneous cryo-EM maps for biomolecular systems encompassing dynamic components. [ABSTRACT FROM AUTHOR]

Soundscape analysis has become integral to environmental monitoring, particularly in marine and terrestrial settings. Fish choruses within marine ecosystems provide essential descriptors for environmental characterization. This study employed a month-long sequence of continuous underwater recordings to generate 24-h spectrograms, utilizing Principal Component Analysis (PCA) specifically adapted to analyze fish choruses. The spectrograms were constructed using a frequency range from 0 to 5 kHz, represented by 1,025 spectral points (frequency binwidth 5 Hz) on a linear scale. A preliminary spectral subsampling reduced the frequency components to 205 spectral points. PCA was then applied to this subsampled data, selecting 7 principal components (PCs) that explained 95% of the variance. To enhance visualization and interpretation, we introduced "acoustic maps" portrayed as heatmaps. This methodology proved valuable in characterizing the structure of the observed environment and capturing pertinent diel patterns of fish choruses. Additionally, these PCA components can be analyzed using acoustic maps to reveal hidden dynamics within the marine acoustic environment. The dimensionality reduction achieved by PCA not only streamlined data handling but also enabled the extraction of spectral information pertinent to fish choruses and the temporal dynamics of the soundscape. In conclusion, our methodology presents a versatile framework extendable to diverse biological choruses and ecoacoustic studies. The straightforward, easily interpretable analysis leverages computations derived from 24-h spectrograms, offering novel insights into the daily dynamics of biological. Choruses and contributing to future advancements in ecoacoustic research. [ABSTRACT FROM AUTHOR]

The increasing variety of research strategies and data collection techniques in information science, the access to large secondary data sets, and the ubiquity of information visualization call for expanding the classification of research methods and exploring how research is communicated visually. This study examined the relationship between types of data used in empirical research, visualizations, and research methods applied in information science studies. It analyzed 751 research articles published in the Journal of the Association for Information Science and Technology (JASIST) using content analysis and machine learning techniques. The study finds that most empirical studies adopted a quantitative design with data mining, bibliometrics, experiments, and surveys as dominant strategies. The substantial use of secondary data points to the shift in how data are collected in empirical research. The JASIST articles used a variety of visualizations to present research designs and findings, with quantitative and mixed methods studies employing primarily tables and charts and qualitative studies relying more on tables and diagrams. This study uniquely explores the relationship between research methods and visualization. It contributes to the classification of the methods in information science by expanding the range of strategies within the quantitative, qualitative, and mixed methods designs. [ABSTRACT FROM AUTHOR]

The study of drug–target interaction plays an important role in the process of drug development. The subject of DTI forecasting has advanced significantly in the last several years, yielding numerous significant research findings and methodologies. Heterogeneous data sources provide richer information and comprehensive perspectives for drug–target interaction prediction, so many existing methods rely on heterogeneous networks, and graph embedding technology becomes an important technology to extract information from heterogeneous networks. These approaches, however, are less concerned with potential noisy information in heterogeneous networks and more focused on the extent of information extraction in those networks. Based on this, a potential DTI predictive network model called FBRWPC is proposed in this paper. It uses a fine-grained similarity selection program to first integrate similarity on similar networks and then a bidirectional random walk graph embedding learning method with restart to obtain an updated drug target interaction matrix. Through the use of similarity selection and fine-grained selection similarity integration, the framework can effectively filter out the noise present in heterogeneous networks and enhance the model's prediction performance. The experimental findings demonstrate that, even after being split up into four distinct types of data sets, FBRWPC can still retain great prediction performance, a sign of the model's resilience and good generalization. [ABSTRACT FROM AUTHOR]

Caffeine is a widely used drug that broadly affects human cognition and brain function. Caffeine acts as an antagonist to the adenosine receptors in the brain. Previous anecdotal reports have also linked caffeine intake with changes in pupil diameter. By modifying the retinal irradiance, pupil diameter modulates all ocular light exposure relevant for visual (i.e., perception, detection and discrimination of visual stimuli) and non-visual (i.e., circadian) functions. To date, the extent of the influence of caffeine on pupillary outcomes, including pupil diameter, has not been examined in a systematic review. We implemented a systematic review laid out in a pre-registered protocol following PRISMA-P guidelines. We only included original research articles written in English reporting studies with human participants, in which caffeine was administered, and pupil diameter was measured using objective methods. Using broad search strategies, we consulted various databases (PsycINFO, Medline, Embase, Cochrane Library, bioRxiv and medRxiv) and used the Covidence platform to screen, review and extract data from studies. After importing studies identified through database search (n = 517 imported, n = 46 duplicates), we screened the title and abstracts (n = 471), finding 14 studies meeting our eligibility criteria. After full-text review, we excluded seven studies, leaving only a very modest number of included studies (n = 7). Extraction of information revealed that the existing literature on the effect of caffeine on pupil parameters is very heterogeneous, differing in pupil assessment methods, time of day of caffeine administration, dose, and protocol timing and design. The evidence available in the literature does not provide consistent results but studies rated as valid by quality assessment suggest a small effect of caffeine on pupil parameters. We summarize the numeric results as both differences in absolute pupil diameter and in terms of effect sizes. More studies are needed using modern pupil assessment methods, robust study design, and caffeine dose–response methodology. [ABSTRACT FROM AUTHOR]

Objective To investigate the key elements for model establishment and determine the evaluation indicators of animal models for pelvic inflammatory disease (PID), providing a reference for improving modelling methods and optimizing the application of PID animal models. Methods The search query "Pelvic Inflammatory Disease" AND "Animal Model" OR "Rat" OR "Mouse" OR" Guinea Pig" OR "Rabbit" OR "Dog" OR "Pig" was used to retrieve relevant literature on PID animal models published from 2013 to 2023 in China Knowledge Network Infrastructure (CNKI), Wanfang, and PubMed databases. The studies were analyzed and categorized based on experimental animal types, modelling methods, modelling cycles, detection indicators, positive control drugs, and administration duration. A database was established for statistical analysis. Results A total of 214 research articles on PID animal models meeting the inclusion criteria were identified. The most commonly used model animals are Sprague Dawley (SD) rats, followed by Wistar rats. The most frequently employed modelling method is a combination of mechanical injury and bacterial infection, followed by the phenol mucilage method. The most common modelling cycles for acute pelvic inflammatory disease (APID) and chronic pelvic inflammatory disease (CPID)/sequelae of pelvic inflammatory disease (SPID) are 8 to 14 days, while for PID models without specific staging, the cycles are 7 days. High-frequency detection methods and indicators include histopathological observation using hematoxylin-eosin staining, enzyme-linked immunosorbent assay (ELISA) for serum-related indicators, morphological changes of tissues observed with the naked eye, and immunohistochemical detection of related protein expression in uterine tissues, and pathological scoring. The most frequently used positive control drugs are Fuke Qianjin Tablets, followed by Jingangteng Capsules. The most common administration duration for APID is 7 days, and for CPID/SPID models, it ranges from 15 to 21 days. Conclusion Currently, SD rats and Wistar rats are commonly used as experimental animals for PID models. The dual modelling method of mechanical injury combined with mixed bacterial infection aligns closely with clinical pathogenesis and can be used to establish a PID model that simulates postoperative uterine cavity infection. Depending on the research objectives, different positive drugs and detection indicators should be selected for comprehensive evaluation. Most existing PID animal model studies are based on western medical diagnosis, with fewer studies focusing on Traditional Chinese Medicine (TCM) syndromes. There is a need to integrate TCM theories of etiology and pathogenesis to construct PID animal models that are more in line with TCM clinical symptoms. [ABSTRACT FROM AUTHOR]

BACKGROUND: The field of toxicology has witnessed substantial advancements in recent years, particularly with the adoption of new approach methodologies (NAMs) to understand and predict chemical toxicity. Class-based methods such as clustering and classification are key to NAMs development and application, aiding the understanding of hazard and risk concerns associated with groups of chemicals without additional laboratory work. Advances in computational chemistry, data generation and availability, and machine learning algorithms represent important opportunities for continued improvement of these techniques to optimize their utility for specific regulatory and research purposes. However, due to their intricacy, deep understanding and careful selection are imperative to align the adequate methods with their intended applications. OBJECTIVES: This commentary aims to deepen the understanding of class-based approaches by elucidating the pivotal role of chemical similarity (structural and biological) in clustering and classification approaches (CCAs). It addresses the dichotomy between general end point–agnostic similarity, often entailing unsupervised analysis, and end point–specific similarity necessitating supervised learning. The goal is to highlight the nuances of these approaches, their applications, and common misuses. DISCUSSION: Understanding similarity is pivotal in toxicological research involving CCAs. The effectiveness of these approaches depends on the right definition and measure of similarity, which varies based on context and objectives of the study. This choice is influenced by how chemical structures are represented and the respective labels indicating biological activity, if applicable. The distinction between unsupervised clustering and supervised classification methods is vital, requiring the use of end point–agnostic vs. end point–specific similarity definition. Separate use or combination of these methods requires careful consideration to prevent bias and ensure relevance for the goal of the study. Unsupervised methods use end point– agnostic similarity measures to uncover general structural patterns and relationships, aiding hypothesis generation and facilitating exploration of datasets without the need for predefined labels or explicit guidance. Conversely, supervised techniques demand end point–specific similarity to group chemicals into predefined classes or to train classification models, allowing accurate predictions for new chemicals. Misuse can arise when unsupervised methods are applied to end point–specific contexts, like analog selection in read-across, leading to erroneous conclusions. This commentary provides insights into the significance of similarity and its role in supervised classification and unsupervised clustering approaches. [ABSTRACT FROM AUTHOR]

Web crawler detection is critical for preventing unauthorized extraction of valuable information from websites. Current methods rely on heuristics, leading to time-consuming processes and inability to detect novel crawlers. Privacy protection and communication burdens during training are overlooked, resulting in potential privacy leaks. To address these issues, we propose a federated deep learning crawler detection model that analyzes access behaviors while preserving privacy. First, individual clients locally host website data, while the central server aggregates information for detection model parameters, eliminating raw user data transmission or access. We then develop an innovative algorithm constructing access path trees from user logs, effectively extracting temporal and spatial behavior features. Additionally, we propose a novel time series model with fused additive attention, enabling effective web crawler detection while preserving privacy and reducing data transmission. Finally, comprehensive evaluations on public datasets demonstrate robust privacy protection and effective detection of emerging crawler types. [ABSTRACT FROM AUTHOR]

Gene co-expression networks are valuable tools for discovering biologically relevant information within gene expression data. However, analysing large datasets presents challenges due to the identification of nonlinear gene–gene associations and the need to process an ever-growing number of gene pairs and their potential network connections. These challenges mean that some experiments are discarded because the techniques do not support these intense workloads. This paper presents pyEnGNet, a Python library that can generate gene co-expression networks in High-performance computing environments. To do this, pyEnGNet harnesses CPU and multi-GPU parallel computing resources, efficiently handling large datasets. These implementations have optimised memory management and processing, delivering timely results. We have used synthetic datasets to prove the runtime and intensive workload improvements. In addition, pyEnGNet was used in a real-life study of patients after allogeneic stem cell transplantation with invasive aspergillosis and was able to detect biological perspectives in the study. [ABSTRACT FROM AUTHOR]

Purpose: This study utilized data mining and machine learning (ML) techniques to identify new patterns and classifications of the associations between nutrient intake and anemia among university students. Methods: We employed K-means clustering analysis algorithm and Decision Tree (DT) technique to identify the association between anemia and vitamin and mineral intakes. We normalized and balanced the data based on anemia weighted clusters for improving ML models' accuracy. In addition, t-tests and Analysis of Variance (ANOVA) were performed to identify significant differences between the clusters. We evaluated the models on a balanced dataset of 755 female participants from the Hebron district in Palestine. Results: Our study found that 34.8% of the participants were anemic. The intake of various micronutrients (i.e., folate, Vit A, B5, B6, B12, C, E, Ca, Fe, and Mg) was below RDA/AI values, which indicated an overall unbalanced malnutrition in the present cohort. Anemia was significantly associated with intakes of energy, protein, fat, Vit B1, B5, B6, C, Mg, Cu and Zn. On the other hand, intakes of protein, Vit B2, B5, B6, C, E, choline, folate, phosphorus, Mn and Zn were significantly lower in anemic than in non-anemic subjects. DT classification models for vitamins and minerals (accuracy rate: 82.1%) identified an inverse association between intakes of Vit B2, B3, B5, B6, B12, E, folate, Zn, Mg, Fe and Mn and prevalence of anemia. Conclusions: Besides the nutrients commonly known to be linked to anemia—like folate, Vit B6, C, B12, or Fe—the cluster analyses in the present cohort of young female university students have also found choline, Vit E, B2, Zn, Mg, Mn, and phosphorus as additional nutrients that might relate to the development of anemia. Further research is needed to elucidate if the intake of these nutrients might influence the risk of anemia. [ABSTRACT FROM AUTHOR]

Many regulatory requirements add significant delay in the licensing of new nuclear power stations. One area of particular interest is the environmental impact of potential atmospheric release. The purpose of this research is to demonstrate effectiveness of meteorological data mining and synthesis from offsite locations to reduce need for onsite data, hence allowing rapid licensing. The automated procedures tested for data mining and extraction of meteorological data from multiple offsite sources and the data analytic tool developed for data fusion are presented here. Three important meteorological parameters from regulatory compliance are considered for this analysis: wind velocity, wind direction, and atmospheric stability. Callaway Nuclear Power Plant (CNPP) is used as our reference site. CNPP uses the Δ T Δ z approach while we use the Vogt method to estimated stability for the offsite locations. Stability classification correlation coefficients between the reference plant and Columbia Regional Airport range from −0.087 to 0.826 for raw with an average of 0.317 ± 0.313. With travel time, correction changed slightly, i.e., a 10 m observation 0.064 ± 0.249 and 0.028 ± 0.123 and a 60 m observation 0.103 ± 0.265 and 0.063 ± 0.155 for the wind from the reference plant to the airport and vice versa, respectively. For Jefferson City Memorial Airport, raw data correlation was from −0.083 to 0.771, with an average of 0.358 ± 0.321. With travel time, correction changed slightly, i.e., 10 m observation 0.075 ± 0.208 and −0.073 ± 0.255 and 60 m observation 0.018 ± 0.223 and −0.032 ± 0.248 for wind from the reference plant to the airport and vice versa, respectively. Stability classification correlation coefficients between the reference plant and St. Louis Lambert International Airport ranged from −0.083 to 0.763 for raw with an average of 0.314 ± 0.295. With travel time, correction changed slightly, i.e., 10 m observation −0.003 ± 0.307 and −0.030 ± 0.277 and 60 m observation −0.030 ± 0.193 and −0.005 ± 0.215 for wind from the reference plant to the airport and vice versa, respectively. It is important to observe that mathematically. stability class correlation coefficients were not great, but in most cases the predicted and observed values were only off by one stability class. Similar correlations were calculated for wind direction and velocities. Our result, when applied to a proposed nuclear power station, can significantly reduce time and effort to prepare a robust environmental protection plan required for license application. [ABSTRACT FROM AUTHOR]

Utilizing deep learning for data mining in biomedicine often falls short in leveraging prior knowledge and adapting to the complexities of biomedical literature mining. Entity recognition, a fundamental task in information extraction, also provides data support for Natural Language Processing (NLP) downstream tasks. Bovine Viral Diarrhea Virus (BVDV) results in considerable economic losses in the cattle industry due to calf diarrhea, bovine respiratory syndrome, and cow abortion. This study aims to extract information on BVDV from relevant literature and build a knowledge base. It enhances feature extraction in the BioBERT pre-trained model using the Machine Reading Comprehension (MRC) framework for information fusion and bi-directionally extracts corpus information through the Bi-LSTM network, followed by a CRF layer for decoding and prediction. The results show the construction of a BVDV Corpus with 22 biomedical entities and introduce the BioBERT-Bi-LSTM-CRF Integrated with MRC (BBCM) model for Named Entity Recognition (NER), combining prior knowledge and the reading comprehension framework (MRC). The BBCM model achieves F 1 -scores of 78.79% and 76.3% on the public datasets JNLPBA and GENIA, respectively, and 67.52% on the BVDV Corpus, outperforming other models. This research presents a targeted NER method for BVDV, effectively identifying related entities and exploring their relationships, thus providing valuable data support for NLP's downstream tasks. [ABSTRACT FROM AUTHOR]

Given the recent increase in demand for electricity, it is necessary for renewable energy sources (RESs) to be widely integrated into power networks, with the two most commonly adopted alternatives being solar and wind power. Nonetheless, there is a significant amount of variation in wind speed and solar irradiance, on both a seasonal and a daily basis, an issue that, in turn, causes a large degree of variation in the amount of solar and wind energy produced. Therefore, RES technology integration into electricity networks is challenging. Accurate forecasting of solar irradiance and wind speed is crucial for the efficient operation of renewable energy power plants, guaranteeing the electricity supply at the most competitive price and preserving the dependability and security of electrical networks. In this research, a variety of different models were evaluated to predict medium-term (24 h ahead) wind speed and solar irradiance based on real-time measurement data relevant to the island of Crete, Greece. Illustrating several preprocessing steps and exploring a collection of "classical" and deep learning algorithms, this analysis highlights their conceptual design and rationale as time series predictors. Concluding the analysis, it discusses the importance of the "features" (intended as "time steps"), showing how it is possible to pinpoint the specific time of the day that most influences the forecast. Aside from producing the most accurate model for the case under examination, the necessity of performing extensive model searches in similar studies is highlighted by the current work. [ABSTRACT FROM AUTHOR]

With the development of precision sensing instruments and data storage devices, the fusion of multi-sensor data in gearbox fault diagnosis has attracted much attention. However, existing methods have difficulty in capturing the local temporal dependencies of multi-sensor monitoring information, and the inescapable noise severely decreases the accuracy of multi-sensor information fusion diagnosis. To address these issues, this paper proposes a fault diagnosis method based on dynamic graph convolutional neural networks and hard threshold denoising. Firstly, considering that the relationships between monitoring data from different sensors change over time, a dynamic graph structure is adopted to model the temporal dependencies of multi-sensor data, and, further, a graph convolutional neural network is constructed to achieve the interaction and feature extraction of temporal information from multi-sensor data. Secondly, to avoid the influence of noise in practical engineering, a hard threshold denoising strategy is designed, and a learnable hard threshold denoising layer is embedded into the graph neural network. Experimental fault datasets from two typical gearbox fault test benches under environmental noise are used to verify the effectiveness of the proposed method in gearbox fault diagnosis. The experimental results show that the proposed DDGCN method achieves an average diagnostic accuracy of up to 99.7% under different levels of environmental noise, demonstrating good noise resistance. [ABSTRACT FROM AUTHOR]

Purpose: This study aimed to review the literature on complementary and alternative therapies, utilizing text mining and trend analysis in nursing research. As CAM becomes increasingly prevalent in healthcare settings, a comprehensive understanding of the current research landscape is essential to guide evidence-based practice, inform clinical decision-making, and ultimately enhance patient outcomes. Method: This study aimed to identify CAM-related literature published from 2018 to 2023. Using the search terms 'complementary therap*', 'complementary medicine', 'alternative therap*', and 'alternative medicine', we performed a comprehensive search in eight databases, including EMBASE, Cochrane Central, PubMed Central, Korea Education and Research Information Service (RISS), Web of Science, KMbase, KISS, and CINAHL. From the text network and topic modeling analysis of 66,490 documents, 15 topics were identified. These topics were classified into two nursing-related topics through an academic classification process involving three doctors with doctoral degrees, three nurses, and three pharmacists. Based on the classified topics, research trends were comparatively analyzed by re-searching the database for 12 nursing and 22 non-nursing literature. Result: This study found that in nursing literature, yoga is used to improve mental symptoms such as stress and anxiety. In non-nursing literature, most of the experimental studies on complementary and alternative therapies were conducted in a randomized manner, confirming that a variety of physiological and objective indicators were used. Additionally, it was discovered that there were differences in the diversity of research subjects and research design methods for the same intervention method. Therefore, future research should focus on broadening the scope of subjects and measurement tools in nursing studies. Additionally, such studies should be conducted with randomization and generalizability in the experimental design in mind. Conclusion: This study employed text network analysis and text mining to identify domestic and international CAM research trends. Our novel approach combined big data-derived keywords with a systematic classification method, proposing a new methodological strategy for trend analysis. Future nursing research should focus on broadening the scope of subjects, diversifying measurement tools, and emphasizing randomization and generalizability in experimental designs. [ABSTRACT FROM AUTHOR]

Aims: Avapritinib was first approved by the FDA in January 2020 and represents the first precision‐targeted drug for gastrointestinal stromal tumours. However, there is a lack of large‐scale data relating to adverse events (AEs) related to its use. We aimed to explore the avapritinib‐related AEs in real‐world practice based on the post‐marketing data. Methods: We extracted all avapritinib‐related reports submitted to the FDA Adverse Event Reporting System (FAERS) by June 2022. Based on disproportionality analysis and Bayesian analysis, we then calculated the reporting odds ratio (ROR), proportional reporting ratio (PRR), information component (IC) and empirical Bayes geometric mean (EBGM) to evaluate whether there is a significant association between avapritinib and AEs. Gender, age and time to onset were comparable between haemorrhage/non‐haemorrhage, serious/non‐serious, death/non‐death AEs, respectively. Results: In total, 3120 cases related to avapritinib were documented in the FAERS database, and 44% were reported within 30 days of commencing avapritinib. A total of 331 different AE signals were detected, and no significant differences between males and females was identified. Although the number of AEs associated with an abnormal skin texture and executive dysfunction was small, the signal intensity is high, suggesting that these events are strongly correlated with avapritinib. Subgroup analysis showed that elderly male patients were more likely to suffer from serious AEs compared to females (P <.01), but there was no significant difference between the haemorrhage group and the non‐haemorrhage group. Analysis of fatalities due to avapritinib‐related AEs indicated that sex, age and time‐to‐onset were all significantly related to death (P <.05). Conclusion: Our study provides a more precise description of the incidence and characteristics of AEs after using avapritinib, clinicians should be particularly careful when prescribing avapritinib to elderly male patients, especially within the 30 days. [ABSTRACT FROM AUTHOR]

Land-cover segmentation, a fundamental task within the domain of remote sensing, boasts a broad spectrum of application potential. We address the challenges in land-cover segmentation of remote-sensing imagery and complete the following work. Firstly, to tackle the issues of foreground–background imbalance and scale variation, a module based on multi-dilated rate convolution fusion was integrated into a decoder. This module extended the receptive field through multi-dilated convolution, enhancing the model's capability to capture global features. Secondly, to address the diversity of scenes and background interference, a hybrid attention module based on large-kernel convolution was employed to improve the performance of the decoder. This module, based on a combination of spatial and channel attention mechanisms, enhanced the extraction of contextual information through large-kernel convolution. A convolution kernel selection mechanism was also introduced to dynamically select the convolution kernel of the appropriate receptive field, suppress irrelevant background information, and improve segmentation accuracy. Ablation studies on the Vaihingen and Potsdam datasets demonstrate that our decoder significantly outperforms the baseline in terms of mean intersection over union and mean F1 score, achieving an increase of up to 1.73% and 1.17%, respectively, compared with the baseline. In quantitative comparisons, the accuracy of our improved decoder also surpasses other algorithms in the majority of categories. The results of this paper indicate that our improved decoder achieves significant performance improvement compared with the old decoder in remote-sensing image-segmentation tasks, which verifies its application potential in the field of land-cover segmentation. [ABSTRACT FROM AUTHOR]

The purpose of this single-case experimental design (SCED) study is to investigate how adaptive prompts in virtual reality (VR)-based social skills training affect the social skills performance of autistic children. Adaptive prompts are driven by autistic children's emotional states. To integrate adaptive prompts in VR-based training, we conducted speech data mining and endorsed micro-adaptivity design. We recruited four autistic children (12–13 years) for the SCED study. We carried out alternating treatments design to evaluate the impacts of adaptive and non-adaptive prompting conditions throughout a series of VR-based social skills training sessions. Using mixed-method data collection and analyses, we found that adaptive prompts can foster autistic children's desirable social skills performance in VR-based training. Based on the study findings, we also describe design implications and limitations for future research. [ABSTRACT FROM AUTHOR]

Background: Liver lesions mainly occur inside the liver parenchyma, which are difficult to locate and have complicated relationships with essential vessels. Thus, preoperative planning is crucial for the resection of liver lesions. Accurate segmentation of the hepatic and portal veins (PVs) on computed tomography (CT) images is of great importance for preoperative planning. However, manually labeling the mask of vessels is laborious and time‐consuming, and the labeling results of different clinicians are prone to inconsistencies. Hence, developing an automatic segmentation algorithm for hepatic and PVs on CT images has attracted the attention of researchers. Unfortunately, existing deep learning based automatic segmentation methods are prone to misclassifying peripheral vessels into wrong categories. Purpose: This study aims to provide a fully automatic and robust semantic segmentation algorithm for hepatic and PVs, guiding subsequent preoperative planning. In addition, to address the deficiency of the public dataset for hepatic and PV segmentation, we revise the annotations of the Medical Segmentation Decathlon (MSD) hepatic vessel segmentation dataset and add the masks of the hepatic veins (HVs) and PVs. Methods: We proposed a structure with a dual‐stream encoder combining convolution and Transformer block, named Dual‐stream Hepatic Portal Vein segmentation Network, to extract local features and long‐distance spatial information, thereby extracting anatomical information of hepatic and portal vein, avoiding misdivisions of adjacent peripheral vessels. Besides, a multi‐scale feature fusion block based on dilated convolution is proposed to extract multi‐scale features on expanded perception fields for local features, and a multi‐level fusing attention module is introduced for efficient context information extraction. Paired t‐test is conducted to evaluate the significant difference in dice between the proposed methods and the comparing methods. Results: Two datasets are constructed from the original MSD dataset. For each dataset, 50 cases are randomly selected for model evaluation in the scheme of 5‐fold cross‐validation. The results show that our method outperforms the state‐of‐the‐art Convolutional Neural Network‐based and transformer‐based methods. Specifically, for the first dataset, our model reaches 0.815, 0.830, and 0.807 at overall dice, precision, and sensitivity. The dice of the hepatic and PVs are 0.835 and 0.796, which also exceed the numeric result of the comparing methods. Almost all the p‐values of paired t‐tests on the proposed approach and comparing approaches are smaller than 0.05. On the second dataset, the proposed algorithm achieves 0.749, 0.762, 0.726, 0.835, and 0.796 for overall dice, precision, sensitivity, dice for HV, and dice for PV, among which the first four numeric results exceed comparing methods. Conclusions: The proposed method is effective in solving the problem of misclassifying interlaced peripheral veins for the HV and PV segmentation task and outperforming the comparing methods on the relabeled dataset. [ABSTRACT FROM AUTHOR]

This article proposes a new algorithm for a newly emerging domain wisdom mining that claims to extract wisdom from data. Association rule mining is one of the dominant data mining techniques based on which a new algorithm called WisRule is proposed that generates both positive and negative association rules. These rules can be used for decision-making with less influence from a specialist. The existing algorithms of association rule extraction are based on the frequency of an itemset, which was introduced into the Apriori algorithm for the first time. In these algorithms, those itemsets are converted to the rules of the form Antecedent ⇒ Consequent that qualify the threshold of support, confidence and similar other measures. WisRule is proposed as an extension to the CBPNARM algorithm. WisRule produces both positive and negative association rules based on their frequency evaluated in a certain context (C), utility (U), time (T) and location (L). Rules that are valid in a given context, have high utility and are valid across multiple time intervals and locations become part of the final ruleset. The evaluation of a rule in these four dimensions is claimed as mining wisdom from the given data that is currently used as a hypothetical basis for a domain expert's decision. WisRule is compared with the Apriori, PNARM and CBPNARM algorithms in terms of precision, recall, number of rules, average confidence, F -measure and execution time. [ABSTRACT FROM AUTHOR]

Assessing healthy cities is a crucial strategy for realizing the concept of "health in all policies". However, most current quantitative assessment methods for healthy cities are predominantly city-level and often overlook intra-urban evaluations. Building on the concept of geographic spatial case-based reasoning (CBR), we present an innovative healthy city spatial case-based reasoning (HCSCBR) model. This model comprehensively integrates spatial relationships and attribute characteristics that impact urban health. We conducted experiments using a detailed multi-source dataset of health environment determinants for middle-layer super output areas (MSOAs) in Birmingham, England. The results demonstrate that our method surpasses traditional data mining techniques in classification performance, offering greater accuracy and efficiency than conventional CBR models. The flexibility of this method permits its application not only in intra-city health evaluations but also in extending to inter-city assessments. Our research concludes that the HCSCBR model significantly improves the precision and reliability of healthy city assessments by incorporating spatial relationships. Additionally, the model's adaptability and efficiency render it a valuable tool for urban planners and public health researchers. Future research will focus on integrating the temporal dimension to further enhance and refine the healthy city evaluation model, thereby increasing its dynamism and predictive accuracy. [ABSTRACT FROM AUTHOR]

The monoclonal antibody (mAb) manufacturing process comes with high profits and high costs, and thus mAb productivity is of vital importance. However, many factors can impact the cell culture process, and lead to mAb productivity reduction. Nowadays, the biopharma industry is actively employing manufacturing information systems, which enable the integration of both online data and offline data. Although the volume of data is large, related data mining studies for mAb productivity improvement are rare. Therefore, a data-driven approach is proposed in this study to leverage both the inline and offline data of the cell culture process to discover the causes of mAb productivity reduction. The approach consists of four steps, namely data preprocessing, phase division, feature extraction and fusion, and cluster comparing. First, data quality issues are solved during the data preprocessing step. Next, the inline data are divided into several phases based on the moving window k-nearest neighbor method. Then, the inline data features are extracted via functional data analysis and combined with the offline data features. Finally, the causes of mAb productivity reduction are identified using the contrasting clusters via the principal component analysis method. A commercial-scale cell culture process case study is provided in this research to verify the effectiveness of the approach. Data from 35 batches were collected, and each batch contained nine inline variables and seven offline variables. The causes of mAb productivity reduction were identified to be the lack of nutrients, and recommended actions were taken according to the result, which was subsequently proven by six validation batches. [ABSTRACT FROM AUTHOR]

In order to further reduce the probability of multiple networks being attacked, different types of network security situation prediction models have received widespread attention and in depth research from scholars both domestically and internationally. With the rapid development of situational awareness modeling technology, various novel technical solutions such as neural networks, time series, and support vector machines have been introduced into the prediction model of network security situations, deeply optimizing and improving the means and methods of situational prediction models, thereby further improving the accuracy of situational prediction models. This study reviews and sorts out the research history and development process of network security situation prediction technology, elaborates on the main principles and current development status of situation prediction models, analyzes the shortcomings and deficiencies of current technical solutions, and points out the future research directions of network security situation prediction model technology. [ABSTRACT FROM AUTHOR]

The proliferation of online self‐archiving platforms has greatly facilitated the dissemination of new research findings. However, the extent to which these platforms have increased the impact of research remains uncertain, especially considering the potential bias of researchers favoring the deposition of higher‐quality preprints. To determine the causal relationship between self‐archiving platforms and research impact, we conducted an investigation using a sample of 5423 published articles from 2018 that had preprints deposited on bioRxiv. These articles were compared to a control group of 7862 similar articles without preprints, identified through text‐mining algorithms. By modeling the differences in forward citations over time between the two groups, we established a positive causal effect of self‐archiving platforms on research impact. However, the effect observed in this study was smaller than that reported in previous studies (18.7% vs. 36%), indicating a more accurate and unbiased result. Additionally, the study explored the underlying mechanisms that contribute to the enhancement of research impact, including early dissemination and increased exposure through social networks facilitated by self‐archiving platforms. Overall, this study expands our understanding of how research is disseminated in the era of Internet platforms. [ABSTRACT FROM AUTHOR]

As a booming technique that allows secret data extraction and information carrier recovery without any loss, reversible data hiding in different carriers has attracted more and more concerns in the field of information security. In this paper, a separable reversible data hiding technique for encrypted 3D meshes is proposed based on self-organized blocking and most significant bit (MSB) prediction. The content-owner traverses all faces of the mesh in the ascending index order. Through self-organized blocking, adjacent vertices are concentrated in different small sets. The central vertex is considered as the reference and the others as embedded vertices in each set. Then, multiple most significant bits between the central vertex and others are adaptively predicted and reserved as embeddable bits for secret data embedding. Because vertex coordinates in each set have a high space correlation and most vertices participate in the prediction process, a huge number of most significant bits can be marked as embeddable bits to embed secret data. Experimental results demonstrate that the proposed method can obtain the highest embedding rate compared with representative methods. To our best knowledge, the average embedding rate of the proposed method is about 28 bits per vertex (bpv) higher than the recently proposed method. Most importantly, instead of recovering meshes with higher quality, original meshes with high visual symmetry/quality can be recovered. [ABSTRACT FROM AUTHOR]

One of the primary challenges in the railway industry revolves around achieving a comprehensive and insightful understanding of track conditions. The geometric parameters and stiffness of railway tracks play a crucial role in condition monitoring as well as maintenance work. Hence, this study investigated the relationship between vertical ballast stiffness and the track longitudinal level. Initially, the ballast stiffness and track longitudinal level data were acquired through a series of experimental measurements conducted on a reference test track along the Tehran–Mashhad railway line, utilizing recording cars for geometric track and stiffness recordings. Subsequently, the correlation between the track longitudinal level and ballast stiffness was surveyed using both frequency-based techniques and machine learning (ML) algorithms. The power spectrum density (PSD) as a frequency-based technique was employed, alongside ML algorithms, including linear regression, decision trees, and random forests, for correlation mining analyses. The results showed a robust and statistically significant relationship between the vertical ballast stiffness and longitudinal levels of railway tracks. Specifically, the PSD data exhibited a considerable correlation, especially within the 1–4 rad/m wave number range. Furthermore, the data analyses conducted using ML methods indicated that the values of the root mean square error (RMSE) were about 0.05, 0.07, and 0.06 for the linear regression, decision tree, and random forest algorithms, respectively, demonstrating the adequate accuracy of ML-based approaches. [ABSTRACT FROM AUTHOR]

Aiming at the problems of low detection accuracy, slow detection speed and poor stability of traditional coal gangue detection based on image processing, a new YOLOv5s-EB (You Only Look Once Version-5s) network model is constructed for coal gangue target detection and location. Replace the PANet (Path Aggregation Network) layer of the original network with the BiFPN (Bidirectional Feature Pyramid Network) feature fusion network to enhance the global information extraction strength. And combined with the attention mechanism module of ECANet (Efficient Channel Attention Networks). 490 sets of multispectral data were obtained through the multispectral data acquisition system, and 980 original samples of coal and gangue were obtained, the original samples are preprocessed by histogram equalization to establish the coal gangue data set, they are trained in the original YOLOv5s, YOLOv5s-ECA, YOLOv5s-BiFPN, YOLOv5s-EB, YOLOv4 and YOLOv7 neural networks respectively. According to the results, the accuracy rate P of YOLOv5s-EB neural network model reaches 98.5%, and the recall rate R reaches 98.4%, the mAP reached 87.55%. Moreover, YOLOv5s-EB network model is relatively small, only 12.5MB. At the same time, the YOLOv5s-EB model obtains the coordinate information of the upper left and lower right corners of the target detection frame during the identification and detection process, and locates the coal gangue target for the convenience of subsequent sorting. [ABSTRACT FROM AUTHOR]

Imbalanced data classification (IDC) presents a significant challenge in data mining (DM), as it frequently occurs in various real-world areas with profound implications for highly skewed databases. IDC revolves around the task of learning from data characterized by a substantial imbalance in the number of samples across its different classes. Hence the Polar-CanisFel (PCF) Optimization-deep ensemble model is designed to address imbalanced big data issues, incorporating the SMOTE technique for rebalancing the dataset. This ensemble classifier leverages a deep convolutional neural network (DCNN), Long Short-Term Memory (LSTM), and Gated Recurrent Neural Network (GRNN) architectures for effective data classification. For the Heart Failure Prediction Dataset, the model reaches an accuracy of 96.35%, sensitivity of 94.54%, and specificity of 96.11%. Further, the accuracy of 95.91%, sensitivity of 95.87%, and specificity of 94.79% are obtained concerning the Stroke Prediction dataset. Finally, when applied to the Hepatitis-C prediction dataset, the model attains an accuracy of 92.79%, sensitivity of 92.90%, and specificity of 92.63% during 90% of training. [ABSTRACT FROM AUTHOR]

Student performance prediction (SPP) is a pivotal task in educational analytics, enabling proactive interventions and optimized resource allocation by educators. Traditional SPP models are often hindered by their complexity and lack of interpretability. This study introduces a novel SPP framework, the Belief Rule Base with automated construction (Auto–BRB), designed to address these issues. Firstly, reference values are derived through data mining techniques. The model employs an IF–THEN rule-based system integrated with evidential reasoning to ensure both transparency and interpretability. Secondly, parameter optimization is achieved using the Projected Covariance Matrix Adaptive Evolution Strategy (P–CMA–ES), significantly enhancing model accuracy. Moreover, the Akaike Information Criterion (AIC) is then applied to fine-tune the balance between model accuracy and complexity. Finally, case studies on SPP have shown that the Auto–BRB model has an advantage over traditional models in terms of accuracy, while maintaining good interpretability. Therefore, Auto–BRB has excellent application effects in educational data analysis. [ABSTRACT FROM AUTHOR]

Feature selection (FS) is a crucial phase in data mining (DM) and machine learning (ML) tasks, aimed at removing uncorrelated and redundant attributes to enhance classification accuracy. This study introduces an improved binary crayfish optimization algorithm (IBCOA) designed to tackle the FS problem. The IBCOA integrates a local search strategy and a periodic mode boundary handling technique, significantly improving its ability to search and exploit the feature space. By doing so, the IBCOA effectively reduces dimensionality, while improving classification accuracy. The algorithm's performance was evaluated using support vector machine (SVM) and k-nearest neighbor (k-NN) classifiers on eighteen multi-scale benchmark datasets. The findings showed that the IBCOA performed better than nine recent binary optimizers, attaining 100% accuracy and decreasing the feature set size by as much as 0.8. Statistical evidence supports that the proposed IBCOA is highly competitive according to the Wilcoxon rank sum test (alpha = 0.05). This study underscores the IBCOA's potential for enhancing FS processes, providing a robust solution for high-dimensional data challenges. [ABSTRACT FROM AUTHOR]

Research on rainfall is critically important due to its significant impact on climate change and natural disasters in Indonesia. Various factors influence rainfall variability. Consequently, when examining spatial aspects, it is likely that spatial dependency exists not only in the response variable but also in the exogenous variables. Hence, a model that accounts for spatial dependencies between these variables is required. The integration of the Spatial Durbin Model (SDM) with Casetti's expansion approach can be utilized to predict spatial patterns of rainfall influenced by exogenous variables. By incorporating spatial effects and relevant independent variables, this model can provide more precise estimates of rainfall distribution across different regions. This modeling technique is particularly effective for accurate rainfall prediction, considering exogenous factors such as air temperature, humidity, solar irradiation, and surface pressure. The SDM with Casetti's expansion approach was employed to predict rainfall patterns in the Java Island region, utilizing data from the National Aeronautics and Space Administration's Prediction of Worldwide Energy Resources (NASA POWER) big data website. The application of this model in the context of rainfall prediction highlights its importance in enhancing the understanding of weather dynamics and aiding disaster risk mitigation in Java Island, a highly populated region characterized by a Monsoon rainfall pattern. The rainfall prediction follows a Knowledge Discovery in Databases (KDD) methodology. The results of this study are expected to be valuable to relevant agencies, such as the Meteorology, Climatology, and Geophysics Agency (BMKG), and agribusiness companies, improving agricultural planning and planting seasons. Additionally, the general public can benefit from more accurate climate information, particularly regarding rainfall. The computational framework is developed within an RShiny web application, and the performance of the proposed technique is measured by the Mean Absolute Percentage Error (MAPE), achieving a very accurate prediction rate of 2.78%. [ABSTRACT FROM AUTHOR]

Steel infrastructure in tunnels significantly affects the accuracy of transient electromagnetic (TEM) data inversion. This study proposes and compares two methods to effectively mitigate this interference: the correction factor method and the prior information constraint method. The correction factor method constructs correction factors using interference data obtained in two ways. The first method, numerical simulation, is theoretically precise but relies heavily on accurate model parameters and requires significant computational resources. The second is conducted by measuring the interference data in the working space. While this approach is simple and operationally convenient, its effectiveness in correction is limited by the measured data quality. The a priori information constraint method improves the inversion by introducing a more accurate initial model. The inversion results of synthetic data indicate that the inversion based on the correction factor method and the prior information constraint method can effectively invert the anomaly. However, the delay effect remains a challenge for the correction factor method. Finally, we invert the field data measured in a mine tunnel by combining the interference processing methods. [ABSTRACT FROM AUTHOR]

With the continuous advancement in Internet-of-Things and deep learning, video action recognition is gradually emerging in daily and industrial applications. Spatiotemporal and motion patterns are two crucial and complementary types of information used for action recognition. However, effectively modelling both types of information in videos remains challenging. In this paper, we propose a spatiotemporal and motion information extraction (STME) network that extracts comprehensive spatiotemporal and motion information from videos for action recognition. First, we design the STME network, which includes three efficient modules: a spatiotemporal extraction (STE) module, a short-term motion extraction (SME) module and a long-term motion extraction (LME) module. The SME and LME modules are used to model short-term and long-term motion representation, respectively. Then, we apply the STE module to capture comprehensive spatiotemporal information which can supplement the video representation for action recognition. According to our experimental results, the STME network achieves significantly better performance than existing methods on several benchmark datasets. Our codes are available at https://github.com/STME-Net/STME. [ABSTRACT FROM AUTHOR]

Traffic flow prediction plays a critical role in urban traffic management and planning. Accurate prediction of traffic flow can enhance traffic efficiency, improve traffic safety, conserve traffic resources, and promote sustainable urban development. Graph convolutional networks (GCN) have great potential in traffic flow prediction due to their ability to handle complex data with topological structures while considering spatial relationships between nodes in data. However, it is difficult for the traditional GCN-based models to capture dynamic spatiotemporal dependencies between the stations since these models usually use static relationship graph in GCN. This paper presents an enhanced approach called the coupled generative graph convolution model (CGGCN) for capturing dynamic regional traffic relationships. The CGGCN learns the adjacency matrix of graph convolution in a generative manner, thereby improving the ability of previous graph convolution models to effectively capture the dynamic relationships of regional traffic within multi-layer structures. Additionally, the paper optimizes the fusion method of coupling graph convolution in multi-level matrix feature flow information aggregation, leading to the efficient extraction of spatiotemporal information. To validate the effectiveness of the proposed model, extensive experiments were conducted on two real traffic datasets obtained from New York, namely NYCBike and NYCTaxi. The results demonstrate the superior performance of the CGGCN model when compared to other eight baseline models. [ABSTRACT FROM AUTHOR]

Federated Learning (FL) has emerged as a promising approach to addressing issues related to centralized machine learning such as data privacy, security and access. Nevertheless, it also brings new challenges incurred by heterogeneity among data statistical levels, devices and models in the context of multi-level federated learning (MlFed) architecture. In this paper, we conceive a new Personalized Multi-level Federated Learning (PerMl-Fed) framework, which extends existing MlFed architecture with three specialized personalized FL methods to address the three challenges. Specially, we design a Transfer Multi-level Federated Learning (TrMlFed) model to mitigate statistical heterogeneity across multiple layers of FL. We propose an Asynchronous Multi-level Federated Learning (AsMlFed) approach which allows asynchronous update in MlFed, thus alleviating device heterogeneity. We develop a Deep Mutual Multi-level Federated Learning (DmMlFed) method based on the concept of deep mutual learning to tackle model heterogeneity. We evaluate the PerMl-Fed framework and associated technologies on the public Wireless Sensor Data Mining (WISDM) dataset. Initial results demonstrate improved average accuracy of 7 % and achieves accuracy ranging from 84 to 92 % across eight different hierarchical group structures. [ABSTRACT FROM AUTHOR]

This study intends to identify research gaps and future trends and provide a framework for the next generation of research to assess how much big data (BD) is employed in hospitality and tourist research. The study is based on a comprehensive quantitative evaluation of the relevant literature: Scopus and Web of Science (WoS)-listed academic works. The following criteria were used to assess the submissions: those who have the following traits an overview of the study’s subject matter, including its theoretical and conceptual framework, data sources, data kind and quantity, data collection methods, and data analysis methodologies. Research shows that the usage of books on hospitality and tourism management has increased in recent years. Massive volumes of data are analyzed using analytical methods. However, the scope of this investigation is really wide. Furthermore, this research contributes to an in-depth and systematic assessment of the extent to which scholars in hospitality/tourism know and work on business intelligence and BD. This is the first complete survey of the literature on the topic of hospitality and tourism. [ABSTRACT FROM AUTHOR]

In the early time of oilfield development, insufficient production data and unclear understanding of oil production presented a challenge to reservoir engineers in devising effective development plans. To address this challenge, this study proposes a method using data mining technology to search for similar oil fields and predict well productivity. A query system of 135 analogy parameters is established based on geological and reservoir engineering research, and the weight values of these parameters are calculated using a data algorithm to establish an analogy system. The fuzzy matter-element algorithm is then used to calculate the similarity between oil fields, with fields having similarity greater than 70% identified as similar oil fields. Using similar oil fields as sample data, 8 important factors affecting well productivity are identified using the Pearson coefficient and mean decrease impurity (MDI) method. To establish productivity prediction models, linear regression (LR), random forest regression (RF), support vector regression (SVR), backpropagation (BP), extreme gradient boosting (XGBoost), and light gradient boosting machine (LightGBM) algorithms are used. Their performance is evaluated using the coefficient of determination (R²), explained variance score (EV), mean squared error (MSE), and mean absolute error (MAE) metrics. The LightGBM model is selected to predict the productivity of 30 wells in the PL field with an average error of only 6.31%, which significantly improves the accuracy of the productivity prediction and meets the application requirements in the field. Finally, a software platform integrating data query, oil field analogy, productivity prediction, and knowledge base is established to identify patterns in massive reservoir development data and provide valuable technical references for new reservoir development. [ABSTRACT FROM AUTHOR]

Large language models (LLMs) have demonstrated promising in-context learning capabilities, especially with instructive prompts. However, recent studies have shown that existing large models still face challenges in specific information extraction (IE) tasks. Moreover, it could have more effectively utilized various prompts such as instruction tuning, diverse demonstrations of in-context learning, and long-range token sequences for assisting language modeling in understanding context. In this study, we propose DILUIE, a unified information extraction framework based on in-context learning with diverse demonstration examples. DILUIE is encoded with an EVA attention mechanism and incremental encoding technology. Based on the constructed diverse demonstrations, we expand the size of instances efficiently in both instruction tuning and in-context learning to gain insights into the potential benefits of utilizing diverse information extraction datasets. To deepen the understanding of context, we further design three auxiliary tasks to assist in aligning contextual semantics. Experimental results demonstrate that DILUIE achieves 2.23 and 2.53% improvements in terms of Micor-/Macor-F1 on average relative to the current state-of-the-art baseline, which also significantly outperforms the GPT-3.5-turbo in zero-shot settings, and the average token length of achieving the best performance over tasks is around 15k. Furthermore, we observe that in-context learning shows enhanced performance when provided with more demonstrations during multiple-shot instruction tuning (8 k). Additionally, increasing the length of instructions (10 k) can result in a more substantial improvement in the upper limits of scaling for in-context learning. Code is available on https://github.com/Phevos75/DILUIE. [ABSTRACT FROM AUTHOR]

Student dropout is a major concern in studies investigating retention strategies in higher education. This study identifies which variables are important to predict student dropout, using academic data from 3583 first-year students on the Business Administration (BA) degree at the University of Barcelona (Spain). The results indicate that two variables, the percentage of subjects failed and not attended in the first semester, demonstrate significant predictive power. This has been corroborated with an additional sample of 10,784 students from three-degree programs (Law, BA, and Economics) at the Complutense University of Madrid (Spain), to assess the robustness of the results. Three different algorithms have also been utilized: neural networks, random forest, and logit. In the specific case of neural networks, the NeuralSens methodology has been employed, which is based on the use of sensitivities, allowing for its interpretation. The outcomes are highly consistent in all cases: both a simple model (logit) and more sophisticated ones (neural networks and random forest) exhibit high accuracy (correctly predicted values) and sensitivity (correctly predicted dropouts). In test set average values of 77% and 69% have been respectively achieved. In this regard, a noteworthy point is that only academic data from the university itself was used to develop the models. This ensures that there's no dependence on other personal or organizational variables, which can often be difficult to access. [ABSTRACT FROM AUTHOR]

Capturing correlations between joints is crucial in skeleton-based action recognition tasks. Transformer has demonstrated its capability in capturing such correlations. However, conventional Transformer-based approaches model the relationships between joints in a unified spatio-temporal dimension, disregarding the unique semantic information that exists in both the spatial and temporal dimensions of skeleton sequences. To address this issue, we present a novel decoupled spatio-temporal grouping Transformer (DSTGFormer) model. The skeleton sequence is split into multiple spatio-temporal groups, each containing a set of consecutive frames. The spatio-temporal positional encoding (STPE) module assigns identity information to each element in the sequence. The spatio-temporal grouping self-attention (STGA) module captures the spatial and temporal relationships between different joints within a spatio-temporal group. This decoupling of the spatial and temporal dimensions enables the extraction of semantic information with different meanings in each dimension. Additionally, we propose a within-group spatial global regularization mechanism to learn more general spatial attention maps, and an inter-group feature aggregation (IGFA) module to enhance the differentiation between similar actions. Our proposed method outperforms the state-of-the-art methods on two large-scale datasets in terms of both recognition accuracy and computational efficiency. [ABSTRACT FROM AUTHOR]

Addressing ecological impacts with effective conservation actions requires information on the links between human pressures and localized responses. Understanding links is a priority for many conservation contexts, including the world's fresh waters, which face intensifying threats to disproportionately high species diversity, including more than half of the world's fish species. Literature synthesis can uncover links and highlight potential research gaps, yet can be very cumbersome and time consuming. Emerging tools like text mining can improve efficiency in extracting relevant information from vast scientific outputs. This study synthesizes evidence of direct anthropogenic threats to major inland fisheries and examines driver‐impact‐response patterns using coupled automated and manual text classification methods. We screened 9336 abstracts from 45 river basins of high importance to inland fish production; 1152 abstracts contained evidence of direct threats to fish. The most common documented drivers were pollution, dams, and fishing pressure, which were most strongly linked to decreased fitness, altered reproduction, and mortality, respectively. Strong impact‐response links to pollution signal potential bias toward documenting acute threats that generate more visible and immediate impacts. The use of machine learning‐based text classification performed best in classifying extraneous information. Results can inform the development of inland fisheries indicators and threat‐based metrics, highlight possible evidence gaps in linking global drivers to fishery‐level responses, and illustrate the application of a coupled synthesis approach for improved efficiency and extraction of information relevant to conservation outcomes. The associated user and interpretation guides address accessibility and technical barriers faced by conservation scientists to improve efficiency in evidence synthesis. [ABSTRACT FROM AUTHOR]

Out of all the racial groups in the United States, people who identify as American Indian and Alaska Native (AI/AN) have disproportionately worse health as a result of living in poverty. The preponderance of research connects poor health with a socioeconomic perspective, which might create prejudice against AI/AN. As already known, AI/AN's high rates of obesity, diabetes, and stroke in comparison with that of other ethnic groups are mainly derived from their impoverished economic conditions that have forced them to consume the food distributed by the U.S. government. When minority health is discussed generally, the ethnic density perspective explains a minority population's positive health despite low socioeconomic status. This perspective helps researchers and practitioners understand the connections of psychological and social factors with physical health and demonstrates positive health effects on minority groups. Despite the high correlation between ethnic density and health having been validated, little to no research has explored AI/AN's health from this perspective. Using 13,064 electronic health records, this research tests the relationship between AI/AN density and health outcomes. This article introduces an innovative analytical strategy (i.e. a data mining technique), which is ideal for discovering frequently appearing health outcomes in a group. The finding reveals positive relationships between health outcomes and AI/AN density. [ABSTRACT FROM AUTHOR]

In the continuously changing labor market, understanding the dynamics of online job postings is crucial for economic and workforce development. With the increasing reliance on Online Job Portals, analyzing online job postings has become an essential tool for capturing real-time labor-market trends. This paper presents a comprehensive methodology for processing online job postings to generate labor-market intelligence. The proposed methodology encompasses data source selection, data extraction, cleansing, normalization, and deduplication procedures. The final step involves information extraction based on employer industry, occupation, workplace, skills, and required experience. We address the key challenges that emerge at each step and discuss how they can be resolved. Our methodology is applied to two use cases: the first focuses on the analysis of the Greek labor market in the tourism industry during the COVID-19 pandemic, revealing shifts in job demands, skill requirements, and employment types. In the second use case, a data-driven ontology is employed to extract skills from job postings using machine learning. The findings highlight that the proposed methodology, utilizing NLP and machine-learning techniques instead of LLMs, can be applied to different labor market-analysis use cases and offer valuable insights for businesses, job seekers, and policymakers. [ABSTRACT FROM AUTHOR]

Background: Investigating emotion sequence patterns in the posts of discussion forums in massive open online courses (MOOCs) holds a vital role in shaping online interactions and impacting learning achievement. While the majority of research focuses on the relationship between emotions and interactions in MOOC forum discussions, research on identifying the crucial difference in emotion sequence patterns among different interaction groups remains in its infancy. Objectives: This research utilizes deep learning and sequential pattern mining to investigate whether there are differences in emotion sequence patterns across different groups of learners who exhibit various types of interactions in online discussion forums. Methods: Data from a comprehensive array of sources, including log files, discussion texts and scores from 498 learners in online discussion forums, were collected for this study. The agglomerative hierarchical algorithm is used to classify learners into groups with different levels of interactions. Additionally, we implement and evaluate multiple deep learning models for detecting different emotions from online discussions. Relevant emotion sequence patterns were identified using sequence pattern analysis and the identified emotion sequence patterns were compared across different groups with different levels of interactions. Results and Conclusions: Using an agglomerative hierarchical algorithm, we classified learners into three distinct groups characterized by different levels of interactions: high, average and low level. Leveraging the bi‐directional long short‐term memory model for emotion detection yielded the highest predictive performance, with an impressive F‐measure of 94.01%, a recall rate of 93.83% and an accuracy score of 95.01%. The results also revealed that learners in the low‐level interaction group experienced more emotion transition from boredom to frustration than the other two groups. Therefore, the aggregation of students into groups and the utilization of their MOOC log data offer educators the capability to provide adaptive emotional feedback, customize assessments and offer more personalized attention as needed. Lay Description: What is currently known about the subject matter: Emotions are dynamic over time when learners experience cognitive disequilibrium/equilibrium.Online interactions are critical components, which influence learners' emotional state, cognitive processes and learning achievement.It is not clear what are differences in emotion sequence patterns across the groups with different interaction types. What the paper adds: An agglomerative hierarchical algorithm was implemented to cluster learners into three groups by analysing behavioural data.We explore possibilities for automated classification of emotions using deep learning approaches.Learners in the low‐level interaction group experienced more emotion transition from boredom to frustration. Implications for practitioners: A considerable amount of effort should be expended to identify and respond to learners who experience boredom and frustration emotions.Designing interventions or scaffolding to facilitate learners' interaction and promote favourable emotions.Educators could provide more personalized support based on learners' online interaction cluster. [ABSTRACT FROM AUTHOR]

Geospatial interpolation plays a pivotal role in spatial analysis because it provides high-quality data support for various spatiotemporal data mining (STDM) tasks. However, statistical methods, such as kriging, face challenges in dealing with complex geo-big data. Additionally, deep-learning-based methods, despite their exceptional performance, suffer from limitations, such as poor interpretability. To harness the complementary advantages of these statistical methods and deep learning approaches, this study proposes a novel geospatial artificial intelligence (GeoAI) framework called deep kriging neural network (DKNN). The primary contribution lies in the development of an asymmetric encoder-decoder structure, which includes a deep-learning-based spatial encoder and a geostatistics-based kriging decoder. The spatial encoder consists of three specialized neural networks, whereas the kriging decoder relies on the proposed unified kriging system. During forward propagation, the kriging decoder leverage messages from the spatial encoder to generate interpolation weights for prediction. Conversely, during backward propagation, the kriging decoder guides the spatial encoder in learning interpretable knowledge. Experiments were conducted using both synthetic and practical datasets. The results demonstrate an average improvement of 20.18% in MAE, 25.04% in RMSE and 24.06% in MAPE when compared to the best-performing baseline method. Furthermore, these results confirm the superior interpretability of our DKNN framework. [ABSTRACT FROM AUTHOR]

Efficient use of energy and other resources, as the basic postulates of the circular economy, is a prerequisite for the green transition to more sustainable cities in the future. The main scientific goal of the paper is the development of a new approach to city governance when it comes to the inefficient use of energy, predominantly fossil fuels, mainly in developing and poor countries. Energy efficiency problems faced by these countries require the introduction of urgent, applicable, and realistically achievable solutions. A prerequisite for adequate analysis and modeling of energy efficiency performance, measures, policies, outcomes, and impacts is the introduction and functioning of the big data management system, which should begin with data mining. On the other hand, adequate data collection has been neglected in many of these countries. The study shows a way to reduce this gap, but in accordance with realistic and limited possibilities for countries with less favorable conditions. In that respect, a conceptual model for the Analytical Service for facilitating energy efficiency in city governance was developed and presented as a driver that can enable cities to manage energy more efficiently. The model is based on an interdisciplinary approach and on the needs of cities in the Republic of Serbia. However, it is designed to allow upgrading in accordance with the capabilities and resources of cities, primarily applicable in developing and poor countries. [ABSTRACT FROM AUTHOR]

As one of the most popular sources of information in the world, Wikipedia is edited by a large, global community of contributors. User-generated nature of this online encyclopedia ensures that the information reflects a wide range of topics. Hovewer, Wikipedia articles are created and edited independently in each language version. Therefore, some topics may be presented with varying degrees of completeness depending on their importance in a particular language community. In this paper, we quantified the concept of Americanization on a global scale through comparative analysis of the coverage of American topics in different language versions of Wikipedia. For this purpose, we analyzed over 90 million Wikidata items and 40 million Wikipedia articles in 58 languages. We discussed whether Americanization is more or less dominant in different languages, regions, and cultures. We showed that the interest in American topics is not universal. Western, developed countries are more Americanized (more interested in topics related to America) than the rest of the world. This is the first global, quantitative confirmation of issues often hypothesized, or assumed, in the literature on Americanization and related phenomena. This study shows that Wikipedia and Wikidata can allow quantification of social science concepts that previously were considered not realistically measurable. Finally, the presented research is also relevant to the discourses on the biases of Wikipedia. [ABSTRACT FROM AUTHOR]

Objective To analyze the experience of Professor Chen Huanchao, a famous TCM doctor in Hubei Province, in treating breast cancer by data mining technology. Methods The medical records of Professor Chen Huanchao’s treatment of breast cancer were collected, and the first prescription of each patient was recorded after screening and sorting. MS Excel 2019 was used to analyze drug frequency, efficacy frequency, and the meridian distribution, and SPSS Modeler 18.0 software was adopted for association rule analysis and network display of drugs. SPSS 27.0 was employed for clustering analysis of high-frequency drugs to summarize medication patterns. Results A total of 185 prescriptions involving 180 traditional Chinese medicines were included, and 29 high-frequency drugs were screened. The medicinal properties were mainly neutral, cold, and warm, and the medicinal flavors were mainly sweet, bitter, and pungent. The meridians were liver, lung, spleen, and kidney meridians. The medicinal effects primarily included tonifying deficiency, clearing heat, and promoting diuresis and dampness. The association rule analysis showed 20 groups of drug pairs, and the cluster analysis mainly revealed two categories. Conclusion Professor Chen Huanchao believes that breast cancer involves root deficiency and excessive symptoms and should be treated from the perspective of “deficiency, blood stasis, phlegm, and toxin.” Genuine-Qi should be strengthened, and Evil-Qi should be eliminated. The symptoms and root causes of this disease should be treated simultaneously while soothing the liver and qi, tonifying the spleen and kidney, promoting blood circulation, removing phlegm and preventing its accumulation, and clearing heat and detoxify. This work provides ideas for the treatment of breast cancer with traditional Chinese medicine. [ABSTRACT FROM AUTHOR]

Accurate precipitation nowcasting is crucial for daily life, but the current forecasting models need further improvement in terms of accuracy. This paper proposed an innovative forecasting model called BTPN to address this issue. The model introduced bidirectional Transformer to extract features from both the forward and backward directions of spatiotemporal sequences, capturing key information and reducing spatiotemporal feature loss. It combined the convolutional Transformer block with the local encoding of convolution and the global encoding of Transformer to enhance spatiotemporal information extraction and correlation, alleviating the problem of long-term spatiotemporal information loss. The model also incorporated a detail extraction module to reduce the loss of local details and mitigate the issue of dissipation in high-value areas. Evaluation on the HKO-7 dataset shows that the BTPN model surpasses other advanced models in terms of MAE, SSIM, and CSI metrics, demonstrating excellent predictive capability in large-scale precipitation and extreme weather scenarios. The experiments demonstrate that the BTPN model possesses higher forecasting accuracy and promising applications. [ABSTRACT FROM AUTHOR]