Social media platforms have become pivotal tools for small and medium-sized enterprises (SMEs), offering vast opportunities for enhanced organizational engagement. However, these platforms also present challenges such as data privacy concerns, feedback management, and content saturation. This systematic review critically evaluates the existing literature on the dual role of social media in fostering organizational engagement while addressing key barriers faced by SMEs. We systematically assessed 104 peer-reviewed articles sourced from Scopus, Web of Science, and Google Scholar, focusing on the impact of social media on marketing strategies and organizational outcomes in SMEs. The Newcastle-Ottawa Scale was used for quality assessment, and effect measures, including mean difference and odds ratio, were employed to evaluate performance metrics such as customer engagement, business performance, and long-term organizational impact. Key findings indicate that 74% of SMEs reported improvements in brand visibility, with customer engagement increasing by 65%. However, significant concerns were identified, with 45% of studies highlighting privacy issues and 52% addressing challenges in managing negative feedback. The review emphasizes that while social media can enhance market reach and customer interaction, its effectiveness largely depends on strategic content management and planning. This review provides actionable insights for SMEs aiming to optimize social media use, highlighting the need for future research to address privacy management and feedback strategies for sustained success.

Background: Immunoglobulin A nephropathy (IgAN) is a complex autoimmune disease, and the exact pathogenesis remains to be elucidated. Methods: We conducted summary data-based Mendelian randomization (SMR) analysis and performed functional mapping and annotation using FUMA to explore genetic loci that are po-tentially involved in the pathogenies of IgAN. Both analyses used summarized data of a recent genome-wide association study (GWAS) on IgANs, which included 477,784 Europeans (15,587 cases and 462,197 controls) and 175,359 East Asians (71 cases and 175,288 controls). We performed separate SMR analysis using CAGE and GTEx eQTL data. Results: Using the CAGE eQTL data, our SMR analysis identified 32 probes tagging 25 unique genes that were pleiotropically/potentially causally associated with IgAN, with the top three probes being ILMN_2150787 (tagging HLA-C, PSMR=2.10×10-18), ILMN_1682717 (tagging IER3, PSMR=1.07×10-16) and ILMN_1661439 (tagging FLOT1, PSMR=1.16×10-14). Using GTEx eQTL data, our SMR analysis identified 24 probes tagging 24 unique genes, with the top three probes being ENSG00000271581.1 (tagging XXbac-BPG248L24.12, PSMR=1.44×10-10), ENSG00000186470.9 (tagging BTN3A2, PSMR=2.28×10-10), and ENSG00000224389.4 (tagging C4B, PSMR=1.23×10-9). FUMA analysis identified 3 independent, significant and lead SNPs, 2 genomic risk loci and 39 genes. Conclusion: We identified many genetic variants/loci that are potentially involved in the patho-genesis of IgAN.

Background: The liver is involved in disseminated tuberculosis in more than 80% of the cases while primary liver involvement is rare, representing < 1% of all cases. Hepatic tuberculosis (TB) can be treated by conventional anti-TB therapy, however, diagnosing this disease still remains a challenge. The diagnosis might be particularly difficult in patients with a single liver lesion that could be misdiagnosed as a tumor or other focal liver lesions. While computed tomography and magnetic resonance imaging findings have been described, there is a paucity of literature on contrast-enhanced ultrasound (CEUS) features of hepatic TB. Case Summary: herein, we describe a case of a patient with tuberculous lymphadenopathy and chronic HCV-related liver disease who developed a single macronodular hepatic TB lesion. Due to the finding of a hepatocellular carcinoma (HCC) highly suggestive CEUS pattern, specifically a LR5 category according to the Liver Imaging Reporting and Data System (LI-RADS), and a good response to antitubercular therapy, a non-invasive diagnosis of HCC was made, and the patient underwent liver resection. We also review the published literature on imaging features of hepatic TB and discuss the diagnostic challenge represented by hepatic TB when occurs as a single focal liver lesion. Conclusions: this report shows for the first time that CEUS pattern of hepatic TB might be misinterpreted as HCC and specific imaging features are lacking. Personal history and epidemiological data are mandatory in interpreting CEUS findings of a focal liver lesion even when the imaging pattern is highly suggestive of HCC.

The target area of the present study is the entrance to the Sulina channel in the Black Sea, the zero-kilometer of the Danube River. This represents the southern gate of the seventh Pan-European transport corridor and is subjected to high navigation traffic. The coastal environment at the Danube’s mouth is very often subjected to strong environmental conditions inducing high risks for navigation hazards. From this perspective, the objective of the present work is to provide a more comprehensive picture concerning the past and future expected dynamics of the environmental matrix in this area, including especially wind and wave conditions. An analysis of some in situ measurements performed at the zero kilometer of the Danube is first carried out for the 15 years 2009-2023. A second analysis is based on data provided by regional climate wind models. Two 30-year periods are considered, the recent past (1976-2005), when also comparisons with ERA5 reanalysis data were performed, and the near future (2041-2070), when two different models and three climate scenarios were considered. Finally, using as a forcing factor each of the wind fields before analyzed, simulations with a spectral wave model were carried out and the nearshore wave conditions were evaluated. The results show that both extreme wind and wave conditions are expected to be slightly enhanced in the future. Strong wind fields are characteristic in this area, with wind gusts exceeding on average with more than 70% the maximum hourly averaged wind speed. As regards the waves, due to the complex nearshore phenomena, considerable enhancements in terms of significant wave heights are induced. Furthermore, there is also a high risk of rogue wave’s occurrence.

Open science, accessibility and knowledge sharing, especially of articles and monographs stemming from a publicly funded research, seem to be quite a positive direction in the development of science and have received almost unanimous approval from a scientific community. However, when it comes to data sharing, the data obtained by qualitative methodology deserve special attention and treatment. Although FAIR principles provide ways to anonymise the data and interlocoutors (as explained in Celjak et al 2020) individuals coming from smaller communities or even communities of practice can sometimes be easily regcognized by members of the same communitiy, especially if the data refers to audio files! The researcher is obliged to thoroughly describe the ways in which the data will be managed and used, and if it will state that the data will be managed in line with FAIR principles, this will inevitably impact the narratives collected. The prerogative to make all the data open will inevitably lead to autocesorship i.e. in creating a kind of FAIRy Tales for the future, interlocutors will share with researchers. Having all that in mind I argue for a more vigilant approach when embracing the idea that all the data should be made FAIR. Not all the data should be made FAIR because this could, in the end, compromise the research process itself. Some data must remain in the space of trust created between main actors in the research process. These data should be treated with CARE principles.

Google Trends data can be informative for infectious disease incidences, including Lyme disease. However, the use of Google Trends for predictive purposes is underutilized. In this study, we tested the ability of Google Trends search data to predict monthly state-level Lyme disease case counts in the United States. We requested Lyme disease data for the years 2010-2021. We downloaded Google Trends search data on terms for Lyme disease, symptoms of Lyme disease, and diseases with similar symptoms as Lyme disease. We built mixed negative binomial models based on a training dataset (2010-2016) and tested the models on a test dataset (2017-2021). A model was built for each search term and monthly lags of search terms were included as predictors. The highest performing models had high predictive ability, indicated by low Root Mean Squared Errors (RMSEs) and close association between observed and predicted case counts. The highest performing model was for the search term “Summer Flu”, which indicates low specificity of some of the terms. We outline challenges of using Google Trends data, including data availability and a mismatch between geographic units. We discuss opportunities for Google Trends data, including prediction of additional zoonotic diseases and incorporating environmental and companion animal data.

Building energy consumption plays an essential role in urban sustainability. The prediction of the energy demand is also of particular importance for developing smart cities and urban planning. Machine learning has recently contributed to the advancement of methods and technologies to predict demand and consumption for building energy systems. This paper presents a state of the art of machine learning models and evaluates the performance of these models. Through a systematic review and a comprehensive taxonomy, the advances of machine learning are carefully investigated and promising models are introduced.

Delineating chilling and forcing periods is one of the challenging topics in understanding how temperatures drive the timing of budburst and bloom in fruit tree species. Here, we investigated this question on olive trees, using flowering data collected over six years on 331 cultivars in the worldwide collection of Marrakech, Morocco. Using a Partial Least Squares approach on a long-term phenology (29 years) of ‘Picholine Marocaine’ cultivar, we showed that the relevance of delineating the chilling and forcing periods depends more on the variability of inter-annual temperatures than on the long-term datasets. In fact, chilling and forcing periods are similar between those delineated by using datasets of 29 years and those of only 6 years (2014–2019). We demonstrated that the variability of inter-annual temperatures is the main factor explaining this pattern. We then used the datasets of six years to assess the chill and heat requirements of 285 cultivars. We classified Mediterranean olive cultivars into four groups according to their chill requirements. Our results, using the Kriging interpolation method, indicated that flowering dates of most of these cultivars (92%) were governed by both chilling and forcing temperatures. Our investigations provided first insights to select adapted cultivars to global warming.

The emergence of precision and digital livestock farming presents an opportunity for sustainable animal farming practices that enhance animal welfare and health. However, this transformation of modern animal farming through digital technology has several implications for the technological, social, economic, and environmental aspects of farming. It is crucial to analyze the ethical considerations associated with the digitalization of modern animal farming, particularly in the context of human-animal relationships and potential objectification. This analysis can help develop frameworks for improving animal welfare and promoting sustainability in animal farming.One of the primary ethical concerns of digital livestock farming is the potential for a digital divide between farmers who have access to advanced technologies and those who do not. This could lead to a disparity in animal welfare and health outcomes for different groups of animals. Additionally, the use of artificial intelligence in digital livestock farming may lead to a loss of personal connection between farmers and animals, which could impact the animal's well-being. Another ethical concern of digital livestock farming is the potential for objectification of animals as mere data points. The use of sensors and other monitoring technologies can provide valuable data on animal health and behavior, but it is important to remember that animals are sentient beings with complex emotional and social needs. The use of digital technologies should not lead to neglect of animal welfare or a lack of human responsibility towards animals.Furthermore, social context becomes essential while integrating technologies in the livestock farming to overcome ethics. By considering the cultural and societal norms of different communities, we can ensure that the use of digital technologies does not undermine these values. To address these ethical challenges, the development of standards and codes of conduct for the adoption and implementation of digital livestock farming tools and platforms can help ensure that animal welfare and sustainability are prioritized. This can help alleviate the privacy concerns of stakeholders and improve sustainability in animal farming practices. Additionally, the use of virtual and augmented reality technologies can provide a way to enhance human-animal interactions and provide more personalized care to animals, further promoting animal welfare.

In today's technologically advanced landscape, sensors feed critical data for accurate decision-making and actions. Ensuring the integrity and reliability of sensor data is paramount to system performance and security. This paper introduces an innovative approach utilizing discrete wavelet transforms (DWT) embedded within microcontrollers to scrutinize sensor data meticulously. Our methodology aims to detect and isolate malfunctions, misuse, or any anomalies before they permeate the system, potentially causing widespread disruption. By leveraging the power of wavelet-based analysis, we embed computational intelligence directly into the microcontrollers, enabling them to monitor and validate their outputs in real-time. This proactive anomaly detection framework is designed to distinguish between normal and aberrant sensor behaviors, thereby safeguarding the system from erroneous data propagation. Our approach significantly enhances the reliability of embedded systems, providing a robust defense against false data injection attacks and contributing to overall cybersecurity.

This study utilizes a combination of optical PlanetScope imagery and Synthetic Aperture Radar (SAR) data from Sentinel-1 to investigate land cover changes in Dili, Timor-Leste, following Tropical Cyclone Seroja. The primary objective is to evaluate how integrating these datasets enhances disaster monitoring and response in flood-affected areas. The Random Forest classifier, known for its robustness in handling high-dimensional and noisy data, was applied to classify land cover into six distinct classes: vegetation, water, built-up areas, bare soil, clouds, and shadows. The classification was performed across three phases—pre-disaster, post-disaster, and recovery—using Google Earth Engine (GEE). Binary segmentation using Otsu thresholding was applied to the SAR images to refine the classification by delineating water bodies from non-water areas. The study achieved high classification accuracy, with overall accuracy ranging from 97.2% to 98.7%, and the Kappa index, which measures agreement between classified and reference data, remained consistently strong, indicating reliable model performance. Key results include a significant increase in water bodies and extensive damage to vegetation and built-up areas during the post-disaster phase, followed by partial recovery in the subsequent period. Despite the high accuracy, urban areas posed classification challenges due to misclassification between built-up and bare soil categories. This research offers a methodological framework for integrating optical and SAR data with machine learning for land cover change detection in post-disaster scenarios. The societal benefits of this study include improved disaster preparedness, enhanced recovery planning, and valuable insights into flood impact mitigation in regions like Timor-Leste, where technical and data limitations persist.

Integrating systems acquired from third parties and legacies has become of great necessity in companies. This is mainly due to the need to exchange information between entities, such as banks, suppliers, customers, allies, etc. Therefore, it is essential to guarantee the integrity of the data and keep the integration up to date with the changes that can occur. Furthermore, reducing the transaction risk and avoiding losing information is necessary. Implementing this complex task involving technological and business challenges requires appropriate architecture implementation. This article presents an architecture named Dynamic Canonical Data Model through agnostic messages. The contribution involves treating the low link in integrating software units, also called the integration of loosely coupled software units. In particular, it focuses on internal data and external data integration. The proposal reduces their integration, maintenance time, and cost, maximizing their scalability and promoting reuse. To illustrate their components, a case study undertaken at the Mexican Logistics Company Paquetexpress is presented. The company has evaluated different enterprise application integration systems over 26 years to achieve a standardized integration. The article describes an architecture designed and implemented for this delivery company in a real-world case. The implementation’s source code was registered in the National Registry of Copyrights of Mexico.

The integration of advanced nanotechnology solutions in healthcare presents unparalleled opportunities for transformative care and cost savings. However, market penetration remains hindered by regulatory, technological, and adoption barriers. This study explores business analytics strategies facilitating successful market integration of nanotechnology innovations in healthcare. A mixed-methods approach combining qualitative expert interviews, quantitative survey analysis, and data-driven modeling is employed.Key findings highlight the critical role of data-driven decision-making, collaborative partnerships, and tailored market segmentation in overcoming adoption hurdles. Specifically, predictive analytics and machine learning algorithms are identified as essential tools for optimizing nanotechnology product development, pricing strategies, and supply chain efficiency. Furthermore, strategic partnerships with healthcare stakeholders and tailored market segmentation enable targeted commercialization and accelerated diffusion.This research contributes to the existing literature by providing actionable insights for nanotechnology firms, policymakers, and healthcare administrators seeking to harness the transformative potential of nanotechnology in healthcare. The proposed business analytics framework offers a valuable roadmap for navigating the complex healthcare landscape and ensuring the sustainable market integration of advanced nanotechnology solutions.

In recent years, Big Data (BD) has become a crucial tool for Small and Medium-sized Enterprises (SMEs), impacting their performance and growth in significant ways. This systematic literature review aims to analyze the effects of BD on SMEs by examining 93 research papers published from 2014 to 2024. Employing the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) framework, the review focuses on key drivers and barriers to BD adoption, including business improvement, economic performance, and revenue growth. The methodology involved a comprehensive analysis of research methodologies used in the studies, addressing biases, gaps, and the need for diverse approaches. The findings reveal that while BD has led to notable enhancements in operational efficiency and revenue for many SMEs, challenges such as limited resources and technical expertise remain. A significant reporting bias was observed, with 47% of the literature comprising quantitative studies, followed by 28% case studies, while mixed-methods and qualitative studies were underrepresented (22% and 17%, respectively). This imbalance suggests a potential overemphasis on quantitative approaches, limiting the diversity of insights available. Addressing these biases is essential to fully harness the potential of BD for SMEs to drive innovation, enhance competitiveness, and achieve better performance in the increasingly data-driven business environment.

In modern agriculture, decision-making is deeply intertwined with data, yet essential agricultural knowledge remains encased within dense scientific texts such as journals, manuals, and free-text reports. This necessitates specialized search systems capable of distilling and delivering precise information in response to specific queries from agricultural users. This study introduces AgriQuery, a sophisticated agent designed to field natural language questions from the agricultural sector by exploring vast troves of scientific documents. A comprehensive review and analysis of farmers' information needs have been conducted, leading to the creation of an information retrieval test collection that includes actual queries, a vast array of scientific documents segmented into passages, and a set of ground truth relevance assessments that map these passages to corresponding queries. We explore and benchmark several information retrieval models, highlighting the efficacy of advanced neural ranking models in this context. AgriQuery's proposed deployment architecture features a client interface on the Telegram platform and a backend model on standard hardware. This test collection aims to catalyze further research into matching natural language queries with scientific text answers, with implications extending beyond agriculture.

Event data loggers are frequently used to record the date and time of tip events in tipping-bucket rain gauges. The HOBO® pendant event data logger is one such commercially-available device commonly used for this purpose. It can record the contact closure of a TBGR reed switch at a maximum timing resolution of 1 second, tied to the timing of the logger clock, which is set each time the logger is launched. These event loggers are ideal for the routine recording of rainfall. This paper addresses the issue of whether they can also be relied upon when estimating short-term intensities, for which they were not designed. New experiments show that for a series of switch closures at fixed intervals other than exact multiples of 1 s, the HOBO® logger fails to record evenly-spaced tip events. Thus, for example, with pulses at fixed 2.75 s intervals, the logger records some events as occurring at 2 s intervals, and others at 3 s intervals. The duration between logged events is correct only when the mean is calculated for a long series of logged events. In natural rainfall, tip events can occur at any time, and inter-tip times, from which intensity can be estimated, will generally not be an integral number of seconds. Consequently, particularly in intense rain, the logger behaviour just described can lead to erroneous estimates of the rainfall rate estimated from the duration of individual inter-tip times. Possible solutions are discussed.

Every year, the Montreal police are confronted with countless crimes committed by criminals. These crimes affect the quality of life of city residents and impose a socio-economic burden on the city. In this study, we conduct a comparative analysis based on several machine learning algorithms to develop a model to predict the crime category in Montreal. The performance of algorithms such as eXtreme Gradient Boosting (XGBoost), Decision Trees (DT) and Random Forest (RF) were analyzed. The performance analysis takes into account the performance metrics such as precision, accuracy, recall and F1-score. This analysis was based on crime data in Montreal from 2015 to 2023. This data is characterized by a strong imbalance between crime categories. To address the data imbalance problem, a data balancing approach based on the SMOTE-ENN algorithm was adopted. In the exploratory data analysis phase, temporal trends by crime category were highlighted. The results of the analysis showed that the XGBoost algorithm outperformed the other two. Specifically, the XGBoost algorithm achieves an accuracy of 92%, while DT and RF achieve an accuracy of 86% and 84%, respectively. As a result, XGBoost was deployed via a web application using the Flask and Swagger UI Python frameworks. This study provides the Montreal police with an effective tool to better utilize their resources in fighting crime. In addition, policymakers in the city of Montreal can use this tool to identify high-risk areas and give them more attention.

In China, "new quality productive forces" have become an important focus for high-quality development; accelerating this development is an important task for the Chinese government in 2024. Such development relies on the traction of the digital economy. In view of this, developing “new quality productive forces” driven by the Chinese digital economy requires focusing on blocking points, such as the insufficient vitality of data, inadequate algorithmic regulation, the uneven distribution of computing power resources and the immature market environment. In order to dredge these blocking points, it is necessary to establish basic rules on data, strengthening algorithm supervision, building a national integrated computing power network, and optimizing the market environment.

The challenge of missing data in scientific research prompts researchers to decide between imputing incomplete data or discarding observations, where discarding can lead to information loss. Various methods exist, from simple deletion to sophisticated approaches like Multiple Imputation (MI). However, these methods often fall short with high-dimensional datasets. Multiple Imputation by Chained Equations (MICE) and Random Forest (RF) proximity imputation offer promising alternatives. Therefore, in this paper, we propose integrating MICE with Bayesian random forest (BRF) to enhance imputation accuracy and predictive power, particularly in high-dimensional analyses. Our approach combines MICE’s efficiency with BRF’s robustness, offering a comprehensive solution to missing data challenges. By way of example, we provide empirical evaluations to validate its effectiveness using synthetic data of various missing data scenarios. The results from the simulations showed that the combination of BRF and MICE offered a promising strategy for high-dimensional analysis in the presence of missing data.

Energy distance is used to eigenvalue distributions in this new Wishart distribution study, providing a new perspective on high-dimensional data. Multivariate statistics relies on Wishart distribution to explain covariance matrices. This analysis shows how degrees of freedom and covariance matrix configurations affect eigenvalue dispersion. We use energy distance based on eigenvalue distributions to assess Wishart distribution differences without the "curse of dimensionality" via extensive simulation simulations. This approach improves measurement accuracy and processing efficiency in distribution comparisons and enables new analytical pathways in scientific fields that need data covariance comprehension. Our results show that degrees of freedom and matrix structure considerably affect energy distances, expanding the theoretical framework and practical applications of statistical models.

Diabetes management requires constant monitoring and individualized adjustments. This study proposes a novel approach that leverages digital twins and Personal Health Knowledge Graphs (PHKGs) to revolutionize diabetes care. Our key contribution lies in developing a real-time, patient-centric digital twin framework built on PHKGs. This framework integrates data from diverse sources, adhering to HL7 standards and enabling seamless information access and exchange. PHKGs offer a flexible and efficient format that supports various applications. As new knowledge about the patient becomes available, the PHKG can be easily extended to incorporate it. This dynamic approach fosters continuous improvement and facilitates the development of new applications. As proof of concept, we have demonstrated the versatility of our digital twin by applying it to different use cases in diabetes management. These include predicting glucose levels, optimizing insulin dosage, providing personalized lifestyle recommendations, and visualizing health data. By enabling real-time, patient-specific care, this research paves the way for more precise and personalized healthcare interventions, potentially improving long-term diabetes management outcomes.

Selection of the most suitable material is one of the key decisions to be taken at the design stage of a manufacturing process. Traditional approaches as Ashby maps based on material properties are widely used in the industry. However, in the production of multimaterial components, the criteria for the selection can include antagonistic approaches. The aim of this work is the implementation of a methodology based on the results of process simulations for several materials and classify them by applying an advanced data analytics method based on Machine Learning (ML), in this case the Support Vector Regression (SVR) and Multi-Criteria Decision Making (MCDM) methodolo-gies, in this case Multi-criteria Optimization and Compromise Solution (VIKOR) combined with Entropy weighting methods. In order to do this, a Finite Element Model (FEM) has been built to evaluate the extrusion force and the die wear in a multi-material co-extrusion process of bimetallic Ti6Al4V-AZ31B billets. After applying SVR and VIKOR combined with Entropy weighting methodologies, a comparison has been established based on the material selection and complexity of the methodology used, resulting that material chosen in both methodologies is very similar and MCDM method is easier to implement because there is no need of evaluate the error of the pre-diction model and the time for data preprocessing is less than the time needed in SVR.

The world has changed. New technologies, new trends, new protocols, new efficient algorithms, and systems have been used widely by civilized countries to have better and more convenient living. In this research, there have been introduced many new terms, technologies, and mechanisms. Moreover, threats, attacks, and vulnerabilities have been studied and a novel scenario has been proposed in order to overcome all these violations that have been presented in this paper. The scenario is based on a security model that has been proposed for critical sectors, such as hospitals, industries, etc., which need efficient solutions to go one step further and improve the secure and efficient living and treatment of people. The aim of this research has been to understand through research the IoT security issues and propose the appropriate solutions based on the most suitable security algorithms. The results, which have been based on the complexity, the throughput, the power consumption, the strength, and the memory usage of the algorithms studied, have been hopeful and helpful for future research and experimentation.

The Genji firefly is a key symbol of the conservation and management of rural environments. The species lives underwater as larvae, in the soil when they pupate, and emerges on the ground as adults. Because of the large differences in habitat conditions between larvae and adults, the habitat requirements of the Genji firefly must be clarified over a wide range, from the instream to the surrounding riparian environment. In this study, we built a habitat suitability model for the Genji firefly by relating local landscape features to the number of individuals surveyed in a small river in an agricultural watershed. For habitat suitability modelling, tree-based machine learning methods, namely Random Forests (RF) and classification and regression trees (CART), are used to model species distributions and extract quantitative information on their ecological characteristics. Because the model performance on the test dataset was poor, we removed noisy absences using model outputs from the RF computation using the entire dataset. As a result, we observed improved model performance, in which there seems to be an optimal level for removing noisy absences. Variable importance and partial dependence plots were then used to visualize the relationship between the local landscape features and habitat suitability of the adult firefly. Detailed information on landscape features extracted using RF and CART is useful for a deeper understanding of the ecology of the Genji fireflies.

This study investigates why young adults live with their parents in Sweden. As young adults’ living arrangements affect decisions about marriage, education, childbirth, and participation in the workforce, more knowledge for policy makers is crucial to implementing effective policies to support young adults and promote financial independence and well-being. Using a data set from 1998 to 2021 at the municipal level in Sweden, we used a spatial autoregressive panel data model to examine the proportion of young adults living at home and regional disparities. The study uncovers intraregional variations, illustrating how different municipalities within Sweden exhibit different patterns of young adults living at home. Our findings reveal that economic factors, such as unemployment, significantly impact this pattern. The dynamics of the housing market, demographic factors, cultural differences, and location-specific characteristics also play an essential role in explaining this pattern. The findings suggest that the key drivers are the lack of rental housing, high unemployment rates, a high degree of urbanisation, interregional migration, and lack of social capital.

Background: Runners have high incidence of repetitive load injuries, and habitual runners often use smartwatches with embedded IMU sensors to track their performance and training. If accelerometer information from such IMUs can provide information about individual tissue loads, then running watches may be used to prevent injuries. Methods: We investigate a combined physics-based simulation and data-based method. 285 running trials from 76 real runners are subjected to physics-based simulation to recover forces in the Achilles tendon and patella ligament, and the collected data are used to train and test a data-based model using elastic net and gradient boosting methods. Results: Correlations up to 0.95 and 0.71 for the patella ligament and Achilles tendon forces, respectively, are obtained, but no single best predictive algorithm can be identified. Conclusions: Prediction of tissues loads based on body-mounted IMUs appears promising but requires further investigation before deployment as a general option for users of running watches to reduce running-related injuries.

Taiwan’s Chi Mei Medical Center has a vision of becoming a sustainable organization. They found they violated the sustainable development goal (SDG) 13 (“Climate Action”) since its workflows consume excessive tangible resources and waste much operation time. To fulfill the vision, the Chi Mei Medical Center first introduced electronic invoicing. Implementing this electronic invoicing included adopting cloud E-invoice data and creating a software robot for auditing them. This study presents this software robot and its contributions. The software robot replaces an internal auditor to log into Taiwan’s E-invoice platform, download cloud E-invoice data, and detect the inconsistency between these cloud and on-premise data. Internal auditors of the Chi Mei Medical Center only needed to confirm the detection results. They welcome this software robot since it significantly reduces their work burdens. They approved more software robots for assisting other workflows. Besides, the Chi Mei Medical Center earned profits after eliminating paper invoices. This elimination helped release less carbon. This study concludes that chasing a sustainable organization is unnecessarily equivalent to the requirement of more costs. A software robot represents the last puzzle for constructing a paperless workflow since it can resolve the resistance of existing workers to a new workflow.

Homogenization of climatic time series aims to remove non-climatic biases which come from the technical changes of climate observations. The method comparison tests of the Spanish MULTITEST project (2015-2017) showed that ACMANT was likely the most accurate homogenization method available at that time, in spite of the tested ACMANTv4 version gave suboptimal results when the test data included synchronous breaks for several time series. The technique of combined time series comparison has been introduced to ACMANTv5 in order to treat better this specific problem. Tests confirm that ACMANTv5 treats adequately synchronous inhomogeneities, but the accuracy has slightly worsened in some other cases. Results for a known daily temperature test dataset for 4 U.S. regions show that the residual errors after homogenization may be larger with ACMANTv5 than with ACMANTv4. Further tests have been performed to learn more about the efficiencies of ACMANTv4 and ACMANTv5, and to find solutions for the appearing problems with the new version. Planned changes in ACMANTv5 are presented in the paper along with connecting test results. The overall results indicate that the combined time series comparison can be kept in ACMANT, but smaller networks should be generated by the automatic networking process of the method. For the further improvements of homogenization methods and for obtaining more reliable and more solid knowledge about their accuracies, more synthetic test datasets mimicking fairly the true spatio-temporal structures of real climatic data would be in need.

Flood modeling and forecasting are key to managing and preparing for extreme flood events. Hydrological flood forecasting aims to predict the system response to different input changes with minimum uncertainties. In that sense, streamflow Data Assimilation (DA) seeks to combine errors between hydrological model and water discharge observations through the update of model states. This paper aims to assess a sub-daily flood forecast system in a basin of the Peruvian Tropical Andes using two sequential data assimilation algorithms called the Ensemble Kalman Filter (EnKF) and the Particle Filter (PF). The study was conducted in the Vilcanota River basin during the rainiest months in 2022 to assess recent potential river floods. This basin is in the southern Peruvian Andes and was selected because it is continually affected by river floods such as occurred in 2010. For this purpose, the lumped GR4H rainfall-runoff model was run forward with 100 ensemble members using two different Satellite Precipitation sources (IMERG-E' and GSMaP-NRT'). Also, four DA experiments (IMERG-E'+EnKF, IMERG-E'+PF, GSMaP-NRT'+EnKF, and GSMaP-NRT'+PF) were conducted by assimilating real-time hourly discharges at the Pisac stream gauge station to examine the improvement of forecast accuracy for lead times of 1—24 hours. Results display good forecast performances during the first 10 hours, especially for the GSMaP'+EnKF scheme. Finally, this work benchmarks the application of streamflow DA in and Andean basin of Peru with sparse data availability and will support the development of more accurate climate services in Peru through hydrologic ensemble predictions.

Biomass gasification acquired great interest over the past decades as an effective and trustable technology to produce energy and fuels with net-zero carbon emissions. Moreover, using biomass waste as feedstock enables to recycle organic wastes and to fit the circular economy goals thus reducing the environmental impacts of waste management. Even if many studies have been already carried on, this kind of process must still be investigated and optimized with the final aim to develop industrial plants for different applications, from the hydrogen production to net-negative emission strategies. Modeling and developing of process simulations became an important tool to investigate the chemical and physical behavior of the plant, allowing to make a first raw optimization of the process and to define heat and material balances of the plant as well as to define optimal geometrical parameters with cost and time effective approaches. The present review paper focuses on the main literature models developed until now to describe biomass gasification process, and in particular on kinetic models, thermodynamic models, and computational fluid dynamic models. The aim of this study is to point out the strengths and the weakness of those models, comparing them and indicating in which situation is better to use an approach instead of another. Moreover, theoretical shortcut models and software simulations, not explicitly addressed by prior reviews, are taken into account. For researchers and designers this review provides a detailed methodology characterization as a guide to develop innovative study or project.

Background: Myalgic encephalomyelitis/chronic fatigue syndrome (ME/CFS) is a complex and debilitating disease with a significant global prevalence of over 65 million individuals. It affects various systems, including the immune, neurological, gastrointestinal, and circulatory systems. Studies have shown abnormalities in immune cell types, increased inflammatory cytokines, and brain abnormalities. Further research is needed to identify consistent biomarkers and develop targeted therapies. A multidisciplinary approach is essential for diagnosing, treating, and managing this complex disease. The current study aims at employing explainable artificial intelligence (XAI) and machine learning (ML) techniques to identify discriminative metabolites for ME/CFS. Material and Methods: The present study used a metabolomics dataset of CFS patients and healthy controls, including 26 healthy controls and 26 ME/CFS patients aged 22-72. The dataset encapsulated 768 metabolites, classified into nine metabolic super-pathways: amino acids, carbohydrates, cofactors, vitamins, energy, lipids, nucleotides, peptides, and xenobiotics. Random forest-based feature selection and Bayesian Approach based-hyperparameter optimization were implemented on the target data. Four different ML algorithms [Gaussian Naive Bayes (GNB), Gradient Boosting Classifier (GBC), Logistic regression (LR) and Random Forest Classifier (RFC)] were used to classify individuals as ME/CFS patients and healthy individuals. XAI approaches were applied to clinically explain the prediction decisions of the optimum model. Performance evaluation was performed using the indices of accuracy, precision, recall, F1 score, Brier score, and AUC. Results: The metabolomics of C-glycosyltryptophan, oleoylcholine, cortisone, and 3-hydroxydecanoate were determined to be crucial for ME/CFS diagnosis. The RFC learning model outperformed GNB, GBC, and LR in ME/CFS prediction using the 1000 iteration bootstrapping method, achieving 98% accuracy, precision, recall, F1 score, 0.01 Brier score, and 99% AUC. Conclusion: RFC model proposed in this study correctly classified and evaluated ME/CFS patients through the selected biomarker candidate metabolites. The methodology combining ML and XAI can provide a clear interpretation of risk estimation for ME/CFS, helping physicians intuitively understand the impact of key metabolomics features in the model.

Social media platforms are increasingly enabling the propagation of content from groups related to drug use, thus posing risks for the wider population and, in particular, individuals who are amenable to drug use and drug addiction. The detection of drug use content on social media platforms is a priority for governments, technology companies, and drug law enforcement organizations. To counter this issue, various techniques have been developed to identify and promptly remove drug use content, while also blocking its creators from network access. In this paper, we introduce a manually annotated Twitter dataset, comprising 156,521 tweets published between 2008 and 2022, specifically compiled for the purpose of drug use detection. The dataset underwent annotation by several group of expert annotators who classified the tweets as either drug use or non-drug use. Exploratory data analysis was conducted to comprehend the dataset's characteristics. Various classification algorithms, including SVM, XGBoost, RF, NB, LSTM, and BERT were employed using the dataset. Among the traditional machine learning models, SVM utilizing term frequency-inverse document frequency features achieved the highest F1-Score (0.9017). However, BERT with textual features concatenated with numerical and categorical features in ensemble method surpassed the performance of traditional models, attaining F1-Score of 0.9112. To facilitate future research and enhance English online drug use classification accuracy, the dataset will be made publicly available.

Our comprehension of fundamental cosmological principles hinges on a thorough understanding of the early universe. The Lambda Cold Dark Matter (ΛCDM) model has emerged as a valuable framework for elucidating various cosmic phenomena, uniting a cosmological constant (Λ) with cold dark matter (CDM). Nevertheless, recent observations, particularly data from the Planck, WMAP, and DES missions that probe the early universe, alongside local measurements of the Hubble constant, have unveiled significant inconsistencies. These inconsistencies have magnified the perplexing issue known as the Hubble Tension, thereby challenging our current understanding of the universe. To address this conundrum, we adopt a comprehensive approach encompassing a review of cosmological fundamentals, an exploration of the ΛCDM model, an examination of the cosmic microwave background (CMB), power spectrum, and perturbation theory, a thorough review of existing research, and finally, an investigation of real data. By undertaking these early universe processes, we aim to understand more about Hubble constant and its consequence in ΛCDM model.

With the development of artificial intelligence technology, manipulators, as an important part of the work of intelligent robots, can replace humans to perform various complex tasks. In recent years, there have been many studies on the remote control of manipulators using various control technologies. Starting from the manufacturing materials of flexible sensors used for manipulators, this paper introduces the base materials, sensing materials, and flexible electrode materials of flexible sensors, respectively, and summarizes the performance of flexible sensors made based on the characteristics of different materials. The basic principles of dipping and coating, lithography, inkjet printing, screen printing, 3D printing and so on are introduced from the perspective of flexible sensor manufacturing process. Some different functions of sensors achieved by different structural designs, such as: tensile cracking, microchannels, etc. are also introduced. Then, from the perspective of recognition accuracy of the manipulator, two kinds of control methods based on flexible sensor by data glove control and surface EMG control are classified and introduced, and the problems existing in three aspects of flexible sensor material preparation, manufacturing process and control series design are summarized. Finally, the possible future research directions in this field are suggested.

High-dimensional measurement error data are becoming more prevalent across various fields. Research on measurement error regression models has gained increasing attention due to the risk of drawing inaccurate conclusions if measurement errors are ignored. When the dimension p is larger than the sample size n, it is challenging to develop statistical inference methods for high-dimensional measurement error regression models due to the existence of bias, nonconvexity of objective function, high computational cost and many other difficulties. Over the past few years, some works have overcome the aforementioned difficulties and proposed several statistical inference methods. This paper mainly reviews the current development on estimation, hypothesis testing and variable screening methods for high-dimensional measurement error regression models and shows the theoretical results of these methods with some directions worthy of exploring for future research.

To assist Java programming learning of novice students, we have developed the web-based Java programming learning assistant system (JPLAS). JPLAS provides several types of exercise problems to cultivate code reading/writing skills at various levels. In JPLAS, the code writing problem (CWP) asks a student to write a source code that will pass the test code given in the assignment where the correctness is verified by running them on JUnit. In this paper, to reduce the teacher load at marking process, we present the answer code validation program that verifies all the source codes from a lot of students for each assignment at a time and reports the number of passing tests for each source code in the CSV file. Besides, to test a source code with various input data, we implement the test data generation algorithm that identifies the data type, generates a new data, and replaces it for each test data in the test code. Furthermore, to verify the correctness of the implemented procedure in the source code, we introduce the intermediate state testing in the test code. For evaluations, we applied the proposal to source codes and test codes in a Java programming course in Okayama university, Japan, and confirmed the validity and effectiveness.

The main problem in pursuing multiple extended targets tracking is distinguishing the origins of the measurements. The association of measurements to the possible origins within the target’s extent is difficult, especially for the occlusions or the detection blind zone which cause the intermittent measurements. To solve the problem, a hierarchical network-based tracklets data association algorithm is proposed. At the low level, the min cost network flow model is used to extract possible tracklets from the divided measurement set. At the high-level, the trajectories are estimated from the tracks produced by the previous low level network. The experimental results show that the hierarchical network-based tracklets data association algorithm outperforms the JPDA and RFS-based method when the measurement is intermittently unavailable.

The article proposes a method for determining the p-value of correlations in compositional data, i.e., those data that arise as a result of dividing the original values by their sum. Data organized in this way are typical for many fields of knowledge, but there is still no consensus on methods for interpreting correlations in such data. In a space closed by normalizing quantity, correlation coefficients behave differently than under normal conditions: their probabilities of occurrence do not coincide with those inherent in the standard scale of estimates. In the tens of the new millennium, almost all newly emerging methods for estimating correlation in compositional data began to require mandatory log-transformation of the variable values. In the method proposed here there are no log-transformations. We return to the early stages of attempting to solve the problem and rely on negative shifts in correlations in the multinomial distribution. In modeling the data, we use a hybrid method that combines the hypergeometric distribution with the distribution of any other law. During our work on the calculation method, we found that the number of degrees of freedom in compositional data measures discretely only when all the normalizing sums are equal and that it decreases when the sums are not equal, becoming a continuously varying quantity. Estimation of the number of degrees of freedom and the strength of its influence on the magnitude of the shift in the distribution of correlation coefficients is the basis of the proposed method.

With the increasing use of cloud-based services for training and deploying machine learning models, data privacy has become a major concern. This is particularly important for natural language processing (NLP) models, which often process sensitive information such as personal communications and confidential documents. In this study, we propose a method for training NLP models on encrypted text data to mitigate data privacy concerns while maintaining similar performance to models trained on non-encrypted data. We demonstrate our method using two different architectures, namely Doc2Vec+XGBoost and Doc2Vec+LSTM, and evaluate the models on the 20 Newsgroups dataset. Our results indicate that both encrypted and non-encrypted models achieve comparable performance, suggesting that our encryption method is effective in preserving data privacy without sacrificing model accuracy. In order to replicate our experiments, we have provided a Colab notebook at the following address: https://t.ly/lR-TP

Soil quality is related to food security and human survival and development. In recent years, due to the acceleration of urbanization and the increase of abandoned land, land degradation occurs, poor topsoil quality. In this study, the minimum data set (MDS) was constructed through principal component analysis (PCA) to determine the indicator data set for evaluating topsoil quality in Tieling County, China. In addition, the soil quality index (SQI) was calculated to analyze the spatial distribution characteristics and influencing reasons of topsoil quality in Tieling County. The re-sults showed that MDS included total potassium (TK), Clay, zinc (Zn), soil organic matter (SOM), soil water content (SWC), cation exchange capacity (CEC), pH, and copper (Cu). The MDS indicators can well replace all indicators to evaluate the topsoil quality in the study area. The overall soil quality of Tieling County showed a trend of low in the east and high in the west, and gradually increased from the hilly area to the plain area. The evaluation results are consistent with field research, which can provide reference for other topsoil quality evaluation, and it also provide a basis for the formulation of soil quality improvement measures.

Data centres, though a necessary part of modern society, are being stigmatised for consuming vast amounts of electricity for their operational and cooling needs. Due to Ireland’s reliance on fossil fuels to meet the increased energy demand of data centres, the data centres are contributing significantly to Ireland’s total carbon emissions. As much of this energy is expelled from data centres as waste heat energy, the potential for recycling some of this wasted heat energy was explored using environmentally friendly systems from recent publications. The recovered waste heat energy was applied in a vertical farming system, and the benefits of this waste heat to the vertical farm were analysed and quantified in two scenarios. Using conservative estimates, it was predicted that each vertical farm could be between 5-23% the size of the data centre and produce enough food to feed between 14-61 adults their daily calorie needs, and between 13-58 people their daily fresh produce requirements, depending on the scenario applied. For a more accurate prediction, each vertical farm would have to be assessed on a case-by-case basis. However, there was not enough data available on Irish data centres to perform these calculations.

Introduction: Weighting is widely used in applied statistics especially while dealing with survey data. In recent years, multilevel modeling under complex survey designs has increased, resulting into demand for level weights. However, survey data that are accessible to the public for use usually do not contain level weights that are useful in multilevel modeling, but final survey weights that are only appropriate for single level analyses. In this paper, we demonstrate how the final survey weights can be used to estimate level weights for multilevel data analysis, and compare a model that applied level weights with one that applied the final survey weights. Methods: A framework for approximating level weights proposed by the Demographic Health Survey (DHS) program was used to estimate the level weights. Models were fitted using a multilevel mixed effects logistic regression method. Estimates from a model that applied survey weights was compared to those from a model that applied level weights. Results: Application of final survey weights instead of level weights underestimated standard errors and led to loss of precision of model estimates. Conclusions: Use of level weights produces estimates with high precision and yields correct values of standard errors hence appropriately informing inference.

In engineering practice, various types of information data are affected by many factors during the collection process. For example, information data measurement errors are caused by equipment performance and the working environment. During the transmission of detection information, the signal distortion caused by energy loss and signal interference causes unpredictable detection errors in the collected information data. Through the study of fractional calculus theory, it was found that it is suitable for studying nonlinear, non-causal, and non-stationary signals, and has the dual functions of improving detection information and enhancing signal strength. Therefore, under the influence of many factors, we applied the fractional difference algorithm to the field of information data processing. Multi-sensor detection data fusion algorithm based on the fractional partial differential equation was adopted to establish its online detection data. A multi-sensor detection data fusion algorithm based on a fractional partial differential equation is established, which effectively fuses the information data detection errors caused by various influencing factors and greatly improves the detection accuracy of information data. The effectiveness of this method is proved through its application in an experiment.

As machine learning and computer vision techniques and methods continue to advance, the collection of naturalistic traffic data from video feeds is becoming more and more feasible. That is especially true for the case of bicycles, for which the collection of naturalistic data is not achievable in the traditional vehicle approach. This study describes a research effort that aims to extract naturalistic cycling data from a video dataset for use in safety and mobility applications. The used videos come from a dataset collected in a previous Virginia Tech Transportation Institute study in collaboration with SPIN in which continuous video data at a non-signalized intersection on the Virginia Tech campus was recorded. The research team applied computer vision and machine learning techniques to develop a comprehensive framework for the extraction of naturalistic cycling trajectories. In total, this study resulted in the collection and classification of 619 bicycle trajectories based on their type of interactions with other road users. The results confirm the success of the proposed methodology in relation to extracting the locations, speeds, and accelerations of the bicycles at a high level of precision. Furthermore, preliminary insights into the acceleration and speed behavior of bicyclists around motorists are determined.

Deep learning dominates automated animal activity recognition (AAR) tasks due to the high performance on large-scale datasets. However, constructing centralised data across diverse farms raises data privacy issues. Federated learning (FL) provides a distributed learning solution to train a shared model by coordinating multiple farms (clients) without sharing their private data. Whereas directly applying FL to AAR tasks often faces two challenges: client-drift during local training and gradient conflicts during global aggregation. In this study, we develop a novel FL framework called FedAAR to achieve AAR with sensor data. Specifically, we devise a prototype-guided local update module to alleviate the client-drift issue, which introduces global prototypes as shared knowledge to force clients to learn consistent features. To reduce gradient conflicts between clients, we design a gradient refinement-based aggregation module to eliminate conflicting components between client gradients during global aggregation, thereby improving the agreement between clients. Experiments are conducted on a public dataset to verify FedAAR’s effectiveness, which consists of 87,621 2-s motion data. The results demonstrate that FedAAR outperforms state-of-the-arts, with precision (75.23%), recall (75.17%), F1-score (74.70%), and accuracy (88.88%), respectively. The ablation experiments also show FedAAR’s robustness against various factors (i.e., different data sizes, communication frequency, and client numbers).

In community-based participatory projects, needs assessments are one of the first steps to identify priority areas. Access-related issues often pose significant barriers to participation for rural and remote communities, particularly Indigenous communities which have a complicated relationship with academia due to a history of exploitation and trauma. In order to bridge this gap, work with Indigenous communities requires consistent and meaningful engagement. The prominence of digital devices (i.e., smartphones) offers an unparalleled opportunity to ethically and equitably engage citizens across jurisdictions, particularly in remote communities. We propose a framework to guide needs assessments which embed digital tools in partnership with Indigenous communities. Guided by this framework, a needs assessment was conducted with a subarctic Métis community in Saskatchewan, Canada. This project is governed by a Citizen Scientist Advisory Council which includes Traditional Knowledge Keepers, Elders, and youth. An environmental scan of relevant programs, key informant interviews, and focus groups were conducted to systematically identify community priority areas. Given the timing of the needs assessment, the community identified the Coronavirus pandemic as a key priority area requiring digital initiatives. Recommendations for community-based needs assessments to conceptualize and implement digital infrastructure are put forward, with an emphasis on self-governance and data sovereignty.

Time series data are significant and are derived from temporal data, which involve real numbers representing values collected regularly over time. Time series have a great impact on many types of data. However, time series have anomalies. We introduce hybrid algorithm named novel matrix profile (NMP) to solve the all-pairs similarity search problem for time series data. The proposed NMP inherits the features from two state-of-the art algorithms: similarity time-series automatic multivariate prediction (STAMP), and short text online microblogging protocol (STOMP). The proposed algorithm caches the output in an easy-to-access fashion for single- and multidimensional data. The proposed NMP algorithm can be used on large data sets and generates approximate solutions of high quality in a reasonable time. The proposed NMP can also handle several data mining tasks. It is implemented on a Python platform. To determine its effectiveness, it is compared with the state-of-the-art matrix profile algorithms i.e., STAMP and STOMP. The results confirm that the proposed NMP provides higher accuracy than the compared algorithms.

The purpose of this study was to evaluate the implementation level of urban Sustainable Development Goals (SDGs) in the Republic of Korea and to measure the extent of internal and external impacts on the implementation level. An evaluation framework was established based on relative efficiency theory, and the implementation level of urban SDGs at the local government unit in the Republic of Korea was examined by performing an analysis of each stage. First, in reference to the 2018 cross-section, the implementation level of target 11.2 (public transportation) was assessed as excellent across the country, compared with the implementation level of targets 11.5 (disaster safety), 11.6 (environment), and 11.7 (public space), which were assessed as needing improvement. Second, the factors positively impacting the implementation level of target 11.2 were urban population, GRDP, financial independence, urbanization area, and bus-only lanes, whereas the factors positively impacting the implementation level of target 11.5 were population density and GRDP. The positive factors influencing the implementation level of target 11.6 (air quality sector) were found to be GRDP, financial independence, administrative area, and renewable energy generation, whereas the effective factors of the implementation level of target 11.6 (waste management sector) were analyzed as GRDP, financial independence, and the population density of households in the waste management area. The positive factors influencing the implementation level of target 11.7 were GRDP, financial independence, administrative area, and green area.

Performing predictive maintenance (PdM) is challenging for many reasons. Dealing with large datasets which may not contain run-to-failure data (R2F) complicates PdM even more. When no R2F data are available, identifying condition indicators (CIs), estimating the health index (HI), and thereafter, calculating a degradation model for predicting the remaining useful lifetime (RUL) are merely impossible using supervised learning. In this paper, a 3 dof delta robot used for pick and place task is studied. In the proposed method, autoencoders (AEs) are used to predict when maintenance is required based on the signal sequence distribution and anomaly detection, which is vital when no R2F data is available. Due to the sequential nature of the data, non-linearity of the system, and correlations between parameter time series, convolutional layers are used for feature extraction. Thereafter, a sigmoid function is used to predict the probability of having an anomaly given CIs acquired from AEs. This function can be manually tuned given the sensitivity of the system or optimized by solving a minimax problem. Moreover, the proposed architecture can be used for fault localization for the specified system. Additionally, the proposed method is capable of calculating RUL using Gaussian process (GP), as a degradation model, given HI values as its input.

Pipeline integrity is an important area of concern for the oil and gas, refining, chemical, hydrogen, carbon sequestration, and electric-power industries, due to the safety risks associated with pipeline failures. Regular monitoring, inspection, and maintenance of these facilities is therefore required for safe operation. Large standoff magnetometry (LSM) is a non-intrusive, passive magnetometer-based mea- surement technology that has shown promise in detecting defects (anomalies) in regions of elevated mechanical stresses. However, analyzing the noisy multi-sensor LSM data to clearly identify regions of anomalies is a significant challenge. This is mainly due to the high frequency of the data collection, mis-alignment between consecutive inspections and sensors, as well as the number of sensor measurements recorded. In this paper we present LSM defect identification approach based on ma- chine learning (ML). We show that this ML approach is able to successfully detect anomalous readings using a series of methods with increasing model complexity and capacity. The methods start from unsupervised learning with "point" methods and eventually increase complexity to supervised learning with sequence methods and multi-output predictions. We observe data leakage issues for some methods with randomized train/test splitting and resolve them by specific non-randomized splitting of training and validation data. We also achieve a 200x acceleration of support-vector classifier (SVC) method by porting computations from CPU to GPU leveraging the cuML RAPIDS AI library. For sequence methods, we develop a customized Convolutional Neural Network (CNN) architecture based on 1D convolutional filters to identify and characterize multiple properties of these defects. In the end, we report the scalability of the best-performing methods and compare them, for viability in field trials.

Over the past decade, wireless communication technologies have developed significantly for intelligent applications in road transport. This paper provides an overview of telecommunications-based intelligent transport systems with a focus on ensuring system safety and resilience. In vehicle-to-everything, these problems are extremely acute due to the specifics of the operation of transport networks, which requires the use of special protection mechanisms. In this regard, it was decided to use blockchain as a system platform to support the needs of transport systems for secure information exchange. This paper describes the technological aspects of implementing blockchain technology in vehicle-to-network; the features of such technology are presented, as well as the features of their interaction.

As of today, there is not any direct report yet of the degree to which missing residues exist for experimentally determined membrane protein (MP) structures, which constitute more than half of current drug targets. With a chain- and position-specific visualisation and a statistical analysis of all MP structures inside PDB (as of September 25, 2019), this article argues that the experimentally uncharted territories (EUTs, i.e., consisting of missing residues) within PDB are pluggable and should be plugged with an experimental data-driven hybrid approach, and calls for continued development of MP structural determination with less and less EUTs, in light of MPs' crucial role in biological and biomedical research, both fundamental and pharmaceutical.

As one of GEO-constellation for environmental monitoring in the next decade, Geostationary Environment Monitoring Spectrometer (GEMS) is designed to observe the Asia Pacific region to provide the information on the atmospheric chemicals, aerosol and cloud properties. For the continuous monitoring of the sensor performance after its launch in early 2020, here we suggest deep convective clouds (DCCs) as a possible target for the vicarious calibration of GEMS, the first UV/VIS hyperspectral sensor onboard a geostationary satellite. Tropospheric Monitoring Instrument (TROPOMI) and Ozone Monitoring Instrument (OMI) are used as a proxy of GEMS, and a conventional DCC detection approach applying the thermal threshold test is used for the DCC detection based on the collocations with Advance Himawari-8 Imager (AHI) onboard Himawari-8 geostationary satellite. DCCs are frequently detected over the GEMS observation area on average over 200 pixels in a single observation scene. Considering the spatial resolution of GEMS, 3.5 km×7 km which is similar to TROPOMI, and its temporal resolution (8 times a day), availability of DCCs for vicarious calibration of GEMS is expected to be sufficient. Inspection of the DCC reflectivity spectra estimated from the OMI and TROPOMI data also shows a promising result. Even though, their observation geometry and sensor characteristics are quite a different, the estimated DCC spectra agree quite a well within a known uncertainty range with comparable spectral features. When the DCC detection is further improved by applying both visible and infrared tests, the variability of DCC reflectivity from the TROPOMI data is reduced by half, from 10% to 5%. This is mainly due to the efficient screening of cold thin cirrus with the visible test and of bright warm clouds with the infrared test. The precise DCC detection is also expected to contribute to the accurate characterization of the cloud reflectivity, which will be further investigated.

The Medi-test system we developed was motivated by the large number of resources available for the medical domain, as well as the number of tests needed in this field (during and after the medical school) for evaluation, promotion, certification, etc. Generating questions to support learning and user interactivity has been an interesting and dynamic topic in NLP since the availability of e-book curricula and e-learning platforms. Current e-learning platforms offer increased support for student evaluation, with an emphasis in exploiting automation in both test generation and evaluation. In this context, our system is able to evaluate a student’s academic performance for the medical domain. Using as input medical reference texts and supported by a specially designed medical ontology, Medi-test generates different types of questionnaires for Romanian language. The evaluation includes 4 types of questions (multiple-choice, fill in the blanks, true/false and match), can have customizable length and difficulty and can be automatically graded. A recent extension of our system also allows for the generation of tests which include images. We evaluated our system with a local testing team, but also with a set of medicine students, and user satisfaction questionnaires showed that the system can be used to enhance learning.

Speech/music classification that facilitates optimized signal processing from classification results has been extensively adapted as an essential part of various electronics applications, such as multi-rate audio codecs, automatic speech recognition, and multimedia document indexing. In this paper, a new technique to improve the robustness of speech/music classifier for 3GPP enhanced voice service (EVS) using long short-term memory (LSTM) is proposed. For effective speech/music classification, feature vectors implemented with the LSTM are chosen from the features of the EVS. Experiments show that LSTM-based speech/music classification produces better results than conventional EVS under a variety of conditions and types of speech/music data.

Polar mesocyclones (MCs) are small marine atmospheric vortices. The class of intense MCs, called polar lows, are accompanied by extremely strong surface winds and heat fluxes and thus largely influencing deep ocean water formation in the polar regions. Accurate detection of polar mesocyclones in high-resolution satellite data, while challenging, is a time-consuming task, when performed manually. Existing algorithms for the automatic detection of polar mesocyclones are based on the conventional analysis of patterns of cloudiness and involve different empirically defined thresholds of geophysical variables. As a result, various detection methods typically reveal very different results when applied to a single dataset. We develop a conceptually novel approach for the detection of MCs based on the use of deep convolutional neural networks (DCNNs). As a first step, we demonstrate that DCNN model is capable of performing binary classification of 500x500km patches of satellite images regarding MC patterns presence in it. The training dataset is based on the reference database of MCs manually tracked in the Southern Hemisphere from satellite mosaics. We use a subset of this database with MC diameters falling in the range of 200-400 km. This dataset is further used for testing several different DCNN setups, specifically, DCNN built “from scratch”, DCNN based on VGG16 pre-trained weights also engaging the Transfer Learning technique, and DCNN based on VGG16 with Fine Tuning technique. Each of these networks is further applied to both infrared (IR) and a combination of infrared and water vapor (IR+WV) satellite imagery. The best skills (97% in terms of the binary classification accuracy score) is achieved with the model that averages the estimates of the ensemble of different DCNNs. The algorithm can be further extended to the automatic identification and tracking numerical scheme and applied to other atmospheric phenomena characterized by a distinct signature in satellite imagery.

The futures market plays a significant role in hedging and speculating by investors. Although various models and instruments are developed for real-time trading, it is difficult to realize profit by processing and trading a vast amount of real-time data. This study proposes a real-time index futures trading strategy that uses the pattern of KOSPI 200 index futures time series data. We construct a pattern matching trading system (PMTS) based on a dynamic time warping algorithm that recognizes patterns of market data movement in the morning and determines the afternoon's clearing strategy. We adopt 13 and 27 representative patterns and conduct simulations with various ranges of parameters to find optimal ones. Our experimental results show that the PMTS provides stable and effective trading strategies with relatively low trading frequencies. Investor communities that have sustained financial markets are able to make more efficient investments by using the PMTS. In this sense, the system developed in this paper is a sustainable investment technique and helps financial markets achieve efficient sustainability.

This paper considers a non-mixture cure model for right censored data. It utilizes the maximum likelihood method to estimate model parameters in the non-mixture cure model. The simulation study is based on Fréchet susceptible distribution to evaluate the performance of the method. Comparing with Weibull and exponentiated exponential distributions, the non-mixture Fréchet distribution is shown to be the best in modeling a real data on allogeneic marrow HLA-matched donors and ECOG phase III clinical trial e1684 data.

This paper aims to provide an adaptation of the TL-moments method to censored data. The present study concentrates on Type-I censored data. The idea of using TL-moments with censored data may seem conflicting. But our perspective in that, we may use data censored from one side and trimmed from the other side. This study is applied to estimate the two unknown parameters of the Weibull distribution. The suggested point is compared with Direct L-moments and ML methods. A Monte Carlo simulation study is carried out to compare these method in terms of estimate average, root of mean square error (RMSE) and relative absolute biases (RAB).

Spatial Data Infrastructures (SDI) established during the past two decades ’unlocked’ heterogeneous geospatial datasets. The European Union INSPIRE Directive laid down the foundation of a pan-European SDI where thousands of public sector data providers make their data available for cross-border and cross-domain reuse. At the same time, SDIs should inevitably adopt new technology and standards in order to remain fit for purpose and address in the best possible way the needs of different stakeholders (government, businesses and citizens). Some of the recurring technical requirements raised by SDI stakeholders include (i) the need for adoption of RESTful architectures, together with (ii) alternative (to GML) data encodings, such as JavaScript Object Notation (JSON) and binary exchange formats, and (iii) adoption of asynchronous publish-subscribe-based messaging protocols. The newly established OGC standard SensorThings API is particularly interesting to investigate for INSPIRE, as it addresses together all three topics. In this manuscript, we provide our synthesised perspective on the necessary steps for the OGC SensorThings API standard to be considered as a solution that meets the legal obligations stemming out of the INSPIRE Directive. We share our perspective on what should be done concerning (i) data encoding, and (ii) the use of SensorThings API as a download service.

Personalized medicine is an aspect of the P4 medicine (predictive, preventive, personalized and participatory) based precisely on the customization of all medical characters of each subject. In personalized medicine, the development of medical treatments and drugs is tailored to the individual characteristics and needs of each subject, according to the study of diseases at different scales from genotype to phenotype scale. To make concrete the goal of personalized medicine, it is necessary to employ high-throughput methodologies such as Next Generation Sequencing (NGS), Genome-Wide Association Studies (GWAS), Mass Spectrometry or Microarrays, that are able to investigate a single disease from a broader perspective. For example, by using genotyping microarrays (e.g. collections of Single Nucleotide Polymorphism - SNP) it is possible to uncover the reasons (i.e. mutation in genes) because a treatment works properly in some patients (for example absence of mutated genes), but it does not work (presence of mutated genes) in others. A side effect of high-throughput methodologies is the massive amount of data produced for each single experiment, that poses several challenges (e.g. high execution time and required memory) to bioinformatic software. Thus a main requirement of modern bioinformatic software is the use of good software engineering methods and efficient programming techniques, able to face those challenges, that include the use of parallel programming and efficient and compact data structures. Thus, to exploit all the potential of this massive amount of data in the short possible time (before that data becomes obsolete), the necessity to develop parallel software tools for efficient data collection and analysis arise. Moreover, due to the heterogeneity of the data produced by the different kinds of experimental platforms, it is necessary to automatize in a comprehensive software pipeline, the various steps that compose a bioinformatic analysis, such as: the preprocessing of raw data to remove noise or corrupted data; the annotation of data with external knowledge (e.g. Gene Ontology), and the integration of molecular data with clinical data. It should be noted that such steps are necessary to make statistical or data mining analysis more effective. This paper presents the design and the experimentation of a comprehensive software pipeline, named microPipe, for the preprocessing, annotation and analysis of microarray-based SNP genotyping data. A case study in pharmacogenomics is presented. The main advantages of using microPipe are: the reduction of errors that may happen when trying to make data compatible among different tools; the possibility to analyze in parallel huge datasets; the easy annotation and integration of data.

This paper aims to develop a low-cost, high-performance and high-reliability computing system to process large-scale data using common data mining algorithms in the Internet of Things computing. Considering the characteristics of IoT data processing, similar to mainstream high performance computing, we use a GPU cluster to achieve better IoT services. Firstly, we present an energy consumption calculation method (ECCM) based on WSN. Then, using the CUDA Programming model, we propose a Two-level Parallel Optimization Model (TLPOM) which exploits reasonable resource planning and common compiler optimization techniques to obtain the best blocks and threads configuration considering the resource constraints of each node. The key to this part is dynamic coupling Thread-Level Parallelism (TLP) and Instruction-Level Parallelism (ILP) to improve the performance of the algorithms without additional energy consumption. Finally, combining the ECCM and the TLPOM, we use the Reliable GPU Cluster Architecture (RGCA) to obtain a high-reliability computing system considering the nodes’ diversity, algorithm characteristics, etc. The results show that the performance of the algorithms significantly increased by 34.1%, 33.96% and 24.07% for Fermi, Kepler and Maxwell on average with TLPOM and the RGCA ensures that our IoT computing system provides low-cost and high-reliability services.

AbstractThe escalating impact of artificial intelligence (AI) has birthed the fascinating technology of deepfakes, capable of meticulously crafting hyper-realistic audio-visual manipulations. Within the realm of healthcare, this technology presents a double-edged sword, brimming with potential for revolutionizing various facets of care delivery while simultaneously harboring significant ethical and practical challenges. This research delves into the complex narrative surrounding AI deepfakes in healthcare, meticulously analyzing both the exciting opportunities they offer, and the inherent risks associated with their implementation.Background:Traditional healthcare practices face limitations in patient engagement, accessibility, and training efficacy. Deepfakes, with their ability to simulate real-world scenarios and interactions, emerge as a potential solution, offering personalized patient education, immersive mental health interventions, remote consultations with virtual avatars, and realistic training simulations for medical professionals.Objective:This research aims to comprehensively understand the multifaceted impact of AI deepfakes in healthcare systems. It seeks to: Identify and analyze the potential benefits of deepfakes in specific healthcare applications. Assess the ethical and practical challenges associated with deepfake implementation in healthcare settings. Propose recommendations for safe, responsible, and ethical integration of deepfakes within the healthcare system.Results/Conclusion:The research findings illuminate a landscape replete with opportunities and challenges. Deepfakes offer the potential to enhance patient education, personalize mental health interventions, facilitate remote consultations, and revolutionize medical training. However, concerns regarding misinformation, ethical breaches, data privacy, and technical limitations pose significant challenges.The conclusion emphasizes the need for a balanced approach that capitalizes on the innovative potential of deepfakes while mitigating potential harm. Collaborative efforts involving healthcare professionals, technologists, and policymakers are crucial for establishing ethical frameworks, ensuring responsible development, and harnessing the positive power of deepfakes to build a future where healthcare benefits from cutting-edge technology while prioritizing patient well-being and ethical principles.

Ridge regression is one of the most popular shrinkage estimation methods for linear models. Ridge regression effectively estimates regression coefficients in the presence of high-dimensional regressors. Recently, a generalized ridge estimator was suggested by generalizing the uniform shrinkage of ridge regression to the non-uniform shrinkage, which was shown to perform well under sparse and high-dimensional linear models. In this paper, we introduce our newly developed R package “g.ridge” (the first version published on 2023-12-07 at https://cran.r-project.org/package=g.ridge) that implements both the ridge estimator and generalized ridge estimators. The package equips with the generalized cross-validation for automatic estimation of shrinkage parameters. The package also includes a convenient tool for generating a design matrix. By simulations, we test the performance of the R package under sparse and high-dimensional settings with the normal and skew-normal error distributions. From the simulation results, we conclude that the generalized ridge estimator is superior to the benchmark ridge estimator based on “glmnet”, and hence, it can be the most recommended estimator under sparse and high-dimensional models. We demonstrate the package using the intracerebral hemorrhage data.

The sensitivity of macroscopic mechanical and thermal properties of grey cast iron is computationally investigated for a variety of graphite microstructures over a wide temperature range. In order to represent common graphite microstructures according to DIN EN ISO 945-1, a synthetic approach is used to algorithmically generate simulation domains. The developed mechanical and thermal model is applied in a large simulation study. The study includes statistical volume elements of the graphite microstructures classes GG-15 and IA2 to IA5, with 10 v.-%, 11 v.-% and 12 v.-% graphite, respectively, for a temperature range from 20 °C to 750 °C. Homogenized macroscopic quantities such as the Young's moduli, Poisson's ratios, yield strengths and thermal conductivities are predicted for the different microstructure classes by applying simulation and data analysis tools of the research data infrastructure Kadi4Mat.

This paper describes a Long Short-Term Memory (LSTM) neural network model used to simulate the dynamics of the OC3 reference design of a Floating Offshore Wind Turbine Spar unit. It crafts an advanced neural network with an encoder-decoder architecture capable of predicting the Spar’s motion and fairlead tensions time series. These predictions are based on wind and wave excitations across various operational and extreme conditions. The LSTM network, trained on an extensive dataset from over 300 fully coupled simulation scenarios using OpenFAST, ensures a robust framework that captures the complex dynamics of floating platform under diverse environmental scenarios. This framework’s effectiveness is further verified by thoroughly evaluating the model’s performance, leveraging comparative statistics and accuracy assessments to highlight its reliability. This methodology contributes to substantial reductions in computational time. This research aims to provide critical insights that facilitate the optimization of offshore wind turbines, marking a step forward in the quest for more efficient and dependable renewable energy solutions.

The World Meteorological Organization (WMO) recommends that the most recent 30-year period, i.e. 1991-2020, shall be used to compute climate normals of geophysical variables. A unique aspect this recent 30-year period is that the satellite-based observations of many different essential climate variables are available during this period, thus opening up new possibilities to provide a robust, global basis for the 30-year reference period in order to allow climate monitoring and climate change studies. Here, using the satellite-based climate data record of cloud and radiation properties, CLARA-A3, for the month of January between 1981 to 2020, we illustrate the difference between climate normal, as defined by guidelines from WMO on calculations of 30-yr climate normals, and climatology. It is shown that this difference is strongly dependent on the climate variable in question. We discuss the impacts of the nature and availability of satellite observations, variable definition, retrieval algorithm and programmatic configuration. It is shown that the satellite-based climate data records show enormous promise in providing climate normal for the recent 30-year period (1991-2020) globally. We finally argue that the holistic perspectives from the global satellite community should be increasingly considered while formulating the future WMO guidelines on computing climate normals.

The lexical analysis of seminal policy-to-diplomacy documents from the socio-environmental discourse of the last fifty year agendas allowed examining the evolution of five themes: resources/waste, pollution, social and economic development, justice, and health. Contextual affinities were strongest between resources, pollution, and health and are linked to societal trends and pressures. On those grounds, the central role of resource stewardship according to nature’s physical limits is highlighted, and dedicated concepts, analytical frameworks, and methodologies with different degrees of sustainability are analyzed. To reframe the identified social and economic problems, the work proposes criteria and choices that (1) allow to compare the dynamics of socioecological states across the planet, (2) help matching the pace of socioecological change by addressing path dependencies through participation and engagement of communities, and (3) enable stakeholders to make trade-offs and take decisions in specific social, economic, political, and cultural contexts. The prioritization of resource justice and responsibility becomes a societal project : from Wellfare State to commonfare communities.

This paper introduces an innovative theoretical framework for quantum-inspired data embeddings, grounded in foundational concepts of quantum mechanics such as superposition and entanglement. This approach aims to advance semi-supervised learning in contexts characterized by limited labeled data by enabling more intricate and expressive embeddings that capture the underlying structure of the data effectively. Grounded in foundational quantum mechanics concepts such as superposition and entanglement, this approach redefines data representation by enabling more intricate and expressive embeddings. Emulating quantum superposition encodes each data point as a probabilistic amalgamation of multiple feature states, facilitating a richer, multidimensional representation of underlying structures and patterns. Additionally, quantum-inspired entanglement mechanisms are harnessed to model intricate dependencies between labeled and unlabeled data, promoting enhanced knowledge transfer and structural inference within the learning paradigm. In contrast to conventional quantum machine learning methodologies that often rely on quantum hardware, this framework is fully realizable within classical computational architectures, thus bypassing the practical limitations of quantum hardware. The versatility of this model is illustrated through its application to critical domains such as medical diagnosis, resource-constrained natural language processing, and financial forecasting—areas where data scarcity impedes the efficacy of traditional models. Experimental evaluations reveal that quantum-inspired embeddings substantially outperform standard approaches, enhancing model resilience and generalization in high-dimensional, low-sample scenarios. This research marks a significant stride in integrating quantum theoretical principles with classical machine learning, broadening the scope of data representation and semi-supervised learning while circumventing the technological barriers of quantum computing infrastructure.

Electricity demand prediction is vital for energy production management and proper exploitation of the present resources. Recently, several novel machine learning (ML) models have been employed for electricity demand prediction to estimate the future prospects of the energy requirements. The main objective of this study is to review the various ML models applied for electricity demand prediction. Through a novel search and taxonomy, the most relevant original research articles in the field are identified and further classified according to the ML modeling technique, perdition type, and the application area. A comprehensive review of the literature identifies the major ML models, their applications and a discussion on the evaluation of their performance. This paper further makes a discussion on the trend and the performance of the ML models. As the result, this research reports an outstanding rise in the accuracy, robustness, precision and the generalization ability of the prediction models using the hybrid and ensemble ML algorithms.

Using both GRACE satellite data and statistical records, we apply the advanced Super-SBM model in this study to evaluate the efficiency of water resource utilization in 34 prefecture-level cities across three provinces in Northeast China from 2003 to 2020. Furthermore, we employ the Tobit model to examine the factors influencing efficiency. Our findings suggest that while spatial clustering is moderately low, the efficiency of water resource utilization in the Northeast Region is praiseworthy and significantly correlates with the level of technological advancement. Four distinct categories can be identified among the prefecture-level cities based on the scale and technological efficiency of water resource utilization. To promote enhanced utilization of water resources, different regions should implement measures that are specifically tailored to their unique circumstances.

Most of the research in data mining concentrated on finding the positive associations that exist in frequent patterns. Frequent patterns have no bearing on the time duration and, therefore, lose interestingness. The Regularity of an itemset is related to the time at which the transaction occurred and the time distance between the transactions. Frequent Regular item sets can be generated considering the Frequency and the Regularity of the occurrence of the Item Sets. The frequent and regular Item sets will be so huge that they cannot be handled in real time. The count of Frequent and regular item sets gets reduced drastically when the properties “closed” and “Maximality” are applied. Finding negative associations among such patterns are important in the field of medicine. Many drugs administered to cure some diseases have counter reactions leading to many other diseases. Negative associations among the mined patterns are important as they reveal significant contradictions frequently among medical drugs administered by medical practitioners to cure some diseases. This paper proposes a method that mines medical databases to find regular, frequent patterns applied with closed and maximal properties and find negative associations among those patterns. The proposed algorithm is accurate to 98% and performs 9% more efficiently than the other algorithms presented in the literature.

Pancreatic neuroendocrine neoplasms (pNENs) are rare tumors accounting for only 1-2% of all pancreatic tumors. pNENs are pathologically heterogeneous and are categorized into three groups (neuroendocrine tumor: NET G1, NET G2 and neuroendocrine carcinoma: NEC) on the basis of Ki-67 proliferation index and mitotic count according to the 2010 WHO classification of gastroenteropancreatic NENs. NEC in this classification includes both histologically well-differentiated and poorly differentiated subtypes, and modification of the WHO 2010 classification is under discussion based on genetic and clinical data. Genomic analysis has revealed NETs G1/G2 have genetic alterations in chromatin remodeling genes such as MEN1, DAXX and ATRX, whereas NECs have an inactivation of TP53 and RB1, and these data suggest that different treatment approaches would be required for NET G1/G2 and NEC. While there are promising molecular targeted drugs, such as everolimus or sunitinib, for advanced NET G1/G2, treatment stratification based on appropriate predictive and prognostic biomarkers is becoming an important issue. The clinical outcome of NEC is still dismal, and a more detailed understanding of the genetic backround together with preclinical studies to develop new agents, including those already under investigation for SCLC, will be needed to improve the prognosis.

Digital twins are gaining in popularity for simulating complex natural and urban environments. In this context, accurate segmentation of objects within 3D urban environments is of crucial importance. The aim of this project is to develop a methodology for extracting buildings from textured 3D meshes. To this end, PicassoNet-II, a semantic segmentation architecture is employed. The methodology also incorporates Markov field-based contextual analysis to assess post-segmentation features. In addition, building instantiation is performed using cluster analysis algorithms. Training this model to fit various datasets requires a large amount of annotated data, both from Quebec City, Canada, and from simulated data. Experimental results show that the use of simulated data improves segmentation accuracy, and the DBScan algorithm proves effective in extracting isolated buildings. This project paves the way for improved applications in 3D urban modeling, offering opportunities in fields ranging from urban planning to resource management. The positive results with simulated data reinforce the impact of this research on improving digital models of our ever-changing urban environments.

This paper provides an in-depth exploration of the role of Big Data and Artificial Intelligence (AI) in advancing dairy farming towards net zero emissions, a critical goal in the face of the global climate crisis. The study emphasizes how these technologies significantly enhance the management of greenhouse gas (GHG) emissions and optimize resource use, thereby contributing to environmental sustainability in agriculture. A key aspect of this transition is the alignment with international climate commitments, such as the Paris Agreement, which are instrumental in steering global efforts toward emission reduction and mitigating climate change. The integration of Big Data and AI in dairy farming emerges as a powerful tool to reduce the sector's environmental impact while sustaining economic growth. The paper delves into the specific applications of these technologies in emission management, including predictive analytics for feed optimization, manure management, and energy efficiency enhancements. It also addresses the broader implications of technological integration in dairy farming, considering aspects like benchmarking standards, data privacy, and the role of policy in fostering sustainable practices. The study underscores the challenges inherent in adopting these advanced technologies, including the need for improved farmer training, data quality, and compatibility with existing systems. It also advocates for enhanced policy frameworks that support sustainable practices, encourage technological adoption, and balance economic viability with environmental responsibility. This comprehensive analysis offers valuable insights into harnessing digital technologies for climate change mitigation and delineates a path for the dairy industry towards achieving net zero emissions, thereby contributing significantly to global environmental sustainability efforts.

In France, the regional airport’s demand for services is facing challenges due to the continuous expansion of the high-speed train, high-speed line, and highway networks. This study focuses on the viability of regional airports in France through technical efficiency using data envelopment, principle component analysis, Malmquist productivity index, and regression analysis using bootstrapping. To face the current competitive environment, the regional airports in France adopted strategies, such as the construction of low-cost carrier (LCC) dedicated terminals (LCCTs) with lower expenses to attract more LCCs, increasing non-aeronautical revenue, and hosting regional hubs of LCCs. This is the first study that analyzes all of the French regional airports. The findings indicate that the existence of LCCTs positively affects technical efficiency on the airport’s performance, and share of LCCs at a regional airport leads to neither the efficiency nor the profit level.

As businesses increasingly adopt advanced technologies to enhance productivity and safety, the integration of human-robot collaboration (HRC) emerges as a transformative approach. This paper explores the role of GPU-accelerated computer vision and generative AI in optimizing HRC within business environments. By leveraging the computational power of GPUs, real-time data processing, and advanced machine learning algorithms, robots can better interpret complex visual cues and adapt to dynamic workspaces. Generative AI further enables the design of intelligent robotic systems capable of anticipating human actions, optimizing task allocation, and ensuring safety through predictive modeling. This research highlights the potential of these technologies to improve operational efficiency, reduce human error, and create safer, more adaptable workplaces. The implications of such advancements are discussed, providing insights into the future of HRC in various industries.

Currently, an interactive environmental planning analysis system platform based on " Three Lines One Permit " (TLOP) is being developed to support environmental planning, construction project approval, and the application of TLOP outcome data in Guangzhou. The main objective is to provide governments, businesses and the public with environmental planning analysis tools to determine the site of construction projects. The platform is using the system architecture of the browser and server. Its core functions are interactive environmental planning analysis tool for construction project and the results display tool supporting map viewing. It provides users with a large number of detailed geospatial data and TLOP results data access and environmental planning analysis functions. This article describes the system architecture and implementation of the system platform and has a case study illustrating the system functionality. At present, the platform has been deployed and trial-operated. The content of the analysis framework is constantly expanding. This promotes the matching of environmental planning and analysis with local conditions. This will implement the application of TLOP and improve the efficiency of project construction and the level of ecological environment planning and management.

In the process of game development, identifying and deleting currently abandoned assets as content iterates can effectively reduce the size of game packages. But the built-in reference checking tool in UE4 can only check static references of assets and cannot identify dynamically referenced resources in the program. We have developed a static analysis tool for analyzing unused assets in the UE4 project to address this issue. This tool checks the function parameters of all loading points, analyzes the value range of the parameter string based on the data dependency relationship of the actual parameter variable, and considers that the assets that match within the range are referenced. Due to the fact that in some cases, the exact data stream of the actual parameter variable is not computable (resulting in false negatives), the reverse analysis tool supports manually marking the parameter range at the loading point. This tool can generate asset collections that are dynamically referenced. The union of its results with the built-in reference checking tool in UE4 is the set of all referenced assets. The difference set between all asset sets and the referenced asset set is the abandoned asset set. This achieves a more complete cleaning of redundant resources and reduces the size of game packages.

Digital image compression is applied to reduce camera bandwidth and storage requirements, but real-time lossless compression on a high-speed high-resolution camera is a challenging task. The article presents hardware implementation of a Bayer colour filter array lossless image compression algorithm on an FPGA-based camera. The compression algorithm reduces colour and spatial redundancy and employs Golomb-Rice entropy coding. A rule limiting the maximum code length is introduced for the edge cases. The proposed algorithm is based on integer operators for efficient hardware implementation. The algorithm is first verified as a C++ model and later implemented on Xillinx Zynq UltraScale+ device using VHDL. An effective tree-like pipeline structure is proposed to concatenate codes of compressed pixel data to generate a bitstream representing data of 16 parallel pixels. The proposed parallel compression achieves up to 56% reduction in image size for high resolution images. Pipelined implementation without any state machine ensures operating frequencies up to 320 MHz. Parallelised operation on 16 pixels effectively increases data throughput to 40 Gbit/s while keeping total memory requirements low due to real-time processing.

This study investigates the transformative role of mobile applications in retail marketing strategies, focusing on how these digital tools have reshaped consumer engagement, personalization, and operational efficiency. Mobile applications have emerged as pivotal assets for retailers, facilitating direct communication with customers through real-time updates, personalized promotions, and tailored content. The integration of digital loyalty programs within mobile apps has streamlined rewards systems, making it easier for customers to engage with and benefit from loyalty initiatives. By leveraging data analytics, retailers can gain deep insights into consumer behavior, optimize inventory management, and refine marketing strategies. The incorporation of augmented reality (AR) and virtual reality (VR) technologies into mobile apps has introduced innovative ways for customers to interact with products and explore virtual showrooms, enhancing the overall shopping experience. Mobile commerce (m-commerce) has also seen significant growth, driven by the convenience and accessibility provided by mobile apps, which support seamless shopping experiences and mobile payments. Despite these advantages, challenges such as data privacy concerns and the need for continuous innovation remain. Retailers must address these issues to maintain consumer trust and stay competitive. Looking ahead, emerging technologies such as artificial intelligence (AI) and machine learning (ML) are expected to further enhance mobile app functionalities and personalization. The focus on sustainability is also influencing mobile app features, aligning with consumer values and expectations. Overall, mobile applications are set to play an increasingly critical role in shaping the future of retail marketing, offering new opportunities for engagement, innovation, and growth.

This study explores the impact of mobile technologies on consumer behavior in retail marketing, examining how advancements in mobile platforms have transformed shopping habits and interactions with brands. Mobile technologies have revolutionized the retail experience by providing unprecedented convenience, allowing consumers to shop at any time and from any location. This shift has led to a marked preference for mobile shopping over traditional methods, fundamentally altering consumer behavior. Key findings reveal that personalization plays a crucial role in enhancing consumer engagement and satisfaction, with mobile technologies enabling tailored recommendations and offers based on individual preferences. Access to real-time information, such as product details and price comparisons, empowers consumers to make more informed purchasing decisions, reflecting a shift towards deliberate and confident buying choices. Social media and social commerce have also become significant factors, with consumers discovering new products and brands through these platforms and benefiting from integrated shopping features. Impulse buying behavior has increased due to the convenience of mobile shopping, with promotional alerts and simplified payment processes contributing to spontaneous purchases. The integration of mobile technologies with physical store experiences has created a more seamless shopping journey, bridging the gap between online and offline interactions. However, challenges such as privacy concerns, data security, and information overload remain significant. Consumers are increasingly aware of data collection risks and may experience fatigue from excessive marketing messages. To navigate this evolving landscape, retailers must balance the advantages of mobile technologies with addressing these challenges to effectively meet consumer needs and expectations.

This study investigates the environmental parameters contributing to the Urban Heat Island (UHI) effect in historically built environments, focusing on Matera's Street Canyon. The primary objective is to enhance understanding of heritage centers' ecological sustainability and management frameworks. The study involves two main phases: the initial research and development phase, including a comprehensive literature review and methodology development, followed by the empirical data gathering and analysis phase, utilizing advanced techniques such as 3D laser scanning, satellite imagery, and meteorological data integration. Key findings reveal significant correlations between urban morphology, material properties, and UHI intensity, suggesting stra-tegic urban planning interventions to mitigate UHI effects. This research provides actionable in-sights for urban planners and policymakers, emphasizing the importance of balancing heritage preservation with modern sustainability needs.

The abstract should be an objective representation of the article and it must not contain results that are not presented and substantiated in the main text and should not exaggerate the main conclusions. The study developed a novel method for evaluating the freshness of citrus fruits by integrating near-infrared spectroscopy with the nonlinear data processing capabilities of a BP neural network. This approach utilizes specific wavelength analysis to distinguish between fresh and non-fresh fruits effectively. Advanced preprocessing techniques are employed to remove spectral anomalies, enhancing the network's ability to accurately identify crucial quality indicators like sugar content. Concurrently, an experiment utilising a MATLAB-based BP neural network optimised the number of hidden layer nodes, identifying 61 as optimal. This configuration achieved impressive metrics, including a mean squared error of 0.0025665 and a root mean squared error of 49.8214, over 1000 training iterations with an 80% learning rate. The model demonstrated a high accuracy rate of 97.6275%, confirming its precision and reliability in assessing citrus freshness. This synergy between advanced neural network processing and spectroscopic techniques marks a significant advancement in agricultural quality assessment, setting new standards for speed and efficiency in data processing.

Drug-target binding is an essential parameter in drug discovery and design to ensure drug efficacy and specificity. In 2022, the concept of a general intermolecular binding affinity calculator (GIBAC) was for the first time coined: $Kd = f(molecules, envPara)$. Technically, GIBAC represents a set of in silico approaches for structural and biophysical data generation towards a paradigm shift in precise drug discovery and design, providing a comprehensive framework for intermolecular binding affinity calculation with adequate accuracy, precision and efficiency. For the first time, this study reports a prototype of GIBAC (semaGIBAC), i.e., a one-dimensional semaglutide-GLP-1R-based mini static GIBAC, based on an experimental complex structure of semaglutide and GLP-1R. Semaglutide is a potent GLP-1 receptor agonist used to treat type 2 diabetes mellitus by regulating blood glucose levels and promoting weight loss. In 2021, a structural modification involving a Val27-Arg28 exchange was manually introduced to enhance semaglutide-GLP-1R binding affinity. This study employs a comprehensive structural and biophysical analysis aimed at thoroughly exploring the sequence space of semaglutide-GLP-1R to design analogues with improved binding affinity, leading to the identification of a promising semaglutide analogue, which binds to GLP-1R with an affinity that is more than two orders of magnitude (113.3 times) higher than native semaglutide. To sum up, this article puts forward a promising structural biophysical approach for developing GLP-1 receptor agonists with enhanced efficacy, and with a GIBAC prototype (semaGIBAC), this article argues again that the time is now ripe for the construction of a real GIBAC to be listed on the agenda of the drug discovery and design community.

Key performance indicators are essential for any company to enhance its competitiveness. How-ever, a common issue is the manual collection of production data using record sheets, which are later digitized on desktop computers and processed in Excel sheets. Shockingly, 41% of companies in Mexico have no plans for digitalization. This work aims to develop a Real-time Productivity Indicator Monitoring System using Industry 4.0 technologies for a medium-sized manufacturing firm specializing in die-cutting automotive parts. The Advanced Quality Planning methodology was applied to develop the Conceptual, Product, and Process Engineering and its validation. The experimental tests demonstrated a reliability level of 99.98%, which exceeded initial expectations. The primary contributions presented in this work are related to the development of algorithms, communication protocols, data analysis, and general optimization of the calculation process. The study's only limitation was the short experimentation time.

The variety of risks due to climate change with a potential impact on Cultural Heritage CH requires a multidisciplinary approach and a preliminary overview of the existing methods for risk analysis and assessment in different fields. Thus, the starting point of the research conducted by the Sapienza PNRR working group consists in a systematic literature review of risk assessment approaches, methods and indicators. As a first outcome, the research has designed a multidisciplinary comprehensive framework consisting of the definition of risk categorization, the framework represented by a measurable index and the main target, according to the classification of Cultural Heritage based on the harmonization of European vocabularies definitions and protocols. The risk assessment framework sets the methodological core of a future multi criteria matrix and digital platform for decision focused on the historic built environment and it is functional to the definition of specific operational guidelines connected to each risk for elaborating descriptive/predictive Architectural Heritage’s transformation scenarios to support the development of mitigation and adaptation strategies.

This study introduces the Dynamic Feedback-Driven Learning Optimization Framework (DFDLOF), an innovative machine learning-based approach to personalize educational pathways. DFDLOF leverages advanced algorithms for in-depth analysis of learner data, enabling the dynamic customization of educational content and methodologies. Its application in diverse online platforms, including Khan Academy and Coursera, underscores its adaptability and scalability. DFDLOF enhances learner engagement and outcomes by providing tailored learning experiences and real-time feedback. Key insights reveal its strengths in personalized education, particularly in dynamically adapting learning paths and the importance of real-time feedback. Challenges identified include integration complexities and data privacy concerns. Future research directions emphasize the need for longitudinal impact studies and broader demographic applications. This study contributes significantly to the evolving domain of adaptive learning technologies, demonstrating the transformative potential of machine learning in personalizing education.

The meticulously engineered powertrain mounting system of hybrid-electric vehicles plays a critical role in minimizing vehicle vibrations and noise, thereby enhancing the longevity of vital powertrain components. However, developing and designing such a system demands substantial time and financial investments due to intricate analysis and modeling requirements. To tackle this challenge, this study integrates data-mining technology into the design and optimization processes of the powertrain mount system. The research focuses on the powertrain mounting system of a transverse four-cylinder hybrid-electric vehicle, employing the CRISP-DM (Cross-Industry Standard Process for Data Mining) methodology to establish a data-mining prediction model for mounting stiffness. This model utilizes three data mining algorithms—Multi-SVR, MRTs, and MLPR—assessing their predictive accuracy concerning mounting system stiffness estimation. A comparative analysis reveals that the MRTs algorithm outperforms others as the most effective prediction model. The proposed predictive model elucidates the quantifiable correlation between vibration isolation performance and installation stiffness, overcoming complexities associated with traditional modeling approaches. Applying this model in powertrain mounting system design showcases the efficacy of the CRISP-DM-based approach, significantly enhancing design efficiency without compromising prediction accuracy.

Intelligent Tutoring Systems (ITS) are increasingly popular for online learning. These systems use adaptive algorithms to recommend relevant content based on students' profiles. However, instructors need to periodically assess students' performance to ensure learning outcomes and adjust strategies accordingly. Our objective is to predict students' progress in advance, enabling teachers to make quicker decisions and facilitating the iterative process of adaptive algorithms. For this study, we collected a dataset from ALIN, an online learning platform, consisting of over 5,000 students' learning records and test results. Using this dataset, we conducted experiments employing various machine learning algorithms. The results indicate that learning behavior contributes to improving forecast performance, while students' progress strongly correlates with their previous test results. Additionally, we discovered that students' progress can be indirectly predicted by forecasting their scores. Furthermore, by breaking down overall scores into several distinct components and predicting individual scores for each component, the accuracy of the forecasts can be improved.

Data mining techniques have garnered significant attention within the realm of education. However, the procurement of ample student data poses a formidable challenge. In response to this challenge, we present a student dataset characterized by its size and distinctive attributes. This dataset encompasses various task-related topics interconnected through a learning pathway, thereby enabling researchers to delve into the data from novel perspectives. Moreover, it encompasses extensive longitudinal student behavioral data, a rarity that adds substantial value. Spanning the years from 2010 to 2021, our dataset comprises a cohort of 7,933 students, 64,344 test scores, and 183,390 behavior records, solidifying its status as a valuable resource for educational research. In our experiments, we achieved successful predictions of students' test outcomes based on behavioral learning data. The strengths of our dataset render it apt for analyzing the nexus between student conduct and academic performance, crafting personalized learning recommendations, and pursuing various other research pursuits.

Efficient traffic management at signalized intersections is integral to urban infrastructure development, requiring accurate estimation of delay times to mitigate congestion and enhance overall transportation systems. Traditional methodologies, including empirical observations and microsimulation software, have been prevalent in assessing delay times; however, their limitations have prompted the exploration of novel technologies like LiDAR (Light Detection and Ranging) sensors. This research study investigates and compares the accuracy of delay time estimations obtained from LiDAR sensor technology with those derived from microsimulation in AIMSUN. LiDAR sensors, known for their high-resolution, real-time data collection capabilities, offer a promising avenue for precise measurement of delay times at signalized intersections. Nonetheless, challenges in sensor placement, environmental influences, and data processing complexities suggest the need for further development and validation. In parallel, microsimulation software, exemplified by AIMSUN, provides a virtual platform for scenario testing but relies on assumptions that may not always mirror real-world traffic dynamics accurately. The comparative analysis conducted in this study aims to critically examine the discrepancies and potential complementarity between delay times obtained from LiDAR sensor technology and those derived from microsimulation in AIMSUN. The research involves an in-depth evaluation of real-time, high-resolution data collected by LiDAR sensors, assessing their accuracy in capturing the intricate movements and behavior of vehicles at signalized intersections. Simultaneously, AIMSUN microsimulation delay time models are scrutinized for their ability to accurately replicate these observed delay times. The disparities identified serve as critical insights into the challenges of both methodologies, prompting the discussion on the prospects of integrating LiDAR-derived data and microsimulation calibration processes to enhance the precision and reliability of delay time estimations. Future traffic management strategies can significantly benefit from a more accurate understanding of delay times, and this study endeavors to contribute to the advancement of methodologies in traffic engineering for more effective urban transportation systems.The paper's findings illuminate the potential and limitations of both LiDAR sensor technology and microsimulation in estimating delay times at signalized intersections. The results highlighted that the LiDAR sensors could accurately calculate delay times at a signalized intersection. Furthermore, the calculated delay time differences by LiDAR and AIMSUN at three days with the highest vehicle volumes (counts) are always less than 6.5%.

This study investigates the application of Light Detection and Ranging (LiDAR) sensor technology for data collection at signalized intersections characterized by a high rate of traffic crashes. The research aims to provide valuable insights into the potential of LiDAR-based data analysis to enhance road safety and traffic management at signalized intersections. The research methodology involved the deployment of LiDAR sensors at Marlboro Pike & Brooks Dr. signalized intersection in Coral Hills, Maryland. Two LiDAR sensors installed in this intersection to collect high-resolution, three-dimensional data of the intersection area from June, 1^st to July, 7^th 2023. The data included information on vehicle trajectories, speeds, and behaviors, as well as pedestrian and cyclist movement patterns. Concurrently, historical traffic crashes recorded and traffic flow data were obtained for the same intersection.The analysis of LiDAR data involved several key aspects including LiDAR data allowed for a precise evaluation of traffic flow patterns, including congestion points, traffic volume fluctuations, and peak-hour behavior. This information provided insights into potential factors contributing to crashes. By analyzing LiDAR data, the study identified near-miss incidents, which are often precursors to actual crashes. This proactive approach could assist in identifying crash-prone areas within the intersection. The LiDAR data analysis also focused on pedestrian and cyclist movements, including jaywalking and bike lane usage. The aim was to identify areas where infrastructure improvements could enhance safety for vulnerable road users. LiDAR data was compared with historical crash data to identify specific locations within the intersection that exhibited a high frequency of crashes. This information can guide targeted safety interventions. Last but not least, the study explored opportunities to optimize traffic signal timings based on real-time traffic data from LiDAR. Adaptive signal control could help mitigate congestion and reduce the risk of crashes.The results of this study demonstrated the potential of LiDAR sensor technology in collecting detailed data for traffic analysis in signalized intersections. By combining LiDAR data with historical crash records and traffic flow data, traffic engineers and urban planners can develop evidence-based strategies to reduce the frequency and severity of crashes in high-risk areas. Ultimately, this research contributes to a comprehensive understanding of how LiDAR technology can be employed to enhance road safety and traffic management, providing valuable insights for traffic engineers, urban planners, and policymakers seeking to improve the safety and efficiency of signalized intersections with a history of high traffic crashes.

In this work, we propose a generalized partially functional linear model, which not only models the relationship between multiple scalar and functional predictors and response, but also automatically estimates the link function. Specifically, we use the functional principal component analysis method to reduce the dimensionality of functional predictors, estimate the regression coefficients using the maximum likelihood estimation method, estimate the link function using the method of local linear regression, iteratively obtain the final estimator, and prove the asymptotic normality of the estimator. The asymptotic normality is illustrated through simulation experiments. Finally, the proposed model is applied to study the influence of environmental, economic, and medical levels on life expectancy in China. In the study functional predictors are the daily air quality index, temperature, and humidity of 58 cities in 2020 and scalar predictors are GDP and number of beds in hospitals.

This study leverages transformer-based models and focuses on data representation strategies in the named entity recognition task, including "single" (one sentence per vector), "merged" (multiple sentences per vector), and "context" (sentences joined with attention to context). Performance analysis reveals that models trained with a single strategy may not perform well on different data representations. A combined training procedure is proposed to address this limitation, using all three strategies to enhance the stability and adaptability of the model. The results of this approach are presented and discussed for various datasets for four languages (English, Polish, Czech, and German), demonstrating the effectiveness of the combined strategy.

Immersive Unit Visualization is an emergent form of visualization that arose from Immersive Analytics where, unlike traditional visualizations, each data point is represented by an individual visual mark in an immersive virtual environment. This practice has focused almost exclusively on virtual reality, excluding augmented reality (AR). This article develops and tests a prototype of an immersive Unit Visualization (Floating Companies II) with two AR devices: head-mounted display (HMD) and hand-held display (HHD). Results from the testing sessions with 20 users were analyzed through qualitative research analysis and thematic coding indicating that, while the HHD enabled a first contact with AR visualization on a familiar device, HMD improved the perception of hybrid space by supporting greater stability of virtual content; wider field of view; improved spatial perception; increased sense of immersion; and more realistic simulation, which impacted on information reading and sense-making. The materialization of abstract quantitative values into concrete reality through its simulation in the real environment and the ludic dimension stand out as important opportunities of this type of visualization. This paper investigates the aspects distinguishing two experiences regarding data visualization in hybrid space; and characterizes ways of seeing information with AR, identifying opportunities to advance information design research.

In recent years, groups of cyber criminals/hackers have carried out cyber-attacks using various tactics with the goal of destabilizing web services in a specific context for which they are motivated. Predicting these attacks is a critical task that assists in determining what actions should be taken to mitigate the effects of such attacks and to prevent them in the future. Although there are programs to detect security concerns on the internet, there is currently no system that can anticipate or foretell whether the attacks will be successful. This research aims to develop sustain-able strategies to reduce threats, vulnerability, and data manipulation of chatbots, consequently improving cyber security. To achieve this goal, we develop a conversational chatbot, an application that uses artificial intelligence (AI) to communicate, and deploy it on social media sites (e.g., Twitter) for cyber security purposes. Chatbots have the capacity to consume large amounts of information and give an appropriate response in an efficient and timely manner, thus rendering them useful in predicting threats emanating from social media. The research utilizes sentiment analysis strategy by employing chatbots on Twitter (and analyzing Twitter data) for predicting future threats and cyber-attacks. The strategy is based on a daily collection of tweets from two types of users: those who use the platform to voice their opinions on important and relevant subjects, and those who use it to share information on cyber security attacks. The research pro-vides tools and strategies for developing chatbots that can be used for assessing cyber threats on social media through sentiment analysis leading to a global sustainable development of businesses. Future research may utilize and improvise on the tools and strategies suggested in our research to strengthen the knowledge domain of chatbots, cyber security, and social media.

Species richness is a widely used measure for assessing the diversity of a particular area. However, observed richness often underestimates the true richness due to resource limitations, particularly in the small-sized sample or highly heterogeneous assemblage. Estimating species richness in a large-scale region typically involves an integrated data set consisting of subsamples collected independently from different subregions. However, the pooled sample of integrated data is no longer a random sample from the entire region, and the use of different sampling schemes results in variations in data formats. Consequently, employing a single sampling distribution to model the pooled sample becomes impractical, rendering existing richness estimators inadequate. This study theoretically explains the applicability of Chao's lower bound estimators in estimating species richness for large-scale areas using the pooled sample. Additionally, a new nonparametric estimator is introduced, which adjusts the bias of Chao's lower bound estimator by leveraging the Good-Turing frequency formula. This proposed estimator only utilizes the pooled sample's singleton, doubleton, and tripleton richness. Simulated data sets across various models are employed to demonstrate the statistical performance of the estimator, showcasing its ability to reduce bias and provide accurate 95% confidence intervals. Real data sets are also utilized to illustrate the practical application of the proposed approach.

Personalized recommendation is an important part of ecommerce platform. In the recommendation system, the neural network is used to enhance collaborative filtering to accurately capture user preferences, so as to obtain better recommendation performance. Traditional recommendation methods focused on the results of a single user behavior, ignoring the modeling of multiple interactive behaviors of users, such as click, add to cart and purchase. Although many studies had also focused on Multi-Behavior modeling, two important challenges remained. 1)Since multiple behavioral context information was ignored, it was still a challenge to identify the multimodal relationships of behaviors. 2) Surveillance signals were still sparse. In order to solve this problem, this paper proposes Two-path Multi-behavior Sequence Modeling(TP_MB). First, a two-path learning strategy is introduced to maximize the multiple interaction information of user items learned by the two paths, which effectively enhances the robustness of the model. Second, a multi-behavior dependent encoder is designed. Contextual information is obtained through behavior dependencies in the interaction of different user. In addition, three contrastive learning methods are designed, which not only obtain additional auxiliary supervision signals, but also alleviate the problem of sparse supervision signals. Extensive experiments on two real datasets demonstrate that our method outperforms state-of-the-art multi-behavior recommendation methods.

Different toll collection types of vehicles and different distribution of tollbooths lead to the toll plaza diverging area becoming a typical vehicle weaving area with frequent crossing behaviors and conflicts on highways. This study aims to identify contributing factors to conflict risks of four vehicle-following patterns in a toll plaza diverging area by developing random parameters ordered logit models with heterogeneity in means and variances. The model can flexibly capture the unobserved heterogeneity of the contributing factors in different vehicle-following patterns. Real-world vehicle trajectory data obtained from the toll plaza diverging area in Nanjing, China, are used for model estimation. The results show that vehicle-following patterns with the same toll collection types have higher percentage of severe conflict risks. The average acceleration of the following vehicles, lane marking indicator, the initial lanes and lane-changes of vehicles are significantly associated with the collision risk levels. The standard deviation of surrogate safety measures of all vehicles in sub-segments are found differ significantly between vehicle-following patterns. Furthermore, a series of likelihood ratio tests are adopted to test the spatial dependence in sub-segments of the diverging area. The findings of this study could provide valuable information for safety improvement in toll plazas.