Search

Expanding traditional video metadata and recommendation systems encompasses challenges that are difficult to address with conventional methodologies. Limitations in utilizing diverse information when extracting video metadata, along with persistent issues like bias, cold start problems, and the filter bubble effect in recommendation systems, are primary causes of performance degradation. Therefore, a new recommendation system that integrates high-quality video metadata extraction with existing recommendation systems is necessary. This research proposes the “Extraction of Meta-Data for Recommendation using keyword mapping,” which involves constructing contextualized data through object detection models and STT (Speech-to-Text) models, extracting keywords, mapping with the public dataset MovieLens, and applying a Hybrid recommendation system. The process of building contextualized data utilizes YOLO and Google’s Speech-to-Text API. Following this, keywords are extracted using the TextRank algorithm and mapped to the MovieLens dataset. Finally, it is applied to a Hybrid Recommendation System. This paper validates the superiority of this approach by comparing it with the performance of the MovieLens recommendation system that does not expand metadata. Additionally, the effectiveness of metadata expansion is demonstrated through performance comparisons with existing deep learning-based keyword extraction models. Ultimately, this research resolves the cold start and long-tail problems of existing recommendation systems through the construction of video metadata and keyword extraction.

The increase in the use of smart devices has led to the realization of the Internet of Everything (IoE). The heart of an IoE environment is a Context-Aware System that facilitates service discovery, delivery, and adaptation based on context classification. The context has been defined in a domain-dependent way, traditionally. The classical models of context have been focused on rich context and lack Cost of Context (CoC) that can be used for decision support. The authors present a philosophy-inspired mathematical model of context that includes confidence in activity classification of context, the actions performed, and the power information. Since a single recurring activity can lead to distinct actions performed at different times, it is better to record the actions. The power information includes the power consumed in the complete context processing and is a quality attribute of the context. Power consumption is a useful metric as CoC and is suitable for power-constrained context awareness. To demonstrate the effectiveness of the proposed work, example contexts are described, and the context model is presented mathematically in this study. The context is aggregated with power information, and actions and confidence on the classification outcome lead to the concept of situational context. The results show that the context gathered through sensor data and deduced through remote services can be made more rich with CoC parameters.

Predicting trajectories and destinations is of considerable relevance in the context of urban mobility, as it can be useful for suggesting detours, avoiding congestion, and optimizing people's commutes. Therefore, this research performs a classification and analysis of trajectory and destination prediction models in articles published from 2017 to 2023. These models were mapped considering: authors; the existence of more than one geographic scenario; the type of forecast; the use of semantic and contextual data; and description of the algorithms. The result consists of discussions of representative works, based on classification, with grouping of techniques. Furthermore, there is a focus on works that used contextual and/or semantic data, from which another framework was developed, specifying the titles of the articles, and whether the methodology involved the use of points or areas of interest, and a reference to how they were generated. This focus expands the previous framework, specifying the differences of a portion of published studies. [ABSTRACT FROM AUTHOR]

Copyright of Lexikos is the property of Bureau of the Woordeboek van die Afrikaanse Taal and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Risk analysis in motor insurance aims to identify factors that increase the frequency of accidents. Telematics data is used to measure behavioural information of drivers. Contextual variables include temperature, rain, wind and traffic conditions that are external to the driver, but may also influence the probability of having an accident, as well as vehicle and personal characteristics. This paper uses a monthly panel data structure and the Poisson model to predict the expected frequency of claims over time. Some meteorological information is included. Two types of claims are considered separately: only those related to at-fault third-party liability accidents, and all types of claims including assistance on the road. A sample of drivers in Spain in 2018–2019 is analysed with information on claiming frequency per month. Drivers were observed for seven months. Our analysis is novel because monthly summaries of telematics information are combined with weather data in a panel structure, revealing that external factors affect the expected claims frequencies. Reckless speeding behaviours and intense urban circulation increase the risk of an accident, which also increases with windy conditions. [ABSTRACT FROM AUTHOR]

Event logs that are recorded by information systems provide a valuable starting point for the analysis of processes in various domains, reaching from healthcare, through logistics, to e-commerce. Specifically, behavioral patterns discovered from an event log enable operational insights, even in scenarios where process execution is rather unstructured and shows a large degree of variability. While such behavioral patterns capture frequently recurring episodes of a process’ behavior, they are not limited to sequential behavior but include notions of concurrency and exclusive choices. Existing algorithms to discover behavioral patterns are context-agnostic, though. They neglect the context in which patterns are observed, which severely limits the granularity at which behavioral regularities are identified. In this paper, we therefore present an approach to discover contextual behavioral patterns. Contextual patterns may be frequent solely in a certain partition of the event log, which enables fine-granular insights into the aspects that influence the conduct of a process. Moreover, we show how to analyze the discovered contextual behavioral patterns in terms of causal relations between context information and the patterns, as well as correlations between the patterns themselves. A complete analysis methodology leveraging all the tools presented in the paper and supplemented by interpretations guidelines is also provided. Finally, experiments with real-world event logs demonstrate the effectiveness of our techniques in obtaining fine-granular process insights. [ABSTRACT FROM AUTHOR]

The Health and Retirement Study is an amazing resource for those studying aging in the United States, and a fantastic model for other countries who have created similar longitudinal studies. The raw amount of information, from data on income, wealth, and use of health services to employment, retirement, and family connections on to the collection of clinical biomarkers can be both empowering and overwhelming to a researcher. Luckily through the process of engagement with the research community and constant improvement, these reams of data are not only consistently growing in a thoughtful and focused direction, they are also explained and summarized to increase the ease of use for all. One of the very useful areas of the HRS is the Contextual Data File (CDF), which is the focus of this review. The CDF provides access to easy-to-use helpful community-level data in a secure environment that has allowed researchers to answer questions that would have otherwise been difficult or impossible to tackle. The current CDF includes data in six categories (University of Michigan Institute for Social Research. 2017. HRS Data Book: The Health and Retirement Study: Aging in the 21st Century, Challenges and Opportunities for Americans. Ann Arbor: University of Michigan. Also available at https://hrs.isr.umich.edu/about/data-book, 17): 1. Socio-economic Status and Demographic Structure 2. Psychosocial Stressors 3. Health Care 4. Physical Hazards 5. Amenities 6. Land Use and the Built Environment. Each of these areas have allowed researchers to answer interesting questions such as what is the impact of air pollution on cognition in older adults (Ailshire, J., and K. M. Walsemann. 2021. "Education Differences in the Adverse Impact of PM 2.5 on Incident Cognitive Impairment Among U.S. Older Adults." Journal of Alzheimer's Disease 79 (2): 615–25), the impact of neighborhood characteristics on obesity in older adults (Grafova, I. B., V. A. Freedman, R. Kumar, and J. Rogowski. 2008. "Neighborhoods and Obesity in Later Life." American Journal of Public Health 98: 2065–71), or even what do we gain from introducing contextual data to a survey analysis (Wilkinson, L. R., K. F. Ferraro, and B. R. Kemp. 2017. "Contextualization of Survey Data: What Do We Gain and Does it Matter?" Research in Human Development 14 (3): 234–52)? My review focuses on the potential to expand contextual data in a few of these areas. From new data sets developed and released by the U.S. Census Bureau, to improved measurements of climate and environmental risk, there are numerous new data sources that would be a boon to the research community if they were joined together with the HRS. The following section begins by breaking down the opportunity provided by community or place-based data before moving on to specific recommendations for new data that could be included in the HRS contextual data file. [ABSTRACT FROM AUTHOR]

Hypotension frequently occurs in intensive care units (ICUs) and is correlated to worsening patient outcomes. In this study, we propose a machine learning (ML) algorithm that predicts hypotensive events in ICUs by extracting the information from patients' contextual data and physiological signals. The algorithm uses patients’ history including demographics, pre-ICU medication, and pre-existing comorbidities, and only five minutes of prior physiological history to predict hypotension up to 30 min in advance. We show that adding demographic information to the physiological data does not improve the algorithm's predictive performance of 84% sensitivity, 89% positive predictive value (PPV), and 98% specificity. Furthermore, the results show that including features extracted from patients’ pre-ICU medications and comorbidities lowers the learning algorithm’ prediction performance and leads to 2% degradation in its F1-score. The feature importance analysis showed that the ratio of MAP to HR (MAP2HR) and the average of RR intervals on the ECG (RRI), both extracted from physiological signals, have the highest weights in the prediction of hypotension.

The e-learning environment should support the handwriting of mathematical expressions and accurately recognize inputted handwritten mathematical expressions. To this end, expression-related information should be fully utilized in e-learning environments. However, pre-existing handwritten mathematical expression recognition models mainly utilize the shape of handwritten mathematical symbols, thus limiting the models from improving the recognition accuracy of a vaguely represented symbol. Therefore, in this paper, a context-aided correction (CAC) model is proposed that adjusts an output of handwritten mathematical symbol (HMS) recognition by additionally utilizing information related to the HMS in an e-learning system. The CAC model collects learning contextual data associated with the HMS and converts them into learning contextual information. Next, contextual information is recognized through artificial intelligence to adjust the recognition output of the HMS. Finally, the CAC model is trained and tested using a dataset similar to that of a real learning situation. The experiment results show that the recognition accuracy of handwritten mathematical symbols is improved when using the CAC model. [ABSTRACT FROM AUTHOR]

COVID-19 was declared to be a pandemic in March 2020 by the World Health Organization. Timely sharing of viral genomic sequencing data accompanied by a minimal set of contextual data is essential for informing regional, national, and international public health responses. Such contextual data is also necessary for developing, and improving clinical therapies and vaccines, and enhancing the scientific community's understanding of the SARS-CoV-2 virus. The Canadian COVID-19 Genomics Network (CanCOGeN) was launched in April 2020 to coordinate and upscale existing genomics-based COVID-19 research and surveillance efforts. CanCOGeN is performing large-scale sequencing of both the genomes of SARS-CoV-2 virus samples (VirusSeq) and affected Canadians (HostSeq). This paper addresses the privacy concerns associated with sharing the viral sequence data with a pre-defined set of contextual data describing the sample source and case attribute of the sequence data in the Canadian context. Currently, the viral genome sequences are shared by provincial public health laboratories and their healthcare and academic partners, with the Canadian National Microbiology Laboratory and with publicly accessible databases. However, data sharing delays and the provision of incomplete contextual data often occur because publicly releasing such data triggers privacy and data governance concerns. The CanCOGeN Ethics and Governance Expert Working Group thus has investigated several privacy issues cited by CanCOGeN data providers/stewards. This paper addresses these privacy concerns and offers insights primarily in the Canadian context, although similar privacy considerations also exist in other jurisdictions. We maintain that sharing viral sequencing data and its limited associated contextual data in the public domain generally does not pose insurmountable privacy challenges. However, privacy risks associated with reidentification should be actively monitored due to advancements in reidentification methods and the evolving pandemic landscape. We also argue that during a global health emergency such as COVID-19, privacy should not be used as a blanket measure to prevent such genomic data sharing due to the significant benefits it provides towards public health responses and ongoing research activities. [ABSTRACT FROM AUTHOR]

Modern cloud-based data infrastructures open new vistas for the deployment of scientometric data into the hands of practitioners. These infrastructures lower barriers to entry by making data more available and compute capacity more affordable. In addition, if data are prepared appropriately, with unique identifiers, it is possible to connect many different types of data. Bringing broader world data into the hands of practitioners (policymakers, strategists, and others) who use scientometrics as a tool can extend their capabilities. These ideas are explored through connecting Dimensions and World Bank data on Google BigQuery to study international collaboration between countries of different economic classification.

COVID-19 was declared to be a pandemic in March 2020 by the World Health Organization. Timely sharing of viral genomic sequencing data accompanied by a minimal set of contextual data is essential for informing regional, national, and international public health responses. Such contextual data is also necessary for developing, and improving clinical therapies and vaccines, and enhancing the scientific community’s understanding of the SARS-CoV-2 virus. The Canadian COVID-19 Genomics Network (CanCOGeN) was launched in April 2020 to coordinate and upscale existing genomics-based COVID-19 research and surveillance efforts. CanCOGeN is performing large-scale sequencing of both the genomes of SARS-CoV-2 virus samples (VirusSeq) and affected Canadians (HostSeq). This paper addresses the privacy concerns associated with sharing the viral sequence data with a pre-defined set of contextual data describing the sample source and case attribute of the sequence data in the Canadian context. Currently, the viral genome sequences are shared by provincial public health laboratories and their healthcare and academic partners, with the Canadian National Microbiology Laboratory and with publicly accessible databases. However, data sharing delays and the provision of incomplete contextual data often occur because publicly releasing such data triggers privacy and data governance concerns. The CanCOGeN Ethics and Governance Expert Working Group thus has investigated several privacy issues cited by CanCOGeN data providers/stewards. This paper addresses these privacy concerns and offers insights primarily in the Canadian context, although similar privacy considerations also exist in other jurisdictions. We maintain that sharing viral sequencing data and its limited associated contextual data in the public domain generally does not pose insurmountable privacy challenges. However, privacy risks associated with reidentification should be actively monitored due to advancements in reidentification methods and the evolving pandemic landscape. We also argue that during a global health emergency such as COVID-19, privacy should not be used as a blanket measure to prevent such genomic data sharing due to the significant benefits it provides towards public health responses and ongoing research activities.

Risk analysis in motor insurance aims to identify factors that increase the frequency of accidents. Telematics data is used to measure behavioural information of drivers. Contextual variables include temperature, rain, wind and traffic conditions that are external to the driver, but may also influence the probability of having an accident, as well as vehicle and personal characteristics. This paper uses a monthly panel data structure and the Poisson model to predict the expected frequency of claims over time. Some meteorological information is included. Two types of claims are considered separately: only those related to at-fault third-party liability accidents, and all types of claims including assistance on the road. A sample of drivers in Spain in 2018–2019 is analysed with information on claiming frequency per month. Drivers were observed for seven months. Our analysis is novel because monthly summaries of telematics information are combined with weather data in a panel structure, revealing that external factors affect the expected claims frequencies. Reckless speeding behaviours and intense urban circulation increase the risk of an accident, which also increases with windy conditions.

Knowledge extraction, data mining, e-learning or web applications platforms use heterogeneous and distributed data. The proliferation of these multifaceted platforms faces many challenges such as high scalability, the coexistence of complex similarity metrics, and the requirement of data quality evaluation. In this study, an extended complete formal taxonomy and some algorithms that utilize in achieving the detection and correction of contextual data quality anomalies were developed and implemented on structured data. Our methods were effective in detecting and correcting more data anomalies than existing taxonomy techniques, and also highlighted the demerit of Support Vector Machine (SVM). These proposed techniques, therefore, will be of relevance in detection and correction of errors in large contextual data (Big data). [ABSTRACT FROM AUTHOR]

As public health laboratories expand their genomic sequencing and bioinformatics capacity for the surveillance of different pathogens, labs must carry out robust validation, training, and optimization of wet- and dry-lab procedures. Achieving these goals for algorithms, pipelines and instruments often requires that lower quality datasets be made available for analysis and comparison alongside those of higher quality. This range of data quality in reference sets can complicate the sharing of sub-optimal datasets that are vital for the community and for the reproducibility of assays. Sharing of useful, but sub-optimal datasets requires careful annotation and documentation of known issues to enable appropriate interpretation, avoid being mistaken for better quality information, and for these data (and their derivatives) to be easily identifiable in repositories. Unfortunately, there are currently no standardized attributes or mechanisms for tagging poor-quality datasets, or datasets generated for a specific purpose, to maximize their utility, searchability, accessibility and reuse. The Public Health Alliance for Genomic Epidemiology (PHA4GE) is an international community of scientists from public health, industry and academia focused on improving the reproducibility, interoperability, portability, and openness of public health bioinformatic software, skills, tools and data. To address the challenges of sharing lower quality datasets, PHA4GE has developed a set of standardized contextual data tags, namely fields and terms, that can be included in public repository submissions as a means of flagging pathogen sequence data with known quality issues, increasing their discoverability. The contextual data tags were developed through consultations with the community including input from the International Nucleotide Sequence Data Collaboration (INSDC), and have been standardized using ontologies - community-based resources for defining the tag properties and the relationships between them. The standardized tags are agnostic to the organism and the sequencing technique used and thus can be applied to data generated from any pathogen using an array of sequencing techniques. The tags can also be applied to synthetic (lab created) data. The list of standardized tags is maintained by PHA4GE and can be found at https://github.com/pha4ge/contextual_data_QC_tags. Definitions, ontology IDs, examples of use, as well as a JSON representation, are provided. The PHA4GE QC tags were tested, and are now implemented, by the FDA's GenomeTrakr laboratory network as part of its routine submission process for SARS-CoV-2 wastewater surveillance. We hope that these simple, standardized tags will help improve communication regarding quality control in public repositories, in addition to making datasets of variable quality more easily identifiable. Suggestions for additional tags can be submitted to PHA4GE via the New Term Request Form in the GitHub repository. By providing a mechanism for feedback and suggestions, we also expect that the tags will evolve with the needs of the community.

Abstract Background The need for a better understanding of food consumption behaviour within its behavioural context has sparked the interest of nutrition researchers for user-documented food consumption data collected outside the research context using publicly available nutrition apps. The study aims to characterize the scientific, technical, legal and ethical features of this data in order to identify the opportunities and challenges associated with using this data for nutrition research. Method A search for apps collecting food consumption data was conducted in October 2016 against UK Google Play and iTunes storefronts. 176 apps were selected based on user ratings and English language support. Publicly available information from the app stores and app-related websites was investigated and relevant data extracted and summarized. Our focus was on characteristics related to scientific relevance, data management and legal and ethical governance of user-documented food consumption data. Results Food diaries are the most common form of data collection, allowing for multiple inputs including generic food items, packaged products, or images. Standards and procedures for compiling food databases used for estimating energy and nutrient intakes remain largely undisclosed. Food consumption data is interlinked with various types of contextual data related to behavioural motivation, physical activity, health, and fitness. While exchange of data between apps is common practise, the majority of apps lack technical documentation regarding data export. There is a similar lack of documentation regarding the implemented terms of use and privacy policies. While users are usually the owners of their data, vendors are granted irrevocable and royalty free licenses to commercially exploit the data. Conclusion Due to its magnitude, diversity, and interconnectedness, user-documented food consumption data offers promising opportunities for a better understanding of habitual food consumption behaviour and its determinants. Non-standardized or non-documented food data compilation procedures, data exchange protocols and formats, terms of use and privacy statements, however, limit possibilities to integrate, process and share user-documented food consumption data. An ongoing research effort is required, to keep pace with the technical advancements of food consumption apps, their evolving data networks and the legal and ethical regulations related to protecting app users and their personal data.

Higher Education Institutions in England are an integral part of the government's social mobility strategy. Contextualisation of undergraduate admissions decisions has emerged as a key tool towards progressing social mobility objectives. The present paper builds on our previous 2013 research by describing findings from 15 qualitative interviews with stakeholders in contextualised admissions. Stakeholders were drawn from government, non-governmental and third sector bodies including those representing the voice of schools and young people. We find that data challenges continue to be a main barrier to the application of contextual admissions. Respondents thought that more consistency and transparency between universities would be helpful to assist applicants and those who support them to better understand contextual data use in undergraduate admissions. Views are divided about whether differential admissions offers represent the most important application of contextual data. Respondents saw potential for using contextual data beyond admissions for supporting students at university and into further study or employment. [ABSTRACT FROM AUTHOR]

Stress is a major concern in daily life, as it imposes significant and growing health and economic costs on society every year. Stress and driving are a dangerous combination and can lead to life-threatening situations, evidenced by the large number of road traffic crashes that occur every year due to driver stress. In addition, the rate of general health issues caused by work-related chronic stress in drivers who work in public and private transport is greater than in many other occupational groups. An in-vehicle warning system for driver stress levels is needed to continuously predict dangerous driving situations and proactively alert drivers to ensure safe and comfortable driving. As a result of the recent developments in ambient intelligence, such as sensing technologies, pervasive devices, context recognition, and communications, driver stress can be automatically detected using multimodal measurements. This critical review investigates the state of the art of techniques and achievements for automatic driver stress level detection based on multimodal sensors and data. In this work, the most widely used data followed by frequent and highly performed selected features to detect driver stress levels are analyzed and presented. This review also discusses key methodological issues and gaps that hinder the implementation of driver stress detection systems and offers insights into future research directions. [ABSTRACT FROM AUTHOR]

Highlights • A solution of context integration for a process with data production variability is proposed. • The solution focuses on context integration by either substitution or enhancement. • Both integrations are based on an extension of the model driven architecture approach. • Substitution or enhancement rules conforming to this extended approach are specified. • Modelling and rules coding of both integration cases show automatization feasibility. Abstract Existent process models can hardly cope with the emerging issue of modelling exponential variable data volumes in systems' workflow, from specifications to operation. Given the strong relation between data context and data variability, this paper considers the automated integration of contextual models for processes with data variability. The proposed approach extends methodologically a platform independent model process, using a contextual data model, to obtain automatically the corresponding platform specific model. Contextual data are thus integrated to a process as a model, within a process. Two particular cases of contextual data models are studied in detail: substitution, when the contextual data model defines generated code, and enhancement, when learned data descriptions constitute the contextual data model. The feasibility and value of integrating a contextual model into a process to handle data variability are shown in detail describing these two use cases. Contextual model integration by substitution to include automatically variable ready to use application services to generate code, and contextual model integration by enhancement applied to supervised image classification based on variable descriptors. Results show that relating data variability and its context by means of automated integration of a designed system component model, simplifies variable data processing of system process models. [ABSTRACT FROM AUTHOR]

The paper suggests an approach to assessing performance of educational institutions with regard to their social specifics. To develop this approach, the authors relied upon 1) results of numerous studies proving correlations between student performance and contextual factors (both in Russia and abroad); 2) foreign colleagues’ experience of solving similar problems; and 3) the idea of providing minimum required information to enable such assessments in contemporary Russia. The fundamental idea lying behind the proposed assessment tool is that, having necessary data at hand, one can identify empirically stable correlations between student performance and contextual factors (e. g. different social composition of students). In research practice, these correlations were revealed through multiple regression analysis. Results of such analysis—established empirical correlations—may then be used to “discount” formal progress, i. e. to have justifiably higher expectations about institutions in more favorable contexts and lower expectations about those in less favorable situations. The authors think over two ways of using this information: based either on a formula or on a specific index (the ndex of school social well-being) they have elaborated. They also draw attention towards possible constraints associated with using these tools and touch upon a more global problem of considering contextual factors in assessing the quality of education in Russia.