Utility Of Data Research Articles

Data-Driven Decision-Making in Health Security Management: Challenges and Opportunities

The incorporation of data-driven decision-making into health security management has altered the method of recognizing, avoiding, and responding to health risks. This study investigates the influence of data-driven tactics on the efficacy of health-care security measures, demonstrating substantial advantages such as faster detection and reaction times. However, it also notes significant hurdles, such as assuring data is accurate and reliable, safeguarding patient privacy, and establishing appropriate technology and training. Ethical factors, such as data security and the possibility of misuse, are crucial to sustaining public confidence. The study indicates that, while data-driven decision-making has many benefits, addressing these difficulties through strong data governance frameworks and constant review is critical for optimizing health security management. Recommendations include improving data security standards and establishing a technology to enable successful data utilization.

Have China’s internal migrants been more settled since 2010? A contribution based on migrants’ age profiles

ABSTRACT This Research Note employs age data to assess whether China’s internal migrants have become more settled since 2010. The aim is to answer the crucial question of whether recent hukou reform initiatives have achieved their goals of improving migrant settlement. We extend a method from existing research that examines two key aspects of settlement – family togetherness and long-term stay of migrants – through analyzing age profiles of migrant stock. Specifically, by scrutinizing age data from the 2010 and 2020 censuses, we evaluate whether the child and elderly dependents of migrants are more engaged in migration and whether migrants growing old can better remain in the destinations. The results show that from 2010 to 2020, the age distribution of migrants became slightly more even across all age groups, yet it was still concentrated in young adults – the overall shape remained largely unchanged. This indicates a small improvement in settlement, which is unsatisfactory given the various hukou reform initiatives aimed at substantially increasing settlement opportunities in the last 10 years. Much greater efforts on hukou reform and support for migrants are needed. Furthermore, our research highlights the utility of age data in assessing the actual extent of migrant settlement, as opposed to the exclusive focus on settlement intentions, which are common in existing studies.

Model-aware privacy-preserving with start trigger method for person re-identification

Person Re-identification (ReID) could search for the same pedestrian from non-overlapping cameras, which completes the pedestrian location and search purpose. However, the process contains much sensitive pedestrian information and raises serious privacy problems. Conventional methods mainly remove identity-related features from pedestrian images to alleviate the privacy issue. Unfortunately, these strategies cause pedestrian information loss and poor data utility. In the paper, we propose a novel Model-Aware Privacy-Preserving with Start Trigger (MPST) method, which not only prevents personal identity for third parties but also achieves accurate pedestrian location for authorized organizations. The core idea is that authorized organizations obtain the start trigger to activate the ReID model that has the ability to search for target pedestrians, while third parties (i.e., hackers) cannot employ the ReID model to complete the pedestrian matching task without the start trigger. To this end, we develop a universal adversarial algorithm to learn an ingenious start trigger for the person ReID system. Afterwards, we further design a model-aware training strategy to facilitate our deep model to perceive issued instructions by synthetically utilizing the start trigger and original pedestrian samples. As a result, we successfully install an activate button to change the ReID model state for deciding whether the deep model has the ability to search for pedestrians or not. Abundant experiments demonstrate that the proposed MPST is effective for pedestrian identity anonymization. Our study achieves superior performance for authorized organizations and completes the privacy protection goal.

Digital Transformation Model of Population Administration Services for Regional Development through a Population Data Utilization System in Medan City

This research aims to examine the influence of digital transformation on population administration services and its implications for regional development in Medan City. Against the background of the need to increase the efficiency and effectiveness of public services, this research adopts a quantitative approach, using tools such as questionnaires, in-depth interviews and observations to collect data. Against the background of the need to increase the efficiency and effectiveness of public services, this research adopts a quantitative approach, using tools such as questionnaires, in-depth interviews and observations to collect data. The research results indicate that digitalization of population services makes a positive contribution to improving the quality of public services, which indirectly influences regional development through increasing efficiency, accessibility and transparency of services. And this research provides insight into e-government strategies in Medan, supporting the effective use of population data in supporting inclusive and sustainable regional development.

UMAP-SMOTENC: A simple, efficient, and consistent alternative for privacy-aware synthetic data generation

The intensification of governmental legislation and the social awareness around data privacy protection severely constrains organizations' data utilization capabilities. As a result, the interest in data anonymization techniques, which should preserve the patterns present in the original data but mitigate the risks of privacy leakage, has also increased. While conventional methods may compromise privacy, recently proposed deep learning generative approaches are computationally expensive and unreliable when used in tabular datasets, hindering the democratization and usability of data. In this paper, we explore this trade-off between privacy and the quality of the anonymized data, establishing a new equilibrium obtained using a synthetic oversampling technique, SMOTE-NC, on a non-linear compressed version of the input space, achieved with the application of UMAP. The introduced approach, UMAP-SMOTENC, constitutes an efficient and consistent solution that can be used without significant efforts on hyperparameter tuning or resourcing to massive computing infrastructures. An experiment was conducted to evaluate the robustness of the proposed solution, comparing several metrics and models across eight datasets with diverse characteristics. The results achieved suggest that the presented method can efficiently synthesize privacy-aware data while conserving the relevant patterns of the real dataset, particularly those required for classification tasks.

Synthetic and privacy-preserving traffic trace generation using generative AI models for training Network Intrusion Detection Systems

Network Intrusion Detection Systems (NIDS) are crucial tools for protecting networked devices from cyberattacks. Recent development in the field of Artificial Intelligence (AI) has provided tremendous advantages in implementing NIDSs able to monitor network traffic and block cyberattacks in real-time. In the literature, it is widely recognized that the effective training of a NIDS requires a large quantity of labeled traffic, representative of attacks. Nonetheless, the availability of public and abundant datasets remains remarkably restricted due to the cost of gathering and labeling real traffic traces and privacy concerns for sharing them. To tackle these challenges, in this paper we present a generative AI model capable of synthesizing anonymized traffic traces from real ones, thus dealing with privacy, abundance, and representativeness. The proposal is based on a Conditional Variational Autoencoder (CVAE) and a preprocessing procedure specifically designed for the generation of new traffic traces. To validate our solution, we conduct an extensive empirical study leveraging three recent and publicly-available datasets, containing benign and malicious traffic. The validation is carried out from both the perspectives of classification performance of a robust NIDS and the quality of synthetic data, in comparison to the utilization of real data. We compare our CVAE with two state-of-the-art AI-based traffic data generators and prove that, trained with traces emitted by our generative model, a NIDS has a limited F1-score loss compared to training on real data; competing models instead struggle or fail to generate traces that are as effective for NIDS training and as statistically similar to the original. We make the synthetic datasets available in both PCAP and tabular formats, to facilitate the reproducibility of our findings and encourage further exploration in the field of generative AI for networking.

Synthetic data for reef modelling

Synthetic data mimics the statistical properties of real-world datasets while removing reference to sensitive or confidential information in the original dataset (Quintana, 2020). Synthetic data is also useful for general model testing and development, with many methods available for generating data from machine learning models (Raghunathan, 2021). Although not widely used in the context of ecological and environmental modelling, synthetic data can support and accelerate model testing and analyses where rightsholders are sensitive to data disclosure for study areas, or data collection is expensive.In the context of reef modelling, synthetic data can be used to support model analyses that can be published without referring to specific sites, reefs, or study areas. This is desirable in the context of decision support for restoration of the Great Barrier Reef. The Reef has many stakeholders and release of early modelling results for intervention scenarios for specific areas would be premature until management or intervention strategy options have been discussed with stakeholders and/or rightsholders. Synthetic data allows a path to publish model and method demonstrations to share knowledge with the reef decision support community without prematurely suggesting policy recommendations for reefs which are sensitive to rightsholders or stakeholders.We showcase a synthetic data pipeline developed for the reef decision-support system ADRIA (Adaptive Dynamic Reef Intervention Algorithms), using methods from the Python package Synthetic Data Vault (Patki et al., 2016) and others. The synthetic data models are developed to emulate the statistics of case-study reefs for publishing decision-support tool demonstrations, testing and method validation without revealing sensitive reef site information. This pipeline includes developing models for tabular (benthic/compositional reef data), spatial-temporal (wave and heat stress data) and spatial network data (coral larval connectivity). Conditional sampling methods which connect spatial relationships across datasets are used to develop synthetic reef data packages which mimic the statistical properties of the original dataset. The utility of the synthetic data is demonstrated on a sample reef data package, and methods used for anonymizing the data are detailed. The results are discussed in the context of formalizing synthetic data for reef modelling. All synthetic data code is available at ADRIA-synthetic-data/README.md at v0.1.0 · open-AIMS/ADRIA-synthetic-data (github.com), DOI: https://doi.org/10.5281/zenodo.10158323.

Utilization of Real-World Data in Drug Development

Utilization of Real-World Data in Drug Development

ID-SR: Privacy-Preserving Social Recommendation Based on Infinite Divisibility for Trustworthy AI

Recommendation systems powered by artificial intelligence (AI) are widely used to improve user experience. However, AI inevitably raises privacy leakage and other security issues due to the utilization of extensive user data. Addressing these challenges can protect users’ personal information, benefit service providers, and foster service ecosystems. Presently, numerous techniques based on differential privacy have been proposed to solve this problem. However, existing solutions encounter issues such as inadequate data utilization and a tenuous trade-off between privacy protection and recommendation effectiveness. To enhance recommendation accuracy and protect users’ private data, we propose ID-SR, a novel privacy-preserving social recommendation scheme for trustworthy AI based on the infinite divisibility of Laplace distribution. We first introduce a novel recommendation method adopted in ID-SR, which is established based on matrix factorization with a newly designed social regularization term for improving recommendation effectiveness. We then propose a differential privacy-preserving scheme tailored to the above method that leverages the Laplace distribution’s characteristics to safeguard user data. Theoretical analysis and experimentation evaluation on two publicly available datasets demonstrate that our scheme achieves a superior balance between privacy protection and recommendation effectiveness, ultimately delivering an enhanced user experience.

NNBGWO-BRCA marker: Neural Network and binary grey wolf optimization based Breast cancer biomarker discovery framework using multi-omics dataset

Background and ObjectiveBreast cancer is a multifaceted condition characterized by diverse features and a substantial mortality rate, underscoring the imperative for timely detection and intervention. The utilization of multi-omics data has gained significant traction in recent years to identify biomarkers and classify subtypes in breast cancer. This kind of research idea from part to whole will also be an inevitable trend in future life science research. Deep learning can integrate and analyze multi-omics data to predict cancer subtypes, which can further drive targeted therapies. However, there are few articles leveraging the nature of deep learning for feature selection. Therefore, this paper proposes a Neural Network and Binary grey Wolf Optimization based BReast CAncer bioMarker (NNBGWO-BRCAMarker) discovery framework using multi-omics data to obtain a series of biomarkers for precise classification of breast cancer subtypes. MethodsNNBGWO-BRCAMarker consists of two phases: in the first phase, relevant genes are selected using the weights obtained from a trained feedforward neural network; in the second phase, the binary grey wolf optimization algorithm is leveraged to further screen the selected genes, resulting in a set of potential breast cancer biomarkers. ResultsThe SVM classifier with RBF kernel achieved a classification accuracy of 0.9242 ± 0.03 when trained using the 80 biomarkers identified by NNBGWO-BRCAMarker, as evidenced by the experimental results. We conducted a comprehensive gene set analysis, prognostic analysis, and druggability analysis, unveiling 25 druggable genes, 16 enriched pathways strongly linked to specific subtypes of breast cancer, and 8 genes linked to prognostic outcomes. ConclusionsThe proposed framework successfully identified 80 biomarkers from the multi-omics data, enabling accurate classification of breast cancer subtypes. This discovery may offer novel insights for clinicians to pursue in further studies.

Mapping the Apps: Ethical and Legal Issues with Crowdsourced Smartphone Data using mHealth Applications

More than 5 billion people in the world own a smartphone. More than half of these have been used to collect and process health-related data. As such, the existing volume of potentially exploitable health data is unprecedentedly large and growing rapidly. Mobile health applications (apps) on smartphones are some of the worst offenders and are increasingly being used for gathering and exchanging significant amounts of personal health data from the public. This data is often utilized for health research purposes and for algorithm training. While there are advantages to utilizing this data for expanding health knowledge, there are associated risks for the users of these apps, such as privacy concerns and the protection of their data. Consequently, gaining a deeper comprehension of how apps collect and crowdsource data is crucial. To explore how apps are crowdsourcing data and to identify potential ethical, legal, and social issues (ELSI), we conducted an examination of the Apple App Store and the Google Play Store in North America and Europe to identify apps that could potentially gather health data through crowdsourcing. Subsequently, we analyzed their privacy policies, terms of use, and other related documentation to gain insights into the utilization of users’ data and the possibility of repurposing it for research or algorithm training purposes. More specifically, we reviewed privacy policies to identify clauses pertaining to the following key categories: research, data sharing, privacy/confidentiality, commercialization, and return of findings. Based on the results of these app search, we developed an App Atlas that presents apps which crowdsource data for research or algorithm training. We identified 46 apps available in the European and Canadian markets that either openly crowdsource health data for research or algorithm training or retain the legal or technical capability to do so. This app search showed an overall lack of consistency and transparency in privacy policies that poses challenges to user comprehensibility, trust, and informed consent. A significant proportion of applications presented contradictions or exhibited considerable ambiguity. For instance, the vast majority of privacy policies in the App Atlas contain ambiguous or contradictory language regarding the sharing of users’ data with third parties. This raises a number of ethico-legal concerns which will require further academic and policy attention to ensure a balance between protecting individual interests and maximizing the scientific utility of crowdsourced data. This article represents a key first step in better understanding these concerns and bringing attention to this important issue.

How to Elucidate Consent-Free Research Use of Medical Data: A Case for "Health Data Literacy".

The extensive utilization of personal health data is one of the key success factors of modern medical research. Obtaining consent to the use of such data during clinical care, however, bears the risk of low and unequal approval rates and risk of consequent methodological problems in the scientific use of the data. In view of these shortcomings, and of the proven willingness of people to contribute to medical research by sharing personal health data, the paradigm of informed consent needs to be reconsidered. The European General Data Protection Regulation gives the European member states considerable leeway with regard to permitting the research use of health data without consent. Following this approach would however require alternative offers of information that compensate for the lack of direct communication with experts during medical care. We therefore introduce the concept of "health data literacy," defined as the capacity to find, understand, and evaluate information about the risks and benefits of the research use of personal health data and to act accordingly. Specifically, health data literacy includes basic knowledge about the goals and methods of data-rich medical research and about the possibilities and limits of data protection. Although the responsibility for developing the necessary resources lies primarily with those directly involved in data-rich medical research, improving health data literacy should ultimately be of concern to everyone interested in the success of this type of research.

METB-09. VARIANT WORKBENCH IN THE KIDS FIRST PROGRAM FACILITATES GENOMIC DISCOVERIES IN PEDIATRIC NEURO-ONCOLOGY RESEARCH

Abstract The Gabriella Miller Kids First Pediatric Research Program (Kids First) aims at facilitating researchers to uncover new insights into the biology of childhood cancer and structural birth defects, including the discovery of shared genetic pathways between these disorders. Kids First Data Resource Center developed the Kids First Data Resource Portal (KFDRP), which is a centralized data platform for both Kids First and collaborative cohorts. Currently, KFDRP facilitates data access for 40 studies with over 35,500 participants. To assist researchers and clinicians in identifying potential disease-causing germline variants in the human genome, KFDRP released the Variant WorkBench (VWB), which facilitates variant querying, manipulation, analysis, and visualization. Cavatica is a widely used bioinformatics analysis platform developed by Velsera. Compared to a previous version, the Cavatica-based VWB has better support for data import/export, more convenient sharing of notebooks and data, and easier billing details, with the same level of scalable, cloud-based computing. Additionally, Cavatica-based VWB has incorporated multiple public reference databases, including Cancer Hotspots, ClinVar, COSMIC, dbNSFP, gnomAD, TOPMed, as well as gene-phenotype links provided by OMIM, HPO, Orphanet, and the Deciphering Developmental Disorders Project. These databases have been converted to parquet files, reducing process time and memory usage compared to regular text files, thus speeding up data retrieval and querying. Furthermore, Cavatica empowers users to create and share custom analysis workflows tailored to specific research questions and datasets, enhancing data utility and analysis accuracy. Here we present a gene-based variant filtering workflow that aggregates information from dbNSFP, HGMD, TOPMed, gnomAD, and ClinVar. We identified 1202 pathogenic/likely pathogenic variants in NF1, a gene that helps regulate cell growth, across 582 pediatric brain tumor samples within 6 mins. Among the variants, there are 21 protein-altering variants. Overall, the upgraded VWB is more powerful, user-friendly, and adaptable.

Spatial prioritization of dugong habitats in India can contribute towards achieving the 30 × 30 global biodiversity target

Indian coastal waters are critical for dugong populations in the western Indian Ocean. Systematic spatial planning of dugong habitats can help to achieve biodiversity conservation and area-based protection targets in the region. In this study, we employed environmental niche modelling to predict suitable dugong habitats and identify influencing factors along its entire distribution range in Indian waters. We examined data on fishing pressures collected through systematic interview surveys, citizen-science data, and field surveys to demarcate dugong habitats with varying risks. Seagrass presence was the primary factor in determining dugong habitat suitability across the study sites. Other variables such as depth, bathymetric slope, and Euclidean distance from the shore were significant factors, particularly in predicting seasonal suitability. Predicted suitable habitats showed a remarkable shift from pre-monsoon in Palk Bay to post-monsoon in the Gulf of Mannar, indicating the potential of seasonal dugong movement. The entire coastline along the Palk Bay-Gulf of Mannar region was observed to be at high to moderate risk, including the Gulf of Mannar Marine National Park, a high-risk area. The Andaman Islands exhibited high suitability during pre- and post-monsoon season, whereas the Nicobar Islands were highly suitable for monsoon season. Risk assessment of modelled suitable areas revealed that < 15% of high-risk areas across Andaman and Nicobar Islands and Palk Bay and Gulf of Mannar, Tamil Nadu, fall within the existing protected areas. A few offshore reef islands are identified under high-risk zones in the Gulf of Kutch, Gujarat. We highlight the utility of citizen science and secondary data in performing large-scale spatial ecological analysis. Overall, identifying synoptic scale ‘Critical Dugong Habitats’ has positive implications for the country's progress towards achieving the global 30 × 30 target through systematic conservation planning.

Seasonal variability of groundwater contributions to fault-zone-hosted banff hot springs, Canada

Analysisof fault-zone-hosted thermal springs provides insights into deep fault-zone processes and crustal-scale fluid movements. However, shallow groundwater mixing obscures chemical signatures associated with deeply sourced groundwater, reducing the utility of thermal spring data for understanding deep fault-zone processes. The Upper Hot Spring (UH) in the Banff Hot Spring system exhibits substantial seasonal variability and is a valuable case for investigating shallow groundwater mixing in fault zones. UH chemistry aligns with binary mixing of cold tritium-rich groundwater from Sulphur Mountain and hot tritium-depleted water from the Sulphur Mountain Thrust (SMT) fault zone. Geochemical and isotopic data from lower elevation springs suggest the extension of binary mixing dynamics to lower elevations. Applying a Monte Carlo-based regression approach, strontium isotope mass balance models simulate one year of 87Sr/86Sr time series at UH within the margin of uncertainty. Utilizing mixing proportions derived from the model, tritium mass balance models successfully simulate the tritium time series at UH over the same period, providing cross-validation. Using relationships between mixing proportions and sulfate, hydrographs for the three highest elevation springs are separated into two components, revealing that the seasonal variability of both components decreases northward as spring elevation decreases. Utilizing common environmental tracers and bypassing direct sampling of inaccessible endmembers, the modeling approach used here may find global applicability for characterizing mixing in fault zones.

A review of the contributions of forensic archaeology and anthropology to the process of disaster victim identification.

Forensic archaeology and anthropology have developed significantly over past decades and now provide considerable assistance to the investigation process of disaster victim recovery and identification. In what are often chaotic death and crime scenes, the formal process of utilizing archaeological methods can bring control, order, and ensure systematic search. Procedures assist in defining scene extent, locating victims and evidence, rule out areas for consideration, and provide standardized recording and quality assurance through dedicated use of standardized forms (pro formas). Combined archaeological and anthropological search methods maximize opportunities to recovery the missing through identifying remains, mapping distributions, and providing accounting of victims at the scene. Anthropological assistance in examinations contributes to individual assessment, resolving commingling and fragmentation issues, and utilizing DNA sampling methods and matching data to reassociate and account for the missing. Utilization of archaeology, anthropology, and DNA matching data provides scope to review crime scene recovery and determine requirements and potential for further survey and retrieval. Adopting the most suitable methods for a particular context can maximize recovery, efficiency, and resource use. Case studies demonstrate the utility of archaeological methods in a range of scenarios. They exemplify the success of multidisciplinary analysis in providing evidence of the sequence of events, the timing of events, the impact of taphonomic processes, the location and accounting of victims, and the demonstration of systematic scene search. The considerations provided in this article, utilizing archaeology and anthropology processes, may assist investigators in planning and implementing responses to mass fatalities.

Amplifying Big Data Utilization in Healthcare Analytics Through Cloud and Snowflake Migration

Amplifying the utilization of big data in healthcare analytics through cloud and Snowflake migration presents a significant opportunity to enhance data-driven insights and decision-making in the healthcare sector. This migration makes it easier to move large amounts of healthcare data to the cloud. Applications deployed in could are scalable for in-depth analysis in Health Care industry. The cloud is becoming more popular for storing data and running applications because it can easily grow with your needs, requires little to no management, improves security, and offers budget flexibility. The benefits of the cloud are obvious -- once you get there. Moving to the cloud requires planning, strategy, and the right tools for data migration. [1] By using Snowflake's advanced data warehousing tools, healthcare organizations can smoothly handle and analyze their complex and varied data. This helps them quickly uncover important insights and make better decisions. The shift to cloud technology and Snowflake has the potential to significantly enhance real-time analytics, personalized patient care, and evidence-based decision-making in healthcare. When healthcare organizations leverage big data in a cloud-based setting, they can discover valuable insights from their data, ultimately improving clinical outcomes, operational efficiency, and healthcare delivery. This study explores how the adoption of cloud and Snowflake in healthcare analytics can bring about transformative change and create new possibilities for leveraging data and generating insights in the healthcare sector.

EPH80 Outpatient Transfusions and Occurrence of Febrile Non-Hemolytic Transfusion Reactions Among U.S. Medicare Beneficiaries, Ages 65 and Older, During 2016-2022: Utility of Real-World Data

EPH80 Outpatient Transfusions and Occurrence of Febrile Non-Hemolytic Transfusion Reactions Among U.S. Medicare Beneficiaries, Ages 65 and Older, During 2016-2022: Utility of Real-World Data

A Review article of pharmacovigilance and studies of clinical research for health care

Pharmacovigilance, the science and activities related to the detection, assessment, understanding, and prevention of adverse effects or any other drug- related problems, is intrinsically linked to effective information management. The pivotal role of information in pharmacovigilance encompassing data collection, analysis, and dissemination for optimal patient safety. The foundation of pharmacovigilance lies in robust information system that facilitate the collection of adverse event reports from healthcare professionals, patients, and other stakeholder. The evolution of data sources, emphasizing the integration of electronic health records, wearable devices and real world evidence to enhance the depth and breadth of information available for analysis. Innovative technologies, including artificial intelligence and machine learning, are transforming pharmacovigilance by automating signal detection and predictive modeling. How those tools are utilized to sift through vast datasets, identifying potential safety concerns and aiding regulatory decision-making. Furthermore, the abstract delves into the importance of structured information sharing between regulatory agencies, pharmaceutical companies, healthcare providers. Timely transparent communication of safety information ensure a proactive response to emerging risk and enable the development of effective risk management strategies.The continues evaluation of information management strategies to adapt to the complexities of modern healthcare and pharmaceutical innovation. In essence, this abstract illuminates the symbiotic relationship between pharmacovigilance and information management, showcasing how the effective utilization of diverse and high quality data is fundamental to advancing drug safety practices and safeguarding public health.

Assessing risk of acute respiratory infectious diseases in crowded indoor settings with digital twin and precision trajectory approach

Indoor environments can pose a substantial respiratory infection risk, especially in densely populated areas. It is therefore vital to evaluate and predict infection risks for mobile individuals engaging in indoor activities. However, previous studies have primarily focused on assessing viral transmission probabilities between relatively stationary individuals, disregarding the dynamic features of pedestrian trajectories. To address this issue, we propose an approach that uses precise trajectory data and digital twin technology to evaluate and forecast indoor infection risks for mobile individuals. Our approach involves the utilization of high-precision trajectory data to develop a time-varying virus density field map (VDFM), forming the basis for infection risk assessment. Additionally, we present a deep-learning model that employs the transformer method to predict future time-varying VDFMs and associated infection risks. Furthermore, we introduce digital twin to comprehend real-time interactions between the physical and digital realms within the structure. To validate our approach, we conducted a case study at the Wuhan International Exposition Center, serving as the control room. We performed a sensitivity analysis on various preventive measures, including mask-wearing, social distancing, and indoor infection control. The results highlighted the significant impact of these measures on individual infection risks associated with indoor activities. Our research contributes to the development of tailored prevention and control strategies, which play a critical role in mitigating the spread of respiratory infections. Thus, this study holds significant implications for technology-facilitated public health services.