Data Integration Research Articles

The integration of big data in finTech: Review of enhancing financial services through advanced technologies

The integration of big data in finTech: Review of enhancing financial services through advanced technologies

Closed-Loop Manufacturing with AI-Enabled Digital Twin Systems

This research provides an in-depth analysis of recent literature on Closed-Loop Manufacturing with AI-Enabled Digital Twin Systems, focusing on the integration of Artificial Intelligence (AI) and Digital Twin technologies within modern manufacturing environments. Through a systematic literature review of studies sourced from leading academic databases such as Scopus, Web of Science, IEEE Xplore, Science Direct, Springer Link, and Google Scholar, this research examines how these advanced technologies are being used to optimize production processes, improve operational efficiency, and reduce costs. The review synthesizes key findings related to real-time data collection, predictive maintenance, and quality control, highlighting the role of AI in enabling self-regulating and self-improving manufacturing workflows. The application of AI and Digital Twin systems in closed-loop manufacturing facilitates enhanced decision-making through continuous feedback loops. These systems allow manufacturers to simulate, predict, and monitor production processes in real-time, enabling proactive maintenance, process optimization, and better-quality control. Moreover, the integration of AI allows for the dynamic adjustment of manufacturing parameters, reducing waste and improving resource utilization. This research identifies and highlights the potential of AI and Digital Twin technologies in driving sustainability and flexibility in manufacturing operations. However, the research also identifies several challenges in implementing AI-enabled Digital Twin systems, including data integration issues, high initial investment costs, and cybersecurity risks. The shortage of skilled professionals capable of managing these advanced systems further hinders widespread adoption. Based on the synthesis of current literature, the research concludes with recommendations for overcoming these obstacles, offering insights into the future of closed-loop manufacturing systems and their potential to transform industrial production processes.

A Comprehensive Survey of Deep Learning and Ensemble Techniques in Glaucoma Detection

Glaucoma stands as a primary contributor to irreversible blindness, necessitating precise and prompt diagnoses for effective management. Recent progress in deep learning, particularly through the use of ensemble methods involving Convolutional Neural Networks (CNNs), has demonstrated considerable potential in automating the detection of glaucoma by analyzing ocular imaging data, such as fundus and Optical Coherence Tomography (OCT) images. This survey provides a thorough overview of the latest ensemble-based approaches developed for glaucoma detection, emphasizing the advantages of integrating various CNN architectures, including ResNet, VGG, and DenseNet, to enhance feature extraction and classification capabilities. The paper explores current trends in transfer learning, multi-modal data integration, and hybrid methodologies that reinforce the performance and adaptability of ensemble methods in clinical environments. Additionally, it addresses challenges like the necessity for high-quality labeled datasets, model interpretability, and generalization across different populations. By exploring into recent studies, the survey aims to identify limitations in existing systems and propose advancements in ensemble- based glaucoma detection, ultimately offering valuable insights into future research path that can narrow the gap between experimental findings and practical clinical applications.

Digital twin applications for predicting and controlling vibrations in manufacturing systems

In Recent times, Digital Twin (DT) technology has emerged as an innovative tool for the enhancement of the efficiency and reliability of manufacturing systems, through the creation of virtual replicas of physical assets, systems and processes. As vibrations in machines and tools can lead to reduced product quality, increased wear and tear, as well as unplanned downtimes, this article explores the application of digital twins for predicting and controlling vibrations in manufacturing systems. The integration of digital twins assists in addressing these challenges through the provision of insights into vibration dynamics, enabling proactive maintenance, and optimizing system performance. It examines how sensor data and advanced computational models converge to simulate and predict vibration behavior in real time. Moreover, the role of artificial intelligence and machine learning in analyzing vibration patterns and prescribing corrective measures is discussed. The article also presents case studies that highlight successful implementations of digital twins in diverse manufacturing contexts, showcasing measurable improvements in productivity and system reliability. In addition, the research identifies key challenges, including data integration complexities, high computational requirements, and cost implications, that manufacturers must address to fully leverage the potential of digital twins. By synthesizing these insights, the paper provides a comprehensive framework for researchers and practitioners seeking to harness digital twin technology for vibration management in manufacturing environments.

Technological Adjuncts to Streamline Patient Recruitment, Informed Consent, and Data Management Processes in Clinical Research: Observational Study.

Patient recruitment and data management are laborious, resource-intensive aspects of clinical research that often dictate whether the successful completion of studies is possible. Technological advances present opportunities for streamlining these processes, thus improving completion rates for clinical research studies. This paper aims to demonstrate how technological adjuncts can enhance clinical research processes via automation and digital integration. Using one clinical research study as an example, we highlighted the use of technological adjuncts to automate and streamline research processes across various digital platforms, including a centralized database of electronic medical records (enterprise data warehouse [EDW]); a clinical research data management tool (REDCap [Research Electronic Data Capture]); and a locally managed, Health Insurance Portability and Accountability Act-compliant server. Eligible participants were identified through automated queries in the EDW, after which they received personalized email invitations with digital consent forms. After digital consent, patient data were transferred to a single Health Insurance Portability and Accountability Act-compliant server where each participant was assigned a unique QR code to facilitate data collection and integration. After the research study visit, data obtained were associated with existing electronic medical record data for each participant via a QR code system that collated participant consent, imaging data, and associated clinical data according to a unique examination ID. Over a 19-month period, automated EDW queries identified 20,988 eligible patients, and 10,582 patients received personalized email invitations. In total, 1000 (9.45%) patients signed consents to participate in the study. Of the consented patients, 549 unique patients completed 779 study visits; some patients consented to the study at more than 1 time period during their pregnancy. Technological adjuncts in clinical research decrease human labor while increasing participant reach and minimizing disruptions to clinic operations. Automating portions of the clinical research process benefits clinical research efforts by expanding and optimizing participant reach while reducing the limitations of labor and time in completing research studies.

Advancing stroke rehabilitation: the role of wearable technology according to research experts

Background Advancements in wearable technology have created new opportunities to monitor stroke survivors’ behaviors in daily activities. Research insights are needed to guide its adoption in clinical practice, address current gaps, and shape the future of stroke rehabilitation. This project aims to: (1) Understand stroke rehabilitation researchers’ perspectives on the opportunities, challenges, and clinical relevance of wearable technology for stroke rehabilitation, and (2) Identify necessary next steps to integrate wearable technology in research and clinical practice. Methods Using a phenomenological qualitative design, two 90-minute focus groups were conducted with 12 rehabilitation researchers. The focus groups consisted of semi-structured, open-ended questions on functional movement behavior, motor performance and benefits and pitfalls of wearable technology. The transcribed focus groups were analyzed using inductive thematic analysis. Results Three main themes were derived from the analysis: (1) Assessing activity performance is critical to inform interventions, (2) The demonstrated benefit is not commensurate with the added hassle, (3) Collaboration is needed between the industry, academia and end-users. Necessary future steps were recognized including the identification of intuitive and actionable metrics, and the integration of sensor-derived data with electronic health records and into clinical workflow to support self-management strategies. Conclusion Wearable technology shows great potential to complement and support stroke rehabilitation. Many key barriers to clinical adoption remain which underscore the necessity to foster collaborations between industry, academia, and the participants we serve.

Use of Semantic Web Technologies to Enhance the Integration and Interoperability of Environmental Geospatial Data: A Framework Based on Ontology-Based Data Access

Use of Semantic Web Technologies to Enhance the Integration and Interoperability of Environmental Geospatial Data: A Framework Based on Ontology-Based Data Access

Integration of on-board monitoring data into infrastructure management for effective decision-making in railway maintenance

Integration of on-board monitoring data into infrastructure management for effective decision-making in railway maintenance

The metabolite transporters of C4 photosynthesis.

C4 photosynthesis is a highly efficient form of photosynthesis that utilises a biochemical pump to concentrate CO2 around rubisco. Although variation in the implementation of this biochemical pump exists between species, each variant of the C4 pathway is critically dependent on metabolite transport between organelles and between cells. Here we review our understanding of metabolite transport in C4 photosynthesis. We discuss how the majority of our knowledge of the metabolite transporters co-opted for use in C4 photosynthesis has been obtained from studying C3 plants, and how there is a pressing need for in planta validation of transporter function in C4 species. We further explore the diversity of transport pathways present in disparate C4 lineages and highlight the important gaps in our understanding of metabolite transport in C4 plants. Finally, through integration of functional and transcriptional data from multiple C3 and C4 plants we propose a molecular blueprint for metabolite transport for NAD-ME photosynthesis.

Collaborative Effort Towards a FAIR and OPEN Indo-Pacific Pollen Database (IPPD)

The Indo-Pacific Pollen Database (IPPD) is a collection of modern and fossil Australian, Southeast Asian, and Oceanian pollen assemblages collected from Quaternary period depositional contexts. This compilation has been in the making since the late 1980s and is now being made available as a constituent database of Neotoma, thereby providing much needed palaeo-data coverage of the previously often underrepresented Indo-Pacific region. In addition, the IPPD is also being hosted by the OCTOPUS database, which integrates archaeology, sedimentology, geomorphology, charcoal, and non-human vertebrate fossil collections in a thoroughly Australasian context. These collections are all available in the same flattened table format, thereby providing regional researchers with multiple data types in an easily accessible manner. This will enable new avenues of cross-disciplinary research in the region. Here, we explore the collaborative efforts involved in compiling the IPPD and integrating it into OCTOPUS, as well as provide background information on both. Further, we consider future opportunities and the importance of FAIR, CARE, and OPEN data integration.

Abstract B028: Multimodal approach to characterization of metabolism and immune modulation with insights from spatial metabolomics and transcriptomics

Abstract Background: Spatial integration of metabolic pathways with single cell-level transcriptomic data in human tumor and normal tissue may elucidate mechanisms supporting tumorigenesis for therapeutic targeting. The suppressive adenosine signaling pathway is an emerging potential target for combination with radiotherapy. This study aims to create an in situ map of the pathway in non-small cell lung cancer (NSCLC) tumor and adjacent normal tissue. We seek to define how distinct cellular compartments cooperate and contribute to adenosine signaling within the tumor microenvironment (TME). Methods: Using Matrix-Assisted Laser Desorption/Ionization mass spectrometry imaging, we examined the spatial distribution of metabolites in paired human NSCLC compared to normal tissue from the same patient (n=15). In situ metabolite quantification and pathway enrichment analysis were performed. Second, we performed single nuclear RNA-sequencing (snRNA-seq) on NSCLC patient samples (n=4) to characterize the transcriptomic landscape of the tumors, including quantification of key members of the adenosine signaling pathway: ADORA2A (A2AR), ADORA2B (A2BR), ENTPD1 (CD39), NT5E (CD73), and ENPP1. Leveraging the average gene expression per cell subtype and pathologist-annotated H&E-stained tissue sections, we are integrating transcriptomic data with the spatial metabolomics to generate an in situ pathway map. Results: In NSCLC tissue, UMP, AMP, and ADP levels were significantly higher in tumor compared to normal tissue (p<0.0001), with mean percentage increases of 79%, 89%, and 73%, respectively. Metabolites downstream of adenosine, adenine and inosine, showed no significant differences (p>0.05). Single nuclear RNA-seq analyses revealed expression of the adenosine 2B receptor, ADORA2B, was highest in fibroblasts, lower in tumor, and absent in the immune compartment. ENTPD1 was expressed by all immune cells and tumor. NT5E was absent in T cells and ENPP1 was absent in macrophages, but expressed in all other immune compartments and tumor. Integration of snRNA-seq data with spatial metabolomics is underway to correlate metabolite abundance and gene expression within distinct cellular compartments to define cell type-specific contribution to adenosine signaling. Conclusion: Our study offers a multimodal approach to spatially resolve metabolic and transcriptomic data in situ relying on frozen NSCLC and normal lung tissue. This has significant translational implications, enabling analysis of biospecimens from multi-institutional clinical trials that precludes processing fresh tissue for single-cell analyses. Herein, we are able to localize key metabolites in untreated tumor and normal tissue and quantify the expression of pathway members at the cellular level. Through spatial integration of these data, we aim to decipher the relationship between distinct cell types within the TME and their contribution to adenosine-driven suppressive changes, then extend to radiotherapy-treated tumors. Citation Format: Chelsea L. Rahiman, Roberto Ribas, Manan Vij, Julia An, Patrick J. McCann, Jason Cham, Chang Liu, Parin Shah, Rosa Martin, Ariel Chen, Simon Cheng, Aleksandar Z. Obradovic, Ramon C. Sun, Catherine S. Spina. {Abstract title} [abstract]. In: Proceedings of the AACR Special Conference in Cancer Research: Translating Targeted Therapies in Combination with Radiotherapy; 2025 Jan 26-29; San Diego, CA. Philadelphia (PA): AACR; Clin Cancer Res 2025;31(2_Suppl):Abstract nr B028.

Accuracy of Genomic Predictions for Resistance to Gastrointestinal Parasites in Australian Merino Sheep

Infection by gastrointestinal nematodes (GINs) in sheep is a significant health issue that affects animal welfare and leads to economic losses in the production sector. Genetic selection for parasite resistance has shown promise in improving animal health and productivity. This study aimed to determine if incorporating genomic data into genetic prediction models currently used in Uruguay could improve the accuracy of breeding value estimations for GIN resistance in the Australian Merino breed. This study compared the accuracy of breeding value predictions using the BLUP (Best Linear Unbiased Prediction) and ssGBLUP (single-step genomic BLUP) models on partial and complete data sets, including 32,713 phenotyped and 3238 genotyped animals. The quality of predictions was evaluated using a linear regression method, focusing on 145 rams. The inclusion of genomic data increased the average individual accuracies by 4% for genotyped and phenotyped animals. For animals with genomic and non-phenotyped data, the accuracy improvement reached 8%. Of these, one group of animals that benefited from an ssGBLUP evaluation came from a facility with a strong connection to the informative nucleus and showed an average increase of 20% in their individual accuracy. Additionally, ssGBLUP slightly outperformed BLUP in terms of prediction quality. These findings demonstrate the potential of genomic information to improve the accuracy of breeding value predictions for parasite resistance in sheep. The integration of genomic data, particularly in non-phenotyped animals, offers a promising tool for enhancing genetic selection in Australian Merino sheep to improve resistance to gastrointestinal parasites.

Digital twins: Transforming the chemical process industry—A review

AbstractDigital twin (DT) technology represents a significant advancement in the digital transformation of the chemical process industry (CPI), offering innovative capabilities for real‐time monitoring, predictive maintenance, and process optimization. This review investigates the current deployment status, frameworks, architectures, and applications of DTs within CPI, highlighting their transformative potential in improving operational efficiency, enhancing safety, and promoting sustainability. By examining case studies from industry leaders and analyzing recent advancements, this study elucidates the critical roles of DTs in asset health monitoring, process optimization, and environmental performance. The review identifies key components of DT frameworks, including data integration, hybrid modelling, and real‐time analytics, which are essential for effective implementation. It further explores challenges such as high computational requirements, integration with legacy systems, cybersecurity risks, and the lack of standardization, which impede widespread adoption. Despite these challenges, the paper emphasizes opportunities for leveraging advanced technologies such as artificial intelligence, edge computing, and 5G connectivity to enhance DT capabilities and scalability. In addition, this review underscores the importance of DTs in addressing global sustainability goals, mainly through their ability to optimize energy consumption, reduce emissions, and facilitate circular economy practices. By synthesizing insights from academia and industry, this study provides a comprehensive understanding of DTs' current state and future potential in CPI, offering strategic directions for research and development. The findings contribute to advancing the deployment of DTs as a cornerstone technology in achieving operational excellence, safety, and sustainability in the chemical process industry.

Communication-efficient federated learning of temporal effects on opioid use disorder with data from distributed research networks.

To develop a distributed algorithm to fit multi-center Cox regression models with time-varying coefficients to facilitate privacy-preserving data integration across multiple health systems. The Cox model with time-varying coefficients relaxes the proportional hazards assumption of the usual Cox model and is particularly useful to model time-to-event outcomes. We proposed a One-shot Distributed Algorithm to fit multi-center Cox regression models with Time varying coefficients (ODACT). This algorithm constructed a surrogate likelihood function to approximate the Cox partial likelihood function, using patient-level data from a lead site and aggregated data from other sites. The performance of ODACT was demonstrated by simulation and a real-world study of opioid use disorder (OUD) using decentralized data from a large clinical research network across 5 sites with 69163 subjects. The ODACT method precisely estimated the time-varying effects over time. In the simulation study, ODACT always achieved estimation close to that of the pooled analysis, while the meta-estimator showed considerable amount of bias. In the OUD study, the bias of the estimated hazard ratios by ODACT are smaller than those of the meta-estimator for all 7 risk factors at almost all of the time points from 0 to 2.5 years. The greatest bias of the meta-estimator was for the effects of age ≥65 years, and smoking. ODACT is a privacy-preserving and communication-efficient method for analyzing multi-center time-to-event data which allows the covariates' effects to be time-varying. ODACT provides estimates close to the pooled estimator and substantially outperforms the meta-analysis estimator. The proposed ODACT is a privacy-preserving distributed algorithm for fitting Cox models with time-varying coefficients. The limitations of ODACT include that privacy-preserving via aggregate data does rely on relatively large number of data at each individual site, and rigorous quantification of the risk of privacy leaks requires further investigation.

Enhancing Smart Farming Management in the Bali Cattle Breeding Center, Sobangan, Bali, Indonesia, through “SIDEWI” Electronic Data Information System

The Sobangan Cattle Breeding Center is currently relying on a manual recording system administered by the office to document cattle data. Due to the substantial number of cattle, such a manual method proves inefficient. The solution lies in SIDEWI, a comprehensive digital recording system for the data. Therefore, this research assessed the breeding center productivity by integrating a digital recording system with maintenance management, addressing the inefficiencies inherent in manual recording. The integration of data through SIDEWI aimed to enhance the accuracy and efficiency of measuring productivity while supporting improvements in maintenance management. The investigation, conducted at Sobangan Cattle Breeding Center in Sobangan Village, Mengwi Sub-district, Badung Regency, spanned from April to November 2023. The program included basic analysis, system development, training, and mentoring. SIDEWI.id, being a digital system, contained features for efficiently managing and recording growth, reproduction, ownership, and health data. The research had the potential to generate more precise and high-quality data, contributing to increased productivity in the cattle farming industry. Through the system, staff could easily access and evaluate the condition of each cattle, facilitating the integration of smart farming management, enhancing productivity, and, becoming a center of excellence for Bali cattle.

Analiza zgodności danych opisowych ewidencji gruntów i budynku z księgami wieczystymi na wybranym przykładzie

There are currently two basic public registers concerning real estate in Poland: the Land and Building Register (EGiB) and the Land and Mortgage Register (KW). The descriptive data in the Land and Building Register includes information on registered plots of land, buildings and premises, while the Land and Mortgage Register presents information on the legal status of the property. These systems operate independently, as they are maintained by different public administration bodies. However, the data contained in the Land and Building Register form the basis for the designation of the property in the Land and Mortgage Register, and thus both registers are interconnected and should contain consistent information. It is crucial that the information repetitively reported in both the EGiB and KW are identical. Consistency of data attribute values contained in both registers provides technical and organisational opportunities for harmonisation and integration of data from both sets. It is also an important factor for conducting investment activities on real estate. Previous analyses by researchers indicate that data on plots in the real estate registers are not sufficiently consistent. The aim of the article is to review the current situation with regard to the consistency of the basic data on land plots contained in the Land and Building Register and Land and Mortgage Registers on a selected example. The analysis by the comparative method was supplemented with the determination of the Jaccard index and the Russel-Rao coefficient. These are indices allowing to determine the degree of similarity between sets containing the same attributes.

A comparative evaluation of GIS spatial analysis tools for prioritizing natural and hybrid shoreline solutions

ABSTRACT Living shoreline suitability assessments guide decisions on shoreline armoring, ensuring the most ecologically balanced shoreline protection methods are selected. This study compares two spatial analysis tools—Weighted Sum (WS) and Suitability Modeler (SM) in ArcGIS Pro 3.1.0—to evaluate their effectiveness in prioritizing natural and hybrid shoreline solutions based on thirteen physical and ecological variables. Data were standardized into 10mx10m raster, with weights assigned using the Living Shoreline Feasibility Model (LSFM). Shoreline segments were classified into three categories: Suitable for living shorelines (LS), hybrid solutions (HS), or not suitable for living shorelines (NLS). Four output maps (weighted/unweighted) were evaluated for accuracy, precision, user-friendliness, flexibility, efficiency, and agreement with LSFM. WS with weight achieved the highest agreement (24.8% Kappa Index), classification accuracy of 78%, 77%, and 77% with improved precision of 0%, 66%, and 85% across categories. WS exhibited better alignment with LSFM results, while SM offered ease of use, data integration, and efficiency advantages. Six shoreline segments with high disagreement between tools were reanalyzed using the LSFM, validating the WS model’s higher accuracy and precision. The findings highlight key methodological considerations in GIS-based shoreline suitability modeling, emphasizing that tool selection should align with project goals, data availability, and user expertise.

An Overview of Blockchain Technology in Architecture and Consensus with Key Advances

Blockchain has revolutionized cryptocurrency since the advent of Bitcoin. Due to its decentralized nature, transparency, security measures, and ability to conduct transactions between untrusted parties, blockchain has received extensive attention recently. Consensus algorithms manage the blockchain and describe how peers achieve data consistency and integration. However, other hurdles persist for blockchain systems, including scalability and energy consumption, and they require to be overcome. The paper introduces a comprehensive overview of distributed ledger technologies (DLTs) with a deeper understanding of the blockchain. Moreover, we conduct a comparative analysis of the most widespread consensus mechanisms using various metrics. And briefly list potential threats, applications across several fields, and possible future directions.

Consumer-grade wearable devices in arrhythmia diagnostics for clinicians: where we are and where we are going.

Atrial arrhythmias, including atrial fibrillation (AF), are a major contributor to cardiovascular morbidity and mortality. Early detection and effective management are critical to mitigating adverse outcomes such as stroke, heart failure, and overall mortality. Wearable devices have emerged as promising tools for monitoring, detecting, and managing atrial arrhythmias near-continuously. This comprehensive analysis explores these wearable technologies' current role and capabilities for clinicians' daily practice. Despite challenges related to data accuracy, privacy, patient compliance, and integration with healthcare systems, ongoing advancements hold significant promise for the future. Continued research and development are essential to fully realize the potential of wearables in improving clinical outcomes for patients with atrial arrhythmias.

The Applications of Machine Learning in the Management of Patients Undergoing Stem Cell Transplantation: Are We Ready?

Hematopoietic stem cell transplantation (HSCT) is a life-saving therapy for hematologic malignancies, such as leukemia and lymphoma and other severe conditions but is associated with significant risks, including graft versus host disease (GVHD), relapse, and treatment-related mortality. The increasing complexity of clinical, genomic, and biomarker data has spurred interest in machine learning (ML), which has emerged as a transformative tool to enhance decision-making and optimize outcomes in HSCT. This review examines the applications of ML in HSCT, focusing on donor selection, conditioning regimen, and prediction of post-transplant outcomes. Machine learning approaches, including decision trees, random forests, and neural networks, have demonstrated potential in improving donor compatibility algorithms, mortality and relapse prediction, and GVHD risk stratification. Integrating “omics” data with ML models has enabled the identification of novel biomarkers and the development of highly accurate predictive tools, supporting personalized treatment strategies. Despite promising advancements, challenges persist, including data standardization, algorithm interpretability, and ethical considerations regarding patient privacy. While ML holds promise for revolutionizing HSCT management, addressing these barriers through multicenter collaborations and regulatory frameworks remains essential for broader clinical adoption. In addition, the potential of ML can cope with some challenges such as data harmonization, patients’ data protection, and availability of adequate infrastructure. Future research should prioritize larger datasets, multimodal data integration, and robust validation methods to fully realize ML’s transformative potential in HSCT.