Data Analysis Framework Research Articles

Compositional data analysis enables statistical rigor in comparative glycomics

Comparative glycomics data are compositional data, where measured glycans are parts of a whole, indicated by relative abundances. Applying traditional statistical analyses to these data often results in misleading conclusions, such as spurious “decreases” of glycans when other structures increase in abundance, or high false-positive rates for differential abundance. Our work introduces a compositional data analysis framework, tailored to comparative glycomics, to account for these data dependencies. We employ center log-ratio and additive log-ratio transformations, augmented with a scale uncertainty/information model, to introduce a statistically robust and sensitive data analysis pipeline. Applied to comparative glycomics datasets, including known glycan concentrations in defined mixtures, this approach controls false-positive rates and results in reproducible biological findings. Additionally, we present specialized analysis modalities: alpha- and beta-diversity analyze glycan distributions within and between samples, while cross-class glycan correlations shed light on previously undetected interdependencies. These approaches reveal insights into glycome variations that are critical to understanding roles of glycans in health and disease.

Pentecostal church leaders’ support to children in need of care and protection

Churches are considered one of the important structures responsible for providing care and support to vulnerable populations. One such population are children in need of care and support. This article presents the support provided by Pentecostal religious leaders to children needing care and protection. The study was conducted in Pentecostal churches in Tshwane Metropolitan Municipality, which is found in Gauteng province, South Africa. This qualitative study used an interpretative phenomenological analysis design. Data were collected from nineteen purposively selected leaders in Pentecostal churches using face-to-face semi-structured interviews. Data analysis was guided by the interpretative phenomenological analysis framework for data analysis. Findings indicate that religious leaders within Pentecostal churches are involved in providing care and support to children in need of care. The process they are engaged in include proper identification of those children, attending to physical, psychosocial and spiritual needs. However, each religious leaders use their approach depending on the relationship they have with members of government institutions such as police services and social workers. In order to enhance the support provided the children in need of care and protection, by religious leaders within Pentecostal churches, it is recommended that religious leaders are well informed about the role of different members of multidisciplinary teams such as social workers, psychologists, police officers, parents and other community structures. Moreover, there should be formalised collaboration and referral processes that will ensure that the child’s rights are not further violated in the process of provision of support.Contribution: The study contributes to the body of knowledge regarding the role Pentecostal church religious leaders are playing in child protection. Furthermore, it sheds light on the importance of a multidisciplinary approach to ensure that children in need of care and protection are holistically supported.

‘It was just the given thing to do’: exploring enablers for high childhood vaccination uptake in East London’s Bangladeshi community—a qualitative study

BackgroundDespite being an underserved ethnic minority group, characteristics which have been associated with low vaccine uptake, the Bangladeshi community in the UK exhibits high childhood vaccination uptake for several vaccines,...

MiMeJF: Application of Coupled Matrix and Tensor Factorization (CMTF) for Enhanced Microbiome-Metabolome Multi-Omic Analysis

Background/Objectives: The integration of microbiome and metabolome data could unveil profound insights into biological processes. However, widely used multi-omic data analyses often employ a stepwise mining approach, failing to harness the full potential of multi-omic datasets and leading to reduced detection accuracy. Synergistic analysis incorporating microbiome/metabolome data are essential for deeper understanding. Method: This study introduces a Coupled Matrix and Tensor Factorization (CMTF) framework for the joint analysis of microbiome and metabolome data, overcoming these limitations. Two CMTF frameworks were developed to factorize microbial taxa, functional pathways, and metabolites into latent factors, facilitating dimension reduction and biomarker identification. Validation was conducted using three diverse microbiome/metabolome datasets, including built environments and human gut samples from inflammatory bowel disease (IBD) and COVID-19 studies. Results: Our results revealed biologically meaningful biomarkers, such as Bacteroides vulgatus and acylcarnitines associated with IBD and pyroglutamic acid and p-cresol associated with COVID-19 outcomes, which provide new avenues for research. The CMTF framework consistently outperformed traditional methods in both dimension reduction and biomarker detection, offering a robust tool for uncovering biologically relevant insights. Conclusions: Despite its stringent data requirements, including the reliance on stratified microbial-based pathway abundances and taxa-level contributions, this approach provides a significant step forward in multi-omics integration and analysis, with potential applications across biomedical, environmental, and agricultural research.

Beyond Macroethics: Developing an Ethical Framework for Interview Data Collection and Analysis to Acknowledge Participant Rights

AbstractParticipant rights and voices are protected through institutional ethical considerations in the social sciences and applied linguistics. Yet, several ethical concerns remain. In addition to adhering to institutional macroethics, researchers should develop microethics to address contextual issues within their research. The need for the development of microethics is particularly important in the qualitative research process where researchers engage in studies with participants rather than treating them merely as data sources. Drawing on key concepts in philosophical hermeneutics, the current study discusses an ethical framework for data collection and analysis that embraces participants’ rights and voices through reflexive questioning, reciprocal dialogues, unbiased listening, and rightful analysis of participants’ data with and from two multilingual families in Norway. Participatory diagramming was employed in a collaborative participatory approach to present the collected data and initial data analysis to the participants, allowing them to review and validate the data analysis conducted by the researchers. Using thematic analysis to analyze participants’ experiences and reflections, our findings indicate that the ethical framework of interview and analysis enhanced researchers’ understanding, empowered participants in the research process, facilitated member-checking, created beneficial collaboration opportunities for the participants, and facilitated reaffirmation of informed consent.

Stream Data Analysis and Processing Frameworks for Detecting Outliers in Human Activities: A Review

Stream Data Analysis and Processing Frameworks for Detecting Outliers in Human Activities: A Review

Condition monitoring and multi-fault classification of hydraulic systems using multivariate functional data analysis.

Condition monitoring and fault classification in engineering systems is a critical challenge within the scope of Prognostics and Health Management (PHM). The fault diagnosis of complex nonlinear systems, such as hydraulic systems, has become increasingly important due to advancements in big data analytics, machine learning (ML), Industry 4.0, and Internet of Things (IoT) applications. Multi-sensor data provides opportunities to predict component conditions; however, environments characterized by multiple sensors and diverse fault states across various components complicate the fault classification process. To address these challenges, this study introduces a novel multivariate Functional Data Analysis (FDA) framework based on Multivariate Functional Principal Component Analysis (MFPCA) for classifying failure conditions in hydraulic systems. The proposed method systematically tackles condition-based diagnostics and addresses fundamental issues in multi-fault classification. Experimental results demonstrate that this approach achieves high classification accuracy using raw multi-sensor data, establishing multivariate FDA as a powerful tool for fault diagnosis in complex systems.

Pythagorean Neutrosophic Bonferroni Mean Based Machine Learning Model for Data Analytics and Sentiment Classification of Product Reviews

To handle incomplete and indeterminate data, neutrosophic logicsetprobability was recognized. The neutrosophic falsehood, truth, and indeterminacy modules show symmetry as the truth and the falsehood appear the similar and perform in a symmetrical method with esteem to the indeterminacy module which aids as a line of the symmetry. Soft set is a general mathematical device to deal with uncertainty. Sentiment analysis (SA) is the foremost task of natural language processing (NLP), where judgments, opinions, thoughts, or attitudes toward an exact subject are removed. Web is a rich foundation of information and unstructured covering numerous text documents with reviews and opinions. The detection of sentiment will be useful for governments, discrete business groups, and decision-makers. With this motivation, this study develops a Data Analytics Framework for Sentiment Classification Using Pythagorean Neutrosophic Bonferroni Mean (DAFSC-PNBM) technique on Product Reviews. The presented DAFSC-PNBM technique mainly aims to determine the nature of sentiments based on product reviews. Primarily, data preprocessing is performed to increase the product review qualities. For the word embedding process, word2vec model is used. Besides, the DAFSC-PNBM model uses the Pythagorean Neutrosophic Bonferroni Mean (PNBM) technique for classification. To enhance the SA performance of the PNBM model, the grey wolf optimizer (GWO) model has been applied as a hyperparameter tune process. The experimentation outcome analysis of the DAFSC-PNBM method occurs and the outcomes are investigated under several features. The experimental study indicated the improvement of the DAFSC-PNBM method across the modern techniques

A Functional Data Analysis Framework Incorporating Derivative Information and Mixed-Frequency Data for Predictive Modeling of Crude Oil Price

A Functional Data Analysis Framework Incorporating Derivative Information and Mixed-Frequency Data for Predictive Modeling of Crude Oil Price

Object prediction and detection of ground-based weapon with an improved YOLO11 approach

The utilization of UAV-based detection technologies in ground weapon system analysis plays a crucial role in supporting real-time tactical decision-making. While previous studies have primarily focused on improving the detection and classification performance of military objects using UAVs, the current study proposes a novel system that not only detects military objects in simulated UAV operational environments but also analyzes the elevation and azimuth angles of detected gun barrels. For object detection, the YOLO11 model was employed in conjunction with the BCEF loss function to enhance detection performance. The proposed system was validated across various environments using synthetically generated images simulating complex battlefield conditions, including rain, challenging terrain, and low-light environments. Even under these adverse conditions, the model demonstrated high detection accuracy and reliability. This study highlights the potential of UAV-based object detection technology as a tactical decision-making support tool, extending its utility from reconnaissance and identification to broader operational roles. Future research need to further evaluate the performance of the proposed model with experimental validation in real-world UAV operational conditions, emphasizing real-time data collection and analysis frameworks.

Contextual Analysis of Financial Time Series

The evaluation of the financial state of small and medium-sized companies is a pressing issue today. This article introduces a novel method to evaluate a company’s financial state, implemented as a module within a decision support system. This component uses fuzzy logic and knowledge engineering methods. The article describes an ontological model that provides the framework for data analysis and financial time-series modeling. The ontological framework simplifies the representation of the trends in the financial indicators under analysis. Integrating an ontology and a set of fuzzy rules makes it possible to develop control systems based on fuzzy inference. This approach provides the analysis and interpretation of results. The experimental results validate the accuracy and effectiveness of the proposed method.

QuICSeedR: an R package for analyzing fluorophore-assisted seed amplification assay data.

Fluorophore-assisted seed amplification assays (F-SAAs), such as real-time quaking-induced conversion (RT-QuIC) and fluorophore-assisted protein misfolding cyclic amplification (F-PMCA), have become indispensable tools for studying protein misfolding in neurodegenerative diseases. However, analyzing data generated by these techniques often requires complex and time-consuming manual processes. In addition, the lack of standardization in F-SAA data analysis presents a significant challenge to the interpretation and reproducibility of F-SAA results across different laboratories and studies. There is a need for automated, standardized analysis tools that can efficiently process F-SAA data while ensuring consistency and reliability across different research settings. Here, we present QuICSeedR (pronounced as "quick seeder"), an R package that addresses these challenges by providing a comprehensive toolkit for the automated processing, analysis, and visualization of F-SAA data. Importantly, QuICSeedR also establishes the foundation for building an F-SAA data management and analysis framework, enabling more consistent and comparable results across different research groups. QuICSeedR is freely available at: https://CRAN.R-project.org/package=QuICSeedR. Data and code used in this manuscript are provided in Supplementary Materials.

Enhancing Big Data Processing Efficiency in AI-Based Healthcare Systems: A Comparative Analysis of Random Forest and Deep

This research focuses on optimizing the speed of Big Data processing using Artificial Intelligence (AI) in healthcare applications. The study integrates Random Forest (RF) and Deep Learning (DL) algorithms with cloud-based computing systems to improve data processing efficiency. The dataset includes both structured data, such as Electronic Health Records (EHR), and unstructured data, like medical images. The results show that RF performs better with structured data, achieving a lower Mean Squared Error (MSE) and higher R-squared (R²) than traditional methods. Meanwhile, DL achieves superior accuracy and Area Under the Curve (AUC) in processing unstructured data. By utilizing the distributed computing power of Spark on a cloud platform, the processing speed was significantly enhanced, as demonstrated by a statistically significant reduction in processing time (p < 0.05) observed through a t-test analysis comparing Spark-based computing with traditional methods. Despite these improvements, challenges such as data privacy and infrastructure costs remain. Despite these improvements, challenges such as data privacy and infrastructure costs remain. This research provides a robust framework for real-time healthcare data analysis, highlighting its potential to improve decision-making processes and patient outcomes in medical services.

Developing a Data Analytics Framework Using Python for Internal Audit Functions of the Accountant General’s Department of Malaysia

Purpose: This study aims to develop a data analytics framework that incorporates Python for continuous auditing purposes. This initiative involves revisiting the existing audit framework to incorporate data analytics with Python capabilities. This comprehensive audit framework will be the foundation for a robust and continuous auditing system, maximising Python’s potential due to its versatility, efficiency, and powerful data analysis capabilities. The proposed framework is designed to significantly enhance the effectiveness and efficiency of continuous auditing practices, specifically within the BPAD of the Accountant General’s Department of Malaysia (AGD). Design/ Methodology/ Approach: This study employs a qualitative methodology to develop a comprehensive audit framework integrating Python for continuous auditing. The approach consists of focus group interviews, in-depth discussions with key stakeholders from the BPAD, and a thorough examination of the current audit procedures and guidelines within existing audit documents. This method facilitates the understanding and identification of current practices and opportunities for improvement tailored to the BPAD's (Bahagian Pengurusan Audit Dalam [BPAD]) requirements while leveraging Python's robust capabilities in data analysis and process automation. Findings: This study discovers several challenges and limitations in the existing audit framework that warrant the development of an analytical data framework using Python for internal audit functions in the public sector. The proposed framework is expected to reduce manual data processing and analysis through automation, increase accuracy in audit results, and provide continuous real-time monitoring, potentially significantly enhancing the division’s continuous auditing capabilities, leading to more efficient, effective, and comprehensive audit processes. Originality/ Value: This study proposes an analytical data framework that incorporates Python for continuous auditing purposes tailored to government agencies' unique requirements and challenges. The framework focuses on integrating data analytics in audit processes, providing a novel approach to enhance internal audit effectiveness in the public sector. The traditional audit fieldwork is divided into two (2) sub-stages: Pre-Audit Analytics and Audit Analytics Fieldwork, following the Extract, Transform, Load (ETL) process for data preparation and analysis. This approach allows for real-time insights, proactive risk management, and improved decision-making. By automating data analysis with Python, the framework also enables the identification of anomalies, fraud detection, and more effective compliance than traditional methods. Keywords: Data analytics, continuous audit, public sector, Python, government

Graffiti in Public Spaces in the City State of Setif, Algeria

Objectives: The present study aims to discover the themes or categories that characterize graffiti writings in public spaces in the City State of Setif, Algeria. It is worth mentioning that Setif City - the state of Setif - is an eastern city in Algeria; it is near to the state where one of the researchers resides. This fact made data collection an easy task. Methods: Using photographing, the researchers collected 330 graffiti tokens from public spaces in six townships of Setif City. However, among the total number of graffiti only 191 graffiti works had writings, and thus, they were selected as the study sample. The researchers relied on the qualitative and quantitative content analyses framework for data analysis. Results: The analysis showed that graffiti in public spaces of Setif City expressed 19 communicative themes or categories, namely society, politics, resistance, peace, education, history, heritage, sports, motherland, art, personal thoughts and sentiments, expressiveness, commerce, prevention, awareness and guidance, embellishment, health, environment, and finally miscellaneousness. Moreover, the study showed that some of graffiti writings have more than one theme or communicative category. Conclusions: The study concludes that the graffiti of Setif City was used to transmit various messages about many different issues in life.

ScMoMtF: An interpretable multitask learning framework for single-cell multi-omics data analysis.

With the rapidly development of biotechnology, it is now possible to obtain single-cell multi-omics data in the same cell. However, how to integrate and analyze these single-cell multi-omics data remains a great challenge. Herein, we introduce an interpretable multitask framework (scMoMtF) for comprehensively analyzing single-cell multi-omics data. The scMoMtF can simultaneously solve multiple key tasks of single-cell multi-omics data including dimension reduction, cell classification and data simulation. The experimental results shows that scMoMtF outperforms current state-of-the-art algorithms on these tasks. In addition, scMoMtF has interpretability which allowing researchers to gain a reliable understanding of potential biological features and mechanisms in single-cell multi-omics data.

CrossIsoFun: predicting isoform functions using the integration of multi-omics data.

Isoforms spliced from the same gene may carry distinct biological functions. Therefore, annotating functions at the isoform level provides valuable insights into the functional diversity of genomes. Since experimental approaches for determining isoform functions are time- and cost-demanding, computational methods have been proposed. In this case, multi-omics data integration helps enhance the model performance, providing complementary insights for isoform functions. However, current methods underperform in leveraging diverse omics data, primarily due to the limited power to integrate the heterogeneous feature domains. Besides, among the multi-omics data, isoform-isoform interactions (IIIs) are a key data source, as isoforms interact with each other to perform functions. Unfortunately, IIIs remain largely underutilized in isoform function predictions until now. We introduce CrossIsoFun, a multi-omics data analysis framework for isoform function prediction. CrossIsoFun combines omics-specific and cross-omics learning for data integration and function prediction. In detail, CrossIsoFun employs a graph convolutional network (GCN) as the omics-specific classifier for each data source. The initial label predictions from GCNs are forwarded to the View Correlation Discovery Network (VCDN) and processed as a cross-omics integrative representation. The representation is then used to produce final predictions of isoform functions. Additionally, an antoencoder within a cycle-consistency generative adversarial network (cycleGAN) is designed to generate IIIs from PPIs and thereby enrich the interactomics data. Our method outperforms the state-of-the-art methods on three tissue-naive datasets and 15 tissue-specific datasets with mRNA expression, sequence, and PPI data. The prediction of CrossIsoFun is further validated by its consistency with subcellular localization and isoform-level annotations with literature support. CrossIsoFun is freely available at https://github.com/genemine/CrossIsoFun. Supplementary data are available at Bioinformatics online.

Enhancing Big Data Processing Efficiency in AI-Based Healthcare Systems: A Comparative Analysis of Random Forest and Deep

This research focuses on optimizing the speed of Big Data processing using Artificial Intelligence (AI) in healthcare applications. The study integrates Random Forest (RF) and Deep Learning (DL) algorithms with cloud-based computing systems to improve data processing efficiency. The dataset includes both structured data, such as Electronic Health Records (EHR), and unstructured data, like medical images. The results show that RF performs better with structured data, achieving a lower Mean Squared Error (MSE) and higher R-squared (R²) compared to traditional methods. Meanwhile, DL achieves superior accuracy and Area Under the Curve (AUC) in processing unstructured data. By utilizing the distributed computing power of Spark on a cloud platform, the processing speed was significantly enhanced, as demonstrated by a statistically significant reduction in processing time (p < 0.05) observed through a t-test analysis comparing Spark-based computing with traditional methods. Despite these improvements, challenges such as data privacy and infrastructure costs remain. Despite these improvements, challenges such as data privacy and infrastructure costs remain. This research provides a robust framework for real-time healthcare data analysis, highlighting its potential to improve decision-making processes and patient outcomes in medical services.

Development of Tools for the Automatic Processing of Advanced Driver Assistance System Test Data

Advanced driver assistance system (ADAS) technologies are key to improving road safety and promoting innovation in the automotive sector. The approval and analysis of ADAS systems, especially automatic emergency braking (AEB) tests, require complex procedures and in-depth data management. This work presents innovative tools developed to facilitate the post-processing of ADAS AEB test data, created in collaboration with Nardò Technical Center. The tool, called Autonomous Code Generation Intelligence (ACGI), introduces an intuitive and intelligent user interface that helps analyze and interpret ADAS test approval regulations. ACGI automates the generation of code sections within a data analytics framework, streamlining the compliance process and significantly reducing the time and programming skills required. This tool allows engineers to focus on high-value tasks, improving overall process efficiency. To achieve this objective, the tool encodes the DAART code framework (Data Analysis and Automated Report Tool) which allows users to carry out real post-processing of the tests conducted on the track. The results demonstrate that both tools simplify and automate critical steps in the ADAS automatic emergency braking test data analysis process. In fact, the tool not only improves the accuracy and efficiency of the analyses but also offers a high degree of customization, making it a flexible and adaptable tool to meet the specific needs of users. In future developments, ACGI could be extended to cover additional ADAS tests and could be equipped with artificial intelligence to suggest configurations based on new regulations.

Uncovering the causal relationships in plant-microbe ecosystems: A time series analysis of the duckweed cultivation system for biomass production and wastewater treatment

The complex interplay among plants, microbes, and the environment strongly affects productivity of vegetation ecosystems; however, determining causal relationships among various factors in these systems remains challenging. To address this issue, this study aimed to evaluate the potential of a data analytical framework called empirical dynamic modeling, which identifies causal links and directions solely from time series data. By cultivating duckweed, a promising aquatic plant for biomass production and wastewater treatment, we obtained a 63-day time series data of plant productivity, microbial community structure, wastewater treatment performance, and environmental factors. We confirmed that empirical dynamic modeling can identify the correct causal directions among temperature, light intensity and plant growth, solely from time series data. Extending the analysis to microbial community data suggested that the bacterial family Comamonadaceae positively affects host duckweed growth and nitrogen removal. Additionally, the predicted abundance of bacterial genes relevant to xenobiotics biodegradation was shown to have a positive effect on organic pollutant removal, supporting the significant role of bacterial metabolism in phytoremediation performance. These results demonstrate the effectiveness of empirical dynamic modeling in uncovering causal relationships within vegetation ecosystems, which are difficult to examine comprehensively through conventional experiment-based approaches.