Frontiers in Big Data最新文献

{"title":"Cheatomaly: weakly supervised video anomaly ranking for exam cheating detection using vision transformers.","authors":"El Mehdi Alaoui Mrani, Anas Bouayad, Khalid Fardousse","doi":"10.3389/fdata.2026.1817120","DOIUrl":"10.3389/fdata.2026.1817120","url":null,"abstract":"<p><p>Detecting cheating in classroom examinations is challenging because suspicious behaviors are often subtle, temporally sparse, and context-dependent. To address the lack of dedicated benchmarks for this setting, we introduce Cheatomaly, a curated video dataset assembled from publicly available classroom examination material and annotated to support weakly supervised anomaly detection. We formulate cheating detection as a weakly supervised video anomaly ranking task using Multiple Instance Learning (MIL) with Vision Transformer features. Videos are divided into temporal segments, and segment-level representations are built using mean pooling and a Mean, Standard Deviation, and Temporal Difference (MSD) formulation. A margin-based ranking objective is used to prioritize anomalous videos and suspicious temporal segments using only video-level labels during training. Experimental results on Cheatomaly show strong video-level discrimination and meaningful frame-level localization across repeated runs. Ablation, baseline, statistical, and sensitivity analyses indicate that temporal aggregation affects the trade-off between ranking and localization but does not produce consistent statistically significant gains. Overall, Cheatomaly provides a realistic benchmark for studying subtle cheating-related anomalies in classroom examinations, and the results highlight that the main challenge lies in modeling context-dependent temporal behavior rather than feature aggregation alone.</p>","PeriodicalId":52859,"journal":{"name":"Frontiers in Big Data","volume":"9 ","pages":"1817120"},"PeriodicalIF":3.8,"publicationDate":"2026-05-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13201167/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148044707","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Optimizing large-scale graph database ingestion through edge value ranking: a proposed framework.","authors":"Phanindra Reddy Madduru, Bijo Thomas","doi":"10.3389/fdata.2026.1768571","DOIUrl":"https://doi.org/10.3389/fdata.2026.1768571","url":null,"abstract":"<p><p>This paper proposes a preprocessing framework for optimizing large-scale graph database ingestion through intelligent edge filtering based on value ranking. We combine adapted PageRank algorithms with business-specific metrics and edge type importance to evaluate and rank edges, enabling selective retention of high-value relationships. The framework introduces three PageRank variants (maximum weight normalization, weighted average, and log-based normalization) with type-specific business value normalization to handle heterogeneous graphs. Current graph database ingestion approaches struggle with scale: loading 6.2TB of data (38 billion objects) requires over 3 weeks, forcing organizations to limit historical data retention. Our approach addresses this through preprocessing-stage filtering before database ingestion. While requiring experimental validation, preliminary analysis suggests potential for 40%-80% data volume reduction depending on graph characteristics, with corresponding improvements in loading efficiency and storage costs. The paper details the theoretical framework, computational complexity analysis, formal property preservation guarantees, and comprehensive validation methodology. This work represents a novel direction in graph database optimization: value-based preprocessing rather than runtime query optimization.</p>","PeriodicalId":52859,"journal":{"name":"Frontiers in Big Data","volume":"9 ","pages":"1768571"},"PeriodicalIF":2.4,"publicationDate":"2026-05-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13199040/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148037537","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A longitudinal multimodal big data infrastructure for precision poultry monitoring.","authors":"Daniel Essien, Yashan Dhaliwal, Suresh Neethirajan","doi":"10.3389/fdata.2026.1821612","DOIUrl":"10.3389/fdata.2026.1821612","url":null,"abstract":"<p><p>Livestock systems are increasingly instrumented with heterogeneous sensors, yet the resulting data remain fragmented, short-lived, and rarely documented as integrated infrastructures. This gap limits the development of robust multimodal artificial intelligence under real production conditions. Here we present a longitudinal multimodal data infrastructure for poultry monitoring, spanning 22 consecutive weeks across five commercial-style barns. The dataset combines continuous RGB video (1080 p, 30 fps), continuous audio (48 kHz), periodic radiometric thermal imaging, and twice-daily environmental measurements, yielding 10.2 terabytes of temporally heterogeneous data. Rather than focusing on a specific predictive task, the study addresses the underlying data-engineering challenge: how to acquire, synchronize, store, and preprocess multimodal streams at production scale. We detail a reproducible system architecture for distributed sensing, local buffering, secure transfer, and cloud-based organization, together with standardized preprocessing pipelines for illumination correction, acoustic denoising, and radiometric temperature extraction. Temporal alignment is achieved through timestamp-based normalization across asynchronous modalities, with explicit characterization of alignment granularity and missing data under real-world constraints. This work positions multimodal livestock sensing as a data-systems problem. The resulting dataset supports longitudinal analysis, cross-modal querying, and the development and evaluation of machine learning and multimodal fusion approaches at appropriate temporal scales. By releasing both data and workflows, we provide a transparent and extensible foundation for building and evaluating AI systems in precision agriculture.</p>","PeriodicalId":52859,"journal":{"name":"Frontiers in Big Data","volume":"9 ","pages":"1821612"},"PeriodicalIF":3.8,"publicationDate":"2026-05-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13199025/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148037410","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Fairness across domains: a unified fairness-aware framework for domain generalization and unsupervised adaptation.","authors":"Kai Jiang, Chen Zhao, Haoliang Wang, Xintao Wu, Latifur Khan, Christan Grant, Feng Chen","doi":"10.3389/fdata.2026.1764468","DOIUrl":"10.3389/fdata.2026.1764468","url":null,"abstract":"<p><p>Fairness in machine learning remains a critical challenge, particularly in the presence of domain shift. We propose a unified fairness-aware framework for both domain generalization (DG) and unsupervised domain adaptation (UDA), which jointly addresses domain shift and sensitive-attribute bias through disentangled representation learning. The framework disentangles content, style, and sensitive factors, and uses them to generate augmented samples that reduce bias while maintaining predictive reliability. Extensive experiments on four datasets demonstrate that the proposed method achieves state-of-the-art performance in both DG and UDA settings. Moreover, it yields a stronger balance between classification accuracy and fairness across diverse domains and sensitive subgroups. By incorporating unlabeled target-domain data, our framework extends prior fairness-aware approaches that were limited to DG and provides new insight into fairness-aware learning under unsupervised adaptation. Overall, this work offers a practical step toward scalable and robust fairness-aware learning in multi-domain environments.</p>","PeriodicalId":52859,"journal":{"name":"Frontiers in Big Data","volume":"9 ","pages":"1764468"},"PeriodicalIF":3.8,"publicationDate":"2026-05-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13199006/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148037523","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Explainable gradient convolutional vector fuzzy pattern analysis based on ensemble model for facial expression recognition.","authors":"Lakshmi Sarvani Videla, Babu Reddy Mukamalla","doi":"10.3389/fdata.2026.1807184","DOIUrl":"10.3389/fdata.2026.1807184","url":null,"abstract":"<p><p>Facial expression recognition using machine learning involves training algorithms to identify and categorize human emotions based on visual cues from facial features. Explainable AI (XAI) enhances this process by providing transparency into how these algorithms arrive at their predictions. While machine learning algorithms provide the capability to recognize facial expressions, explainable AI offers the crucial ability to understand and interpret these recognition processes, leading to more robust, fair, and trustworthy systems. The aim of this research is to propose a novel method in facial expression recognition using segmentation by an ensemble machine learning algorithm and explainable AI model. The input consists of facial expression images, which are first processed for noise removal and normalization. The processed images are then segmented using the Explainable Gradient Convolutional Vector Fuzzy Pattern Recognition (ExGrConVFuzPR) model. The proposed method was evaluated on the JAFFE, CK, and AFLW datasets. The model achieved promising results with an accuracy of 97%, precision of 96%, recall of 96%, F1-score of 97%, and RMSE of 0.043. These outcomes demonstrate that the suggested approach provides good performance along with improved interpretability.</p>","PeriodicalId":52859,"journal":{"name":"Frontiers in Big Data","volume":"9 ","pages":"1807184"},"PeriodicalIF":3.8,"publicationDate":"2026-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13193875/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148018434","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Detection and classification of lung cancer using sequential hybridization of CNN and RNN type architectures.","authors":"Maheswari Vutukuri, Parveen Sultana Habibullah","doi":"10.3389/fdata.2026.1786859","DOIUrl":"10.3389/fdata.2026.1786859","url":null,"abstract":"<p><strong>Introduction: </strong>Early and accurate lung cancer detection from computed tomography (CT) images remains a challenging task because of the complex morphology of lung nodules, class imbalance, variation in image quality, and the risk of overfitting in deep learning models. Conventional manual interpretation is time-consuming and may be affected by inter-observer variability. Therefore, an automated and reliable CT-based classification framework is required to support early identification of benign, malignant, and normal lung conditions.</p><p><strong>Methods: </strong>This study proposes a sequential hybrid deep learning framework that integrates convolutional and recurrent neural network components for multiclass lung cancer classification. A dataset of 1,600 CT-scan images collected from multiple hospital data repositories across Bengaluru was used and divided in an approximate 70:30 ratio for training and validation. The preprocessing pipeline includes contrast enhancement using Contrast Limited Adaptive Histogram Equalization (CLAHE), morphological operations for lung segmentation, and nodule-focused masking to isolate diagnostically relevant lung regions. Data augmentation and transfer learning were applied to improve model generalization and reduce overfitting. DenseNet201 was used for feature extraction, while a bidirectional gated recurrent unit (BiGRU) module was incorporated for sequential representation learning. Hyperparameter optimization and early stopping were used to improve training stability and classification performance.</p><p><strong>Results: </strong>The proposed DenseNet201-BiGRU sequential hybrid architecture achieved an overall accuracy of 95.8%. The class-wise accuracies were 97.33% for benign cases, 93.33% for malignant cases, and 96.67% for normal cases. Precision, recall, and F1-score values further demonstrated that the model maintained reliable classification performance across diverse and imbalanced CT image classes.</p><p><strong>Discussion: </strong>The results indicate that sequential hybridization of DenseNet201-based feature extraction with BiGRU-based representation learning provides an efficient, precise, and robust framework for CT-based lung cancer classification. The proposed method improves classification reliability by combining enhanced preprocessing, focused lung-region extraction, transfer learning, and recurrent modeling. However, further validation using larger, multi-center datasets and additional clinical testing is required before real-world deployment and broader diagnostic application.</p>","PeriodicalId":52859,"journal":{"name":"Frontiers in Big Data","volume":"9 ","pages":"1786859"},"PeriodicalIF":3.8,"publicationDate":"2026-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13193839/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148018408","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Strategic cyber intelligence with advanced analytics in Latin America: a perspective.","authors":"Tamara Briones-Lascano, Vanessa Vergara-Lozano, Alex Miranda-Andrade","doi":"10.3389/fdata.2026.1733733","DOIUrl":"10.3389/fdata.2026.1733733","url":null,"abstract":"<p><p>Digital transformation in Latin America has widened the attack surface, while exposing long-standing gaps in policy, capability, and data stewardship. From this perspective, we argue that the region can move from reactive cybersecurity to strategic cyber intelligence by embedding advanced analytics into an intelligence cycle that connects multisource data, governed models, and operational playbooks with clear accountability. We synthesize the demonstrated technical gains, diagnose implementation constraints, and outline a near-term agenda that includes a regional maturity index, comparative outcome studies, and decision research on explainability and bias. Thus, our position was practical. Analytics amplifies a good strategy only when governance, trustworthy data, and skilled teams are in place. This Perspective contributes a strategic analytical framework that links advanced analytics, governance, and decision-making to strengthen cyber intelligence and digital resilience in Latin America.</p>","PeriodicalId":52859,"journal":{"name":"Frontiers in Big Data","volume":"9 ","pages":"1733733"},"PeriodicalIF":3.8,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13175815/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147965417","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Novel approach of encrypted network traffic classification using deep convolutional neural network with Artificial Bee Colony and Genetic Algorithm.","authors":"Sujan Kumar Mohanty, Satyajit Rath, Satya Ranjan Sahu, Bikram Kumar Parida, Rakesh Chandra Balabantaray","doi":"10.3389/fdata.2026.1821270","DOIUrl":"10.3389/fdata.2026.1821270","url":null,"abstract":"<p><p>The encode network traffic makes it difficult to perform successful and dynamic classification. This paper will present the use of a hybrid model to be used with the publicly available QUIC dataset to classify VPN and non-VPN encrypted traffic based on a Deep Convolutional Neural Network (DCNN) and Long Short-Term Memory (LSTM) network, which is optimized by the Artificial Bee Colony (ABC) and Genetic Algorithm (GA). The method involves multi-angle processing - preprocessing, Min-Max normalization, and features selection of with correlation analysis, Fisher Score, and mutual information to obtain a tiny, but meaningful feature set (Size, Batch Cache, Delta Previous Packet). The chosen features are translated to 2D tensors through a sliding time window of consecutive packets, which allows the spatio-temporal DCNN+LSTM architecture to represent the level of intra- and inter-packet feature associations as well as inter- and intra-packet time dynamics. The disadvantages of single-optimization are overcome using a dual metaheuristic optimization strategy again whereby the work of the global hyperparameter exploration is done using ABC and the structural optimization is done using GA. The imbalance of classes is reduced with weighted loss functions and stratified data division. The accuracy of the model is 99.66% with 0.994 ROC-AUC and 0.987 PR-AUC and its MCC is 0.963 which is even greater than that of the traditional classifiers (Decision Tree, Random Forest, SVM, KNN), individual deep-learning models (CNN, LSTM), and image-based FlowPic method. Three-quarters of stratified cross-validation marks the case of consistent generalization (99.53% ± 0.09% mean accuracy), and an ablation study confirms the value of any one of the components. The findings prove that the presented framework can be applied to monitor the network traffic on encrypted networks which are security-sensitive and in real-time.</p>","PeriodicalId":52859,"journal":{"name":"Frontiers in Big Data","volume":"9 ","pages":"1821270"},"PeriodicalIF":3.8,"publicationDate":"2026-04-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13160765/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147935387","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The designing of a transparent hybrid machine learning framework for water leak detection: a systematic review.","authors":"Chinemerem M Anozie, Tite Tuyikeze, Ibidun C Obagbuwa, Fezile Matsebula","doi":"10.3389/fdata.2026.1761377","DOIUrl":"10.3389/fdata.2026.1761377","url":null,"abstract":"<p><strong>Introduction: </strong>Global water scarcity is increasingly exacerbated by substantial water losses, with approximately 30% of treated water lost annually due to leaks in aging Water Distribution Networks (WDNs). Addressing this challenge requires advanced and reliable leak detection mechanisms. This study investigates the design of a transparent hybrid machine learning framework aimed at improving the accuracy and effectiveness of water leak detection systems.</p><p><strong>Methods: </strong>A systematic literature review was conducted following PRISMA guidelines. A total of 27 relevant studies were analyzed, focusing on hybrid deep learning approaches that incorporate data fusion, mixed models, and ensemble techniques for leak detection in WDNs.</p><p><strong>Results: </strong>The findings indicate that hybrid and ensemble learning techniques are becoming more important in the identification of water leaks. Several studies reported exceptional high performance, with some models achieving up to 99% balanced accuracy by leveraging multiple data modalities. These approaches demonstrate strong resilience and adaptability across varying operational conditions.</p><p><strong>Discussion: </strong>Despite their high performance, the complexity and \"black-box\" nature of hybrid models limit their practical deployment. The study highlights the importance of integrating Explainable Artificial Intelligence (XAI) techniques to enhance transparency, interpretability, and user trust. The review concludes that future intelligent leak management systems should combine high-performing hybrid models with XAI to develop efficient, interpretable, and trustworthy decision-support systems that support sustainable water resource management.</p>","PeriodicalId":52859,"journal":{"name":"Frontiers in Big Data","volume":"9 ","pages":"1761377"},"PeriodicalIF":3.8,"publicationDate":"2026-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13157643/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147876736","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Beyond performance metrics: evaluating the unique value of generative AI in hybrid cybersecurity threat detection.","authors":"Juan Antonio González-Ramos, Pablo Chamoso","doi":"10.3389/fdata.2026.1768366","DOIUrl":"https://doi.org/10.3389/fdata.2026.1768366","url":null,"abstract":"<p><strong>Introduction: </strong>This study examines the role of generative artificial intelligence (GenAI) in cybersecurity threat detection, focusing on its usefulness in workflows that support human decision-making.</p><p><strong>Methods: </strong>Experiments were performed on the BODMAS dataset (134,435 samples) and a smaller exploratory subset of UNSW-NB15. State-of-the-art machine learning (ML) classifiers were compared with a zero-shot large language model (LLM) using standard classification metrics, while also considering latency, cost, and hallucination risk.</p><p><strong>Results: </strong>ML classifiers consistently outperformed the LLM-based system on standard detection metrics. However, the LLM showed value in cases of ambiguity, where it could provide short plain-language explanations, organize alert-related context, and generate initial interpretations for instances that did not match learned classes.</p><p><strong>Discussion: </strong>GenAI is unlikely to replace ML-based detection methods, but it can provide useful interpretive support for ambiguous or unfamiliar alerts. A hybrid pipeline is therefore proposed, in which ML handles high-confidence and time-sensitive decisions, while the LLM is used selectively for low-confidence cases or when explanatory support is needed. Human oversight remains necessary to address hallucination risk and ensure reliability.</p>","PeriodicalId":52859,"journal":{"name":"Frontiers in Big Data","volume":"9 ","pages":"1768366"},"PeriodicalIF":2.4,"publicationDate":"2026-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC13157654/pdf/","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147876669","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}