Large Datasets Research Articles

Architectural Design for Data Security in Cloud-based Big Data Systems

التصميم المعماري للنظام هو عملية إبداعية بعد كل شيء. المتطلبات غير الوظيفية وبنية البرامج لها علاقة قوية. يعد أمن النظام أحد الشواغل الكبيرة وهو حاجة ومتطلب غير وظيفي. يجب أن يعتمد الأسلوب والهيكل المعماري المختاران للنظام على متطلبات النظام غير الوظيفية. تُستخدم تقنيات البيانات الضخمة لتخزين كميات هائلة من البيانات التشغيلية في المجال العام. تم اقتراح مخططات هيكل وسلوك النظام التي تستخدم تصميمًا معماريًا آمنًا لنظام يعمل عبر السحابة. تم التحقيق في مكونات مختلفة من البيانات الضخمة في هذا العمل البحثي نظرًا لخطورة القضايا الأمنية التي تركز على الخصوصية والسرية. يعد تأمين البيانات عبر السحابة التي يتم الاستعانة بمصادر خارجية لها مصدر قلق متزايد. هناك مسؤولو قواعد بيانات ضارة من الخارج ومن الداخل يمكنهم الوصول إلى البيانات الخاصة والحساسة وتعديلها ، وبالتالي يمكن أن يكون مزود خدمة قاعدة البيانات مخادعًا. آليات الأمان مطلوبة بالضرورة لحماية البيانات الحساسة الموجودة على السحابات العامة. على مستوى التطبيق ، يضمن الحل المقترح خصوصية وسرية البيانات الموجودة على السحابة. تم إجراء اختبارات مكثفة ، وكانت نتائج هذا البحث كما يلي: كشفت النتائج المسجلة عن اختلافات ذات دلالة إحصائية في النص العادي ومحتويات الوسائط المتعددة (أي الصوت والفيديو) مع قياس الوقت بالمللي ثانية لمجموعات البيانات الصغيرة والمتوسطة والكبيرة.

Battery Longevity and Its Predictors in Subcutaneous Implantable Cardioverter-Defibrillators (S-ICDs): A Mathematical Analysis Derived from a Large Dataset

Battery Longevity and Its Predictors in Subcutaneous Implantable Cardioverter-Defibrillators (S-ICDs): A Mathematical Analysis Derived from a Large Dataset

A hybrid constrained continuous optimization approach for optimal causal discovery from biological data.

Understanding causal effects is a fundamental goal of science and underpins our ability to make accurate predictions in unseen settings and conditions. While direct experimentation is the gold standard for measuring and validating causal effects, the field of causal graph theory offers a tantalizing alternative: extracting causal insights from observational data. Theoretical analysis has shown that this is indeed possible, given a large dataset and if certain conditions are met. However, biological datasets, frequently, do not meet such requirements but evaluation of causal discovery algorithms is typically performed on synthetic datasets, which they meet all requirements. Thus, real-life datasets are needed, in which the causal truth is reasonably known. In this work we first construct such a large-scale real-life dataset and then we perform on it a comprehensive benchmarking of various causal discovery methods. We find that the PC algorithm is particularly accurate at estimating causal structure, including the causal direction which is critical for biological applicability. However, PC does only produces cause-effect directionality, but not estimates of causal effects. We propose PC-NOTEARS (PCnt), a hybrid solution, which includes the PC output as an additional constraint inside the NOTEARS optimization. This approach combines PC algorithm's strengths in graph structure prediction with the NOTEARS continuous optimization to estimate causal effects accurately. PCnt achieved best aggregate performance across all structural and effect size metrics. https://github.com/zhu-yh1/PC-NOTEARS.

Javanese part-of-speech tagging using cross-lingual transfer learning

<span dir="ltr">Large datasets that are publicly available for POS tagging do not always exist </span><span dir="ltr">for some languages. </span><span dir="ltr">One of those languages is Javanese, a local language in </span><span dir="ltr">Indonesia, which is considered as a low-resource language. This research aims </span><span dir="ltr">to examine the effectiveness of cross-lingual transfer learning for Javanese POS </span><span dir="ltr">tagging by fine-tuning the state-of-the-art Transformer-based models (such as </span><span dir="ltr">IndoBERT, mBERT, and XLM-RoBERTa) using different kinds of source lan</span><span dir="ltr">guages that have a higher resource (such as Indonesian, English, Uyghur, Latin, </span><span dir="ltr">and Hungarian languages), and then fine-tuning it again using the Javanese lan</span><span dir="ltr">guage as the target language. We found that the models using cross-lingual trans</span><span dir="ltr">fer learning can increase the accuracy of the models without using cross-lingual </span><span dir="ltr">transfer learning by 14.3%–15.3% over LSTM-based models, and by 0.21%–</span><span dir="ltr">3.95% over Transformer-based models. Our results show that the most accurate </span><span dir="ltr">Javanese POS tagger model is XLM-RoBERTa that is fine-tuned in two stages </span><span dir="ltr">(the first one using Indonesian language as the source language, and the second </span><span dir="ltr">one using Javanese language as the target language), capable of achieving an </span><span dir="ltr">accuracy of 87.65%</span>

Extremely compact video representation for efficient near-duplicates detection

With the influx of online video uploads, a robust method for detecting video copies under various distortions is essential for copyright protection and search efficiency. We propose a compact video representation that uses a Siamese Neural Network for near-duplicate detection. This approach achieves up to 0.998 recall and 0.853 precision, even with distorted 56x56px miniatures. Consequently, we derive extremely compact video descriptors, facilitating video fragment retrieval in large datasets. Our method pre-selects frames from a video by identifying local maximums from the interframe differences curve, preserving characteristic sequence patterns even after extreme compression. Utilizing a simpler convolution-based model in the Siamese Neural Network, we improve results by up to 8% over VGG-16, with a 1.7-fold reduction in inference time. With compact descriptors of 1.875 kB, our models outperform others by more than two times. Additionally, we introduce a new dataset with dynamically changing scenes, enhancing its suitability for near-duplicate video detection.

Hybrid CNN-LSTM for Predicting Diabetes: A Review.

Diabetes is a common and deadly chronic disease caused by high blood glucose levels that can cause heart problems, neurological damage, and other illnesses. Through the early detection of diabetes, patients can live healthier lives. Many machine learning and deep learning techniques have been applied for noninvasive diabetes prediction. The results of some studies have shown that the CNN-LSTM method, a combination of CNN and LSTM, has good performance for predicting diabetes compared to other deep learning methods. This paper reviews CNN-LSTM-based studies for diabetes prediction. In the CNNLSTM model, the CNN includes convolution and max pooling layers and is applied for feature extraction. The output of the max-pooling layer was fed into the LSTM layer for classification. The CNN-LSTM model performed well in extracting hidden features and correlations between physiological variables. Thus, it can be used to predict diabetes. The CNNLSTM model, like other deep neural network architectures, faces challenges such as training on large datasets and biological factors. Using large datasets can further improve the accuracy of detection. The CNN-LSTM model is a promising method for diabetes prediction, and compared with other deep-learning models, it is a reliable method.

A Survey on Progressive Visualization.

Currently, growing data sources and long-running algorithms impede user attention and interaction with visual analytics applications. Progressive visualization (PV) and visual analytics (PVA) alleviate this problem by allowing immediate feedback and interaction with large datasets and complex computations, avoiding waiting for complete results by using partial results improving with time. Yet, creating a progressive visualization requires more effort than a regular visualization but also opens up new possibilities, such as steering the computations towards more relevant parts of the data, thus saving computational resources. However, there is currently no comprehensive overview of the design space for progressive visualization systems. We surveyed the related work of PV and derived a new taxonomy for progressive visualizations by systematically categorizing all PV publications that included visualizations with progressive features. Progressive visualizations can be categorized by well-known visualization taxonomies, but we also found that progressive visualizations can be distinguished by the way they manage their data processing, data domain, and visual update. Furthermore, we identified key properties such as uncertainty, steering, visual stability, and real-time processing that are significantly different with progressive applications. We also collected evaluation methodologies reported by the publications and conclude with statistical findings, research gaps, and open challenges.

Re-identification from histopathology images

In numerous studies, deep learning algorithms have proven their potential for the analysis of histopathology images, for example, for revealing the subtypes of tumors or the primary origin of metastases. These models require large datasets for training, which must be anonymized to prevent possible patient identity leaks. This study demonstrates that even relatively simple deep learning algorithms can re-identify patients in large histopathology datasets with substantial accuracy. In addition, we compared a comprehensive set of state-of-the-art whole slide image classifiers and feature extractors for the given task. We evaluated our algorithms on two TCIA datasets including lung squamous cell carcinoma (LSCC) and lung adenocarcinoma (LUAD). We also demonstrate the algorithm’s performance on an in-house dataset of meningioma tissue. We predicted the source patient of a slide with F1 scores of up to 80.1% and 77.19% on the LSCC and LUAD datasets, respectively, and with 77.09% on our meningioma dataset. Based on our findings, we formulated a risk assessment scheme to estimate the risk to the patient’s privacy prior to publication.

Factors influencing craniofaciadental changes in skeletal Class III orthognathic surgery by using machine learning

Background/purposeIn skeletal Class III patients, treatment options include camouflage and orthognathic surgery. This study used machine learning to investigate factors influencing dental, skeletal, and soft tissue morphological changes following skeletal Class III orthognathic surgery. Materials and methodsA retrospective analysis was conducted at Taipei Medical University Hospital. The study analyzed the lateral cephalometric radiographs of 58 patients with skeletal Class III who underwent orthognathic surgery. Web-based cephalometric software was used to obtain cephalometric tracing measurements, including dental, skeletal, and soft tissue parameters at pretreatment (T0) and posttreatment (T1), and assess postsurgical changes (T1−T0). Conventional statistical models were used for data analysis, followed by the application of machine learning–based random forest regression to identify influencing factors, as characterized by the feature of importance (FI). ResultsAll cephalometric variables except SNA, A to NP, overbite, and lower lip to E-plane differed significantly between T0 and T1. ANB was significantly influenced by surgery type (P = 0.045), whereas IMPA and lower lip to E-plane were significantly influenced by sex (IMPA P = 0.029; lower lip to E-plane P = 0.033). According to machine learning results on the influence of pretreatment conditions, overjet was a key factor influencing several dependent variables, namely, changes in ANB (FI = 0.226), B to N-Perp (FH) (FI = 0.259), and Pog to N-Perp (FH) (FI = 0.257). ConclusionMachine learning revealed the overjet plays a dominant role in several dependent variables, including changes in ANB, B to N-Perp (FH), and Pog to N-Perp (FH). Future studies should use a larger dataset and three-dimensional data.

Preliminary findings of a ‘test bundle’ to accelerate the diagnosis of MS and NMOSD following Optic Neuritis

No study has investigated the length of time it takes to diagnose multiple sclerosis (MS) or neuromyelitis optic spectrum disorder (NMOSD, aquaporin 4 antibody disease or myelin oligodendrocyte glycoprotein antibody disease, MOGAD) following the onset of de novo optic neuritis (ON). Minimizing the time between ON and downstream diagnoses needs urgency since early diagnosis equals early treatment. The time elapsed from ON to a subsequent diagnosis of MS/NMOSD was estimated through analysis of retrospective data collected from the Axon Registry (AR) of the American Academy of Neurology (AAN) and from the University of Kentucky (UK), Lexington. The time to diagnose MS/NMOSD was arbitrarily set as occurring < 6 months (early) or > 6 months (delayed) following ON. Data was collected between 2007-2021 (AR) and 2012 to 2022, for UK, respectively.Of the 4015 ON patients from the AR dataset, 1069 (26.6%) were diagnosed with MS, with 857 (80.2%) diagnosed < 6 months (early) and 212 (19.8%) diagnosed after > 6 months (delayed). Secondly, 420/4015 (10.4%) were diagnosed with NMOSD (either MOGAD or AQP4 antibody disease), of which 340/420 (80.9%) were diagnosed < 6 months (early) and 80/420 (19%) diagnosed > 6 months (delayed). In the UK dataset, a total of 90/1464 individuals (6.14%) were diagnosed with MS; of these, 69 patients (76.7%) were diagnosed at < 6 months (early) and included a sub-group of 25 (27.8%) diagnosed < 4 weeks; 21 (23.3%) were diagnosed > 6 months (delayed) following ON. In either dataset (AR or UK, between 20% - 23% of MS diagnoses occurred > 6 months (delayed) after a diagnosis of ON. An accelerated diagnosis (4 weeks or less) of MS/NMOSD following ON in the UK data suggests that it is possible to minimize the time to a downstream diagnosis if a ‘test bundle’ of MRI of orbits, brain, C-spine, cerebrospinal fluid (CSF) analysis, and serum testing for NMOSD is used. Additional studies using prospective, larger datasets are required to confirm our findings.

Conceptual structure of emotions.

Theories of semantic organization have historically prioritized investigation of concrete concepts pertaining to inanimate objects and natural kinds. As a result, accounts of the conceptual representation of emotions have almost exclusively focused on their juxtaposition with concrete concepts. The present study aims to fill this gap by deriving a large set of normative feature data for emotion concepts and assessing similarities and differences between the featural representation of emotion, nonemotion abstract, and concrete concepts. We hypothesized that differences between the experience of emotions (e.g., happiness and sadness) and the experience of other abstract concepts (e.g., equality and tyranny), specifically regarding the relative importance of interoceptive states, might drive distinctions in the dimensions along which emotion concepts are represented. We also predicted, based on constructionist views of emotion, that emotion concepts might demonstrate more variability in their representation than concrete and other abstract concepts. Participants listed features which we coded into discrete categories and contrasted the feature distributions across conceptual types. Analyses revealed statistically significant differences in the distribution of features among the category types by condition. We also examined variability in the features generated, finding that, contrary to expectation, emotion concepts were associated with less variability. Our results reflect subtle differences between the structure of emotion concepts and the structure of, not only concrete concepts, but also other abstract concepts. We interpret these findings in the context of our sample, which was restricted to native English speakers, and discuss the importance of validating these findings across speakers of different languages. (PsycInfo Database Record (c) 2024 APA, all rights reserved).

A New Method for the Detection of Siliceous Microfossils on Sediment Microscope Slides Using Convolutional Neural Networks

AbstractDiatom communities preserved in sediment samples are valuable indicators for understanding the past and present dynamics of phytoplankton communities, and their response to environmental changes. These studies are traditionally achieved by counting methods using optical microscopy, a time‐consuming process that requires taxonomic expertise. With the advent of automated image acquisition workflows, large image data sets can now be acquired, but require efficient preprocessing methods. Detecting diatom frustules on microscope images is a challenge due to their low relief, diverse shapes, and tendency to aggregate, which prevent the use of traditional thresholding techniques. Deep learning algorithms have the potential to resolve these challenges, more particularly for the task of object detection. Here we explore the use of a Faster Region‐based Convolutional Neural Network model to detect siliceous biominerals, including diatoms, in microscope images of a sediment trap series from the Mediterranean Sea. Our workflow demonstrates promising results, achieving a precision score of 0.72 and a recall score of 0.74 when applied to a test set of Mediterranean diatom images. Our model performance decreases when used to detect fragments of these microfossils; it also decreases when particles are aggregated or when images are out of focus. Microfossil detection remains high when the model is used on a microscope image set of sediments from a different oceanic basin, demonstrating its potential for application in a wide range of contemporary and paleoenvironmental studies. This automated method provides a valuable tool for analyzing complex samples, particularly for rare species under‐represented in training data sets.

Disparities in Dual-energy X-ray Absorptiometry Scan Utilization Across Race/Ethnic Groups Before and After Hip Fractures

Background: Geriatric hip fractures are common and important sentinel events regarding bone health. Although dual x-ray absorptiometry (DEXA) scans are a standard method for determining bone density, differences in use among various race/ethnic groups around the time of hip fracture may reveal disparities within the healthcare system. Methods: The 2014 to 2016 Medicare Standard Analytic Files PearlDiver data set was used to identify geriatric patients sustaining hip fracture. From that cohort, those who had a DEXA scan before or after their fracture were defined. For the defined cohorts, patient age, sex, Elixhauser Comorbidity Index, race/ethnicity, and income (based on zip code) were defined and compared with univariate and multivariate analyses. Results: Of 58,099 hip fracture patients, only 19.8% had had a DEXA scan before fracture and 3.9% of the remaining group had the DEXA scan after fracture. Of the hip fracture population, 91.0% identified as White and 9.0% as non-White (Native American, Black, Hispanic, Asian, or Other). Before hip fracture, controlling for other variables and compared with White patients, all non-White categories were at lesser odds of having had the DEXA scan. After hip fracture, Black, Hispanic, and other patients were also at lesser odds of having the DEXA scan. Discussion: Using a large Medicare data set, controlling for patient age, sex, Elixhauser Comorbidity Index, and income marker, this study revealed disparities in DEXA scan utilization across race/ethnic groups before and after presenting with a hip fragility fracture. Identification of such disparities highlights the needs for improved medical access and care for this at-risk hip fracture population.

Visual speech recognition using compact hypercomplex neural networks

Recent progress in visual speech recognition systems due to advances in deep learning and large-scale public datasets has led to impressive performance compared to human professionals. The potential applications of these systems in real-life scenarios are numerous and can greatly benefit the lives of many individuals. However, most of these systems are not designed with practicality in mind, requiring large-size models and powerful hardware, factors which limit their applicability in resource-constrained environments and other real-world tasks. In addition, few works focus on developing lightweight systems that can be deployed in such conditions. Considering these issues, we propose compact networks that take advantage of hypercomplex layers that utilize a sum of Kronecker products to reduce overall parameter demands and model sizes. We train and evaluate our proposed models on the largest public dataset for single word speech recognition for English. Our experiments show that high compression rates are achievable with a minimal accuracy drop, indicating the method’s potential for practical applications in lower-resource environments. Code and models are available at https://github.com/jpanagos/vsr_phm.

Generating Synthetic Data for Medical Imaging.

Artificial intelligence (AI) models for medical imaging tasks, such as classification or segmentation, require large and diverse datasets of images. However, due to privacy and ethical issues, as well as data sharing infrastructure barriers, these datasets are scarce and difficult to assemble. Synthetic medical imaging data generated by AI from existing data could address this challenge by augmenting and anonymizing real imaging data. In addition, synthetic data enable new applications, including modality translation, contrast synthesis, and professional training for radiologists. However, the use of synthetic data also poses technical and ethical challenges. These challenges include ensuring the realism and diversity of the synthesized images while keeping data unidentifiable, evaluating the performance and generalizability of models trained on synthetic data, and high computational costs. Since existing regulations are not sufficient to guarantee the safe and ethical use of synthetic images, it becomes evident that updated laws and more rigorous oversight are needed. Regulatory bodies, physicians, and AI developers should collaborate to develop, maintain, and continually refine best practices for synthetic data. This review aims to provide an overview of the current knowledge of synthetic data in medical imaging and highlights current key challenges in the field to guide future research and development.

Higher Order Polynomial Transformer for Fine-Grained Freezing of Gait Detection.

Freezing of Gait (FoG) is a common symptom of Parkinson's disease (PD), manifesting as a brief, episodic absence, or marked reduction in walking, despite a patient's intention to move. Clinical assessment of FoG events from manual observations by experts is both time-consuming and highly subjective. Therefore, machine learning-based FoG identification methods would be desirable. In this article, we address this task as a fine-grained human action recognition problem based on vision inputs. A novel deep learning architecture, namely, higher order polynomial transformer (HP-Transformer), is proposed to incorporate pose and appearance feature sequences to formulate fine-grained FoG patterns. In particular, a higher order self-attention mechanism is proposed based on higher order polynomials. To this end, linear, bilinear, and trilinear transformers are formulated in pursuit of discriminative fine-grained representations. These representations are treated as multiple streams and further fused by a cross-order fusion strategy for FoG detection. Comprehensive experiments on a large in-house dataset collected during clinical assessments demonstrate the effectiveness of the proposed method, and an area under the receiver operating characteristic (ROC) curve (AUC) of 0.92 is achieved for detecting FoG.

Enhanced Early Detection of Thyroid Abnormalities using a Hybrid Deep Learning Model: A Sequential CNN and K-Means Clustering Approach

The thyroid gland, often referred to as the butterfly gland due to its shape, is located in the neck and plays a crucial role in regulating metabolism. It is susceptible to various health conditions, including hypothyroidism, hyperthyroidism, thyroid cancer, and thyroid nodules. Early detection of these conditions is essential for accurate diagnosis and effective treatment. Detecting thyroid nodules using machine learning and deep learning techniques presents a challenging yet promising research avenue. The choice of model depends on the characteristics of the patient's thyroid data, the dataset size, and the available computational resources. Hybrid models can be employed to handle complex data more effectively. In this study, a sequential Convolutional Neural Network (CNN) model was developed due to its capability to automate feature extraction and focus on Regions-of-Interest (ROIs) for detecting thyroid abnormalities. The proposed model achieved an accuracy of 81.5%, with a precision of 97.4% and a sensitivity of 83.1%, indicating its robustness in classifying images as benign or malignant. The confusion matrix provided further performance insights. Data segmentation was enhanced using K-means clustering for its scalability and efficiency in processing large medical image datasets. Compared to traditional models, the proposed hybrid approach demonstrated a significant improvement in diagnostic accuracy and precision, achieving performance gains of approximately 15-20% over baseline methods. These advancements underscore the potential of integrating machine learning and deep learning in medical diagnostics, paving the way for more reliable and efficient diagnostic tools for healthcare professionals.

Graph-Based Unsupervised Feature Selection for Interval-Valued Information System.

Feature selection has become one of the hot research topics in the era of big data. At the same time, as an extension of single-valued data, interval-valued data with its inherent uncertainty tend to be more applicable than single-valued data in some fields for characterizing inaccurate and ambiguous information, such as medical test results and qualified product indicators. However, there are relatively few studies on unsupervised attribute reduction for interval-valued information systems (IVISs), and it remains to be studied how to effectively control the dramatic increase of time cost in feature selection of large sample datasets. For these reasons, we propose a feature selection method for IVISs based on graph theory. Then, the model complexity could be greatly reduced after we utilize the properties of the matrix power series to optimize the calculation of the original model. Our approach can be divided into two steps. The first is feature ranking with the principles of relevance and nonredundancy, and the second is selecting top-ranked attributes when the number of features to keep is fixed as a priori. In this article, experiments are performed on 14 public datasets and the corresponding seven comparative algorithms. The results of the experiments verify that our algorithm is effective and efficient for feature selection in IVISs.

SHINE: A Scalable Heterogeneous Inductive Graph Neural Network for Large Imbalanced Datasets

SHINE: A Scalable Heterogeneous Inductive Graph Neural Network for Large Imbalanced Datasets

Automated detection of Bornean white-bearded gibbon (Hylobates albibarbis) vocalizations using an open-source framework for deep learning.

Passive acoustic monitoring is a promising tool for monitoring at-risk populations of vocal species, yet, extracting relevant information from large acoustic datasets can be time-consuming, creating a bottleneck at the point of analysis. To address this, an open-source framework for deep learning in bioacoustics to automatically detect Bornean white-bearded gibbon (Hylobates albibarbis) "great call" vocalizations in a long-term acoustic dataset from a rainforest location in Borneo is adapted. The steps involved in developing this solution are described, including collecting audio recordings, developing training and testing datasets, training neural network models, and evaluating model performance. The best model performed at a satisfactory level (F score = 0.87), identifying 98% of the highest-quality calls from 90 h of manually annotated audio recordings and greatly reduced analysis times when compared to a human observer. No significant difference was found in the temporal distribution of great call detections between the manual annotations and the model's output. Future work should seek to apply this model to long-term acoustic datasets to understand spatiotemporal variations in H. albibarbis' calling activity. Overall, a roadmap is presented for applying deep learning to identify the vocalizations of species of interest, which can be adapted for monitoring other endangered vocalizing species.