Volume Of Data Research Articles

Deep learning for economic transformation: a parametric review

Deep learning (DL) is increasingly recognized for its effectiveness in analyzing and forecasting complex economic systems, particularly in the context of Pakistan's evolving economy. This paper investigates DL's transformative role in managing and interpreting increasing volumes of intricate economic data, leading to more nuanced insights. DL models show a marked improvement in predictive accuracy and depth over traditional methods across various economic domains and policymaking scenarios. Applications include demand forecasting, risk evaluation, market trend analysis, and resource allocation optimization. These processes utilize extensive datasets and advanced algorithms to identify patterns that traditional methods cannot detect. Nonetheless, DL's broader application in economic research faces challenges like limited data availability, complexity of economic interactions, interpretability of model outputs, and significant computational power requirements. The paper outlines strategies to overcome these barriers, such as enhancing model interpretability, employing federated learning for better data privacy, and integrating behavioral and social economic theories. It concludes by stressing the importance of targeted research and ethical considerations in maximizing DL's impact on economic insights and innovation, particularly in Pakistan and globally.

A novel compression methodology for medical images using deep learning for high-speed transmission

Medical imaging is a rapidly growing field having a high impact on the early detection, diagnosis and surgical planning of diseases. Several imaging techniques such as computed tomography (CT), magnetic resonance imaging (MRI) and ultrasound (US) imaging generate a higher volume of data, necessitating additional storage and communication requirements. Hence, image compression is utilized in medical field to reduce redundancy and alleviate memory and bandwidth issues. This paper presents a novel deep learning-based compression method to reduce the size of medical images. This method employs a deep convolutional neural network for learning compact representations of medical images, then coded by a Huffman encoder. The compression process is reversed to reconstruct the original image. Several tests are conducted to compare the results with other wellknown compression methods. The proposed model achieved a mean peak signal-to-noise ratio (PSNR) of 42.82 dB with storage space saving (SSS) of 96.15% for CT, 43.88 dB with SSS of 96.25% for MRI, 46.29 dB with SSS of 96.07% for US and 43.51 dB with SSS of 96.95% for X-ray images. The findings showed that the proposed compression technique could greatly compress the image size, saving storage space, facilitating better transmission and preserving critical diagnostic information.

Authenticated Range Querying of Historical Blockchain Healthcare Data Using Authenticated Multi-Version Index

With growing adoption of blockchain in established and emerging applications, there is an increasing need to support efficient ad hoc querying of authenticated historical data. This is especially true in fields such as healthcare to meet the rigorous security and regulatory requirements of ever-expanding digital health platforms. Existing blockchain systems, however, offer little or no support for querying capabilities over historical data. Although a full blockchain archive node can be used to maintain historical records of all executed transactions on the chain, it is not scalable when dealing with large volumes of data. Moreover, such ‘offline’ historical data lack tamper evidence support. To address these issues, we introduce an authenticated index structure called Authenticated Multi-Version Skip List (AMVSL), designed to support a rich set of query features over historical blockchain data. We further present three range queries: SVRK, MVRK, and MVAK, which offer querying over a range of keys and a range of versions. Our experimental evaluation of two healthcare-inspired examples demonstrates that AMVSL efficiently supports these queries and can achieve performance that is several orders of magnitude faster than existing authenticated data structures.

High-accuracy data readout in multi-dimensional optical data storage using convolutional neural networks

The escalating global volume of digital data poses a critical challenge for storage solutions. Optical data storage techniques have garnered lots of interests due to their excellent offline storage capabilities, including low energy consumption, high capacity, and long lifespan. However, despite the focus on data recording, minimal attention has been dedicated to the readout aspect. This study introduced femtosecond laser direct writing to perform multi-dimensional optical data storage and employed a specialized convolutional neural network to enhance voxel readout accuracy. The proposed network architecture achieved a remarkable voxel readout accuracy of 98.83%, surpassing support vector machine method (90.07%) and LeNet (96.85%). Furthermore, the proposed method yielded a substantial increase in actual user capacity, outperforming traditional approaches and presenting a novel solution for addressing readout challenges in multi-dimensional optical data storage.

Identifying low-dimensional trajectories of mechanically-ventilated patient systems: Empirical phenotypes of joint patient+care processes to enhance temporal analysis in ARDS research.

Refined management of mechanically ventilation is an obvious target for improving patient outcomes, but is impeded by the nature of data for study and hypothesis generation. The connections between clinical outcomes and temporal development of iatrogenic injuries current lung-protective ventilator settings remain poorly understood. Analysis of lung-ventilator system (LVS) evolution at relevant timescales is frustrated by data volume and multiple sources of heterogeneity. This work motivates, presents, and validates a computational pipeline for resolving LVS systems into the joint evolution of data-conditioned model parameters and ventilator information. Applied to individuals, the workflow yields a concise low-dimensional representation of LVS behavior expressed in phenotypic breath waveforms suitable for analysis. The effectiveness of this approach is demonstrated through application to multi-day observational series of 35 patients. Individual patient analyses reveal multiple types of patient-oriented dynamics and breath behavior to expose the complexity of LVS evolution; less than 10% of phenotype changes related to ventilator settings changes. Dynamics are shown to including both stable and unstable phenotype transitions as well as both discrete and continuous changes unrelated to ventilator settings. At a cohort scale, 721 phenotypes constructed from individual data are condensed into a set of 16 groups that empirically organize around certain settings (positive end-expository pressure and ventilator mode) and structurally similar pressure-volume loop characterizations. Individual and cohort scale phenotypes, which may be refined by hypothesis-specific constructions, provide a common framework for ongoing temporal analysis and investigation of LVS dynamics.

Multi-objective hybrid optimized task scheduling in cloud computing under big data perspective

The new and rising paradigm of cloud computing offers customers various possibilities of task computation based on their desires and choices. Customers receive services from cloud computing systems as a utility. Customers are enthusiastic about low-cost service availability and task completion times that are kept to be minimum. To achieve client fulfilment, the service provider must schedule the jobs to the right resources if the cloud server gets many user requests. The rapid growth in data volume necessitates petabytes processing of data each day. Unstructured, semi-structured, and structured data are all described in terms of their rapid growth and availability. In order to make correct and timely decisions, it must be processed appropriately. In this research, we present BWUJS (Black Widow Updated Jellyfish Search), a multi-objective hybrid optimization-based task scheduling algorithm. This work considers task generation from the Bigdata perspective. The clustering of tasks is performed via the Map Reduce framework with an Improved K-means clustering model. After task clustering, the task priority estimation is performed. Finally, the scheduling is performed via BWJSU based on certain constraints like priority, makespan, completion time, resource utilization, and degree of imbalance.

An interpretable ensemble structure with a non-iterative training algorithm to improve the predictive accuracy of healthcare data analysis

The modern development of healthcare is characterized by a set of large volumes of tabular data for monitoring and diagnosing the patient's condition. In addition, modern methods of data engineering allow the synthesizing of a large number of features from an image or signals, which are presented in tabular form. The possibility of high-precision and high-speed processing of such large volumes of medical data requires the use of artificial intelligence tools. A linear machine learning model cannot accurately analyze such data, and traditional bagging, boosting, or stacking ensembles typically require significant computing power and time to implement. In this paper, the authors proposed a method for the analysis of large sets of medical data, based on a designed linear ensemble method with a non-iterative learning algorithm. The basic node of the new ensemble is an extended-input SGTM neural-like structure, which provides high-speed data processing at each level of the ensemble. Increasing prediction accuracy is ensured by dividing the large dataset into parts, the analysis of which is carried out in each node of the ensemble structure and taking into account the output signal from the previous level of the ensemble as an additional attribute on the next one. Such a design of a new ensemble structure provides both a significant increase in the prediction accuracy for large sets of medical data analysis and a significant reduction in the duration of the training procedure. Experimental studies on a large medical dataset, as well as a comparison with existing machine learning methods, confirmed the high efficiency of using the developed ensemble structure when solving the prediction task.

Scaling neural machine translationto 200 languages.

The development of neural techniques has opened up new avenues for research in machine translation. Today, neural machine translation (NMT) systems can leverage highly multilingual capacities and even perform zero-shot translation, delivering promising results in terms of language coverage and quality. However, scaling quality NMT requires large volumes of parallel bilingual data, which are not equally available for the 7,000+ languages in the world1. Focusing on improving the translation qualities of a relatively small group of high-resource languages comes at the expense of directing research attention to low-resource languages, exacerbating digital inequities in the long run. To break this pattern, here we introduce No Language Left Behind-a single massively multilingual model that leverages transfer learning across languages. We developed a conditional computational model based on the Sparsely Gated Mixture of Experts architecture2-7, which we trained on data obtained with new mining techniques tailored for low-resource languages. Furthermore, we devised multiple architectural and training improvements to counteract overfitting while training on thousands of tasks. We evaluated the performance of our model over 40,000 translation directions using tools created specifically for this purpose-an automatic benchmark (FLORES-200), a human evaluation metric (XSTS) and a toxicity detector that covers every language in our model. Compared with the previous state-of-the-art models, our model achieves an average of 44% improvement in translation quality as measured by BLEU. By demonstrating how to scale NMT to 200 languages and making all contributions in this effort freely available for non-commercial use, our work lays important groundwork for the development of a universal translation system.

Congruential Summation-Triggered Identification of FIR Systems under Binary Observations and Uncertain Communications

With the advancement of network technology, there has been an increase in the volume of data being transmitted across networks. Due to the bandwidth limitation of communication channels, data often need to be quantized or event-triggered mechanisms are introduced to conserve communication resources. On the other hand, network uncertainty can lead to data loss and destroy data integrity. This paper investigates the identification of finite impulse response (FIR) systems under the framework of stochastic noise and the combined effects of the event-triggered mechanism and uncertain communications. The study provides a reference for the application of remote system identification under transmission-constrained and packet loss scenarios. First, a congruential summation-triggered communication scheme (CSTCS) is introduced to lower the communication rate. Then, parameter estimation algorithms are designed for scenarios with known and unknown packet loss probabilities, respectively, and their strong convergence is proved. Furthermore, an approximate expression for the convergence rate is obtained by data fitting under the condition of uncertain packet loss probability, treating the trade-off between convergence performance and communication resource usage as a constrained optimization problem. Finally, the rationality and correctness of the algorithm are verified by numerical simulations.

Machine learning with taxonomic family delimitation aids in the classification of ephemeral beaked whale events in passive acoustic monitoring.

Passive acoustic monitoring is an essential tool for studying beaked whale populations. This approach can monitor elusive and pelagic species, but the volume of data it generates has overwhelmed researchers' ability to quantify species occurrence for effective conservation and management efforts. Automation of data processing is crucial, and machine learning algorithms can rapidly identify species using their sounds. Beaked whale acoustic events, often infrequent and ephemeral, can be missed when co-occurring with signals of more abundant, and acoustically active species that dominate acoustic recordings. Prior efforts on large-scale classification of beaked whale signals with deep neural networks (DNNs) have approached the class as one of many classes, including other odontocete species and anthropogenic signals. That approach tends to miss ephemeral events in favor of more common and dominant classes. Here, we describe a DNN method for improved classification of beaked whale species using an extensive dataset from the western North Atlantic. We demonstrate that by training a DNN to focus on the taxonomic family of beaked whales, ephemeral events were correctly and efficiently identified to species, even with few echolocation clicks. By retrieving ephemeral events, this method can support improved estimation of beaked whale occurrence in regions of high odontocete acoustic activity.

Evasive attacks against autoencoder-based cyberattack detection systems in power systems

The digital transformation process of power systems towards smart grids is resulting in improved reliability, efficiency and situational awareness at the expense of increased cybersecurity vulnerabilities. Given the availability of large volumes of smart grid data, machine learning-based methods are considered an effective way to improve cybersecurity posture. Despite the unquestionable merits of machine learning approaches for cybersecurity enhancement, they represent a component of the cyberattack surface that is vulnerable, in particular, to adversarial attacks. In this paper, we examine the robustness of autoencoder-based cyberattack detection systems in smart grids to adversarial attacks. A novel iterative-based method is first proposed to craft adversarial attack samples. Then, it is demonstrated that an attacker with white-box access to the autoencoder-based cyberattack detection systems can successfully craft evasive samples using the proposed method. The results indicate that naive initial adversarial seeds cannot be employed to craft successful adversarial attacks shedding insight on the complexity of designing adversarial attacks against autoencoder-based cyberattack detection systems in smart grids.

Near-pair patch generative adversarial network for data augmentation of focal pathology object detection models.

The limited volume of medical training data remains one of the leading challenges for machine learning for diagnostic applications. Object detectors that identify and localize pathologies require training with a large volume of labeled images, which are often expensive and time-consuming to curate. To reduce this challenge, we present a method to support distant supervision of object detectors through generation of synthetic pathology-present labeled images. Our method employs the previously proposed cyclic generative adversarial network (cycleGAN) with two key innovations: (1)use of "near-pair" pathology-present regions and pathology-absent regions from similar locations in the same subject for training and (2)the addition of a realism metric (Fréchet inception distance) to the generator loss term. We trained and tested this method with 2800 fracture-present and 2800 fracture-absent image patches from 704 unique pediatric chest radiographs. The trained model was then used to generate synthetic pathology-present images with exact knowledge of location (labels) of the pathology. These synthetic images provided an augmented training set for an object detector. In an observer study, four pediatric radiologists used a five-point Likert scale indicating the likelihood of a real fracture (1 = definitely not a fracture and 5 = definitely a fracture) to grade a set of real fracture-absent, real fracture-present, and synthetic fracture-present images. The real fracture-absent images scored , real fracture-present images , and synthetic fracture-present images . An object detector model (YOLOv5) trained on a mix of 500 real and 500 synthetic radiographs performed with a recall of and an score of . In comparison, when trained on only 500 real radiographs, the recall and score were and , respectively. Our proposed method generates visually realistic pathology and that provided improved object detector performance for the task of rib fracture detection.

Bayesian network structure learning with a new ensemble weights and edge constraints setting mechanism

AbstractBayesian networks (BNs) are highly effective in handling uncertain problems, which can assist in decision-making by reasoning with limited and incomplete information. Learning a faithful directed acyclic graph (DAG) from a large number of complex samples of a joint distribution is currently a challenging combinatorial problem. Due to the growing volume and complexity of data, some Bayesian structure learning algorithms are ineffective and lack the necessary precision to meet the required needs. In this paper, we propose a new PCCL-CC algorithm. To ensure the accuracy of the network structure, we introduce the new ensemble weights and edge constraints setting mechanism. In this mechanism, we employ a method that estimates the interaction between network nodes from multiple perspectives and divides the learning process into multiple stages. We utilize an asymmetric weighted ensemble method and adaptively adjust the network structure. Additionally, we propose a causal discovery method that effectively utilizes the causal relationships among data samples to correct the network structure and mitigate the influence of Markov equivalence classes (MEC). Experimental results on real datasets demonstrate that our approach outperforms state-of-the-art methods.

Fostering the Development of Earth Data Science Skills in a Diverse Community of Online Learners: A Case Study of the Earth Data Science Corps

Today’s data-driven world requires earth and environmental scientists to have skills at the intersection of domain and data science. These skills are imperative to harness information contained in a growing volume of complex data to solve the world's most pressing environmental challenges. Despite the importance of these skills, Earth and Environmental Data Science (EDS) training is not equally accessible, contributing to a lack of diversity in the field. This creates a critical need for EDS training opportunities designed specifically for underrepresented groups. In response, we developed the Earth Data Science Corps (EDSC) which couples a paid internship for undergraduate students with faculty training to build capacity to teach and learn EDS using Python at smaller Minority Serving Institutions. EDSC faculty participants are further empowered to teach these skills at their home institutions which scales the program beyond the training lead by our team. Using a Rasch modeling approach, we found that participating in the EDSC program had a significant impact on undergraduate learners’ comfort and confidence with technical and non-technical data science skills, as well as their science identity and sense of belonging in science, two critical aspects of recruiting and retaining members of underrepresented groups in STEM.

Subdata selection for big data regression: an improved approach

In the big data era researchers face a series of problems. Even standard approaches/methodologies, like linear regression, can be difficult or problematic with huge volumes of data. Traditional approaches for regression in big datasets may suffer due to the large sample size, since they involve inverting huge data matrices or even because the data cannot fit to the memory. Proposed approaches are based on selecting representative subdata to run the regression. Existing approaches select the subdata using information criteria and/or properties from orthogonal arrays. In the present paper we improve existing algorithms providing a new algorithm that is based on D-optimality approach. We provide simulation evidence for its performance.Evidence about the parameters of the proposed algorithm is also provided in order to clarify the trade-offs between execution time and information gain. Real data applications are also provided.

Experimental demonstration of positioning the cooperation terminal for underwater wireless optical communication based on visual navigation

Underwater wireless optical communication (UWOC) is a useful way to transmit a large volume of data in ocean engineering. In application, one of the UWOC terminals is usually carried on an underwater robot to actively adjust its orientation and position to establish an optical link, which requires the mobile terminal to locate the cooperation partner. At a short communication distance, visual navigation is a preferred method to measure the position. In this method, a camera is installed on the mobile terminal while several light-emitting diodes (LEDs) are in the cooperation one. In the image of the camera, by capturing the pattern formed of LEDs light spots, the relative position and orientation between terminals could be calculated. However, in a UWOC system, visual navigation is interfered with by the UWOC transmitter since it forms an additional light spot in the camera’s image. To solve this issue, we present a UWOC-compatible visual navigation method, in which the UWOC light spot is distinguished with the hue, saturation, and value (HSV) color model. Then, we experimentally demonstrate the effectiveness of the method in a pool, applying signals with different bitrates and power on the transmitter. The results show that, while the distance between terminals is within 350 cm and the yaw angle is within 5°, the measured errors are within 1.77 cm and 0.92°, respectively, which is accurate enough for most UWOC applications. The method presented in this paper is simple, pragmatic, and useful for establishing a UWOC link.

Whole-Genome Alignment: Methods, Challenges, and Future Directions

Whole-genome alignment (WGA) is a critical process in comparative genomics, facilitating the detection of genetic variants and aiding our understanding of evolution. This paper offers a detailed overview and categorization of WGA techniques, encompassing suffix tree-based, hash-based, anchor-based, and graph-based methods. It elaborates on the algorithmic properties of these tools, focusing on performance and methodological aspects. This paper underscores the latest progress in WGA, emphasizing the increasing capacity to manage the growing intricacy and volume of genomic data. However, the field still grapples with computational and biological hurdles affecting the precision and speed of WGA. We explore these challenges and potential future solutions. This paper aims to provide a comprehensive resource for researchers, deepening our understanding of WGA tools and their applications, constraints, and prospects.

INTEGRATING MACHINE LEARNING AND BIG DATA ANALYTICS FOR REAL-TIME DISEASE DETECTION IN SMART HEALTHCARE SYSTEMS

The integration of machine learning (ML) and big data analytics within smart healthcare systems represents a transformative advancement in medical services, emphasizing efficiency, accuracy, and patient-centered care. This paper investigates the application of these advanced technologies in real-time disease detection, showcasing their potential to revolutionize healthcare delivery. Smart healthcare systems leverage a multitude of technological components, including Internet of Things (IoT) devices, sensors, and artificial intelligence (AI), to enable continuous monitoring and diagnostics. This real-time monitoring facilitates prompt interventions and treatment adjustments, which is particularly advantageous for managing chronic conditions and acute illnesses where timely responses are critical to improving patient outcomes. Despite the evident benefits, traditional healthcare infrastructures face significant challenges such as delays in diagnosis due to manual processes, inefficient data handling resulting in data silos, and limited interoperability between different healthcare providers, leading to worsened health outcomes and increased healthcare costs. The integration of ML and big data analytics offers promising solutions to these challenges. ML algorithms can process vast amounts of healthcare data to identify patterns and predict outcomes with high accuracy, such as recognizing early signs of diseases like cancer or diabetes from medical images or electronic health records (EHRs). Big data analytics complements ML by providing the necessary infrastructure to handle and process large volumes of health data, enabling the collection, storage, and analysis of structured data from EHRs, unstructured data from clinical notes, and real-time data from wearable devices. By integrating these technologies, healthcare providers can gain deeper insights into patient health trends and outcomes, leading to more informed decision-making and better patient management. This study employs a qualitative research design, focusing on five genuine case studies: the Mayo Clinic's predictive analytics for heart disease, Cleveland Clinic's use of ML for cancer diagnosis, Kaiser Permanente's diabetes management program, Johns Hopkins Hospital's sepsis detection system, and Mount Sinai Health System's genomic data analysis. Each case study is chosen for its relevance and comprehensive data, detailing the specific healthcare environment and context. This paper interprets these findings in the broader context of smart healthcare systems and existing literature, emphasizing the importance of these technologies in modernizing healthcare and addressing inefficiencies. The challenges encountered during integration, such as data privacy concerns and interoperability issues, are examined along with implemented solutions.

Influencing Factors on Pupillary Light Responses as a Biomarker for Local Retinal Function in a Large Normative Cohort.

Investigating influencing factors on the pupillary light response (PLR) as a biomarker for local retinal function by providing epidemiological data of a large normative collective and to establish a normative database for the evaluation of chromatic pupil campimetry (CPC). Demographic and ophthalmologic characteristics were captured and PLR parameters of 150 healthy participants (94 women) aged 18 to 79 years (median = 46 years) were measured with L-cone- and rod-favoring CPC protocols. Linear-mixed effects models were performed to determine factors influencing the PLR and optical coherence tomography (OCT) data were correlated with the pupillary function volume. Relative maximal constriction amplitude (relMCA) and latency under L-cone- and rod-favoring stimulation were statistically significantly affected by the stimulus eccentricity (P < 0.0001, respectively). Iris color and gender did not affect relMCA or latency significantly; visual hemifield, season, and daytime showed only minor influence under few stimulus conditions. Age had a statistically significant effect on latency under rod-specific stimulation with a latency prolongation ≥60 years. Under photopic and scotopic conditions, baseline pupil diameter declined significantly with increasing age (P < 0.0001, respectively). Pupillary function volume and OCT data were not correlated relevantly. Stimulus eccentricity had the most relevant impact on relMCA and latency of the PLR during L-cone- and rod-favoring stimulation. Latency is prolonged ≥60 years under scotopic conditions. Considering the large study collective, a representative normative database for relMCA and latency as valid readout parameters for L-cone- and rod-favoring stimulation could be established. This further validates the usability of the PLR in CPC as a biomarker for local retinal function.

Prostate Health Index density aids the diagnosis of prostate cancer detected using magnetic resonance imaging targeted prostate biopsy in Taiwanese multicenter study.

Multiparametric magnetic resonance imaging (mpMRI) followed by MRI-targeted prostate biopsy is the current standard for diagnosing prostate cancer (PCa). However, studies evaluating the value of biomarkers, including prostate health index (PHI) and its derivatives using this method are limited. We aimed to investigate the efficacy of PHI density (PHID) in guiding MRI-targeted prostate biopsies to identify clinically significant prostate cancers (csPCa). The multicenter prospectively registered prostate biopsy database from three medical centers in Taiwan included patients with PHI and MRI targeted and/or systematic prostate biopsies. We assessed the required values of prostate-specific antigen (PSA), prostate volume, PHI, PHID, and Prostate Imaging Reporting & Data System (PI-RADS) score using multivariable analyses, receiver operating characteristic curve analysis, and decision curve analyses (DCA). csPCa was defined as the International Society of Urological Pathology Gleason group ≥2 PCa, with an emphasis on reducing unwarranted biopsies. The study cohort comprised 420 individuals. Diagnoses of PCa and csPCa were confirmed in 62.4% and 47.9% of the participants, respectively. The csPCa diagnosis rates were increased with increasing PI-RADS scores (20.5%, 44.2%, and 73.1% for scores 3, 4, and 5, respectively). Independent predictors for csPCa detection included PHI, prostate volume, and PI-RADS scores of 4 and 5 in multivariable analyses. The area under the curve (AUC) for csPCa of PHID (0.815) or PHI (0.788) was superior to that of PSA density (0.746) and PSA (0.635) in the entire cohort, and the superiority of PHID (0.758) was observed in PI-RADS 3 lesions. DCA revealed that PHID achieved the best net clinical benefit in PI-RADS 3-5 and 4/5 cases. Among PI-RADS 3 lesions, cutoff values of PHID 0.70 and 0.43 could eliminate 51.8% and 30.4% of omitted biopsies, respectively. PHI-derived biomarkers, including PHID, performed better than other PSA-derived biomarkers in diagnosing PCa in MRI detected lesions.