Deluge Of Data Research Articles

A sane approach to the high volume of alert transmissions in remote monitoring- turning of clinically non-relevant alerts decreases substantially workload

Abstract Background Remote monitoring (RM) offers a safe and effective method of monitoring patients with cardiac implantable electronic devices (CIEDs). The downside of RM is the data deluge of various transmissions, the majority of which are non-actionable. It has been suggested that optimizing alert transmissions could partly overcome this problem. Purpose The purpose of this study is to evaluate how the workload in RM can be safely decreased by thoroughly assessing the clinical relevance of each alert and deactivating non-relevant alerts. Methods Data on the number of alerts, scheduled and patient-initiated transmissions, as well as the causes and actions initiated by the transmissions, were systematically collected from the year 2023, during which the approach of actively deactivating clinically non-relevant alerts was conducted (A sane approach, Figure 1). The trend of alert transmissions and the proportion of actionable scheduled transmissions are presented. Results Overall, during the study period, 8182 transmissions were generated from 3732 followed CIEDs. Of these, 2306 were alert transmissions, and the rate of alerts decreased by 56% during the follow-up, from 0.07 to 0.04 per device per month. Additionally, our data shows that new alerts that have not occurred in the previous six months occurred on average at a rate of 0.03 per CIED per month, and this trend remained unchanged during the follow-up. Of the 3335 scheduled transmissions, 11% (364) were actionable, and both the number and proportion of actionable scheduled transmissions remained unchanged during the follow-up period. Interestingly, no alerts were triggered from 1124 (70%) of all patients but 88 (2%) of all CIEDs generated 30% of all alerts. Conclusions In this study, we demonstrate that RM workload can be decreased by actively evaluating the clinical relevance of each alert transmission. Our approach, where non-relevant alerts are turned off, likely does not impair patient safety and thus this practise enhance the RM.

A Cloud-Based Solution to a Radar Data Deluge

An open-science tool built to support NASA missions is making synthetic aperture radar, once the domain only of subject matter experts, more accessible for nonspecialists and real-world applications.

Energy Conscious Squirrel Search based Task Scheduling Mechanism in Fog Environment

ABSTRACTThe swift explosion of Internet of Things (IoT) devices in the past few years has resulted in a deluge of data that requires timely processing. However, transmitting such massive amounts of data in and out from cloud leads to high latency and network bandwidth. Consequently, the field of fog computing has turned out as a feasible platform for utilizing resources within the vicinity of IoT devices for providing services in a timely manner. The resource constrained trait of fog nodes demands judicious management of resources in satisfying the requirements of IoT applications. This makes energy efficiency a core issue in fog networks. This article addresses the issue of energy efficiency by proposing an energy conscious squirrel search algorithm (EcSSA) for scheduling tasks in fog environment. A salient feature of EcSSA lies in the novel objective function that aims to optimize the energy consumption by minimizing the cumulative active time of all nodes in the network. Simulation studies conducted as part of this work demonstrate that the proposed approach significantly improves average energy consumption, average makespan, and carbon dioxide emission rate in comparison to the existing algorithms.

Scalable Bayesian uncertainty quantification with data-driven priors for radio interferometric imaging

Abstract Next-generation radio interferometers like the Square Kilometer Array have the potential to unlock scientific discoveries thanks to their unprecedented angular resolution and sensitivity. One key to unlocking their potential resides in handling the deluge and complexity of incoming data. This challenge requires building radio interferometric (RI) imaging methods that can cope with the massive data sizes and provide high-quality image reconstructions with uncertainty quantification (UQ). This work proposes a method coined QuantifAI to address UQ in RI imaging with data-driven (learned) priors for high-dimensional settings. Our model, rooted in the Bayesian framework, uses a physically motivated model for the likelihood. The model exploits a data-driven convex prior potential, which can encode complex information learned implicitly from simulations and guarantee the log-concavity of the posterior. We leverage probability concentration phenomena of high-dimensional log-concave posteriors to obtain information about the posterior, avoiding MCMC sampling techniques. We rely on convex optimisation methods to compute the MAP estimation, which is known to be faster and better scale with dimension than MCMC strategies. QuantifAI allows us to compute local credible intervals and perform hypothesis testing of structure on the reconstructed image. We propose a novel fast method to compute pixel-wise uncertainties at different scales, which uses 3 and 6 orders of magnitude less likelihood evaluations than other UQ methods like length of the credible intervals and Monte Carlo posterior sampling, respectively. We demonstrate our method by reconstructing RI images in a simulated setting and carrying out fast and scalable UQ, which we validate with MCMC sampling. Our method shows an improved image quality and more meaningful uncertainties than the benchmark method based on a sparsity-promoting prior. QuantifAI’s source code is available from https://github.com/astro-informatics/QuantifAI.

Formal Theories of Special Interest Influence

The impact of money on politics—whether through campaign finance, lobbying, or independent expenditure—raises key normative questions about democratic representation and accountability. In recent years there has been a deluge of new data allowing researchers to study money in politics from new and exciting perspectives. As a complement to this trend, there has also been a resurgence of interest in developing formal models to provide new theoretical insights that can help us understand how, why, and when money influences politics and policy. We review several major themes in this literature, focusing specifically on exchange-based models, informational models, and subsidy-based models. We compare and contrast the key contributions, and limitations, of each approach in understanding the role of lobbying and campaign finance in politics. We also discuss future avenues for research that incorporate aspects of each approach, which, we believe, will introduce new theoretical insights for understanding special interest influence.

Why Multimodal Data is Growing In Pharma

Technology advances in both R&D and patient care have created a deluge of data, including instrument and experimental data, -omics data, clinical study results, patient data, patent data, publication data, etc. Making connections between these different datasets is essential to developing impactful medicines and driving more personalized patient care.

The social media sentiment analysis framework: deep learning for sentiment analysis on social media

Researching public opinion can help us learn important facts. People may quickly and easily express their thoughts and feelings on any subject using social media, which creates a deluge of unorganized data. Sentiment analysis on social media platforms like Twitter and Facebook has developed into a potent tool for gathering insights into users' perspectives. However, difficulties in interpreting natural language limit the effectiveness and precision of sentiment analysis. This research focuses on developing a social media sentiment analysis (SMSA) framework, incorporating a custom-built emotion thesaurus to enhance the precision of sentiment analysis. It delves into the efficacy of various deep learning algorithms, under different parameter calibrations, for sentiment extraction from social media. The study distinguishes itself by its unique approach towards sentiment dictionary creation and its application to deep learning models. It contributes new insights into sentiment analysis, particularly in social media contexts, showcasing notable advancements over previous methodologies. The results demonstrate improved accuracy and deeper understanding of social media sentiment, opening avenues for future research and applications in diverse fields.

Application and Comparison of Machine Learning and Database-Based Methods in Taxonomic Classification of High-Throughput Sequencing Data.

The advent of high-throughput sequencing technologies has not only revolutionized the field of bioinformatics but has also heightened the demand for efficient taxonomic classification. Despite technological advancements, efficiently processing and analyzing the deluge of sequencing data for precise taxonomic classification remains a formidable challenge. Existing classification approaches primarily fall into two categories, database-based methods and machine learning methods, each presenting its own set of challenges and advantages. On this basis, the aim of our study was to conduct a comparative analysis between these two methods while also investigating the merits of integrating multiple database-based methods. Through an in-depth comparative study, we evaluated the performance of both methodological categories in taxonomic classification by utilizing simulated data sets. Our analysis revealed that database-based methods excel in classification accuracy when backed by a rich and comprehensive reference database. Conversely, while machine learning methods show superior performance in scenarios where reference sequences are sparse or lacking, they generally show inferior performance compared with database methods under most conditions. Moreover, our study confirms that integrating multiple database-based methods does, in fact, enhance classification accuracy. These findings shed new light on the taxonomic classification of high-throughput sequencing data and bear substantial implications for the future development of computational biology. For those interested in further exploring our methods, the source code of this study is publicly available on https://github.com/LoadStar822/Genome-Classifier-Performance-Evaluator. Additionally, a dedicated webpage showcasing our collected database, data sets, and various classification software can be found at http://lab.malab.cn/~tqz/project/taxonomic/.

DATA PROTECTION LAWS IN INDONESIA ANALYZING LEGAL IMPLICATIONS AND CASE STUDIES IN THE DIGITAL AGE

<p>Navigating the data deluge of the digital age demands a nuanced approach to personal data protection. This research delves into this critical issue through a multifaceted lens, utilizing case studies and analysis of Indonesian data protection regulations. By examining real-life scenarios, we reveal the tangible challenges individuals and organizations face in managing personal data effectively. Our in-depth exploration of existing regulations provides a critical assessment of their strengths and limitations, paving the way for informed recommendations for future improvements. This contribution transcends mere theoretical analysis, offering a practical understanding of the complexities and intricacies of data protection law in Indonesia's dynamic digital landscape. By bridging the gap between theory and practice, this research empowers individuals, organizations, and policymakers to navigate the evolving landscape of personal data protection with greater clarity and confidence.</p><p>Keywords: Personal Data Protection, Digital age, Legal Aspects.</p>

Design of a Meaningful Framework for Time Series Forecasting in Smart Buildings

This paper aims to provide discernment toward establishing a general framework, dedicated to data analysis and forecasting in smart buildings. It constitutes an industrial return of experience from an industrialist specializing in IoT supported by the academic world. With the necessary improvement of energy efficiency, discernment is paramount for facility managers to optimize daily operations and prioritize renovation work in the building sector. With the scale of buildings and the complexity of Heating, Ventilation, and Air Conditioning (HVAC) systems, the use of artificial intelligence is deemed the cheapest tool, holding the highest potential, even if it requires IoT sensors and a deluge of data to establish genuine models. However, the wide variety of buildings, users, and data hinders the development of industrial solutions, as specific studies often lack relevance to analyze other buildings, possibly with different types of data monitored. The relevance of the modeling can also disappear over time, as buildings are dynamic systems evolving with their use. In this paper, we propose to study the forecasting ability of the widely used Long Short-Term Memory (LSTM) network algorithm, which is well-designed for time series modeling, across an instrumented building. In this way, we considered the consistency of the performances for several issues as we compared to the cases with no prediction, which is lacking in the literature. The insight provided let us examine the quality of AI models and the quality of data needed in forecasting tasks. Finally, we deduced that efficient models and smart choices about data allow meaningful insight into developing time series modeling frameworks for smart buildings. For reproducibility concerns, we also provide our raw data, which came from one “real” smart building, as well as significant information regarding this building. In summary, our research aims to develop a methodology for exploring, analyzing, and modeling data from the smart buildings sector. Based on our experiment on forecasting temperature sensor measurements, we found that a bigger AI model (1) does not always imply a longer time in training and (2) can have little impact on accuracy and (3) using more features is tied to data processing order. We also observed that providing more data is irrelevant without a deep understanding of the problem physics.

Research on the data-driven marketing: Case of Huawei

The ubiquity of the internet and the pervasive interconnectedness of our digital lives have led to an unprecedented surge in user-generated data. This deluge of data, often referred to as the "new oil," presents businesses with a vast reservoir of opportunities to gain profound insights into their customer base. Huawei has recognized that within this vast data landscape lies the power to craft marketing strategies and product innovations that deeply resonate with their audience. In essence, Huawei's journey through the realms of data-driven marketing and target marketing serves as a guiding star for other businesses navigating the digital age. Their unwavering commitment to harnessing data for enhanced customer engagement, amplified market competitiveness, and the enduring sustainability of their brand underscores the transformative power of data. This article serves as an illuminating case study, offering a roadmap and a wellspring of inspiration for companies striving to thrive in the data-centric landscape of the digital era. In a world of boundless possibilities, Huawei's story stands as a testament to the notion that data is not merely a resource; it is the very foundation of innovation and growth in this transformative era.

Consumer Decision-Making in the Era of Information Overload

What has emerged as a new paradigm in consumer decision-making in the modern digital age is "information overload," the result of the deluge of data, reviews, ads, and suggestions that customers see at every online interaction. Customers face advantages and disadvantages as a result of information overload. On the one hand, customers are able to do more thorough research on products, services, and brands because to the abundance of information available to them. Decision fatigue, anxiety, and poor decisions can result from consumers being overwhelmed by the sheer abundance of information.

Detection and Analysis of Short Linear Motif-Based Protein-Protein Interactions with SLiMAn2 Web Server.

Interactomics is bringing a deluge of data regarding protein-protein interactions (PPIs) which are involved in various molecular processes in all types of cells. However, this information does not easily translate into direct and precise molecular interfaces. This limits our understanding of each interaction network and prevents their efficient modulation. A lot of the detected interactions involve recognition of short linear motifs (SLiMs) by a folded domain while others rely on domain-domain interactions. Functional SLiMs hide among a lot of spurious ones, making deeper analysis of interactomes tedious. Hence, actual contacts and direct interactions are difficult to identify.Consequently, there is a need for user-friendly bioinformatic tools, enabling rapid molecular and structural analysis of SLiM-based PPIs in a protein network. In this chapter, we describe the use of the new webserver SLiMAn to help digging into SLiM-based PPIs in an interactive fashion.

IPREDICT: AI enabled proactive pandemic prediction using biosensing wearable devices

The emergence of pandemics poses a persistent threat to both global health and economic stability. While zoonotic spillovers and local outbreaks may not be fully preventable, early detection of infections in individuals before they spread to communities can make a major difference in containing an infectious disease and stopping it from becoming an epidemic and then a pandemic.In this paper, we propose a novel Artificial Intelligence (AI)-based pandemic prediction framework called iPREDICT—a concept framework designed to leverage the power of AI and crowd-sensed data for accurate and timely pandemic prediction. The core idea of iPREDICT is to leverage the deluge of data that can be harnessed from connected and wearable biosensing devices. iPREDICT system then works by monitoring anomalies in the biomarkers at the individual level and correlating them with similar anomalies observed in other members of the community. Using AI-based anomaly detection in conjunction with analysis of the spatiotemporal growth of the correlated anomalies, iPREDICT thus can potentially detect and monitor the emergence of a local outbreak in near real-time to predict a potential pandemic.However, not every outbreak has the potential to become a pandemic. We illustrate how tools like graph neural networks can be leveraged to determine optimal thresholds as a function of a large number of demographical, social, and geographical factors that determine the spatiotemporal spread of an outbreak, thus quantifying the risk of it becoming an epidemic or pandemic.We also identify essential technological and social challenges that require attention to transform iPREDICT from an idea into a globally deployable solution for future pandemic prediction and management. To provide deeper insights into iPREDICT design challenges and trigger research towards possible solutions we present a COVID-19 based case study. The results signify the impact of variation in biosensing hardware, data sampling rate, and compression rate on the performance of AI models that underpin various components of the iPREDICT system.

Secure data access using blockchain technology through IoT cloud and fabric environment

AbstractIn the current landscape, staying abreast of the latest technological advancements is a formidable challenge, especially given the deluge of data inundating the internet. The realization has dawned that effectively managing the surge in emerging data necessitates the integration of multiple technologies. In pursuit of this objective, the Internet of Things (IoT), renowned for its sensor‐based data capture capabilities, is frequently coupled with blockchain technology to ensure secure data storage and access. This amalgamation, in turn, leverages the cloud environment when data volume surpasses a machine's processing capacity, thus mitigating infrastructure and maintenance costs. This study endeavors to optimize data storage within the blocks of the blockchain (BCT) by storing an index that points to the actual data. This innovative approach not only conserves storage space but also enhances operational efficiency. Furthermore, it simplifies the task of identifying malicious or faulty nodes deployed at different locations for data capture within the prescribed time frame. To exemplify this implementation, a case study is presented, focusing on securing user votes through the creation of contracts. The results showcased underscore the preference for a permissioned blockchain, such as Fabric, over a permissionless one, like Ethereum, particularly in the context of security considerations. The findings reveal that as the number of operations (in this case, votes cast) increases, Ethereum's performance deteriorates, while Fabric exhibits exceptional robustness. Additionally, the study analyzes sensor data simulated via IoT nodes before and after the application of security algorithms to underscore the significance of the proposed Secure Cloud‐Based Blockchain (SCB2) model. The analysis encompasses various facets, including the creation, validation, and computation times of transactions and blocks within a node, and positions the model favorably in comparison to existing literature.

Paying attention to astronomical transients: introducing the time-series transformer for photometric classification

Abstract Future surveys such as the Legacy Survey of Space and Time (LSST) of the Vera C. Rubin Observatory will observe an order of magnitude more astrophysical transient events than any previous survey before. With this deluge of photometric data, it will be impossible for all such events to be classified by humans alone. Recent efforts have sought to leverage machine learning methods to tackle the challenge of astronomical transient classification, with ever improving success. Transformers are a recently developed deep learning architecture, first proposed for natural language processing, that have shown a great deal of recent success. In this work, we develop a new transformer architecture, which uses multihead self-attention at its core, for general multivariate time-series data. Furthermore, the proposed time-series transformer architecture supports the inclusion of an arbitrary number of additional features, while also offering interpretability. We apply the time-series transformer to the task of photometric classification, minimizing the reliance of expert domain knowledge for feature selection, while achieving results comparable with state-of-the-art photometric classification methods. We achieve a logarithmic-loss of 0.507 on imbalanced data in a representative setting using data from the Photometric LSST Astronomical Time-Series Classification Challenge. Moreover, we achieve a micro-averaged receiver-operating-characteristic area under curve of 0.98 and micro-averaged precision–recall area under curve of 0.87.

Integrating Neuroscience Principles into the Development of a Tailored Daily Report: A Universal Design Approach

Abstract Information management environments are typically dynamic, data-rich, and inherently multimodal but often do not support users sufficiently. Information management environments include the tools, supports, and persons which collect, organize, manage, and maintain information. The dynamism of the environment arises because of users’ need to use top-down attentional and memory approaches while attempting to use the available resources. In addition to the specific attentional and cognitive demands, many information management environments treat users as a monolithic group. The complexity of the interaction between the environment, the knowledge worker, and their individual needs creates serious difficulties in developing tailored tools and reports. Despite the intent of these “tailored” reports to simplify the interaction between the knowledge worker and the deluge of data for decision-making purposes, successfully creating a tailored report is still an active area of research. However, in the last decade, technologies that were considered theoretical have now been realized via the fourth industrial revolution. The success of the fourth industrial revolution has resulted in tools such as machine learning to drive the automated tailoring of information for individual knowledge workers. Despite early successes, the drive toward complete individualization and differentiation solely through computational means seems to reduce the effectiveness of the individual and has shown only limited success. To address these shortcomings, the authors of this essay suggest using a more comprehensive framework (Universal Design) to develop a tailored report. Universal Design (UD) is a design framework based upon the Universal Design for Learning framework. UD is a framework that promotes inclusive and equitable access to information for all knowledge workers through the application of “equalizer.” By acknowledging and addressing users’ individual needs and information processing preferences, UD can support creating a generative environment in which every individual has their needs met without individualization and differentiation occurring through specific automation. Keywords: Universal design, Adaptive environments, Information processing, Generative information environments, Knowledge workers.

AI Renaissance, artificial intelligence, information overload, human-computer interaction, decision-making

Objective: This paper aims to explore the concept of AI as a modern-day Renaissance movement, triggered by the proliferation of the internet and advancements in artificial intelligence technologies. It delves into the transformative impact of AI on human-computer interactions and decision-making processes.
 Results: O’Leary's (1997) early notion of a Renaissance movement sparked by the internet's ubiquity finds resonance in the emergence of the AI renaissance. AI technologies such as natural language processing, machine learning, heuristic language processing, and neural networks have integrated into intricate networked computing environments. These technologies facilitate the handling, retrieval, and analysis of vast amounts of data available on the World Wide Web. Given the overwhelming volume of data, direct human analysis has become impractical, necessitating AI-driven support for efficient data utilization. In today's competitive and tech-driven landscape, the time available for decision-making has diminished, prompting reliance on intelligent agents and delegating decision-making tasks to these digital surrogates.
 Conclusions: The contemporary AI renaissance signifies a paradigm shift in human-computer dynamics. The convergence of AI technologies with the internet's vast information landscape has created a symbiotic relationship, redefining traditional computer roles. AI-enabled tools not only manage the deluge of data but also extend decision-making capabilities, optimizing efficiency in an increasingly fast-paced world. This transformative movement transcends conventional computing boundaries and has paved the way for a new era of human-machine interaction.

An objective criterion to evaluate sequence-similarity networks helps in dividing the protein family sequence space.

The deluge of genomic data raises various challenges for computational protein annotation. The definition of superfamilies, based on conserved folds, or of families, showing more recent homology signatures, allow a first categorization of the sequence space. However, for precise functional annotation or the identification of the unexplored parts within a family, a division into subfamilies is essential. As curators of an expert database, the Carbohydrate Active Enzymes database (CAZy), we began, more than 15 years ago, to manually define subfamilies based on phylogeny reconstruction. However, facing the increasing amount of sequence and functional data, we required more scalable and reproducible methods. The recently popularized sequence similarity networks (SSNs), allows to cope with very large families and computation of many subfamily schemes. Still, the choice of the optimal SSN subfamily scheme only relies on expert knowledge so far, without any data-driven guidance from within the network. In this study, we therefore decided to investigate several network properties to determine a criterion which can be used by curators to evaluate the quality of subfamily assignments. The performance of the closeness centrality criterion, a network property to indicate the connectedness within the network, shows high similarity to the decisions of expert curators from eight distinct protein families. Closeness centrality also suggests that in some cases multiple levels of subfamilies could be possible, depending on the granularity of the research question, while it indicates when no subfamily emerged in some family evolution. We finally used closeness centrality to create subfamilies in four families of the CAZy database, providing a finer functional annotation and highlighting subfamilies without biochemically characterized members for potential future discoveries.

A Hybrid Recommender System Based on Autoencoder and Latent Feature Analysis.

A recommender system (RS) is highly efficient in extracting valuable information from a deluge of big data. The key issue of implementing an RS lies in uncovering users' latent preferences on different items. Latent Feature Analysis (LFA) and deep neural networks (DNNs) are two of the most popular and successful approaches to addressing this issue. However, both the LFA-based and the DNNs-based models have their own distinct advantages and disadvantages. Consequently, relying solely on either the LFA or DNN-based models cannot ensure optimal recommendation performance across diverse real-world application scenarios. To address this issue, this paper proposes a novel hybrid recommendation model that combines Autoencoder and LFA techniques, termed AutoLFA. The main idea of AutoLFA is two-fold: (1) It leverages an Autoencoder and an LFA model separately to construct two distinct recommendation models, each residing in a unique metric representation space with its own set of strengths; and (2) it integrates the Autoencoder and LFA model using a customized self-adaptive weighting strategy, thereby capitalizing on the merits of both approaches. To evaluate the proposed AutoLFA model, extensive experiments on five real recommendation datasets are conducted. The results demonstrate that AutoLFA achieves significantly better recommendation performance than the seven related state-of-the-art models.