Context Of Big Data Research Articles

DIGITAL TWIN SOLUTION IMPLEMENTED ON ENERGY HUB TO FOSTER SUSTAINABLE SMART ENERGY CITY, CASE STUDY OF SUSTAINABLE SMART ENERGY HUB

Abstract. The scarcity of energy is one of humanity's most pressing issues in the twenty-first century. These problems can be found in various areas, including energy supply, exchange, and consumption. Population growth, rising global energy demand, natural resource shortages, and environmental concerns contribute to energy scarcity. Furthermore, energy shortage needs the expansion of renewable energies and energy efficiency, a major concern for all governments and organisations. Building energy efficiency is a crucial concept to consider when it comes to smart cities. Buildings are the greatest energy consumers, accounting for 40% of total energy consumption. Recent advances in machine learning within a big data context have paved the way for more efficient building energy management. Building energy consumption may be successfully managed by a real-time measurement procedure, allowing the economy to shift from a linear to a circular consumption model. This will tackle the issue of late notice of failed energy-saving initiatives and allow for immediate correction to restore the energy management system to ultimate performance.The energy hub might be as small as a single home energy system or as large as an energy system for the city. This paper will present a case study on developing a smart energy hub called Hubgrade 4.0 that relies on connected products using digital twin as a significant enabler for energy-saving initiatives. Hubgrade 4.0 provides an innovative approach to successfully implementing energy efficiency improvement using artificial intelligence and real-time data. Hubgrade 4.0 is the name of Enova by Veolia smart energy hub; Enova is the regional leader in integrated energy and multi-technical services, delivering performance-based energy and facilities management solutions. The energy hub digital twin is a link between a physical platform that administers the energy hub's IoT and a virtual platform that can derive services that are valid for the energy hub. Successful enterprises are using several new technologies to achieve the goals of Industry 4.0: efficiency, speed, agility, and customer-centricity. This paper concluded and highlighted lessons learned from the successful implementation of innovative energy management, which relied on a dedicated organisation, effective adoption of digital technologies, and embracing new business models, resulting in power savings of 254 million kW and water savings of around 3 million cubic meters, as well as financial savings of about 138 million AED in 5 years since Hubgrade 4.0 started operations its first energy-saving contract in 2017.

Construction of College Chinese Blended Teaching Mode Based on Decision Tree Classification Model in New Media Context.

Based on the context of new media and big data, this article uses the decision tree classification model to construct the college Chinese hybrid teaching mode. In order to verify the accuracy of ID3 algorithm prediction, the comparison of the ID3 algorithm, K-means algorithm, and support vector machine classification algorithm was made, and the experimental results show that the ID3 decision tree classification algorithm has better prediction and classification ability, for the construction of college Chinese hybrid teaching mode provides certain practical value and reference basis.

Heterogeneity in acute PM₂.₅ mortality: big data strategies in the Mexico City Metropolitan Area

Background and aim. Identification of subgroups at greater risk of mortality from PM₂.₅ may inform targeted public health interventions. The case-crossover design is a powerful tool for studying acute PM₂.₅ mortality associations in large registries where statistical interaction indicates differentially susceptible subgroups. We explore shrinkage with resampling to identify these groups in a big data context. Methods. We used a time-stratified case-crossover design to investigate the association between PM₂.₅ with 1.5 million ICD-10 coded non-external 18+ years-old death records from the Mexico City Metropolitan Area, 2004–2019. Daily municipal-level exposures for PM₂.₅ and temperature came from population-weighting 1km satellite-based model predictions, and were scaled to z-scores. We assessed whether the subgroup-specific association of PM₂.₅ exposure (lag₀₁) with daily mortality varied from the overall association for PM₂.₅ by including weighted effect coded interaction terms of lag₀₁ PM₂.₅ by cause-of-death:age-group:sex groupings (56 interaction terms), adjusting for temperature. We fit conditional logistic regression with shrinkage for regularization (ridge regression), and cross-validation to select the value of λ with the minimum mean square error. Finally, bootstrap resampling was used for coefficient confidence intervals (95%CI). Results. Overall, a 10μg/m³ higher lag₀₁ PM₂.₅ was associated with 1.46% higher mortality (95%CI: 1.30-1.77). Subgroups exhibited substantial variation (point estimates from 1.1% to 1.91%) with the strongest associations seen for: circulatory system in females ≥80 years-old (1.91%, 95%CI: 1.51%-2.92%); respiratory system in females ≥80 years-old (1.86%, 95%CI: 1.44%-3.30%); and respiratory system in females 65-79 years-old (1.83%, 95%CI: 1.56%-3.61%). Conclusion. Regularization techniques and inclusion of multi-way interactions in big data analyses aid in systematically identifying specific subpopulations with enhanced response to PM₂.₅ relative to the population-average association. Keywords PM₂.₅, penalized regression, case crossover, mortality, big data

Assisting Laboratory Management Based on Network Big Data Mining Technology

In today’s big data context, the composition of virtual networks is becoming increasingly complex, so it is neither easy nor difficult to strengthen the control of network security issues. This paper studies the important content of network big data mining-assisted laboratory management. On the basis of discussing the connotation of laboratory safety, combined with management practice, this paper puts forward some suggestions on laboratory safety management. This paper puts forward some views and thoughts on some problems existing in the management and experimental teaching of chemistry laboratory. By judging the stability of instruments and equipment, we know whether the calibration status of instruments and equipment has changed during this period, so as to ensure the sustainable use of instruments and equipment and the accuracy and traceability of laboratory test results. The use of laboratory management system can greatly improve the utilization rate of laboratory equipment, promote students’ autonomous learning, and promote the standardization of laboratory construction. Improve the network monitoring method of big data mining technology and the application mechanism of big data network monitoring, in one type of laboratory. Teachers and students in the laboratory can reasonably arrange their own time according to their own interests to guide and operate experiments. Through continuous operation and practice, students’ practical ability and experimental knowledge level should be improved as much as possible.

Topics and changing characteristics of knowledge organization research in the 21st century: a content analysis

PurposeKnowledge organization (KO) has been advancing at a progressively rapid pace under the influence of information technology. This study aims to explore the topics, characteristics, and trends of KO research in the 21st century.Design/methodology/approachThe full text of 4,360 KO-related articles published from 2000 to 2021 is collected. Through content analysis, this study identifies the topics, research methods, and application areas of each article, and the statistics are presented through a series of visualizations.FindingsIn total, 13 main topics, 105 sub-topics, 16 research methods, and 57 application areas are identified. Notably, classification has always been an important topic, while linked data, automated techniques, and ontology have become popular topics recently. Significant changing features have also occurred. The versatile use of research methods has increased, with empirical research becoming the mainstream. Application areas show a trend of refinement from subject areas to specific scenarios. Construction techniques present a combination of automated techniques, crowdsourcing, and experts.Originality/valueKO has evolved and diversified due to technological developments. This study is the first to focus on the continuous changing features over an extended, 21-year period, as opposed to sampling a few years. It also provides clues and insights for researchers and practitioners interested in KO to understand how it has changed in the Semantic Web and big data context.

Missing values and data enrichment: an application to social media liking

In the big data context, it is very frequent to manage the analysis of missing values. This is especially relevant in the field of statistical analysis, where this represents a thorny issue. This study proposes a strategy for data enrichment in presence of sparse matrices. The research objective consists in the evaluation of a possible distinction of behaviour among observations in sparse matrices with missing data. After selecting among the multiple imputation methods, an innovative technique will be presented to impute missing observations as a negative position or a neutral opinion. This method has been applied to a dataset measuring the interaction between users and social network pages for some Italian newspapers.

Content-Based Video Big Data Retrieval with Extensive Features and Deep Learning

In the era of digital media, the rapidly increasing volume and complexity of multimedia data cause many problems in storing, processing, and querying information in a reasonable time. Feature extraction and processing time play an extremely important role in large-scale video retrieval systems and currently receive much attention from researchers. We, therefore, propose an efficient approach to feature extraction on big video datasets using deep learning techniques. It focuses on the main features, including subtitles, speeches, and objects in video frames, by using a combination of three techniques: optical character recognition (OCR), automatic speech recognition (ASR), and object identification with deep learning techniques. We provide three network models developed from networks of Faster R-CNN ResNet, Faster R-CNN Inception ResNet V2, and Single Shot Detector MobileNet V2. The approach is implemented in Spark, the next-generation parallel and distributed computing environment, which reduces the time and space costs of the feature extraction process. Experimental results show that our proposal achieves an accuracy of 96% and a processing time reduction of 50%. This demonstrates the feasibility of the approach for content-based video retrieval systems in a big data context.

Review on A big data-based innovative knowledge teaching evaluation system in universities

With the widespread use of digital technologies such as big data, cloud computing and artificial intelligence in higher education, how to establish a scientific and systematic evaluation system to turn the traditional classroom with the one-way transmission of knowledge into an interactive space for exchanging ideas and inspiring wisdom has become an essential task for human resource management in universities, and a key to improving teaching quality. However, due to the debate between scientism and humanism in teaching evaluation, studies related to teaching performance have been isolated from human resource management, resulting in the lack of a systematic vision and framework for such studies. Relevant studies are still limited to the evaluation contents of different evaluation subjects. Evaluations also tend to focus only on the teaching process, ignoring the objectives of talent training, making it difficult for evaluations to play a goal-oriented role and hindering the further development of relevant studies. Therefore, this paper draws on human resource management methodologies and analyzes knowledge teaching evaluation system characteristics in colleges and universities in a big data context to construct a “multiple evaluations, trinity and four-step closed-loop” big data-based knowledge teaching evaluation system. “Trinity” represents evaluation from three performance dimensions: teaching effect, teaching behavior and teaching ability. “Multiple evaluations” represents the design of teaching performance indicators based on teaching data, breaking the barriers between different evaluation subjects. “Four-step closed-loop” draws on performance management theory to standardize the teaching performance management process from four aspects: planning, implementation, evaluation, and feedback. This evaluation system provides a systematic methodology for unifying the theory and practice of innovative knowledge teaching evaluation system in universities in a big data context.

Innovation and Development of University Education Management Informationization in the Big Data Environment

With the arrival of the big data era, the role of big data can be fully utilized, and the comprehensive data evaluation is carried out to perform education information evaluation. In the general circumstance of computerized learning, college teaching regulation has new features and novel orientations. Along with the speedy progression of sci-tech, the pace of dissemination of data is continuously quickening, and it is being increasingly easy for the public to interact and carry on with their lives. Because people use the network to access a variety of data information, the system cannot handle huge amounts of data; this is the cause of the era. In the process of the comprehensive approach of the information age, with the impact of the Age of Big Data, the administration of intelligence in universities has transformed. Big Data InfoTech has infiltrated into all realms of community lifestyle. How to cope with the transformation of informationization of university education management in the era is a serious challenge for relevant personnel. This study begins by discoursing the essential implication of big data, followed by a diagnosis of the questions involved in the establishment of computerization in high schools under the environment of big data, comprising the imminent solutions to the dilemmas in collegiate education maintenance, the issues raised by privatization in high schools, and the strategies for education management. This is followed by the proposal of the innovative educational administration informationization development trend in the big data context. In this research, there are 11 professors in the expert group, accounting for 44%, 8 associate professors, accounting for 32%, and 6 lecturers or below, accounting for 24%. This study makes full use of a large number of procedural data generated in educational management activities to achieve an efficient, comprehensive, accurate, and objective evaluation, which provides strong technical support for educational management informatization evaluation.

On physics-informed data-driven isotropic and anisotropic constitutive models through probabilistic machine learning and space-filling sampling

Data-driven constitutive modeling is an emerging field in computational solid mechanics with the prospect of significantly relieving the computational costs of hierarchical computational methods. Additionally, this data-driven paradigm could enable a seamless connection of experimental data probing material responses with numerical simulations at the structural level. Traditionally, these surrogates have just been trained using datasets which map strain inputs to stress outputs for elastic and inelastic materials directly. Recently, artificial neural networks (ANNs) have instead been trained to additionally incorporate the underlying physical laws in the construction of these models. However, ANNs do not offer convergence guarantees from an engineering point of view and are majorly reliant on user-specified parameters. In contrast to ANNs, Gaussian process regression (GPR) is based on nonparametric modeling principles as well as on fundamental statistical knowledge and hence allows for strict convergence guarantees. Motivated by the recent work by Frankel et al. (2021) which is based on rewriting the stress output as a linear combination of an irreducible integrity basis, in this work we present a physics-informed and data-driven constitutive modeling approach for isotropic and anisotropic hyperelastic materials at finite strain. The trained surrogates are able to respect physical principles such as material frame indifference, material symmetry, thermodynamic consistency, stress-free undeformed configuration, and the local balance of angular momentum. Our approach is based on probabilistic machine learning and uniquely can be used in the big data context while maintaining the benefits of GPR. As sampling in the mixed invariant space poses a unique challenge, we additionally present the first sampling approach that directly generates space-filling points in the invariant space corresponding to a bounded domain of the deformation gradient tensor. The sampling technique is based on simulated annealing and provides more efficient and reliable physics-informed constitutive models. Overall, the presented approach is tested on synthetic data from isotropic and anisotropic constitutive laws and shows surprising accuracy even far beyond the limits of the training domain, indicating that the resulting surrogates can efficiently generalize as they incorporate knowledge about the underlying physics.

A new adaptive sampling algorithm for big data classification

The exponential growth of the quantity of data that circulates on the web led to the emergence of the big data phenomenon. This fact is a natural consequence of the proliferation of social media, mobile devices, the abundance of free online storage, and new technologies like the internet of things. Subsequently, big data has created several challenges to the computer science community, among which the large size of data is the most challenging. Traditional machine learning algorithms used mostly for insight extraction find themselves inadequate, even on high-performance computer architectures. For instance, big data analytics algorithms can overcome the size issue by either: (1) adapting the existing machine learning techniques to the scale of the big data; or, (2) by sampling big datasets, choosing randomly much smaller subsets of the data population, to meet what current algorithms can handle. In the present work, we aim to proceed through the second alternative to address the size challenge in the big data context. We propose intelligent sampling techniques based on Scalable Simple Random Sampling (ScaSRS) and Subsampled Double Bootstrap (SDB). Test results carried out on public generic datasets show that our proposal is able to address the size dimension efficiently. The proposed algorithms were evaluative on a classification task where the obtained results provided significant improvement compared to the state-of-the-art.

A Comprehensive Review Study on: Optimized Data Mining, Machine Learning and Deep Learning Techniques for Breast Cancer Prediction in Big Data Context

In recent years, big data in health care is commonly used for the prediction of diseases. The most common cancer is breast cancer infections of metropolitan Indian women as well as in women worldwide with a broadly factor occurrence among nations and regions. According to WHO, among 14% of all cancer tumours in women breast cancer is well-known cancer in women in India also. Few researches have been done on breast cancer prediction on Big data. Big data is now triggering a revolution in healthcare, resulting in better and more optimized outcomes. Rapid technological advancements have increased data generation; EHR (Electronic Health Record) systems produce a massive amount of patient-level data. In the healthcare industry, applications of big data will help to improve outcomes. However, the traditional prediction models have less efficiency in terms of accuracy and error rate. This review article is about the comparative assessment of complex data mining, machine learning, deep learning models used for identifying breast cancer because accuracy rate of any particular algorithm depends on various factors such as implementation framework, datasets(small or large),types of dataset used(attribute based or image based)etc. Aim of this review article is to help to choose the appropriate breast cancer prediction techniques specifically in the Big data environment to produce effective and efficient result, Because “Early detection is the key to prevention-in case of any cancer”.

ICHC Framework

The Goal in this paper is to propose a cultural heritage data model and evolve towards the creation of a framework based on MongoDB that will allow to manage a JSON model representing the cultural heritage of a city ICHC (Intelligent Cultural Heritage of a City). This manuscript per the authors noticed that during the census of cultural heritage, the presence of human resources linked to heritage is not something that is represented in a smart engine of a framework. Which is why the goal is to integrate the human resource and therefore add a relational aspect to the NoSql documents so that the resulting framework can have a smart engine to link data.This model is a set of ICHD (Intelligent Cultural Heritage Document) which are JSON documents that represent of the different types of cultural heritage entities. Those documents will be managed in a MongoDB repository architecture that will allow to them, so that the microservices-based ICHC framework can offer a big data context that can handle a huge variety, volume and velocity of data and be based on distributed operations.

Efficient Trustworthiness Management for Malicious User Detection in Big Data Collection

Data collection in big data is an effective way to aggregate information that the collector is interested in. However, there is no assurance for the data that the users provide. Since collector does not have the ability to check the authenticity of every piece of information, the trustworthiness of users participated in the collection become important. In this paper, we design an efficient approach to calculate users’ trustworthiness in data collection for big data context. We divide the trustworthiness into familiarity trustworthiness and similarity trustworthiness, and study the influences of user actions on trustworthiness. To prevent malicious users from raising their trustworthiness and providing false information that may mislead final results, we also design a security queue to record users’ historical trust information, so that we can detect malicious users with high accuracy. Simulation results show that our model can sensitively resist the malicious actions of users.

A tree-based stacking ensemble technique with feature selection for network intrusion detection

Several studies have used machine learning algorithms to develop intrusion systems (IDS), which differentiate anomalous behaviours from the normal activities of network systems. Due to the ease of automated data collection and subsequently an increased size of collected data on network traffic and activities, the complexity of intrusion analysis is increasing exponentially. A particular issue, due to statistical and computation limitations, a single classifier may not perform well for large scale data as existent in modern IDS contexts. Ensemble methods have been explored in literature in such big data contexts. Although more complicated and requiring additional computation, literature has a note that ensemble methods can result in better accuracy than single classifiers in different large scale data classification contexts, and it is interesting to explore how ensemble approaches can perform in IDS. In this research, we introduce a tree-based stacking ensemble technique (SET) and test the effectiveness of the proposed model on two intrusion datasets (NSL-KDD and UNSW-NB15). We further enhance incorporate feature selection techniques to select the best relevant features with the proposed SET. A comprehensive performance analysis shows that our proposed model can better identify the normal and anomaly traffic in network than other existing IDS models. This implies the potentials of our proposed system for cybersecurity in Internet of Things (IoT) and large scale networks.

The Role of Vocabularies in the Age of Data: The Question of Research Data

The objective of this work is to discuss how vocabularies can contribute to assigning computational semantics to digital research data within the context of Big Data, so that computers can process them, allowing their reuse on large scale. A conceptualization of data is developed in an attempt to make it clearer what would be data, as an essential element of the Big Data phenomenon, and in particular, digital research data. It then proceeds to analyse digital research data uses and cases and their relation to semantics and vocabularies. Data is conceptualized as an artificial, intentional construction that represents a property of an entity within a specific domain and serves as the essential component of Big Data. The concept of semantic expressivity is discussed, and is used to classify the different vocabularies; within such a classification ontologies, are shown to be a type of knowledge organization system with a higher degree of semantic expressivity. Features of vocabularies that may be used within the context of the Semantic Web and the Linked Open Data to assign machine-processable semantics to Big Data are suggested. It is shown that semantics may be assigned at different data aggregation levels.

An End-to-End Big Data Deduplication Framework based on Online Continuous Learning

While big data benefits are numerous, most of the collected data is of poor quality and, therefore, cannot be effectively used as it is. One of the leading big data quality challenges is data duplication. Indeed, the gathered big data are usually messy and may contain duplicated records. The process of detecting and eliminating duplicated records is known as Deduplication, or Entity Resolution or also Record Linkage. Data deduplication has been widely discussed in the literature, and multiple deduplication approaches were suggested. However, few efforts have been made to address deduplication issues in Big Data Context. Also, the existing big data deduplication approaches are not handling the case of the decreasing performance of the deduplication model during the serving. In addition, most current methods are limited to duplicate detection, which is part of the deduplication process. Therefore, we aim through this paper to propose an End-to-End Big Data Deduplication Framework based on a semi-supervised learning approach that outperforms the existing big data deduplication approaches with an F-score of 98,21%, a Precision of 98,24% and a Recall of 96,48%. Moreover, the suggested framework encompasses all data deduplication phases, including data preprocessing and preparation, automated data labeling, duplicate detection, data cleaning, and an auditing and monitoring phase. This last phase is based on an online continual learning strategy for big data deduplication that allows addressing the decreasing performance of the deduplication model during the serving. The obtained results have shown that the suggested continual learning strategy has increased the model accuracy by 1,16%. Furthermore, we apply the proposed framework to three different datasets and compare its performance against the existing deduplication models. Finally, the results are discussed, conclusions are made, and future work directions are highlighted.

Knowledge organization and its contributions in a Big Data context

Resumo O objetivo deste trabalho é analisar o fenômeno Big Data (contexto tecnológico que lida com análises de fluxos intensos de dados para a consecução de informações que possam ser relevantes para diversos atores sociais) e seus impactos na Organização do Conhecimento (área que possibilita a descoberta informacional utilizando-se, para isso, da construção de ferramentas organizacionais de cunho lógico-semântico, como tesauros, taxonomias e sistemas de classificação, objetivando a disseminação e desenvolvimento do conhecimento na sociedade) por meio de uma proposta de categorização da produção científica. Com base nas categorias orientadas ao produto, aos processos e à cognição, e nas dimensões epistemológica, aplicada, política e social, da ISKO-Brasil, esta proposta representa uma possibilidade de compreensão do fenômeno de dados na Organização do Conhecimento. Usa o método exploratório para a revisão de literatura e de busca em bases de dados especializadas sobre os temas Big Data e Organização do Conhecimento. Os resultados demonstram a predominância de um perfil mais aplicado e orientado a processos relacionados à coleta, curadoria e utilização de dados. Conclui-se que é necessária a ampliação de pesquisas relacionadas às questões sociais, cognitivas, epistemológicas e metodológicas, bem como a elaboração de mais estudos voltados à ética nesse cenário intenso de dados. A pesquisa contribui para a compreensão e ampliação dos cenários de pesquisa sobre Big Data na Organização do Conhecimento.

Ensemble Feature Selection Approach for Imbalanced Textual Data Using MapReduce

Feature selection is a fundamental pre-processing phase in text classification. It speeds up machine learning algorithms and improves classification accuracy. In big data context, feature selection...

A timeline model for clinical events: empowering data

Data visualization is key in the Big Data context, enabling different cognitive perspectives over large datasets. These visual perspectives can prompt relevant advantages with regard to healthcare records, because they may contribute to a faster, more understandable, and adequate way to capture patients’ health history and overall condition, thus improving healthcare quality.Timelines are well-known visual artifacts that help healthcare professionals to visualize patients’ electronic health records (EHR) over a time period. As data stored in EHR tend to quickly grow with each interaction between patient and healthcare system both number and size, traditional linear timelines are can increasingly become more difficult to manage visually, as they often span over different screens. Considering that a holistic analysis is desirable to provide proper and quality health services, data visualization should enable a seamless understanding of patients’ health history and overall condition. When dealing with critical episodes - such as an emergency - where time is an important factor, this is even more decisive. Furthermore, traditional timelines do not support multidimensional data representation. This paper presents a new visual model of time-dependent EHR based on radial models. It is capable of simultaneously displaying several data categories that characterize patients’ medical history, enabling medical professionals to be aware of different data categories over time in a single display, without the need to scroll between screens.