Big Data Methods Research Articles

A study of Taiwanese children’s learning and preferences in game-based learning scenarios

Game-Based Learning (GBL) today involves the use of computers and video games specifically aimed at producing learning outcomes among children. Most games are designed to balance different subject matters and to assess the ability of the learners in retaining or applying the acquired knowledge. Children enjoy playing games and are completely involved in the activity for its own sake. “Flow State” refers to the amplification of a child’s concentration, interest, and mindsets while learning. This study intends to verify children’s preferences and interests in Game-based Learning. The study used big data analysis and methods to let children play 10 different games. The results will answer the following questions: 1. How long can children stay engaged while playing digital games? What is the relation between the length of engagement and their flow state? 2. Do children’s preferences in games differ between genders? 3. What are the children's preferences in games regarding different ages? 4. What are the relations between children's interests and achievements? Is children’s flow state related to their learning performances? The study answered the above questions in a quality-focused manner as a reference to the game design for early childhood and preschool teachers.

Effects of Using Big Data Methods on Optimizing Electrical Systems

Effects of Using Big Data Methods on Optimizing Electrical Systems

FORECASTING OF FINANCING OF ENTERPRISE CONVERSION

Purpose of the study. The task set by the President of Russia to increase the output of civilian products at the enterprises of the defense complex to 50% in 2030 requires the study of various ne-cessary resources, as well as models and methods of managing them. In the context of the econom-ic crisis caused by the coronavirus in 2020, the relevance of studying the possibilities of achieving this significant task is increasing. In this work, the goal is to develop a mathematical model, conduct modeling and assess the need for financing the growth of civilian output at enterprises in the re-search and development industry. Methods. A simulation model for multi-period forecasting of the financial state of the enterprise is used. Methods of processing big data are used to obtain the in-itial information. The means of regression analysis are used to determine the dependencies of the fi-nancial statements. Scenario analysis methods allow us to consider and highlight the significant fac-tors influencing the research goal. Results. A multi-period model of forecasting the financial and economic state of an enterprise has been developed to assess the consequences of an increase in ci-vilian production at enterprises of scientific research and development. The initial data of financial statements based on open data from Russian Agency for Statistics (Rosstat) were obtained, and the aggregation of reporting indicators was carried out. Simulation calculations were carried out in the scenarios of inertial growth, growth with an increase in efficiency, and replacement growth. The task of increasing the share of civilian products to 50% by 2030 at scientific and technical en-terprises in Russia will require significant additional funding, an estimate of about 1,300 billion ru-bles in an inertial scenario. The development and implementation of a program to improve the effi-ciency of enterprises significantly reduces the need for additional financing, the estimate is about 1,100 billion rubles with a slight improvement in efficiency parameters. Conclusion. The results of this study can be used to develop industrial development programs both at the industry level and at the level of individual enterprises. Increasing the output of civilian products will require significant funding. Development and implementation of operational efficiency programs of enterprises can significant-ly reduce the need for additional funding.

Understanding the Concept of BIG Data Testing, Strategies and Methods

This paper explains the concept of BIG data and the process of testing BIG data technology. There are various procedures which are used to perform testing of BIG data technology. It is to make sure that all the functions of BIG data work smoothly without getting errors. This paper will explain the concept and strategies used to perform the BIG data testing.

381 Smart Farming for Extensive Grazing Ruminant Production Systems

Abstract Smart farming for extensive grazing systems includes applications linking environment and supply-chain, including metrics for climate, soils, pastures, animals and animal products to enhance management, optimization and predictions. Technological developments for remote monitoring in extensive systems have varied in their success and remain limited in uptake, and include: In-field, fixed-device monitoring of livestock numbers, water, photosynthesis and greenhouse gas emissions; body composition and physiology assessments using devices fixed to handling facilities; ground- or aerial-based livestock, water, pasture, invasive weeds and/or soil monitoring using photogrammetry or technologies including LiDAR; multi-channel, satellite-based spectrometry coupled with weather and soil grids to model and predict pasture biomass components; automated in-field liveweight measurement and drafting; virtual fencing; on- and in-animal devices to monitor location, activity, behaviors and physiology; GPS to monitor asset and personnel location. These technologies target productivity, efficiency, health and welfare of ruminants, including genetic improvement, and more efficient, sustainable resource use, including soils, pastures and water, to improve individual ruminants and grazing systems. We have developed and validated technologies for remote, in-field determination of animal behaviors, pasture characteristics including availability and disappearance mapping for calibration and validation of satellite images, and pasture intake under varying grazing conditions. Examples of our R&D include experimental on-animal sensor devices to classify and monitor behaviors in extensive systems, and development of a GrazingApp linking satellite imagery, weather and soil information to model and predict animal production. Development of these technologies has required analytical methods for big data, including machine learning and artificial intelligence. These and other applications that function in near to real-time are enhanced by management and aggregation of enormous amounts of data generated by sensors and other devices into useful metrics before transmission using wireless networks. These metrics are the basis for data-driven management decisions that reduce risk and enhance profit for grazing enterprises.

First do no harm: An exploration of researchers' ethics of conduct in Big Data behavioral studies.

Research ethics has traditionally been guided by well-established documents such as the Belmont Report and the Declaration of Helsinki. At the same time, the introduction of Big Data methods, that is having a great impact in behavioral research, is raising complex ethical issues that make protection of research participants an increasingly difficult challenge. By conducting 39 semi-structured interviews with academic scholars in both Switzerland and United States, our research aims at exploring the code of ethics and research practices of academic scholars involved in Big Data studies in the fields of psychology and sociology to understand if the principles set by the Belmont Report are still considered relevant in Big Data research. Our study shows how scholars generally find traditional principles to be a suitable guide to perform ethical data research but, at the same time, they recognized and elaborated on the challenges embedded in their practical application. In addition, due to the growing introduction of new actors in scholarly research, such as data holders and owners, it was also questioned whether responsibility to protect research participants should fall solely on investigators. In order to appropriately address ethics issues in Big Data research projects, education in ethics, exchange and dialogue between research teams and scholars from different disciplines should be enhanced. In addition, models of consultancy and shared responsibility between investigators, data owners and review boards should be implemented in order to ensure better protection of research participants.

Analysis of related factors between sudden sensorineural hearing loss and serum indices base on artificial intelligence and big data

Objective:The etiology and pathophysiologic mechanism of sudden sensorineural hearing loss are undefined. We will use artificial intelligence and big data methods to explore the correlation between sudden sensorineural hearing loss and serum indices. Method:A total of 1218 patients with sudden deafness admitted to Sun Yat-sen Memorial Hospital were selected as the experimental group, 95 861 healthy subjects were randomly selected as the control group at the same period. Serum biochemical indexes in two groups were collected and analyzed by TreeNet and CART machine learning algorithms, to screen out highly correlated indicators with sudden sensorineural hearing loss and dig out a set of clinical features for people with high risk of sudden sensorineural hearing loss. Result:It was found that high prevalence rate of sudden sensorineural hearing loss is related to eosinophils, reticulocyte and fibrinogen. The areas under the receiver operator characteristic curves（ROC-AUC） were exploited to evaluate the prediction performance of TreeNet model. Overall the TreeNet model has provided high predictive ability by ROC curve, achieving AUC of 0.99, both recall and accuracy rate of 99.90%. Conclusion:There is significant difference between sudden deadness and normal people in serum biochemical indexes. Eosinophil is the first important indicator to distinguish sudden sensorineural hearing loss. Treenet model has important referenced significance for the screening and diagnosis of sudden sensorineural hearing loss.

Processing of Bathymetric Data: The Fusion of New Reduction Methods for Spatial Big Data.

Floating autonomous vehicles are very often equipped with modern systems that collect information about the situation under the water surface, e.g., the depth or type of bottom and obstructions on the seafloor. One such system is the multibeam echosounder (MBES), which collects very large sets of bathymetric data. The development and analysis of such large sets are laborious and expensive. Reduction of the spatial data obtained from bathymetric and other systems collecting spatial data is currently widely used. In commercial programs used in the development of data from hydrographic systems, methods of interpolation to a specific mesh size are very frequently used. The authors of this article previously proposed original the true bathymetric data reduction method (TBDRed) and Optimum Dataset (OptD) reduction methods, which maintain the actual position and depth for each of the measured points, without their interpolation. The effectiveness of the proposed methods has already been presented in previous articles. This article proposes the fusion of original reduction methods, which is a new and innovative approach to the problem of bathymetric data reduction. The article contains a description of the methods used and the methodology of developing bathymetric data. The proposed fusion of reduction methods allows the generation of numerical models that can be a safe, reliable source of information, and a basis for design. Numerical models can also be used in comparative navigation, during the creation of electronic navigation maps and other hydrographic products.

Blood pressure management in patients receiving renal replacement therapy.

Hypertension is the most common complication of kidney disease, diabetes, and other cardiovascular diseases. In addition, it is a critical factor in the progression of these diseases, and hence, blood pressure management is highly recommended worldwide, in accordance with the major guidelines. However, there are two blind spots in the management system: one concerns patients with cancer, and the other concerns patients receiving renal replacement therapy. End-stage renal failure is the final stage of hypertension, and nephrologists usually treat hypertension in both nondialysis patients and dialysis patients. Nephrologists first attempt to manage the blood pressure of dialysis patients using the same method employed for nondialysis patients, i.e., by deciding on a target blood pressure at the clinic. However, this is exceedingly difficult because dialysis patients have lost their most important body-fluid autoregulatory mechanism and have varying body weights during the dialysis session. Moreover, numerous lines of evidence and clinicians' observations have suggested that hypotension during a dialysis session leads to an unfavorable prognosis. However, when the target blood pressure is increased to avoid hypotension during a dialysis session, the risk of atherosclerosis and bleeding complications will be increased. Many nephrologists may feel unsure of choosing a target blood pressure using traditional methods. Recently, home blood pressure and average blood pressure have become new indices of blood pressure management. We believe that further advancements of this old and important theme will be possible with new technologies and big-data analytical methods.

Analysis of the Big Data Methods, Challenges and Applications in Intelligent Transportation Systems

Analysis of the Big Data Methods, Challenges and Applications in Intelligent Transportation Systems

Decolonising Digital Media Research Methods: Positioning African Digital Experiences as Epistemic Sites of Knowledge Production

ABSTRACT This introductory essay argues for a decolonial approach that privileges qualitative methods in ways that position African digital experiences as “epistemic sites” of knowledge production in their own right in digital media scholarship. In proffering this argument, we challenge and confront elements of the global knowledge system, which are driven by an implicit “civilising mission” in which methods and intellectual approaches drawn from the West are seen as sacrosanct, while approaches and concepts emerging from the Global South are deemed to have a lower ontological density in the hierarchical ordering of knowledge. We explore methodological questions that relate to the studies carried in this Special Issue and consider various strategies for aligning digital media scholarship with Southern epistemologies—whether these are found in the “epistemologies of everyday” popular culture or epistemologies emerging through the work of African activists and artists. Equally, we emphasise the value of methods that pay attention to issues of power and economic extraction to understand the very different roles of social media platforms in various African countries. The paper also considers how the precarious and contingent nature of infrastructure and African cities in general demands methods that pay attention to issues of digital materiality and infrastructure. Finally, we discuss Big Data methods and the need for African researchers to establish themselves more firmly in this space.

Artificial intelligence and the hunt for immunological disorders.

Artificial intelligence has pervasively transformed many industries and is beginning to shape medical practice. New use cases are being identified in subspecialty domains of medicine and, in particular, application of artificial intelligence has found its way to the practice of allergy-immunology. Here, we summarize recent developments, emerging applications and obstacles to realizing full potential. Artificial/augmented intelligence and machine learning are being used to reduce dimensional complexity, understand cellular interactions and advance vaccine work in the basic sciences. In genomics, bioinformatic methods are critical for variant calling and classification. For clinical work, artificial intelligence is enabling disease detection, risk profiling and decision support. These approaches are just beginning to have impact upon the field of clinical immunology and much opportunity exists for further advancement. This review highlights use of computational methods for analysis of large datasets across the spectrum of research and clinical care for patients with immunological disorders. Here, we discuss how big data methods are presently being used across the field clinical immunology.

Mental Health Outcomes Associated with Risk and Resilience among Military-Connected Youth.

The present study aimed to describe patterns of risk and protective factors affecting U.S. Army families and their association with mental health diagnoses among military-connected children. Wartime military service is associated with increased adverse outcomes for military-connected youth, but few studies have explored the impact of concurrent risk and access to protective factors. Using big data methods to link existing datasets, protective factors (e.g., marital and family functioning) were drawn from a voluntary survey completed by 1,630 US Army spouses. Risk factors (e.g., parent mental health, family moves, deployment) were drawn from Department of Defense (DoD) archival data. Rates of mental health diagnoses among youth were derived from DoD healthcare records. Using the three-step method of latent profile analysis, five profiles emerged with variability across risk and protective factors. The largest group (40% of the sample) had considerable protective factors and limited risk exposure. Statistically significant differences in the prevalence of mental health diagnoses among military-connected youth were observed across profiles (χ2 =30.067, df=4, p<.001), with the highest rates (31.1% and 30.5%) observed in the two profiles with the lowest protective factors. Findings suggest most military families are faring well and highlight the importance of a thorough assessment that evaluates both the stressors military families face and the strengths they possess.

МЕТОДЫ ОБРАБОТКИ БОЛЬШИХ ДАННЫХ В ПСИХОЛОГИЧЕСКИХ ИССЛЕДОВАНИЯХ

&#x0D; &#x0D; &#x0D; The study and analysis of data processing methods in psychological research is the main goal of the work. Big data methods are a collection of statistical methods that can find complex signals in large amounts of data.&#x0D; &#x0D; &#x0D;

Changes and Countermeasures of Investigation Activities Under the Background of Big Data

In recent years, the ideas and methods of big data have caused a substantial change in the field of social and economic life and brought new opportunities and challenges to the public, prosecutors, and judicial organs. However, academic research on big data investigation is still at an early stage, and no theory and method of using big data systems have been formed. Therefore, this study focuses on examining the effect of big data on modern investigation activities and discusses how to use big data to improve the efficiency of investigation activities. The study also proposes the author’s views and opinions on how to maintain high efficiency in big data investigations. This study investigates the application of big data in investigative activities. First, the background of big data and the significance of studying big data investigation are introduced. On this basis, the origin and development of big data and the informatization of investigation are systematically classified. The connotation and changes of the investigation and the informatization of investigation under the background of big data are further examined. This study suggests that big data influences investigative thinking, investigative methods, and techniques. Moreover, traditional investigation methods should be reformed to understand big data investigation. Last, considering the risks that big data may bring to investigation activities, how to use big data to enhance investigation activities from the perspectives of privacy protection, platform establishment, and talent training is analyzed. Keywords: big data, investigation activities, investigation reform and response DOI: 10.7176/DCS10-9-06 Publication date: September 30 th 2020

Tracking Fluctuations in Psychological States using Social Media Language: A Case Study of Weekly Emotion

Personality psychologists are increasingly documenting dynamic, within–person processes. Big data methodologies can augment this endeavour by allowing for the collection of naturalistic and personality–relevant digital traces from online environments. Whereas big data methods have primarily been used to catalogue static personality dimensions, here we present a case study in how they can be used to track dynamic fluctuations in psychological states. We apply a text–based, machine learning prediction model to Facebook status updates to compute weekly trajectories of emotional valence and arousal. We train this model on 2895 human–annotated Facebook statuses and apply the resulting model to 303 575 Facebook statuses posted by 640 US Facebook users who had previously self–reported their Big Five traits, yielding an average of 28 weekly estimates per user. We examine the correlations between model–predicted emotion and self–reported personality, providing a test of the robustness of these links when using weekly aggregated data, rather than momentary data as in prior work. We further present dynamic visualizations of weekly valence and arousal for every user, while making the final data set of 17 937 weeks openly available. We discuss the strengths and drawbacks of this method in the context of personality psychology's evolution into a dynamic science. © 2020 European Association of Personality Psychology

Using Big Data and Machine Learning in Personality Measurement: Opportunities and Challenges

This conceptual paper examines the promises and critical challenges posed by contemporary personality measurement using big data. More specifically, the paper provides (i) an introduction to the type of technologies that give rise to big data, (ii) an overview of how big data is used in personality research and how it might be used in the future, (iii) a framework for approaching big data in personality science, (iv) an exploration of ideas that connect psychometric reliability and validity, as well as principles of fairness and privacy, to measures of personality that use big data, (v) a discussion emphasizing the importance of collaboration with other disciplines for personality psychologists seeking to adopt big data methods, and finally, (vi) a list of practical considerations for researchers seeking to move forward with big data personality measurement and research. It is expected that this paper will provide insights, guidance, and inspiration that helps personality researchers navigate the challenges and opportunities posed by using big data methods in personality measurement. © 2020 European Association of Personality Psychology

Using population register data for health services research – the Finnish experience

Abstract The personal identification number was introduced in Finland in the mid-1960s. By 1970, it was universally used in administrative databases including population census, causes of death, cancer, hospital discharge, and health insurance registries. Early on data protection regulations recognised the use of registries and ID numbers for research and register linkages which allowed expanding the use of register data in population health and health services research. The possibility to analyse electronic health records (eHRs) linked to individual whole-population sociodemographic data has allowed the use of a wide range of study designs from cross-sectional to longitudinal studies and to various hierarchical designs. Some registers extend follow-up time up to over 50 years with detailed mapping of individual event histories. Data also allow detailed disentangling of individual and contextual factors, such as socioeconomics and comorbidities vs. provider characteristics. While some data items draw on administrative decisions or clinical discretion, such as granting insurance benefits or decisions on surgery, the research use of the data requires understanding of processes used to construct data items. The use of population registers in health services research is clearly cost-effective. However, the lack of a high-performance computing capacity and environment suitable for processing large sensitive data, as well as inadequate information on the use of primary health care and eHRs has limited efficient use of extensive and complex linkage schemes and the utilisation of machine learning. The Finnish register authorities have improved computing facilities for research use and the legislative reform on secondary use of health care data is opening eHRs for research use granting higher granularity in describing content and quality of care. These developments enable big-data methods to be an essential part of the future methodological toolbox for health service research.

Exploring research trends in big data across disciplines: A text mining analysis

Using big data has been a prevailing research trend in various academic fields. However, no studies have explored the scope and structure of big data across disciplines. In this article, we applied topic modeling and word co-occurrence analysis methods to identify key topics from more than 36,000 big data publications across all academic disciplines between 2012 and 2017. The results revealed several topics associated with the storage, collection and analysis of large datasets; the publications were predominantly published in computational fields. Other identified research topics show the influence of big data methods and techniques in areas beyond computer science, such as education, urban informatics, business, health and medical sciences. In fact, the prevalence of these topics has increased over time. In contrast, some themes like parallel computing, network modeling and big data analytic techniques have lost their popularity in recent years. These results probably reflect the maturity of big data core topics and highlight flourishing new research trends pertinent to big data in new domains, especially in social sciences, health and medicine. Findings of this article can be beneficial for researchers and science policymakers to understand the scope and structure of big data in different academic disciplines.

Economic Supply and Demand with Data Analytics Functionalities

The primary goal of this article is to start a discussion about the possibility to connect supply and demand with data analytics functionalities in the frame of a dynamic system environment. So, a number of classical supply and demand topics, concepts, and definitions, as well as state-of-the-art data analytics concepts are reviewed firstly. Then, the critical modeling problem of both concepts “supply” and “demand” using system dynamics is introduced, analyzed, and examined. Finally, supply, demand, big data and data analytics are considered in a system dynamics modeling environment.&#x0D; Actually, the proposed paper provides an initial approach (introduction) to the main (basic) procedures, analytical approaches and methods of data and big data analysis. In particular, a framework to help program staff in their job and approaches on supply and demand issues using big data procedures and methods is presented. Accordingly, this article aims to support the work of data analytics and statistics staff across various content areas with big data functionalities.&#x0D; This article was created because the state-of-the-art concept “using data and information in meaningful and smart ways” includes many opportunities and possibilities and obviously a great deal of information is involved. Doubtless, some of this information has a great complexity and it is highly dependent upon specialized data, information and knowledge like the “data analytics” concept. However, there are many ways of “using data in smart ways” that are more primitive and that involve relatively simple enough procedures.&#x0D; Hence, the purpose of the current paper is to provide data analytics functionalities in supply and demand applications with a contemporary framework for thinking about, working with, and benefiting from an increased ability to use big data smartly and efficiently.&#x0D; Finally, the current paper should be characterized as a knowledge generation opinion article which recommends the inclusion of data analytics and distributed technology in supply and demand industry in order to enhance functionalities and compatibility to state-of-the-art ICT.