Field Of Big Data Research Articles

Class Imbalance Handling with Deep Learning Enabled IoT Healthcare Diagnosis Model

The rapid advancements in the field of big data, wearables, Internet of Things (IoT), connected devices, and cloud environment find useful to improve the quality of healthcare services. Medical data classification using the data collected by the wearables and IoT devices can be used to determine the presence or absence of disease. The recently developed deep learning (DL) models can be used for several processes such as classification, natural language processing, etc. This study presents a bacterial foraging optimization (BFO) based convolutional neural network-gated recurrent unit (CNN-GRU) with class imbalance handling (CIH) model, named BFO-CNN-GRU-CIH for medical data classification in IoT enabled cloud environment. The proposed BFO-CNN-GRU-CIH model initially enables the IoT devices to gather healthcare data and preprocess it for further processing. In addition, Lempel Ziv Markov chain Algorithm (LZMA) is employed for the compression of healthcare data to reduce the amount of data being communicated. Besides, Synthetic Minority Over-sampling Technique (SMOTE) is applied to handle class imbalance data problems. Moreover, BFO with CNN-GRU model is utilized to perform the classification process in which the hyperparameters of the CNN-GRU model are optimally adjusted by the use of BFO algorithm. In order to showcase the better performance of the BFO-CNN-GRU-CIH model, a wide range of simulations take place on three benchmark datasets and the results portrayed the betterment of the BFO-CNN-GRU-CIH model over the recent state of art approaches.

Preface

International Conference on Computer, Big Data And Artificial IntelligenceData has always existed in the changes of human society, constantly changing how humans learn about the world. It is also on the basis of data and information that human beings have made many efforts to explore the planet we live in. Not until modern information technology represented by electronic computer emerges did mankind make a qualitative leap in its ability to master and process data. In recent years, big data and artificial intelligence almost domain human activity, which provides a complex ecosystem of information and services on a global scale. Big data is essentially embodied as a digital virtual image for building the real world. Based on the premise of sufficient computing power and efficient data analysis methods, the in-depth study of this digital virtual image will make it possible to understand and discover the operation, state and laws of real complex systems.The 2nd International Conference on Computer, Big Data and Artificial Intelligence(ICCBDAI 2021) was co-organized by Central South University, Hunan University and Beijing Institute of Technology. Approximately 40 universities had participated the event, and there was over 2000 views for the live broadcast of this conference. Originally the conference was planned to be held in Beihai, China, however, considering the COVID-19 pandemic situation, it was decided to be held virtually online. As the conference organizer, the safety and well-being of our participants are our top priority.The conference aims to provide an international forum where engineers, researchers, practitioners and industrial partners in the field of Computer, Big Data and Artificial Intelligence can discuss/exchange/share recent advances/developments and future perspectives in the use of these technologies in various applications. In line with the aims of the ICCBDAI 2021 conference, and as maybe seen from the table of contents, the papers cover a wide range of topics under a variety of themes: Big Data Analysis and Measurement, Recent Advances in Artificial Intelligence with Applications, Intelligent Image Processing and Recognition, Challenges and Opportunities in Cloud Computing and Edge Computing, Big Data Analytics for Intelligent Transportation, etc.ICCBDAI 2021 was sponsored and supported by the followings:Central South UniversityHunan UniversityDalarna UniversityGuangxi UniversityChengdu University of Information TechnologyChangchun University of TechnologySilesian University of TechnologyList of Committee are available in this pdf.

Optimisation of energy consumption in cloud video surveillance centre based on monitoring and placement of virtual machines

Cloud computing is one of the most popular computational models, which requires plenty of physical devices where services are provided based on user demand. A majority of data centres need plenty of energy consumption which has become a challenge in recent years. Regarding cloud video surveillance - as a contemporary research field of cloud computing and big data, the service, due to the high demand for monitoring remote places, continually consumes surplus energy to process the high-volume data. This study considers the importance of energy consumption in cloud video surveillance, and it has been tried to increase the efficiency of servers concerning energy usage. The proposed method employs virtual machine placement in two steps, including monitoring and placement, to reduce energy consumption and increase the efficiency of servers. Implementation results in Cloudsim showed that it reduces energy consumption and increases resource efficiency.

Recent Books and Journals Articles in Public Opinion, Survey Methods, Survey Statistics, Big Data, Data Science, and User Experience Research. 2020 Update

Welcome to the 13th edition of this column on recent books and journal articles in the field of public opinion, survey methods, survey statistics, Big Data, data science and user experience research. After a hiatus due to the pandemic which affected my productivity, I am publishing this 2020 update. Special issues of journals have a space in this article because, in my view, they are like edited books. I also added review papers from the journal series of Annual Reviews because these papers are seminal state of the art writeups, a mini book, if you wish on a specific subject.

Recent Books and Journals Articles in Public Opinion, Survey Methods, Survey Statistics, Big Data, Data Science, and User Experience Research. 2019 Update

Welcome to the 12th edition of this column on recent books and journal articles in the field of public opinion, survey methods, survey statistics, Big Data, data science and user experience research. After a hiatus due to the pandemic which affected my productivity, I am publishing this 2019 update, and shortly, I will publish the 2020 update. Special issues of journals have a space in this article because, in my view, they are like edited books. I also added review papers from the journal series of Annual Reviews because these papers are seminal state of the art writeups, a mini book, if you wish on a specific subject.

Big data and AI: a potential solution to end the conundrum of too big to fail financial institutions?

Abstract The “too big to fail” institutions are a widespread concern, especially in the financial world. Their failure can create severe economic downturns and social turmoil. In past bank failures, governments intervened with public funds to save such institutions from collapse to avoid economic downturns. Since, measures have been put in place to prevent bank failures and limit the utilisation of public funds. However, failures cannot be prevented and risks of affecting the economy are always present in the case of too big to fail institutions. This article explores the possibilities offered by recent advancements in the fields of Big Data and Artificial Intelligence, widely implemented by the financial institutions themselves, as tools to be used by authorities in ending the too big to fail conundrum. The adequate implementation of these technological capabilities will contribute to the areas already targeted by governments – reducing the probability of failure and providing tools to limit negative externalities and spillover effects – and will also introduce a new capability that could address the too big to fail matter. Since financial institutions are, in their essence, data hubs, now in a digitalised format, the possibilities to automate tasks and provide insight for decisions should address the issue. The actual transfer of assets and liabilities to institutions that can carry on the activity, currently need years to be handle:. Big Data and Artificial Intelligence technologies could make such operations a matter of hours or days.

Considerations on the Impact of Emerging and Disruptive Technologies on Security Policies

Abstract The issue of the impact of emerging and disruptive technologies on security policy is a major concern of the North Atlantic Treaty Alliance. This is also demonstrated by the meeting between the Board members and the newly-established Advisory Group for Emerging and Disruptive Technologies, consisting of top experts in the fields of Cyber, Artificial Intelligence, Quantum Computing, Big Data, Space, Robotics and Autonomous or Biotechnological Systems, to find new synergies between NATO, the private, governmental and academic sectors and to maintain the technological supremacy of the Alliance. At the same time, the fact that the Romanian Army has mastered the defining elements of the impact of emerging and disrupted technologies on security policy and acts to make them operational is demonstrated by the meeting of July 12, 2021, of the Minister of National Defense, Nicolae-Ionel Ciuca with Heidi Grant, director of the US Defense and Security Cooperation Agency, on which occasion Romania received from the US the name of “Dependable Undertaking (DU)” under which contracts for the purchase of military equipment can be concluded without any payment in advance. Based on these elements, we would like to continue to talk about some aspects of innovation in dual military technologies, such as the influence of emerging and disruptive technologies on the organization and use of the armed forces. The research method undertaken consisted in identifying bibliographic resources, studying them, drawing relevant conclusions and formulating points of view on the impact of emerging and disruptive technologies on security policies.

Real-Time Based Big Data and E-Learning: A Survey and Open Research Issues

Big data is considered a remarkable aspect of development communication and information systems. In terms of delivery, retrieval, and storage, a vast volume of complex data exceeds the capability of conventional software and device capabilities. As a result, advanced alternative solutions that allow their control flow is becoming more prevalent. One of the most difficult fields of information management and technology is the real-time management, analysis, and processing of big data. These issues can be seen in a large amount of everyday produced data in a variety of places, including online social networks and the method of logging cell phone data. This survey looks at several studies that use a range of methods to handle, interpret, and process big data in real-time. Hence, the objective of this survey is to provide a comprehensive overview of the integration between real-time and big data fields of study with the field of E-learning. Finally, this survey also presents the colorful aspects of big data and their relationship to E-learning domains such that e-learning platforms, big data frameworks, and datasets used.

Incremental autoencoders for text streams clustering in social networks

Clustering data streams in order to detect trending topic on social networks is a chal- lenging task that interests the researchers in the big data field. In fact, analyzing such data needs several requirements to be addressed due to their large amount and evolving nature. For this purpose, we propose, in this paper, a new evolving clustering method which can take into account the incremental nature of the data and meet with its principal requirements. Our method explores a deep learning technique to learn incrementally from unlabelled examples generated at high speed which need to be clustered instantly. To evaluate the performance of our method, we have conducted several experiments using the Sanders, HCR and Terr-Attacks datasets.

Transfer learning based recurrent neural network algorithm for linguistic analysis

AbstractEach language is a system of understanding and skills that allow language users to work together, hypothesize, express thoughts, opinions; wishes need to be articulated. Linguistics is the research of these structures in all respects: the composition, usage, and sociology of language, in particular, are the core of linguistics. Machine learning is the research area that allows machines to learn without being specifically scheduled. In linguistics, the design of writing is understood to be a foundation for many distinct company apps and probably the most useful if incorporated with machine learning methods. Research shows that besides text tagging and algorithm training, there are major problems in the field of big data. This article provides a collaborative effort (transfer learning integrated into recurrent neural network) to analyze the distinct kinds of writing between the language's linear and noncomputational sides and to enhance granularity. In addition to this, this article creates a recurrent neural network model for learning and processing text data automatically. RNN based linguistic process is fast and cost‐effective. It analyses the text data automatically and iteratively. This is the main reason for using RNN for the linguistic process. The outcome demonstrates stronger incorporation of granularity into the language from both sides. Comparative results of machine learning algorithms are used to determine the best way to analyze and interpret the structure of the language.

What can machines do?

Mit zunehmender Rechen- und Speicherkapazität hält in der Medizin fast unaufhaltsam die Anwendung von Big Data und künstlicher Intelligenz Einzug. Haupteinsatzgebiete sind bisher v. a. in der Radiologie und Pathologie, jedoch auch in weiteren Bereichen wie der Genomsequenzierung bis hin zur Psychiatrie zu finden. Durch die Auswertung von immer größeren Datenmengen wird nach Mustern gesucht, die die Arbeit der Ärzte erleichtern können, indem sie eine Vorselektion betreiben. Darüber hinaus bestehen auch Bemühungen bisher unerkannte Zusammenhänge aufzudecken. Große Datenmengen werden von den Patienten selbst über sog. Wearables erfasst. Wie können diese Daten sinnvoll genutzt werden? Welche Gefahren bestehen? Auch in der Urologie gibt es Bestrebungen, eine Verbesserung der Behandlung von z. B. Harnwegsinfektionen oder Nierensteinen durch den Einsatz von vernetzten Computersystemen zu erreichen. Auf dem Gebiet von Big Data und Künstlicher Intelligenz sind in den nächsten Jahren große Fortschritte zu erwarten. Es wird auch zu einer erheblichen Erweiterung der Einsatzgebiete kommen, und wir sind somit erst am Anfang der Entwicklung.

Applying Machine Learning to the Development of Prediction Models for Bank Deposit Subscription

It is not easy for banks to sell their term-deposit products to new clients because many factors will affect customers’ purchasing decision and because banks may have difficulties to identify their target customers. To address this issue, we use different supervised machine learning algorithms to predict if a customer will subscribe a bank term deposit and then compare the performance of these prediction models. Specifically, the current paper employs these five algorithms: Naïve Bayes, Decision Tree, Random Forest, Support Vector Machine and Neural Network. This paper thus contributes to the artificial intelligence and Big Data field with an important evidence of the best performed model for predicting bank term deposit subscription.

Технологическое целеполагание в рамках новой образовательной области: «Большие данные» для системы профессиональной подготовки будущего экономиста

A weighty argument in favor of including the new educational area «Big Data» in the practice of professional training of the future economist is the competence in the field of building adequate predictive models, which is in demand in the modern labor market. Indeed, any leader is interested in improving the quality of the decisions made. This interest increases in conditions of sanctions pressure and post-pandemic restrictions, in difficult socio-economic conditions, when most of the resources are limited, the previously identified cause-and-effect relationships lose their relevance and the responsibility for decisions is significantly increased. Features of the implementation of the technological approach to disclosing the content of the new educational area «Big Data» in the system of professional training of the future economist is presented in this article as follows: firstly, in the form of a system of micro-goals at the basic level, and secondly, in the form of a system of micro-goals at an advanced level. Thus, within the framework of the technological goal-setting of the content of the new educational field, the principle of variability of the professional training of the future economist is implemented. Substantively presented in the article micro-goals cover various issues of using quantitative methods, mathematical and computational modeling. In addition, the formulations of micro-goals include requirements for the development of new tools that support big data analysis. Note that the implementation of technological goal-setting is necessary to strengthen the applied orientation of the training of a future economist, allows us to make a methodological emphasis on applied problems of socio-economic topics, the methods of solving which are in demand in future professional activities. The material of the article can be useful to teachers of the higher school of economics, as well as to anyone interested in modern methodological approaches to structuring educational content and achievements in the field of big data.

How does air pollution affect travel behavior? A big data field study

• This paper reports the first attempt to study the general impact of air pollution on a large population’s travel behavior via “big field data”: 4.6 billion mobile positioning records of 813,360 people during 61 winter days. • Comparing to the mixed findings in the literature, we find that air pollution does have a significantly negative impact on travel behavior. • People reduce their travel distance slightly but reduce their travel area greatly on air polluted days. In detail, people reduce the average RG by 0.76%, but reduce the average NP by 6.57% as AQI increases 100 points. • People in different demographic groups react to air pollution differently. Younger people (50 and under) reduce more NP, while older people (above 50) reduce more RG on heavily air polluted days. Exposure to ambient air pollution causes 4.2 million deaths worldwide every year; thus, people may avoid traveling on polluted days. However, the extant studies have mixed findings of the travel behavior on polluted days, caused by the shortcomings of survey data and specific activity data. In order to fulfill this research gap, this study evaluates the relationship between air pollution and travel behavior based on approximately 4.6 billion mobile positioning records in Xi’an, China. Moreover, this study also investigates how different demographic groups travel differently on polluted days. The results indicate that air pollution has a significantly negative correlation with travel behavior. Specifically, (1) people reduce travel distance slightly but reduce travel area greatly; and (2) younger people (50 and under) reduce more travel area while older people (over 50) reduce more travel distance on polluted days.

Big data analytics, resource orchestration, and digital sustainability: A case study of smart city development

Smart cities are expected to improve the efficiency and effectiveness of urban management, including public services, public security, and environmental protection, and to ultimately achieve Sustainable Development Goal (SDG) 11 for making cities inclusive, safe, resilient, and sustainable. Big data have been identified as a key enabler in the development of smart cities. However, our understanding of how different data sources should be managed and integrated remains limited. By analyzing data applications in the development of a sustainable smart city, this case study identified three phases of development, each requiring a different approach to orchestrating diverse data sources. A framework identifying the phases, data-related issues, data orchestration and its interaction with other resources, focal capabilities, and development approaches is developed. This study benefits both researchers and practitioners by making theoretical contributions and by offering practical insights in the fields of smart cities and big data.

Big Data and Firm Performance: An Outside-in Approach

ABSTRACT Little research has been undertaken into how marketing capabilities can leverage on big data analytics to improve firm performance. This study investigates whether an outside-in customer relationship management (CRM) linking capabilities can leverage big data analytics and organizational resources to improve firm performance. Structural equation modeling was used to analyze data collected from 315 employees in Jordanian companies. The results indicate that big data analytics presented through the amalgamation of data, technology, and human skills have a strong impact on CRM linking capabilities. Also, market information processing capabilities combining customer-focus and inter-functional coordination for knowledge interpretation also have a positive effect on CRM linking capabilities. CRM linking consequently has a positive impact on multi-dimensional firm performance. This study contributes to the field of big data through its adoption of an outside-in approach that integrates a range of capabilities into an integrative framework that delineates the process of successful big data.

Building Architecture of Intelligent Control System for Urban Rail Transit System

The increase in the volume of passenger transportation in megalopolises and large urban agglomerations is efficiently provided by the integration of urban public transit systems and city railways. Traffic management under those conditions requires creating intelligent centralised multi-level traffic control systems that implement the required indicators of quality, comfort, and traffic safety regarding passenger transportation. Besides, modern control systems contribute to traction power saving, are foundation and integral part of the systems of digitalisation of urban transit and the cities. Building systems solving the traffic planning and control tasks is implemented using algorithms based on the methods of artificial intelligence, principles of hierarchically structured centralised systems, opportunities provided by Big Data technology. Under those conditions it is necessary to consider growing requirements towards software as well as theoretical design and practical implementation of network organisation.This article discusses designing architecture and shaping requirements for developed applications and their integration with databases to create a centralised intelligent control system for the urban rail transit system (CICS URTS). The article proposes the original architecture of the network, routing of information flows and software of CICS URTS. The routing design is based on a fully connected network. This allows to significantly increase the network bandwidth and meet the requirements regarding information protection, since information flows are formed based on the same type of protocols, which prevents emergence of covert transmission channels. The implementation of the core using full connectivity allows, according to the tags of information flows, to pre-form the routes for exchange of information between servers and applications deployed in CICS URTS. The use of encrypted tags of information flows makes it much more difficult to carry out attacks and organise collection of information about the network structure.Platforms for development of intelligent control systems (ICS), which include CICS URTS, high computing power, data storage capacity and new frameworks are becoming more available for researchers and developers and allow rapid development of ICS. The article discusses the issues of interaction of applications with databases through a combination of several approaches used in the field of Big Data, substantiates combination of Internet of Things (IoT) methodology and microservice architecture. This combination will make it possible to single out business processes in the system and form streaming data processing requiring operational analysis by a human, which is shown by relevant examples.Thus, the objective of the article is to formalise the principles of organising data exchange between CICS URTS and automated control systems (ACS) of railway companies (in our case, using the example of JSC Russian Railways), URTS services providers, and city government bodies, implement the developed approaches into the architecture of CICS URTS and formalise principles of organisation of microservice architecture of CICS URTS software. The main research methods are graph theory, Big Data and IoT methods.

Country-Specific Interests towards Fall Detection from 2004–2021: An Open Access Dataset and Research Questions

Falls, which are increasing at an unprecedented rate in the global elderly population, are associated with a multitude of needs such as healthcare, medical, caregiver, and economic, and they are posing various forms of burden on different countries across the world, specifically in the low- and middle-income countries. For these respective countries to anticipate, respond, address, and remedy these diverse needs either by using their existing resources, or by developing new policies and initiatives, or by seeking support from other countries or international organizations dedicated to global public health, the timely identification of these needs and their associated trends is highly necessary. This paper addresses this challenge by presenting a study that uses the potential of the modern Internet of Everything lifestyle, where relevant Google Search data originating from different geographic regions can be interpreted to understand the underlining region-specific user interests towards a specific topic, which further demonstrates the public health need towards the same. The scientific contributions of this study are two-fold. First, it presents an open-access dataset that consists of the user interests towards fall detection for all the 193 countries of the world studied from 2004–2021. In the dataset, the user interest data is available for each month for all these countries in this time range. Second, based on the analysis of potential and emerging research directions in the interrelated fields of Big Data, Data Mining, Information Retrieval, Natural Language Processing, Data Science, and Pattern Recognition, in the context of fall detection research, this paper presents 22 research questions that may be studied, evaluated, and investigated by researchers using this dataset.

Preface

Due to recent pandemic, the 2021 International Conference on Big Data and Intelligent Algorithms (BDIA 2021) which was planned to be held in Chongqing, China was held virtually online during July 9-11, 2021. The decision to hold the virtual conference was made in compliance with many restrictions and regulations that were imposed by countries around the globe. Such restrictions were made to minimize the risk of people contracting or spreading the COVID-19 through physical contact. There were 70 individuals who attended this online conference, represented many countries including Tunisia, Iran, Spain and China.BDIA 2021 dedicates to create a platform for academic communications between specialists and scholars in the fields of Big Data and Intelligent Algorithms. The conference created a path to establish a research relation for the authors and listeners with opportunities for collaboration and networking among the universities and institutions for promoting research and developing technologies. BDIA 2021 welcomes all high-quality research papers and presentations from related research fields.During the conference, the conference model was divided into three sessions, including oral presentations, keynote speeches, and online Q&A discussion. In the first part, some scholars, whose submissions were selected as the excellent papers, were given about 5-10 minutes to perform their oral presentations one by one. Then in the second part, keynote speakers were each allocated 30-45 minutes to hold their speeches. In the second part, we invited two professors as our keynote speakers. Prof. Zhikui Chen, from Dalian University of Technology, China, performed a speech: Multimodal data learning and applications. And then we invited Prof. Fengqing Han, from Chongqing Jiaotong University, China as our finale keynote speaker. He made a wonderful speech: The Asymmetric Evolutionary Game Based on Dynamic Payoff. Their insightful speeches had triggered heated discussion in the third session of the conference. Every participant praised this conference for disseminating useful and insightful knowledge.The proceedings are a compilation of the accepted papers and represent an interesting outcome of the conference. Topics include but are not limited to the following areas: Big Data, Intelligent Data Processing, Algorithms, Nature Inspired Computing and Optimization, Intelligent Data Fusion. All the papers have been through rigorous review and process to meet the requirements of International publication standard.We would like to acknowledge all of those who supported BDIA 2021. The help and contribution of each individual and institution was instrumental in the success of the conference. In particular, we would like to thank the organizing committee for its valuable inputs in shaping the conference program and reviewing the submitted papers.We sincerely hope that the BDIA 2021 turned out to be a forum for excellent discussions that enabled new ideas to come about, promoting collaborative research. We are sure that the proceedings will serve as an important research source of references and knowledge, which will lead to not only scientific and engineering findings but also new products and technologies.Committee of BDIA 2021List of Committee member are available in this pdf

The Research Hotspot and Path Evolution of Big Data in Healthcare Industry: Visualized Analysis Based on Cite Space

Along with the swift development of big data, the application fields of big data have become more and more broad, as well as the fusing of big data and healthcare. In this paper, CiteSpace, the bibliometrics software, was used for analyzing the research status and hotspots of big data in healthcare fields. Taking big data and healthcare as the keywords, the core database of Web of Science from 2011 to 2020 has been retrieved. According to author/country/organization co-authorship analysis and author/journal/reference co-cited analysis, the research status of big data in healthcare was discussed. Through the keywords co-occurrence network and cluster analysis, research hotspot and path evolution of big data in healthcare were also studied.