Big Data Applications Research Articles

A prototype-assisted clustered federated learning for big data security and privacy preservation

In the rapidly expanding field of IoT, data production has reached an unprecedented scale, providing valuable insights that accelerate decision-making processes. However, ensuring the privacy and security of this massive amount of data poses significant challenges. In this paper, we propose using clustered federated learning (CFL) as a solution to ensure both the security and privacy of big data by uploading model weights while keeping the data stored locally. Nevertheless, there are practical challenges in applying CFL to big data: (1) the participating FL clients are unlikely to have identical data distributions; (2) insufficient attention is given to the similarity between different clusters; and (3) CFL tends to ignore the class imbalance problem (i.e., long-tailed), which hinders its application in big data and affects the quality of target tasks. To address these issues and enable widespread CFL deployment in big data applications, this paper proposes a prototype-assisted clustered federated learning framework (MDSPFL). It relaxes the assumption of unique data distribution for each client, allowing the client’s local dataset to follow multiple source distributions considering classification class imbalance, thereby aligning with clients in a big data environment. Specifically, MDSPFL employs the proximal update mechanism to handle workload surges caused by mixed distribution and unavailability of similarity between cluster models. Additionally, MDSPFL introduces a class-balanced local training mechanism to resolve the long-tailed problem, which utilizes contrastive learning and class prototypes to enforce a uniform distribution of all classes in the feature space. We conduct extensive experiments on different datasets (EMNIST, Cifar10, Cifar100), and the experimental results demonstrate the effectiveness of our proposed MDSPFL in big data scenarios with imbalance and mixed-distribution clients.

Environmental impact assessment of the manufacture and use of N- type and P-type photovoltaic modules in China

For a long time, solar power has been considered a clean and non-polluting energy source because it absorbs sunlight without consuming other energy or materials and does not emit pollutants. Nevertheless, the manufacturing and end-of-life stages of solar power systems leave an environmental footprint and produce pollutants. Hence, a global perspective on photovoltaic (PV) systems using life cycle assessment methodology is necessary. Here, we investigated the life cycle impacts of P- and N-type PV modules in terms of their energy consumption, carbon emissions, and human toxicity potential. In addition, the energy payback durations of P- and N-type PV modules were computed. In this study, we used the Life Cycle Assessment Basic Database from the National Engineering Laboratory of Industrial Big Data Application Technology at Beijing University of Technology to create a life cycle assessment model for N-type PV modules. Subsequently, we performed a life cycle assessment of Chinese silicon N-type- and P-type PV modules. The research system encompassed the production processes for metallic silicon materials, solar-grade silicon materials, silicon wafers, cells and modules, utilization, recycling, and other interrelated processes. We found that the production and processing of silicon-to-solar-grade polysilicon feedstock were crucial stages that significantly affected the energy consumption and environment of P- and N-type PV modules in China. The high electricity consumption of this process, combined with the dominance of coal power in China's electricity structure, contributed to the substantial energy consumption and environmental impacts of the PV modules. Therefore, this stage is critical for the low-carbon and environmentally sustainable manufacturing of N-type PV modules in China. Carbon emissions for both the P-type and N-type PV modules were lower only during the cell production phase but higher during the other stages when compared to the P-type and N-type PV modules. The n-type bifacial PV modules yielded the highest return on investment in terms of energy. Different regions and installation types have a substantial impact on the carbon emissions of P-type and N-type PV modules. Projections indicate that the potential to lower carbon emissions from n-type PV modules will increase by 2060.

Application of Big Data in College Student Education Management Based on Data Warehouse Technology and Integrated Learning

Integrated learning has attracted much attention from industry and academia. In the new era, colleges and universities need to discuss information management in light of actual conditions, integrate different data in each information system into the same database, so as to form a data warehouse based on the integrated database which can truly reflect the historical changes of data and provides support for managers' decision-making. This paper analyzes the clustering effect of standard differential evolution algorithm, improved differential evolution algorithm and K-means algorithm. The algorithm is tested using Iris and Wine database marts, the results show that the K-means algorithm is a relatively poor algorithm and its accuracy is significantly lower than the other two. Based on big data, multi-factor interactive variance analysis technology is used to analyze different data indicators and influencing factors. Therefore, colleges and universities can use the database to better understand the problems and advantages in management, thus to improve management efficiency and teaching level.

Research on Personal Medical Information Protection Based on Big Data

The rapid development of big data, cloud computing, and artificial intelligence has brought new opportunities to the development of the medical field. The emergence of electronic medical records and medical information systems has provided great convenience for people's medical treatment. However, the arrival of the big data era also poses new challenges to the protection of human medical privacy. The development and application of medical big data have led to explosive growth of data in the medical field, putting pressure on the management of medical institutions. The sharing of medical data between medical institutions and between medical institutions and third parties also poses significant security risks. Moreover, medical data leakage incidents have been continuously exposed in recent years, seriously infringing on the identity and privacy rights of patients. This article aims to explore the research on personal medical information protection based on big data. Firstly, the importance and necessity of protecting personal medical information were analyzed, as well as the current application status and existing problems of big data in medical information management. Secondly, a comparative analysis of domestic and international research on medical privacy protection was elaborated, including the analysis of medical information privacy protection standards in the United States, Europe, and Asia, and the differences and commonalities of international medical information privacy protection standards were compared and analyzed. Then, the theoretical basis of medical information privacy protection was summarized. Then, the application methods and technologies of big data in personal medical information protection were discussed. Finally, relevant countermeasures and suggestions for the protection of personal medical information in big data were discussed, including privacy protection technologies and policy recommendations, as well as ethical issues and norms for the protection of medical information privacy. Through this study, it is hoped that it can provide reference and inspiration for the protection of personal medical information in big data, and provide ideas and suggestions for future development directions.

Navigating Strategic Balance: CEO Big Data Orientation, Environmental Investment, and Technological Innovation in Chinese Manufacturing

In the digital age, China’s economic development is transitioning from high speed to high quality. Through the application of digital technology, China’s manufacturing industry is moving toward more environmentally friendly and sustainable innovation, which makes it of great significance to study the effect of green investment and big data on innovation. Grounded in strategic management theory, this paper examines the interplay between CEO big data orientation, environmental investment, and their joint impact on technological innovation in manufacturing enterprises. Data are extracted from annual reports of listed Chinese manufacturing companies using computer-assisted text analysis methods and evaluated with negative binomial regression. The results indicate an inverted U-shaped relationship between CEO big data orientation and technological innovation. The results further explain that as CEO big data orientation increases, enterprises with higher levels of green investment will reach the peak of technological innovation performance earlier. According to China’s intelligent manufacturing in 2035, we have proposed some methods and suggestions for green investment and big data applications.

The use of big data analytics for human resource management in an organization

Aim. To examine the application of big data in the field of human resource management and in organizational network analysis as a methodology to study the patterns of employee interaction within a formal organizational structure to improve the effectiveness of the human resource management system.Objectives. Theoretical analysis of existing methodologies for evaluating data on human resources of an organization to provide new opportunities for enterprise transformation; identification of hidden information on human resources and its use for internal staff development, retention and training; study of the possibilities of using organizational network analysis (ONA) to improve the effectiveness of human resource management.Methods. The authors used system and logical approaches, general scientific methods (analysis, synthesis), methods of comparative and economic analysis, analytical processing of information, graphical presentation of information.Results. The sources of big data are analyzed, the main indicators characterizing the state of personnel and allowing to forecast its development, dynamics of preservation of human resources in the organization, its training are allocated. The directions of using organizational network analysis in the personnel management system are proposed.Conclusions. The identified potential advantages of using organizational network analysis in the analytics of data on human resources in the organization will contribute to the reduction of staff turnover, optimization of staff structure, improvement of experience and knowledge sharing within the organization. This, according to the author’s position, will lead the enterprise to a positive economic effect and open new opportunities for its transformation

Analysis of the Impact of Big Data Technology on Environmental Pollution Control Audit

As China strives towards the second centenary goal, increasing attention is being paid to environmental pollution and other related issues. Concurrently, with the rapid development of big data technology, many big data solutions have been applied to environmental pollution control audits, exerting a significant impact. This paper presents the current situation of environmental pollution audits, summarizing the application of big data from the perspectives of both domestic and international research. In terms of data collection and data analysis for environmental pollution audits, cloud platform technology, and visualization technology are selected based on multiple data sources. The impact in the field of environmental pollution control audits is further analyzed. It is found that the environmental pollution audit cloud platform is not yet perfect, the technical skills of audit personnel are insufficient, and some technologies are not mature. Relevant suggestions are put forward to provide a reference for the future development of big data technology and its integration with environmental pollution control audits.

Enhancing Safety and Quality in College Sports Management Through Big Data and Artificial Intelligence (AI)

The purpose of this study is to explore how artificial intelligence (AI) and big data can be used to solve the twin issues of athlete safety and sports event quality in a college sports environment. Furthermore, this study attempts to fill the literature vacuum regarding the application and effectiveness of artificial intelligence and big data in improving safety and quality in collegiate sports administration by investigating possible synergies between these elements and the implementation of developed technologies. This qualitative study used a sampling method to conduct in-depth interviews with 18 sports administrators and commentators. Using coding and classification methods, the data were evaluated thematically with a focus on artificial intelligence and big data applications. Research has found that artificial intelligence and big data play a key role in proactively reducing injuries, optimizing athlete performance and enabling data-driven decision-making. It also identifies barriers and opportunities for integrating these technologies, revealing their dynamic potential. This study provides new perspectives on the relationship between safety and quality and the application of artificial intelligence and big data in collegiate sports management. It also highlights the ways in which these technologies have transformative potential in sport. The findings have important implications for educational programs and policy development aimed at managing responsible technology integration and preparing future professionals in the field of sport management.

Laboratory Preparation for Digital Medicine in Healthcare 4.0: An Investigation Into the Awareness and Applications of Big Data and Artificial Intelligence.

Healthcare 4.0. refers to the integration of advanced technologies, such as artificial intelligence (AI) and big data analysis, into the healthcare sector. Recognizing the impact of Healthcare 4.0 technologies in laboratory medicine (LM), we seek to assess the overall awareness and implementation of Healthcare 4.0 among members of the Korean Society for Laboratory Medicine (KSLM). A web-based survey was conducted using an anonymous questionnaire. The survey comprised 36 questions covering demographic information (seven questions), big data (10 questions), and AI (19 questions). In total, 182 (17.9%) of 1,017 KSLM members participated in the survey. Thirty-two percent of respondents considered AI to be the most important technology in LM in the era of Healthcare 4.0, closely followed by 31% who favored big data. Approximately 80% of respondents were familiar with big data but had not conducted research using it, and 71% were willing to participate in future big data research conducted by the KSLM. Respondents viewed AI as the most valuable tool in molecular genetics within various divisions. More than half of the respondents were open to the notion of using AI as assistance rather than a complete replacement for their roles. This survey highlighted KSLM members' awareness of the potential applications and implications of big data and AI. We emphasize the complexity of AI integration in healthcare, citing technical and ethical challenges leading to diverse opinions on its impact on employment and training. This highlights the need for a holistic approach to adopting new technologies.

Opportunities and Challenges of Utilising Big Data on SATUSEHAT Platform in Nursing: A Literature Review

The SATUSEHAT platform which is Indonesia Health Services (IHS) is a form of digital transformation initiated by the Indonesian Ministry of Health. This platform integrates the health data of all Indonesian people including medical records across health facilities which will develop into a national health data center and has the opportunity to become big health data for the Government. To face this, the nursing field must prepare for various opportunities and challenges. Objective: To provide an overview of the opportunities and challenges of utilizing big data through the SATUSEHAT platform in the nursing field. The method used in this research is literature review. The keywords used were Big data in nursing and The Application of big data for the future. Literature searches were conducted using the online database method starting from 2015-2022 through ScienceDirect, ProQuest and Clinical Key. As a result of the literature review with a case study design, it was found that opportunities for big data utilization include personalized care, nursing research development, data-based policy formulation, while challenges include increasing data processing and management competencies, integrating big data education curriculum, privacy and ethical issues and standardizing nursing terminology Recommendations It is hoped that further research can discuss the preparations that must be made to maximize the potential for big data utilization in the future.

Random kernel k-nearest neighbors regression.

The k-nearest neighbors (KNN) regression method, known for its nonparametric nature, is highly valued for its simplicity and its effectiveness in handling complex structured data, particularly in big data contexts. However, this method is susceptible to overfitting and fit discontinuity, which present significant challenges. This paper introduces the random kernel k-nearest neighbors (RK-KNN) regression as a novel approach that is well-suited for big data applications. It integrates kernel smoothing with bootstrap sampling to enhance prediction accuracy and the robustness of the model. This method aggregates multiple predictions using random sampling from the training dataset and selects subsets of input variables for kernel KNN (K-KNN). A comprehensive evaluation of RK-KNN on 15 diverse datasets, employing various kernel functions including Gaussian and Epanechnikov, demonstrates its superior performance. When compared to standard KNN and the random KNN (R-KNN) models, it significantly reduces the root mean square error (RMSE) and mean absolute error, as well as improving R-squared values. The RK-KNN variant that employs a specific kernel function yielding the lowest RMSE will be benchmarked against state-of-the-art methods, including support vector regression, artificial neural networks, and random forests.

Agile-Ant: Self-Managing Distributed Cache Management for Cost Optimization of Big Data Applications

Distributed in-memory processing frameworks accelerate application runs by caching important datasets in memory. Allocating a suitable cluster configuration for caching these datasets plays a crucial role in achieving minimal cost. We present Agile-ant, a self-managing framework that identifies important datasets and scales out the cluster memory to cache them on the fly without any human interaction, without any prior knowledge of the application, the characteristics of the input data, the specification of the computing resources and their utilization by multiple-tenants. We evaluate Agile-ant on various real-world applications. Compared with our baseline, Agile-ant reduces execution cost by 78.3% on average and provides better performance than the related work.

Big data application simulation platform design for onboard distributed processing of LEO mega-constellation networks

Big data application simulation platform design for onboard distributed processing of LEO mega-constellation networks

Applications of Medical Big Data and Personal Information Protection

In the current social environment, the generation and application of medical big data is closely related to the personal information security of every citizen. With the continuous development of medical technology, the application of medical big data has become increasingly widespread. On one hand, it can promote the development of medical technology, including drug development, personalized medicine, and precision treatment. On the other hand, medical big data also concerns the private information of citizens, which is a crucial part of personal information protection. However, in practice, there often exists a contradiction between medical big data and the protection of citizens' personal information rights. From the perspective of medical big data, there are overlaps and differences among citizens' personal information, privacy information, medical health information, and medical big data information. Relying solely on the “informed consent” rule for personal information cannot effectively protect personal information comprehensively or guarantee the application and development of medical big data. This article analyzes the issues surrounding Chinese medical big data in terms of personal information from a legal perspective, and proposes corresponding solutions to these issues. It is hoped that this research can contribute to advancing the legalization of medical data openness, re-examining patients' personal information in the context of medical big data, and balancing the conflicts between individual privacy interests, public interests, and economic benefits of medical data, thus better protecting individuals' personal information interests under social and private benefits.

Unveiling the Power of Big Data: Insights into Big Data Analytics, Applications, and Advancements

Abstract: In the era of digital transformation, the exponential growth of data from multifaceted origins has fundamentally revolutionized decision-making and strategic planning across global industries. Big Data, distinguished by its immense volume, rapid velocity, diverse variety, and critical veracity, introduces unprecedented opportunities alongside formidable challenges. This journal explores the foundational concepts, methodologies, and applications of Big Data and analytics. It delves into the types and characteristics of Big Data, examines sources and collection methods, outlines analytical steps and tools, and addresses the inherent challenges. Through comprehensive analysis, this journal aims to provide insights into leveraging Big Data for informed decision-making, innovation, and competitive advantage in various sectors.

LEVERAGING BIG DATA TECHNOLOGIES FOR ENHANCED PUBLIC PARTICIPATION IN PUBLIC FINANCIAL MANAGEMENT

The article is devoted to the topical issues regarding the implementation of Big Data technologies in public finance management. The application of Big Data has the potential to enhance transparency and accountability in the use of budgetary resources, increase trust in government, improve the efficiency of budget resource utilization, better understand citizens' needs, and engage the public in public finance management. The purpose of the study is to explore theoretical, methodological, and practical aspects, as well as to develop recommendations for the implementation of Big Data processing and analysis technologies to enhance public participation in public financial management. The article examines traditional methods of civil engagement in the budgetary process, identifies their disadvantages, and explores Big Data technology potential based on Computational Linguistics and Machine Learning to strengthen public participation. Developments in sentiment analysis and opinion mining have been adapted to the field of public finance. A generative model for analyzing public sentiment on social networks regarding public finance management has been constructed and tested. The approaches developed for using Big Data technologies can be implemented in the field of public finance to enhance public participation in their management as advisory tools for the realization of representative democracy and require further theoretical elaboration and practical application to improve the analysis of alternative sentiments, prevent manipulation of public opinion, and abuse within the network.

Research and Practice of Teacher-Student Competition Training Mode based on "Big Data Application Development" Vocational Skill Competition

Research and Practice of Teacher-Student Competition Training Mode based on "Big Data Application Development" Vocational Skill Competition

Big Data Challenges and Opportunities for Disaster Early Warning System

The application of big data in early warning systems (EWS) for multi-hazard risk management is becoming increasingly popular due to its enormous potential. Nevertheless, despite noteworthy achievements, there are still several enduring obstacles. This study aims to evaluate the advantages and difficulties through a comprehensive SWOT (strengths, weaknesses, opportunities, threats) analysis and the use of existing literature. An extensive literature analysis was conducted, incorporating perspectives of researchers from diverse background investigating both technical and social elements. The study results showed several notable strengths, such as unmatched accuracy and comprehensiveness, the incorporation of several data sources to improve prediction and forecasting, and the exploitation of up-to-the-minute data. On the other hand, problems, such as insufficient monitoring of hazards and a scarcity of interconnected sensors, especially common in less developed countries, were recognized. Lack of adequate coverage leaves a substantial percentage of the population vulnerable to disaster risks as a result of inadequate early warning systems. Ultimately, although big data offers significant possibilities, its complete capacity remains unexplored in the least developing nations due to existing obstacles, such as shortage of skilled worker, data accuracy and privacy which can be solved by enhancing technology education, capacity building, and practice. The objective of this study is to help such nations identify and overcome underlying challenges by implementing suitable measures.

Strategic financial decision-making in sustainable energy investments: Leveraging big data for maximum impact

In the context of escalating environmental concerns and the transition towards a greener economy, sustainable energy investments have emerged as a pivotal area for financial growth and innovation. This paper outlines a strategic framework for financial decision-making in sustainable energy investments, emphasizing the transformative role of big data. By integrating big data analytics into the investment process, stakeholders can enhance market analysis, risk assessment, performance monitoring, and predictive modeling, leading to more informed and effective investment strategies. The paper delves into various big data sources, analytical tools, and technologies that facilitate the collection, processing, and interpretation of vast amounts of information. Additionally, it presents case studies illustrating successful applications of big data in solar and wind energy projects, highlighting best practices and common challenges. The discussion extends to future trends, including advancements in artificial intelligence and machine learning, which are poised to further revolutionize the sector. The paper concludes with strategic recommendations for developing a data-driven investment approach, building robust data infrastructures, and fostering a culture of continuous learning and adaptation. By leveraging big data, investors can maximize the impact of their investments, drive sustainable growth, and contribute to the global energy transition. Keywords: Sustainable Energy Investments, Big Data Analytics, Strategic Financial Decision-Making, Market Analysis, Risk Assessment, Predictive Modeling.

Reform and Development of College Music Teaching under the Background of Big Data

With the progress of the times, big data has gradually influenced the daily lives of people and is gradually changing the ways people learn. Big data plays a role in the field of college music education, changing college music education methods significantly. The use of big data technology can make teaching resources more abundant and teaching methods more diversified, which improves the efficiency and quality of college music education. The application of big data has long been the norm in the field of education. As an innovative educational means, colleges should make full use of the advantages of big data to promote college music education and to cultivate the growth of students.