Big Data Model Research Articles

Security and Privacy Issues in IoT-Based Big Data Cloud Systems in a Digital Twin Scenario

Due to its unique type of services, Cloud Computing could operate as a “base technology” for other technologies; this attracts researchers to develop sustainable Cloud systems. It is a new generation of services that offers an opportunity for users to access and manage their information, applications, and data regardless of place and time. Nevertheless, there is a type of service that can include large amounts of data, called Big Data, and it consists of the rapid use of the Internet of Things (IoT) to produce large data sets. In this work, initially, we present Cloud Computing (CC) and Big Data (BD) exported from IoT, focusing on the security and management challenges of both. Notably, we combine the two aforementioned technologies to examine their related characteristics and discover new perspectives and opportunities for their integration and to achieve a sustainable environment called a Digital Twin scenario. Subsequently, we present how Cloud Computing contributes to IoT-based Big Data, aiming to fill a scientific gap in the sector of their integration regarding security and privacy. Finally, we additionally survey the security challenges of the integrated model of BD and CC and then propose a novel security algorithm for sustainable Cloud systems in a Digital Twin scenario. The experimental results presented are based on the use of the encryption algorithms AES, RC5, and RSA, and our proposed model extends the advances of CC and IoT-based BD, offering a highly novel and scalable service platform to achieve better privacy and security services.

Retracted: An Empirical Study on Application of Virtual Reality Animation Technology by Big Data Model

Retracted: An Empirical Study on Application of Virtual Reality Animation Technology by Big Data Model

Retracted: Sports Economic Mining Algorithm Based on Association Analysis and Big Data Model.

[This retracts the article DOI: 10.1155/2022/1518202.].

Big data analytics-based approach for robust, flexible and sustainable collaborative networked enterprises

Networked enterprises (NEs) in the current business are constantly under pressure from stakeholders and government restrictions to encourage ethical and transparent behavior in using natural resources, and their impacts on nearby and global ecosystems, people, and communities. In addition, NEs face vulnerable economical challenges including, market changes, personalized consumer trends, as well as, environmental and social restrictions. In this context, this paper addresses the problem of sustainable NEs vulnerabilities. To do so, a big data analytics-based approach is developed to drive sustainable NEs flexibility and robustness. More specifically, flexibility refers to the network’s ability to respond quickly to changes and risks. While robustness concerns the development of optimum and long-term strategies enabling the network to cope with severe environmental risks and economical costs. Moreover, even if the literature is rich with Big Data models and frameworks developed for sustainable enterprises, there is a real need to scale and extend existing models to cover all sustainability pillars (i.e., social, environmental, and economical) and sustainable value creation (SVC). Accordingly, flexibility and robustness coupling with big data analytics (BDA) levels (i.e. descriptive analytics, diagnostic analytics, predictive analytics, prescriptive analytics) will enable NEs to grow sustainability in order to create sustainable value. Finally, to demonstrate the applicability of the developed approach, the corporate environmental impact (CEI) database is used to evaluate the sustainable development goals (SDGs) of NEs. The obtained numerical results show the efficiency of our approach.

A comparison study Big Data Analytics Methods for Selecting Suitable Method

Nowadays, Big Data become very critical and can help organizations to make decisions by analyzing feedback and reviews from customers. There are large amounts of data that is growing because of the extensive use of networks, social media, and other sources. Big data analytics can enhance a company's understanding of a customer's needs and preferences. By analyzing data organizations can personalize and relevant product or service; So that, there is a need to analyze such huge amounts of data. There are many types of analytics methods and each one has its own objectives. Therefore, this work highlights two ways for classifying big data analytics methods. Big data models and their methodologies were clearly outlined in this paper. Additionally we compare different categories of big data analytics techniques depending on data kinds like audio, video, social media, and predictive analytics. Also, this work intended to study the big data analytics methods for selecting the suitable method.

Software Engineering Classification Model and Algorithm Based on Big Data Technology

With the development of internet technology, cloud computing is becoming increasingly popular, and it has a wide range of applications in various fields, such as mobile payments and the Internet of Things. The big data model is a very important and valuable set of useful and unique information. This article mainly introduces the establishment of an object-oriented architecture-based machine learning system classification model using big data analysis methods, as well as the use of neural network algorithms to construct machine learning system classification patterns. Through examples, a comparative experiment is conducted to verify the effectiveness of traditional manual annotation modeling methods combined with parallel processing. Its experimental results show that the model has high accuracy, with an accuracy rate above 92% and a recall rate above 94%, and its F1 value is infinitely close to 1, indicating that the average accuracy and precision of the model is very high.

Retracted: An Empirical Study on Big Data Model and Visualization of Internet+ Teaching

Retracted: An Empirical Study on Big Data Model and Visualization of Internet+ Teaching

Retracted: Development and Performance Evaluation of Digital Technology and Radio and Television Integration Based on Big Data Model

Retracted: Development and Performance Evaluation of Digital Technology and Radio and Television Integration Based on Big Data Model

Wordle data analysis based on time series analysis model

Using LSTM time series analysis and forecasting is an important guide for Wordle's game development direction planning and economic revenue visualization. Accurate game report data prediction is of great significance for game development, economic investment, post-game planning, and improving player experience. As Wordle's game becomes more and more popular, it is essential to make predictions and projections about the future of the game as well as collate the data. In order to accurately predict the data reported by Wordle players in the future, based on the theory of time series analysis, combined with the extensive collection and screening of retrieval data, and the advantages of LSTM model and linear regression equation in the direction of prediction, a multi-dimensional prediction model for big data was established. With this prediction model, the development of Wordle games can be predicted according to a variety of prediction dimensions. After the accurate prediction of big data, the influential factors behind the data can be analyzed, which can simplify people's understanding of data to a certain extent, and successfully realize the transition from sophisticated technology to service-oriented demand.

Retracted] Storage Method for Medical and Health Big Data Based on Distributed Sensor Network

Monitoring and collecting medical data using embedded medical diagnostic devices with multiple sensors and sending these actual measured data to the corresponding health monitoring centers using multipurpose wireless networks to take necessary measures to coordinate with family medical service centers and regional medical service departments is a popular medical big data architecture. However, healthcare big data is characterized by large data volume, fast growth, multimodality, high value and privacy, etc. How to organize and manage it in a unified and efficient way is an important research direction at present. In response to the problems of low balance and poor security in the storage of data collected by distributed sensor networks in healthcare systems, we propose a distributed storage algorithm for big data in healthcare systems. The platform adopts Hadoop distributed file system and distributed file storage framework as the healthcare big data storage solution, and implements data integration, multidimensional data query and analysis mining components based on Spark‐SQL data query tool, Spark machine learning algorithm library and its mining and analysis pipeline development, respectively. The distributed storage model of big data and three data storage levels are constructed using cloud storage architecture, and the data storage intensity as well as levels are calculated by high data access in the upper level, data connection in the middle level, and data archiving in the lower level according to the set known data granularity, odds, and elasticity to realize big data storage. It is experimentally verified that the above algorithm has high distribution balance and low load balance in the storage process.

An Imbalanced Dataset and Class Overlapping Classification Model for Big Data

Most modern technologies, such as social media, smart cities, and the internet of things (IoT), rely on big data. When big data is used in the real-world applications, two data challenges such as class overlap and class imbalance arises. When dealing with large datasets, most traditional classifiers are stuck in the local optimum problem. As a result, it’s necessary to look into new methods for dealing with large data collections. Several solutions have been proposed for overcoming this issue. The rapid growth of the available data threatens to limit the usefulness of many traditional methods. Methods such as oversampling and undersampling have shown great promises in addressing the issues of class imbalance. Among all of these techniques, Synthetic Minority Oversampling TechniquE (SMOTE) has produced the best results by generating synthetic samples for the minority class in creating a balanced dataset. The issue is that their practical applicability is restricted to problems involving tens of thousands or lower instances of each. In this paper, we have proposed a parallel mode method using SMOTE and MapReduce strategy, this distributes the operation of the algorithm among a group of computational nodes for addressing the aforementioned problem. Our proposed solution has been divided into three stages. The first stage involves the process of splitting the data into different blocks using a mapping function, followed by a pre-processing step for each mapping block that employs a hybrid SMOTE algorithm for solving the class imbalanced problem. On each map block, a decision tree model would be constructed. Finally, the decision tree blocks would be combined for creating a classification model. We have used numerous datasets with up to 4 million instances in our experiments for testing the proposed scheme’s capabilities. As a result, the Hybrid SMOTE appears to have good scalability within the framework proposed, and it also cuts down the processing time.

Research on economic development trend of reform and opening up: based on big data modeling analysis method

The development of information technology proves the possibility of acquiring large samples of policy text information and promotes innovative research based on the policy informatics approach of fusing data from multiple sources. This paper constructs a new public policy model based on existing data on economic system reform, and uses multi-types of textual big data such as government website, official weblog, and social media as the object of collection, to conduct a big data measurement on policy concerns related to the theory and practice of economic system reform since the reform and opening up. And this paper constructs a fine-grained measurement and portray the evolutionary trend of policy concerns and policy implementation. Based on the database, this paper helps to analyse the economic development trend since the reform and opening up, evaluate and monitor the implementation effect of different incentive policies and establish an iterative feedback mechanism, and provides a reference for relevant decision-making departments.

Prediction of Electric Load Neural Network Prediction Model for Big Data

Spike sorting algorithms is a considerable significant way to collect neural signals in neural signal acquisition systems. One method to realize this function in hardware aspect is to use absolute-value detector. In this paper, the common circuit topology is given by using static CMOS and PTL technology. Then, through comparing with the delay and energy of unit reference inverter, the optimal energy-delay model when sacrificing extra 50% delay can be obtained by the way changing the size of CMOS and Vdd simultaneously, which save nearly 83% energy dissipate than minimal delay model.

Big Data Maturity Assessment Models: A Systematic Literature Review

Big Data and analytics have become essential factors in managing the COVID-19 pandemic. As no company can escape the effects of the pandemic, mature Big Data and analytics practices are essential for successful decision-making insights and keeping pace with a changing and unpredictable marketplace. The ability to be successful in Big Data projects is related to the organization’s maturity level. The maturity model is a tool that could be applied to assess the maturity level across specific key dimensions, where the maturity levels indicate an organization’s current capabilities and the desirable state. Big Data maturity models (BDMMs) are a new trend with limited publications published as white papers and web materials by practitioners. While most of the related literature might not have covered all of the existing BDMMs, this systematic literature review (SLR) aims to contribute to the body of knowledge and address the limitations in the existing literature about the existing BDMMs, assessment dimensions, and tools. The SLR strategy in this paper was conducted based on guidelines to perform SLR in software engineering by answering three research questions: (1) What are the existing maturity assessment models for Big Data? (2) What are the assessment dimensions for Big Data maturity models? and (3) What are the assessment tools for Big Data maturity models? This SLR covers the available BDMMs written in English and developed by academics and practitioners (2007–2022). By applying a descriptive qualitative content analysis method for the reviewed publications, this SLR identified 15 BDMMs (10 BDMMs by practitioners and 5 BDMMs by academics). Additionally, this paper presents the limitations of existing BDMMs. The findings of this paper could be used as a grounded reference for assessing the maturity of Big Data. Moreover, this paper will provide managers with critical insights to select the BDMM that fits within their organization to support their data-driven decisions. Future work will investigate the Big Data maturity assessment dimensions towards developing a new Big Data maturity model.

Fast training of a transformer for global multi-horizon time series forecasting on tensor processing units

Time Series Forecasting (TSF) is essential to key domains, and the Transformer neural network has advanced the state-of-the-art on global, multi-horizon TSF benchmarks. The quadratic time and memory complexity of the Vanilla Transformer (VT) hinders its application to Big Data environments; therefore, multiple efficient variants of the VT that lower complexity via sparse self-attention have been proposed. However, less complex algorithms do not directly produce faster executions, and machine learning models for Big Data are typically trained on accelerators designed for dense-matrix computation that render slower performance with sparse matrices. To better compare the accuracy-speed trade-off of the VT and its variants, it is essential to test them on such accelerators. We implemented a cloud-based VT on Tensor Processing Units to address this task. Experiments on large-scale datasets show that our Transformer achieves good predictive performance when compared to state-of-the-art models while reducing training times from hours to under 2 min.

Explore Big Data Analytics Applications and Opportunities: A Review

Big data applications and analytics are vital in proposing ultimate strategic decisions. The existing literature emphasizes that big data applications and analytics can empower those who apply Big Data Analytics during the COVID-19 pandemic. This paper reviews the existing literature specializing in big data applications pre and peri-COVID-19. A comparison between Pre and Peri of the pandemic for using Big Data applications is presented. The comparison is expanded to four highly recognized industry fields: Healthcare, Education, Transportation, and Banking. A discussion on the effectiveness of the four major types of data analytics across the mentioned industries is highlighted. Hence, this paper provides an illustrative description of the importance of big data applications in the era of COVID-19, as well as aligning the applications to their relevant big data analytics models. This review paper concludes that applying the ultimate big data applications and their associated data analytics models can harness the significant limitations faced by organizations during one of the most fateful pandemics worldwide. Future work will conduct a systematic literature review and a comparative analysis of the existing Big Data Systems and models. Moreover, future work will investigate the critical challenges of Big Data Analytics and applications during the COVID-19 pandemic.

A Trajectory Big Data Storage Model Incorporating Partitioning and Spatio-Temporal Multidimensional Hierarchical Organization

Trajectory big data is suitable for distributed storage retrieval due to its fast update speed and huge data volume, but currently there are problems such as hot data writing, storage skew, high I/O overhead and slow retrieval speed. In order to solve the above problems, this paper proposes a trajectory big data model that incorporates data partitioning and spatio-temporal multi-perspective hierarchical organization. At the spatial level, the model partitions the trajectory data based on the Hilbert curve and combines the pre-partitioning mechanism to solve the problems of hot writing and storage skewing of the distributed database HBase; at the temporal level, the model takes days as the organizational unit, finely encodes them into a minute system and then fuses the data partitioning to build spatio-temporal hybrid encoding to hierarchically organize the trajectory data and solve the problems of efficient storage and retrieval of trajectory data. The experimental results show that the model can effectively improve the storage and retrieval speed of trajectory big data under different orders of magnitude, while ensuring relatively stable writing and query speed, which can provide an efficient data model for trajectory big data mining and analysis.

A big-data-driven matching model based on deep reinforcement learning for cotton blending

ABSTRACT China’s cotton textile industry is undergoing a critical period of digital transformation and upgrading to cope with pressure and challenges such as rising labour costs and large fluctuations in raw material prices. Developing a cost-based competitive advantage while ensuring a high-quality product is a critical problem in intelligent manufacturing. From the perspective of big data and reinforcement learning, the authors designed a reward value combining transaction, interaction, and measurement data by combining the reward mechanism and Markov decision for a combination of different raw materials in the intelligent textile factory. The authors propose a big data-driven application to the depth of the reinforcement learning to solve problems and build a big-data-driven matching model based on deep reinforcement learning to cotton matching. The offline strategy is designed to construct a memory bank and neural network, and the incentive mechanism of reinforcement learning is used to iterate the optimal yarn matching scheme to achieve the goal of intelligent cotton matching. The results show that deep reinforcement learning can be optimised using big data on the premise of quality assurance. Manufacturing costs can be optimised using a matching model of big data based on a deep reinforcement learning model.

Retraction Note: Visualization model of big data based on self-organizing feature map neural network and graphic theory for smart cities

Retraction Note: Visualization model of big data based on self-organizing feature map neural network and graphic theory for smart cities

Connections between Big Data and Smart Cities from the Supply Chain Perspective: Understanding the Impact of Big Data

This study explores the impact of Big Data and smart city initiatives on supply chain management. The effects of smart cities and SCM integration on sustainable development are also examined. Big Data, smart cities, and supply chain characteristics have all received a significant amount of attention (supply network structure, governance mechanisms). Based on literature reviews, we created a comprehensive model for supply chains, Big Data, and smart cities. The study concluded that smart cities have various consequences for network architecture and governmental systems. Future research directions in supply chain management and smart cities are also addressed in this paper. A comprehensive model was developed that can be used to undertake empirical research on the implications of smart cities and Big Data on supply chain management and sustainable development in the future. Big Data, smart cities, and supply chains have more than merely causal interactions, and Big Data and smart cities will hugely impact sustainable development and SCM operations. Several studies have recently examined the use of information technology in supply chains, but few have specifically addressed smart cities and Big Data, according to literature analyses.