Big Data Theory Research Articles

Facial Micro-expression Recognition Algorithm Based on Big Data

The 21st century is the era of big data. All aspects of society, from facial expressions to national defense and military, will generate massive amounts of data. Facial expression recognition technology, as a new technology spawned in the era of big data, has broad applications The prospects are widely used in intelligent transportation, assisted medical care, distance education, interactive games and public safety. In recent years, it has attracted more scholars’ attention and has become another research hotspot in the field of computer vision and machine learning. The purpose of this article is to study the facial micro-expression recognition algorithm based on big data. This time, big data technology is used to analyze the algorithm. Big data can better solve the small changes in face recognition and complex data processing. This paper firstly summarizes the basic theory of big data, derives the core technology of big data, and analyzes its shortcomings and shortcomings based on the current research status of facial micro-expression in my country, and finally discusses the big data based on big data. Research on facial micro-expression recognition algorithm under the following. This article takes the research situation of the face micro-expression recognition by related companies as the survey object, and analyzes it through the literature data method, questionnaire survey method, mathematical statistics method and other research methods. Experimental results show that the lower the dimensionality reduction, the less classification time is used. When the dimensionality reduction is 45 dimensions, the recognition rate of facial expressions is the highest.

Opportunities for a New Content and Methodological Line “Big Data Analysis” to Modernize the Training System of the Future Economist

The aim of the study is to apply the theory of pedagogical technologies to reveal the possibilities of the new content and methodological line “Big Data Analysis” in the aspect of modernizing the training system of the future economist.Materials and methods. During the study, theoretical and empirical research methods were used, in particular, a theoretical analysis of methods for structuring the content of education and managing the educational and cognitive activities of higher school students based on technological goal-setting and identifying a sequence of tasks, according to the content and methods of solving graduates close to future professional activities; studying the products of pedagogical activities of lecturers of higher education and experimental work, including the method of pedagogical experiment.Results. The necessity of modernization of the system of professional training of the future economist in the context of the development of data science through the selection and implementation of a new content-methodological line “Big Data Analysis” is substantiated. It points to the demand for methods of pedagogical design and the theory of pedagogical technologies for the methodologically expedient inclusion of elements of Big Data theory in the practice of professional training of future bachelors of economics. At the same time, attention is paid to both the content of already developed academic disciplines “Probability theory and mathematical statistics”, “Decision theory”, “System’s analysis in Economics”, “Instrumental methods in Economics”, and the setting of new professionally significant academic disciplines related to quantitative justification of the decisions made. The article presents and methodically describes the components of the content-methodological line “Big Data Analysis”: firstly, a sequence of six micro-goals that allow setting the implementation of this contentmethodological line in the language of educational and cognitive activities of the future bachelor of economics and taking into account the capabilities of new digital tools that support Big Data analysis models; secondly, five didactic modules that can be used to form individual educational trajectories of students of economic bachelor’s degree. Six types of application tasks are presented and characterized, which are of fundamental importance for the implementation of this content-methodological line. These tasks include the following: “Application problem for the analysis of Big Data on the RapidMiner platform”; “Data clustering application”; “Applied problem of soft and hard clustering”; “Applied classification problem”; “Applied problem on the application of methods for finding association rules”; “Applied problem for text mining”.Conclusion. The approach proposed by the authors to structuring the content of professional training of the future bachelor of economics allows us to maintain the balance of four educational components of the content and methodological line “Big Data Analysis”: experience in cognitive and creative activities, experience in implementing standard methods of activity and emotional and value relations (ideals of entrepreneurship, value orientations and motives of economic activity, etc.) The material presented in this article can be useful for lecturers of the higher economic school, as well as for everyone who is interested in the modern achievements of data science.

Big data theory based spectrum sensing algorithm for the satellite cognitive radio network

In order to deal with the difficulty of spectrum sensing in cognitive satellite wireless networks, a large-scale cognitive network spectrum sensing algorithm based on big data analysis theory is studied, and a new algorithm using mean exponential eigenvalue is proposed. This new approach fully uses all the eigenvalues in sample covariance matrix of the sensing results to make the decision, which can effectively improve the detection performance without obtaining the prior information from licensed users. Through simulation, the performance of various large scale cognitive radio spectrum sensing algorithms based on big data analysis theory is compared, and the influence of satellite to ground channel conditions and the number of sensing nodes on the performance of the algorithm is discussed.

Human Resource Management of Internet Enterprises Based on Big Data Mobile Information System

With the progress of science and technology, the advent of VR panorama, the era of Big Data has arrived, which has set off a revolution in the development and future destiny of Internet companies. Human resource management (HRM) is an important department of Internet companies. This paper introduces the principle and value of Big Data and related theories of HRM. This paper discusses three aspects of HRM in our company using Big Data theory: employee turnover prediction, salary comparison, and talent evaluation method, and puts forward suggestions for optimization and improvement of the company’s HRM. The results show that, through the company’s project manager’s ability to quantify data and analyze a set of data quantitative research, comparative analysis of the ability of three candidates Q, W, and E showed that W is the most suitable for the company’s project manager staff.

Research on Teaching Ability Evaluation Model of University Teachers Based on Computer Big Data Theory

As the backbone theory to guarantee the teaching level of universities, teachers are essential resources for the healthy development of universities. However, some universities are still lack of data support in the process of carrying out the evaluation of teachers’ teaching ability, which leads to the evaluation process is not scientific and reasonable, and it is difficult to reflect teachers’ real teaching ability objectively and fairly. Based on this, this paper first analyzes the comprehensive evaluation model of university teachers’ teaching ability under the big data theory, and then studies the application effect of the teaching ability evaluation model based on the big data theory.

Analysis on the New Ways of International Trade Cross Border E-Commerce Research from Big Data Theory

With the popularity of the Internet, the server terminal will receive massive data every day. Therefore, China has entered the era of big data. Mobile terminal applications have subverted people’s traditional user experience, which has brought significant changes in business model. Therefore, big data has become an important strategic resource, which has become an important means of technological innovation used by enterprises. Through big data mining and other technologies, enterprises can analyze the global price changes in international trade (hereinafter referred to as ITT). By analyzing user behavior, enterprises can push appropriate products to users. Therefore, big data technology has been applied to ITT, especially Cross Border E-Commerce (hereinafter referred to as CBEC). Therefore, this paper first analyzes the application process of big data technology to CBEC. Then, this paper puts forward the future business model. Finally, some suggestions are put forward.

Research on Data Acquisition and Sharing Methods Under Power Demand Side Management Based on Big Data Mining Analysis

Nowadays, China’s power demand system reform has gone through many stages. With the rapid growth of China’s population, China’s power demand is also increasing rapidly. After experiencing the heavy pressure growth period, the power system really provides us with great convenience. However, it will also bring a lot of bad problems. In order to solve these problems, we must innovate the electric power industry [1]. Data acquisition and sharing in side management mode is the basic part of power demand management. Nowadays, the development of big data has gradually become prosperous. Many experts believe that data mining can be used to support data acquisition and sharing of power side management. This paper briefly summarizes the theory of power big data and power side management. On this basis, this paper proposes a data source and data sharing model based on data mining.

Retraction: Research on Teaching Ability Evaluation Model of University Teachers Based on Computer Big Data Theory (J. Phys.: Conf. Ser. 1992 032003)

This article has been retracted by IOP Publishing following an allegation that raises concerns this article may have been created, manipulated, and/or sold by a commercial entity. In addition, IOP Publishing has seen no evidence that reliable peer review was conducted on this article, despite the clear standards expected of and communicated to conference organisers. The authors of the article have been given opportunity to present evidence that they were the original and genuine creators of the work, however at the time of publication of this notice, IOP Publishing has not received any response. IOP Publishing has analysed the article and agrees there are enough indicators to cause serious doubts over the legitimacy of the work and agree this article should be retracted. The authors are encouraged to contact IOP Publishing Limited if they have any comments on this retraction. Retraction published: 9 September 2022

Research on the Integration of ESP and Big Data in Modern College English Teaching

In the context of big data, it analyzes ESP-based college English teaching. First, it explains the big data theory in ESP, and then discusses the resource discovery service, information storage service, resource organization service, and information retrieval service of English teaching. On the basis of the service content of ESP in college English teaching, it expounds the self-learning mode of college English based on ESP theory from the aspects of one-stop resource service, subject knowledge service, information visualization service and smart service.

Research on the method of children’s body shape recognition based on big data technology of dressed human body

In this paper, a large number of children samples are collected to establish a database with detailed measurement index information. The data are analyzed and the figure of children are divided into three types. On the basis, the Naive Bayesian (NB) algorithm is applied to the study of figure discrimination, and the discriminant model is established. The discrimination of children figure is realized. At the same time, based on big data theory, the similar body of the test sample in the database is found through querying based on minimum difference algorithm. The unknown detailed measurement data of the test sample can be replaced by the similar body, to provide data support for the relevant application areas or dressed the human body that need to obtain detailed measurement information about the children.

Research on Big Data Theory and Trend of Quality Management in Automobile Industry

As a typical manufacturing industry, the automobile industry has high requirements for quality management. Today, with the rapid development of information technology, it is important to consider the characteristics of quality management in the industry and the whole life cycle of automobile products. Based on this perspective, an evaluation index system of quality management data and a big data platform of quality management for the automobile industry were established. This research has guiding significance for governments to serve the development of the automobile industry and for enterprises to improve their quality capability.

Small Data Theorizing

AbstractSmall data theorizing encompasses the ways communities of collaborators deliberate over the status of data through a set of three mediational logics that pose alternatives to datafication. Small data theorizing is a way of generalizing a framework for understanding the role of the collaborators in digital archiving and database design processes, which often involve both communication researchers and ordinary institutions, such as universities and museums. This framework for mediational logics extends the critiques of big data theory, and its monolithic claims about autonomous technologies and power in society, by elaborating the ways people actively maintain their connectedness to data in archival design. At the same time, it joins critical communication theory’s central concerns about power with a praxis. This can help all communication researchers in seeing how communities are theorizing practical alternatives to archives that are designed for big data and their ecosystems.

The Social Representations and Legal Theory of Artificial Intelligence, Robotics and Big Data in Healthcare

This paper reports on a qualitative survey carried out among 17 experts sharing free associations on the introduction of AI, robotics and big data into the healthcare sector, featuring the benefits and risks but also contemporary applications of Artificial Intelligence (AI), robotics and big data in healthcare. The survey was implemented by a standardized questionnaire featuring open-ended questions, which the author emailed to potential respondents. The paper subsequently reports on the results of the survey in structured form using correspondence analysis by classifying respondents into four key stakeholder groups, namely (1) individuals in academia or education, (2) those dealing with health care issues form a business, economics and finance perspective, (3) medical and healthcare professionals and (4) public servants and legal professionals. Finally, the paper discusses economic, social and legal implications of the results. Survey results indicate that AI, robotics and big data in the healthcare sector may lead to more tailored medicine with precision, efficiency and excellence in assisting humans. However, big data involves risk such as commodification and misuse of data, as well as privacy and safety risk. AI may result in market disruptions that ultimately increase costs and bring about unpredictable risk. The paper also discusses currently ongoing legal trend in robotics, which result in robots increasingly being considered as quasi-human, big data analytics trends affecting taxation, regulatory attempts to overcome discrimination, and social stratification derived from big data insights.

MAPPING URBAN AREAS USING DENSE TIME SERIES OF LANDSAT IMAGES AND GOOGLE EARTH ENGINE

Abstract. Urban information extraction from satellite based remote sensing data could provide the basic scientific decision-making data for the construction and management of future cities. In particular, long-term satellite based remote sensing such as Landsat observations provides a rich source of data for urban area mapping. Urban area mapping based on the single-temporal Landsat observations is vulnerable to data quality (such as cloud coverage and stripe), and it is difficult to extract urban areas accurately. The composite of dense time series Landsat observations can significantly reduce the effect of data quality on urban area mapping. Multidimensional array is currently effective theory for geographic big data analysis and management, providing a theoretical basis for the composite of dense time series Landsat observations. Google Earth Engine (GEE) not only provides rich satellite based remote sensing data for the composite of dense time series data, but also has powerful massive data analysis capabilities. In the study, we chose Random Forest (RF) algorithm for the urban area extraction owing to its stable performance, high classification accuracy and feature importance evaluation. In this work, the study area is located in the central part of the city of Beijing, China. Our main data source is all Landsat8 OLI images in Beijing (path/row: 123/32) in 2017.Based on the multidimensional array for geographic big data theory and the GEE cloud computing platform, four commonly used reducer methods are selected to composite the annual dense time series Landsat 8 OLI data. After collecting the training samples, RF algorithm was selected for supervised classification, feature importance evaluation and accuracy verification for urban area mapping. The results showed that 1), compared with the single temporal image of Landsat 8 OLI, the quality of annual composite image was improved obviously, especially for urban extraction in cloudy areas; 2) for the evaluation results of feature importance based on RF algorithm, Coastal, Blue, NIR, SWIR1 and SWIR2 bands were the more important characteristic bands, while the Green and Red bands were comparatively less important; 3) the annual composite images obtained by the ee.Reducer.min, ee.Reducer.max, ee.Reducer.mean and ee.Reducer.median methods were classified and accuracy verification was carried out using the verification points. The overall accuracy of the urban area mapping reached 0.805, 0.820, 0.868 and 0.929, respectively. In summary, the ee.Reducer.median method is a suitable method for annual dense time series Landsat image composite, which could improve the data quality, and ensure the difference of features and the higher accuracy of urban area mapping.

Evaluation Method of the Spatial-Temporal Complementary Characteristics Between Power Source and Load Based on Power Big Data

With the rapid development of the intermittent renewable energy power generations such as wind power and solar power and the new random load such as EV, the double randomness become a great threat the safe and stable operation of power system. It has become a hot issue raised increasingly concern from the academic and engineering fields that how to reduce the randomness and volatility of the two sides of the system by utilizing the spatial-temporal complementary characteristics of different energy resources and loads. In this paper, the evaluation model of complementary characteristics between power and load across time and space based on the Power Big Data theory is proposed. By simulating the complementarity of the power supply and load between Northwest China and European load centres from three dimensions: load-load complementarity, source-source complementarity and source-load complementarity, it proves there are great complementary benefit by interconnecting the grids with different regions across continents, which provides a theoretical basis for the next implementation of the Global Energy Interconnection.

Capacity Credit Algorithm and Index of the New Energy of Wind Energy and Solar Energy based on Big Data

Since twenty-first century, many countries have accelerated their development, and the energy on the earth has been gradually consumed, which not only has caused the lack of energy, but also the environmental pollution. Therefore, people have paid much attention to the related problems. Based on the research of big data theory, the credibility algorithm of new energy was established in this paper. And through the establishment of wind farm power generation model, its reliability and indicators were analyzed. Thus, the feasibility of replacing old energy with new energy sources was explored. And through the analysis of the data, the reliability of wind farms and photovoltaic power plants was evaluated.

Health status diagnosis of distribution transformers based on big data mining

AbstractIn the fault detection technology of distribution transformer, the traditional artificial intelligence algorithm has been unable to achieve its efficient analysis and processing, but also unable to achieve the elimination of misdiagnosis caused by improper interval segmentation in the process of fault diagnosis of distribution transformer. In a word, the problem that always exists in transformer fault diagnosis technology is the problem of discretization of fault data. In order to solve this problem, this paper creatively proposes a health condition diagnosis method of distribution transformer based on large data. This method innovatively proposes that the dissolved gas analysis value of distribution transformer is the conditional attribute, and the fault type is the decision attribute, and the fault decision table is established. The continuous attribute data in the decision table are discretized by using the optimization behavior of large data sets. Subsequently, the discretized decision table is simplified by using the big data theory, and the decision table of fault diagnosis rules is established, which greatly simplifies the difficulty of attribute simplification of decision table and makes diagnosis more convenient. Finally, an example shows that the proposed method can effectively discretize and reduce samples. Compared with traditional methods, it improves the accuracy of fault diagnosis.

Analysis of blockage reasons of air preheater based on big data

With the rapid development of Internet and computer technology, the era of big data has arrived. With the increasingly high degree of automation in the power industry, data mining technology and cloud computing technology are continuously developing in the power industry to deal with massive operational data. Supervisory Information System (SIS) and Distributed Control System (DCS) have been widely used in power plants, which enables massive operation data of power plants to be saved. As data mining technology rises rapidly in the power industry, many scholars begin to use data mining technology to study and solve problems encountered in power plants. Air preheater is a kind of heat exchange equipment which USES the waste heat of flue gas to heat the air needed for boiler combustion. The air preheater can recover the heat of flue gas, reduce the temperature of smoke exhaust and improve the efficiency of boiler. In recent years, the phenomenon of air-preheater clogging is increasing. Based on big data theory, this paper investigated 26 thermal power generating units - a total of 52 air preheaters with a capacity of 300∼600MW, and applied the neural network Modeling method to the air preheater clogging reasons identification system. So we can find out the clogging reasons of air preheaters timely and accurately, slow down and avoid the clogging of air preheater.

The construction of sports culture industry growth forecast model based on big data

With the development of social economy, sports industry has shown its economic advantages. Sports industry has shown great potential in improving national economy, guiding social consumption, and adjusting industrial structure. However, compared with the rapid development of sports industry, the research on the growth law of sports culture industry is relatively backward, which largely restricts the further development of China’s sports industry. For this problem, this paper analyzes the feasibility of sports culture industry growth prediction based on big data theory from the perspective of data mining, proposes a sports culture industry growth prediction model based on genetic neural network, and realizes the prediction of sports culture industry growth law under the background of big data. The simulation result shows that the optimized neural network can effectively improve the efficiency and accuracy of prediction and show strong robust in predicting the laws of sports culture industry.

Big data research guided by sociological theory: a triadic dialogue among big data analysis, theory, and predictive models

Computational social science has integrated social science theories and methodology with big data analysis. It has opened a number of new topics for big data analysis and enabled qualitative and quantitative sociological research to provide the ground truth for testing the results of data mining. At the same time, threads of evidence obtained by data mining can inform the development of theory and thereby guide the construction of predictive models to infer and explain more phenomena. Using the example of the Internet data of China’s venture capital industry, this paper shows the triadic dialogue among data mining, sociological theory, and predictive models and forms a methodology of big data analysis guided by sociological theories.