Big Data Environment Research Articles

Research on Enterprise Internal Audit Work in Big Data Environment

Enterprise internal audit and internal control work are important parts of enterprise management, To increase corporate operating profit and to promote sustainable development of enterprises, corporate managers should professionally cope with the relationship between the internal audit and internal control of the enterprise and enhance the performance in both tasks simultaneously. Recently, due to the rapid development of Internet equipment and mobile communications, the advent of the big data era has brought some challenges to the internal audit work of enterprises. This article focuses on the internal audit of enterprises in the era of big data. The problems with the internal audit work of the enterprise will be analyzed and the corresponding internal audit work countermeasures will be provided.

The Status Quo and Problem Analysis of the application of intelligent enterprise management accounting in the Big Data Era

Management accounting plays a pivotal role in the operation of an enterprise. By means of management accounting, an enterprise could make reasonable accounting of enterprise costs, optimize resource allocation within enterprises and reduce the waste of resources. Therefore, management accounting is the major resource of the information that helps with decision-making of business managers. In recent years, the big data technology and intelligent technology has been continuously improved, so the traditional management accounting model is facing great challenges. Therefore, the application of intelligent management accounting into the in-depth analysis of big data within all enterprise will cast positive influence on long-term development of the enterprise. This article aims to analyze the current status of the application of intelligent management accounting into enterprise in the present big data environment. In accordance with the application of intelligent management accounting in enterprise budget management, cost management, performance management, and others, the problems with the current application of intelligent management accounting will be summarized. Then, some effective solutions to solve those problems will be provided, expecting to provide crucial enlightenment on the application of intelligent management accounting to promote the development of Chinese enterprises in the era of big data.

Application of the LDA Model to Semantic Annotation of Web-based English Educational Resources

Based on the LDA model, this paper builds a three-layer semantic model of Web English educational resources “document-topic-keyword”, models the semantic topics of resource documents, and obtains the semantic topics and keywords of document resources as the semantic labels of resources. The experimental results show that document LDA topic modeling is beneficial to the macroscopic classification of Web English educational resources. The experimental results show that LDA topic modeling of documents is useful for macroscopic cataloging of Web English educational resources, highlighting teaching priorities, difficulties, and interrelationships, while LDA modeling of teaching topics with the same teaching content expands the metadata generation method of resource description based on the basic education metadata standard and provides more information about the inherent characteristics of resources. The semantic information can be used to mine the semantic thematic features and detailed differences inherent in the resources, and the final performance analysis verifies the parallel computing advantages of the LDA model in a big data environment.

Student Physical Health Information Management Model under Big Data Environment

Health is considered an important foundation for students’ success. However, with the accelerated pace of life, rising pressure from various parties, weak health awareness, lack of exercise time, and other reasons, students’ physical quality is generally declining, the incidence of health diseases is increasing, and the onset age tends to be younger. With the development of the concept of “health first,” health management continues to expand and extend and students’ health management has attracted more attention from many aspects. Due to the late and low starting point of health management research and the lack of professional theoretical support, a complete, mature, and effective health management service system has not been established to deal with the students’ health. In order to make student health management more scientific, normative, and effective, this article has proposed big data technology to build the student health information management model. The first step of the approach is to store and analyze the data of students’ physical health. It is necessary to combine the data collection, supervision, data analysis, and data application of students’ physical health and gradually improve the national monitoring and evaluation system of students’ physical health. Student health check-up management platform is mainly used in realizing the school student information management and student health information relationship between system, science, standardization, and automation, and its main task is to use a computer to perform daily management of all previous medical information of students, such as query, modify, add, delete, and enhance the physical health of students information management ability given the large data analysis of useful information. In addition, we have built a doctor recommendation model based on online questions and answers to give specific health recommendations for students of different physiques.

Application of Wireless Sensor Networks in the Sensitive Data Security of Intelligent Data Center under the Big Data Environment

In the big data environment, wireless sensor networks (WSN) are constantly improving themselves and are widely used in all walks of life. The WSN collects, processes and transmits the information of the sensed object in the monitoring area. In recent years, WSN have also made good progress in environmental change detection, traffic control, and sensitive data security management. The purpose of this article is to study the application of WSN in the security management of sensitive data in the data center under the big data environment. This article first describes the characteristics of WSN, and discusses the security management requirements of sensitive data in WSN based on big data technology. Secondly, it analyzes the problems in the security management of sensitive data and conducts research from different directions. Finally, in response to these problems, the implementation of the WSN in the security management of sensitive data provides some help to solve the problem. Thereby effectively reducing the energy consumption of network nodes, reducing the amount of data transmitted by the network, and extending the life cycle of the WSN. Experimental research results show that the most demanded level in security management is data confidentiality, which is 47.15%, followed by data freshness and data integrity, which are 28.49% and 24.36%, respectively. In summary, it is necessary to increase efforts to improve the security management of sensitive data.

Analysis of Big Data Embedded Mapping Model Oriented to Prediction of Subordinate Relationship

With the rapid development of information technology, research on big data information has gone deep into all walks of life, and massive amounts of data spew out anytime and anywhere. This paper proposes a domain-subordinate relationship acquisition that combines multiple strategies and word representations. From semi-structured text and unstructured text, the candidate entity upper-lower relationship entity pairs are extracted, and then the obtained candidate upper-lower relationship entity pairs are verified by the support vector machine method to obtain high-quality candidate entity pairs. In the training phase, an exploratory method is designed to search for the optimal solution, and a greedy mechanism is introduced to evaluate the effectiveness of the reinforcement learning agent, so that the virtual node mapping scheme can continuously move towards higher system returns. Evolution has finally achieved the optimal virtual network mapping decision, so that large-scale tasks can be deployed to task processing nodes in the appropriate underlying network to achieve efficient task execution in a big data environment. The experimental results show that the Tard method can effectively avoid model overfitting and improve the task recognition processing ability in the actual application process under the premise of meeting large-scale task requests.

Construction of the Rural Information Service Platform under Big Data Environment

Construction of the Rural Information Service Platform under Big Data Environment

Research and application of privacy protection technology based on big data environment

With the development of the Internet of Things, the popularization of the mobile Internet, and the rapid promotion of social networks, the growth of data has entered a big explosion, and the development of information technology has caused a torrent of big data. The continuous development of technology brings people convenience, speed and comfort, but also hides hidden worries. Combined with differential privacy and clustering, a clustering-based differential privacy universal dataset release method for mixed datasets is proposed: using k-prototype clustering algorithm to group records in the hybrid dataset to reduce differential privacy Query sensitivity and the amount of noise to be added to improve data utility while providing data privacy protection; perform attribute difference calculations for numerical attributes and categorical attributes combined with weights, and measure their information loss separately. Finally, Experimental results show that this algorithm can improve the usability of data publishing.

Information Automatic Sharing Model Based on Big Data Mining Algorithm

The advent of the era of big data has promoted the transformation of traditional financial management models, and the automated sharing of public financial information has gradually appeared in the public’s field of vision. Gradually recognized by business managers, there has been an upsurge in the application of public financial information automated sharing models. Especially it has been widely used in large enterprises and multinational enterprises, and it has also attracted the attention of many large enterprises. With the continuous maturity of big data technology, financial information has shown diversified characteristics, and more accurate financial analysis capabilities are required. The management of enterprises has gradually realized that applying big data mining algorithms to the automated sharing of public financial information should be possible. Bring new progress to sharing centers and enterprises. Slowly, with the continuous development of technology, more and more senior corporate managers realize the importance of automated sharing of public financial information and the practicality of big data mining algorithms. Research shows that this article mainly uses the literature research method to study the origin, definition and implementation process of the public financial information automation sharing model by domestic and foreign scholars, and proposes the process modules that need to be improved and optimized under the big data environment. Studies have proved that the company’s products have gradually gained advantages after 2015, reflecting that the company’s profitability is gradually recovering, and the utility of the automatic sharing model of public financial information based on big data mining algorithms has begun to gradually come into play. At the same time, the main business income and net profit respectively showed a downward trend in 2015, and showed a steady increase after 2009. In 2008, the company’s public financial information automatic sharing model based on big data mining algorithms incurred relatively large costs in the early stage, which also had a greater impact on the company’s related profit indicators.

Brand Loyalty Measurement Model Based on Machine Learning Clustering Algorithm

In the “new economy” represented by the Internet economy background, online consumption as the representative of the new forms of consumption is gradually changing people’s consumption idea and way, online brand loyalty has the extremely important status in the field of online consumption, to stimulate consumption and achieve accurate enterprise marketing, risk control and decision support, improve efficiency and product design business model, business forms, and even change of business thinking, improve enterprise competitiveness is of great significance in the field of online. It is urgent and necessary to apply scientific and effective machine learning method to systematically analyse and study online brand loyalty. In the big data environment, facing the massive data information provided by online consumption, traditional technology methods have gradually failed to meet the competitive needs of enterprises to create and maintain brand loyalty. The traditional random sampling method is difficult to locate the consumer groups with high brand loyalty. At the same time, the traditional data processing technology can not deal with the online consumption behavior with the characteristics of massive, mixed and unstructured data. Traditional approaches have limitations when it comes to the sheer volume of online data and how to use it in real time to target the needs of a brand’s consumer group. The purpose of this study is to build an online consumption of the era of big data model of artificial intelligence, machine learning model, by machine learning method, branded goods purchase behavior of consumers online clustering, building an online brand loyalty measurement model, achieve similar loyalty user clustering, at the same time realize the online measurement of brand loyalty. Among them, focus on machine learning path, machine learning algorithm, model construction methods, and model verification and optimization methods.

A Study on Deep Learning Model-based Object Classification for Big Data Environment

A Study on Deep Learning Model-based Object Classification for Big Data Environment

Research on Human Resource Management System Based on Internet of Things Technology

At present, with the arrival of the information age, the era of big data and artificial intelligence gradually set foot on the stage of history. With the development of the Internet of Things and the arrival of the era of big data, enterprises have been equipped with the ability to master and process large amounts of data. In the context of big data environment, by analyzing the relationship between big data and the six modules of human resource management, and combining with the workplace changes in the epidemic era in the future, some guidance is given to telecommuting.

A new computer-based index for swimming pools' environmental health assessment in big data environment by consensus-based fuzzy group decision-making models.

Swimming pools are popularly used for sport and recreational purposes worldwide. These places influence swimmers' health as they are considered public places. This study attempted to introduce a process mining framework which analyzes the environmental health status in swimming pools. In this context, a new numerical index namely Swimming Pool Environmental Health Index (SPEHI) was developed through which, big data extracted from checklists of environmental health inspection of swimming pools were analyzed in fuzzy environment. The methodology comprises MCDM (Multi- Criteria Decision-Making) approach including fuzzy TOPSIS (Technique for Order Preference by Similarity to Ideal Solution) and fuzzy OWA (Ordered Weighting Average). The performance of this index was evaluated through an applied example on 12 swimming pools in Shiraz, Iran that was run for a three-year sequence from 2015 to 2017. Among 30 evaluation criteria used in this index, the greatest (0.61) and lowest (0.35) group weights were dedicated to "Residual chlorine biological water quality" and "existence of drinking water facilities", respectively. For the study area, SPEHI showed a wide range of environmental health conditions between 37.8 (Relatively good) to 98.19 (Excellent). The extended index could shrink swimming pool's big data to concise values which are interpretable for health experts and managers of sport sector. It helps figuring out the trends of hygiene conditions in a swimming pool over the time and easy access to compare a city's swimming pools as well. The methodology is flexible in structure and thus, it could be applied for other sporting places.

Malware Detection using Deep Learning

Malicious software or malware continues to pose a major security concern in this digital age as computer users, corporations, and governments witness an exponential growth in malware attacks. Current malware detection solutions adopt Static and Dynamic analysis of malware signatures and behaviour patterns that are time consuming and ineffective in identifying unknown malwares. Recent malwares use polymorphic, metamorphic and other evasive techniques to change the malware behaviour’s quickly and to generate large number of malwares. Since new malwares are predominantly variants of existing malwares, machine learning algorithms are being employed recently to conduct an effective malware analysis. This requires extensive feature engineering, feature learning and feature representation. By using the advanced MLAs such as deep learning, the feature engineering phase can be completely avoided. Though some recent research studies exist in this direction, the performance of the algorithms is biased with the training data. There is a need to mitigate bias and evaluate these methods independently in order to arrive at new enhanced methods for effective zero-day malware detection. To fill the gap in literature, this work evaluates classical MLAs and deep learning architectures for malware detection, classification and categorization with both public and private datasets. The train and test splits of public and private datasets used in the experimental analysis are disjoint to each other’s and collected in different timescales. In addition, we propose a novel image processing technique with optimal parameters for MLAs and deep learning architectures. A comprehensive experimental evaluation of these methods indicate that deep learning architectures outperform classical MLAs. Overall, this work proposes an effective visual detection of malware using a scalable and hybrid deep learning framework for real-time deployments. The visualization and deep learning architectures for static, dynamic and image processing-based hybrid approach in a big data environment is a new enhanced method for effective zero-day malware detection.

The antecedent and consequence behaviour of sustainable tourism: integrating the concepts of marketing strategy and destination image

ABSTRACT Drawing on integrated concepts of marketing strategy and destination image, this study proposes and develops a model of antecedent and consequence behaviour for sustainable tourism. A survey of 505 tourists was conducted. In the antecedent model, perceived risk may indirectly affect travel behaviour through psychological involvement and destination image. In the consequence model, we found that marketing strategy was related to increased destination impression and thus enhanced sustainable tourism intention. Specifically, it is not surprising that in a big data environment, new technology sharing may also enhance the positive evaluation of destinations that encourage sustainable behaviour.

Application of DASH client optimization and artificial intelligence in the management and operation of big data tourism hotels

The hotel uses modern information technology to establish a customer data group, which contains information about the customer's information on space configuration, color design, etc., and uses scientific operation methods to accelerate the rapid, transformation and upgrading of the hotel. The rapid development of information technology represented by the big intelligent mobile cloud has a lot of functions, can meet the needs of different customers and diversified characteristics at the same time, and provides a complete, stable and accurate information integration platform for hotel system management. The main research directions of DASH include client adaptive algorithm design, multi-client fairness and resource utilization issues, client improvement under multiple servers, and server load balancing. The development and application of scientific and technological information has broken through the development path of the hotel management system, providing new development space and opportunities for the improvement of the hotel management system, but at the same time it will also face more new challenges. Therefore, this article focuses on the characteristics of the tourism accommodation management system under the big data environment, and analyzes the development of the hotel management system under the network environment. The purpose is to provide some reference and reference significance.

ExpanDrogram: Dynamic Visualization of Big Data Segmentation over Time

In dynamic and big data environments the visualization of a segmentation process over time often does not enable the user to simultaneously track entire pieces. The key points are sometimes incomparable, and the user is limited to a static visual presentation of a certain point. The proposed visualization concept, called ExpanDrogram, is designed to support dynamic classifiers that run in a big data environment subject to changes in data characteristics. It offers a wide range of features that seek to maximize the customization of a segmentation problem. The main goal of the ExpanDrogram visualization is to improve comprehensiveness by combining both the individual and segment levels, illustrating the dynamics of the segmentation process over time, providing “version control” that enables the user to observe the history of changes, and more. The method is illustrated using different datasets, with which we demonstrate multiple segmentation parameters, as well as multiple display layers, to highlight points such as new trend detection, outlier detection, tracking changes in original segments, and zoom in/out for more/less detail. The datasets vary in size from a small one to one of more than 12 million records.

Research on Decentralized Access Control in Big Data Environment

With the rapid increase of network data, there are many challenges of security about data sharing in big data environment. The traditional attribute-based access control model generally adopts the centralized method. In the process of practical operation, once the decision node is attacked, the method will bring security risks to data resources. In order to improve the security of centralized access control and adapt to both dynamic and fine-grained characteristics of data access control in big data environment. The decentralized access control method for big data is proposed by combining the blockchain technology with attribute-based access control model.

A New Methodology for Storing Consistent Fuzzy Geospatial Data in Big Data Environment

In this era of big data, as relational databases are inefficient, NoSQL databases are a workable solution for data storage. In this context, one of the key issues is the veracity and therefore the data quality. Indeed, as with classic data, geospatial big data are generally fuzzy even though they are stored as crisp data (perfect data). Hence, if data are geospatial and fuzzy, additional complexities appear because of the complex syntax and semantic features of such data. The NoSQL databases do not offer strict data consistency. Therefore, new challenges are needed to be overcome to develop efficient methods that simultaneously ensure the performance and the consistency in storing fuzzy geospatial big data. This paper presents a new methodology that tackles the storage issues and validates the fuzzy spatial entities' consistency in a document-based NoSQL system. Consequently, first, to better express the structure of fuzzy geospatial data in such a system, we present a logical model called Fuzzy GeoJSON schema. Second, for consistent storage, we implement a schema-driven pipeline based on the Fuzzy GeoJSON schema and semantic constraints.

Research on Prediction Accuracy of Mathematical Modeling Based on Big Data Prediction Model

At present, people’s food demand in the late stage of the new coronavirus is affected by many aspects and various factors, and the current prediction method is affected by redundant data, which leads to poor accuracy of the prediction results. In addition, in order to prevent the mismatch between food supply and demand in the event of major health events, the prediction model was selected in the big data environment and the prediction accuracy of the mathematical model was studied. Through the improvement of various prediction models and the comparison of prediction accuracy, it is found that the improved grey Verhulst has higher accuracy and is more suitable for short-term prediction.