Big Data Analysis Model Research Articles

A Study on the Integrated Development of Artificial Intelligence and Tourism from the Perspective of Smart Tourism

In order to provide better travel experience for users under smart tourism, a data model that can be used for tourism analysis which is constructed by combining big data, Hadoop and crawler technology. Then, we combine with Item-based recommendation algorithm and the technology collected by crawler technology based on this model. It can provide an example of the specific integration application of big data analysis model and tourism. The results showed that the analysis model can highly recommend scenic spots favored by tourists. So it can provide reference for the integration of ARTIFICIAL intelligence and tourism, as well as a concrete example for the integration of artificial intelligence and tourism in the future.

Research on Computer Programming Optimization System Based on Big Data Technology

To improve network programming efficiency, the paper proposes a network automatic programming method based on big data analysis technology. Build a big data analysis model for automatic network programming. The dissertation uses the distributed information fusion method to extract the significant data feature of automatic network programming, extract the associated feature quantity of automatic network programming big data, and combine the fuzzy membership analysis method to carry out the synthesis operation and fuzzy comprehensive evaluation decision of automatic network programming and build network automation Programming multi-level index evaluation system to realize automatic network programming optimization.

RETRACTED: Independent and innovative learning of gymnastics teaching based on computer interaction

In order to improve the independent and innovative learning ability of gymnastics teaching, the independent and innovative learning and resource information interaction model of gymnastics teaching based on computer interaction is proposed, the integrated information statistics and big data analysis model of independent and innovative learning of gymnastics teaching is constructed, the independent and innovative learning and optimal control of gymnastics teaching are carried out by using the methods of big data mining and resource information fusion, and the data clustering analysis model of independent and innovative learning of gymnastics teaching is established. Statistical characteristic analysis method is used to construct independent innovative learning resource set and fuzzy information fusion processing for gymnastics teaching. Statistical evaluation and fuzzy degree optimization detection method are used to design independent innovative learning algorithm for gymnastics teaching. Computer interactive control method is used to realize adaptive optimization in independent innovative learning process for gymnastics teaching and realize independent innovative learning optimization for gymnastics teaching. The simulation results show that the convergence of using the algorithm to carry out independent and innovative learning in gymnastics teaching is good, and the ability of scheduling and clustering of independent and innovative learning resources in gymnastics teaching is good, thus improving the independent and innovative learning ability and the level of resource sharing in gymnastics teaching.

A distributed big data analytics model for people re-identification based dimensionality reduction

Big data analytics is a vast domain includes intelligent processing systems. Intelligent video surveillance generates a huge volume of data; and unstructured data requires fast processing speed. In...

A distributed big data analytics model for people re-identification based dimensionality reduction

A distributed big data analytics model for people re-identification based dimensionality reduction

A Study on Acer Mono Sap Integration Management System Based on Energy Harvesting Electric Device and Sap Big Data Analysis Model

This study set out to invent an Information and Communication Technologies (ICT)-based smart Acer mono sap collection electric device to make efficient use of the labor force by reducing inefficient activities of old manual work to record sap exudation and state information. Based on the assumption that environmental information would have close connections with Acer mono sap exudation to reinforce the competitive edge of production in forest products, the study analyzed correlations between Acer mono sap exudation and environmental information and predicted Acer mono exudation. A smart collection of electric devices would gather data about Acer mono sap exudation per hour on outdoor temperature, humidity, conductivity, and wind direction and velocity, and was installed in four areas in the Republic of Korea, including Sancheong, Gwangyang, Geoje, and Inje. Collected data were used to analyze correlations between environmental information and Acer mono sap exudation using four different algorithms, including linear regression, Support Vector Machine (SVM), Artificial Neural Network (ANN), and random forest, to predict Acer mono sap exudation. Remarkable outcomes were obtained across all the algorithms except for linear regression, demonstrating close connections between environmental information and Acer mono sap exudation. The random forest model, which showed the most outstanding performance, was used to make a mobile app capable of providing predicted Acer mono sap exudation and collected environmental information.

Construction and Application of a Financial Big Data Analysis Model Based on Machine Learning

Construction and Application of a Financial Big Data Analysis Model Based on Machine Learning

RETRACTED: Research on the innovation of college English teaching based on curriculum thinking

In order to realize the quantitative evaluation and analysis of the effect of college English teaching innovation reform, this paper puts forward the evaluation model of college English teaching innovation reform based on curriculum thinking, establishes the big data analysis model of college English teaching innovation reform effect, analyzes the constraint parameters of college English teaching innovation reform effect evaluation by means of statistical quantitative analysis, and abstracts the entropy characteristic quantity of big data, which is the effect of college English teaching innovation reform. The methods of spatial game equilibrium control and fuzzy decision are used to optimize and evaluate the effect evaluation of college English teaching innovation reform, the expert system analysis model of college English teaching innovation reform effect evaluation is established, and the hierarchical grey relational analysis method is used to carry out adaptive optimization and decision control for the evaluation of college English teaching innovation reform effect. The curriculum ideological and political model is used to optimize the reform of college English teaching innovation, and the quantitative analysis of the effect of college English teaching innovation reform is realized. The test results show that this method can effectively realize the evaluation decision of college English teaching innovation reform, with high reliability and strong innovative learning ability.

The impasse of competitive intelligence today is not a failure. A special issue for papers at the ICI 2020 Conference

The impasse of competitive intelligence today is not a failure. A special issue for papers at the ICI 2020 Conference

Big data analytics and international market selection: An exploratory study

A great deal of information is available on international trade flows and potentialmarkets. Yet many exporters do not know how to identify, with adequate precision, thosemarkets that hold the greatest potential. Even if they have access to relevant information, thesheer volume of information often makes the analytical process complex, time-consuming andcostly. An additional challenge is that many exporters lack an appropriate decision-makingmethodology, which would enable them to adopt a systematic approach to choosing foreignmarkets. In this regard, big-data analytics can play a valuable role. This paper reports on thefirst two phases of a study aimed at exploring the impact of big-data analytics on internationalmarket selection decisions. The specific big-data analytics system used in the study was theTRADE-DSM (Decision Support Model) which, by screening large quantities of marketinformation obtained from a range of sources identifies optimal product‒market combinationsfor a country, industry sector or company. Interviews conducted with TRADE-DSM users aswell as decision-makers found that big-data analytics (using the TRADE-DSM model) didimpact international market-decision. A case study reported on in this paper noted thatTRADE-DSM was a very important information source used for making the company’sinternational market selection decision. Other interviewees reported that TRADE-DSMidentified countries (that were eventually selected) that the decision-makers had not previouslyconsidered. The degree of acceptance of the TRADE-DSM results appeared to be influenced byTRADE-DSM user factors (for example their relationship with the decision-maker andknowledge of the organization), decision-maker factors (for example their experience andknowledge making international market selection decisions) and organizational factors (forexample senior managements’ commitment to big data and analytics). Drawing on the insightsgained in the study, we developed a multi-phase, big-data analytics model for internationalmarket selection.

Risk Assessment Algorithm for Agricultural Value Chain Financing in Coastal Areas Based on HMM Model

Chen, J., 2020. Risk assessment algorithm for agricultural value chain financing in coastal areas based on HMM model. In: Yang, Y.; Mi, C.; Zhao, L., and Lam, S. (eds.), Global Topics and New Trends in Coastal Research: Port, Coastal and Ocean Engineering. Journal of Coastal Research, Special Issue No. 103, pp. 42–46. Coconut Creek (Florida), ISSN 0749-0208.In order to realize the quantitative evaluation and automatic prediction of the risk factors of agricultural value chain financing in coastal areas, an algorithm for the risk assessment of agricultural value chain financing in coastal areas based on HMM model is proposed. Establishing the big data analysis model of agricultural value chain financing risk in coastal areas, using the statistical quantitative analysis method to analyze the constraint parameters of agricultural value chain financing risk assessment in coastal areas, using the method of output stability gain evaluation and fuzzy decision-making to optimize the decision-making and evaluation of agricultural value chain financing risk in coastal areas, using the adaptive weighted learning algorithm to carry out the adaptive optimization of agricultural value chain financing risk assessment in coastal areas. The simulation results show that the accuracy and confidence level of agricultural value chain financing risk assessment in coastal areas are high and the efficiency of agricultural value chain financing risk assessment in coastal areas is improved.

Deep learning based big medical data analytic model for diabetes complication prediction

The revolution in digitization makes the health care sector as a prime source of big data. The analysis of these data could be a great supporting source for deriving new insights, which increases the care and awareness about health. Diabetes together with its complications has been recognized worldwide as a chief public health threat. Predicting diabetic complications is considered as a highly effectual technique for augmenting the survival rate of diabetic patients. While many studies currently use medical images and structured medical records, very limited efforts have been dedicated for applying Data Mining (DM) techniques for unstructured textual medical records, for instance, admission and discharge records. Many DM techniques have been generated for envisaging diabetic complications. But in existing methods, the classification as well as prediction accuracy is not so high. So this paper proposes a model centered on Deep Learning (DL) for predicting complications of Type 2 Diabetes Mellitus. The proposed model follows data collection, pre-training, feature extraction, Deep Belief Network (DBN), validation process, and classification steps for predicting diabetic complications. Finally, the performances proffered by the proposed DL based Big Medical Data Analytics model using DBN as well as the prevailing techniques are contrasted with respect to Precision, accuracy, and Recall. The Training, as well as the Testing process, delineates the pervasiveness of risk with an accuracy of 81.20%. This realistic prediction model will be very much useful for effectively managing diabetes.

Analysis of Physical Education Teaching Evaluation System

In order to realize the accurate evaluation of physical education teaching quality, a big data analysis model of physical education teaching quality evaluation is proposed, and the system analysis the evaluation of physical education teaching .Big data classification and identification of physical education quality are carried out by using K-means clustering method. According to the results of statistical feature clustering of physical education quality, the input effectiveness of physical education hardware facilities is evaluated. Establish the quantitative evaluation model of financial expenditure and PE teaching quality evaluation project performance, adopt F statistic quantity analysis method to adjust the structure of physical education teaching hardware input and teacher force input. According to the statistical analysis results of physical education teaching quality evaluation, the self-adaptive evaluation of physical education teaching quality evaluation is carried out, and the optimization of physical education teaching quality evaluation is realized by combining the big data analysis method.

DESIGN OF COOPERATIVE UPDATE MECHANISM OF NATIONAL RESOURCES INVESTIGATION AND BASIC SURVEYING AND MAPPING

Abstract. National resources investigation and basic surveying and mapping are two important tasks of the surveying and mapping department, and they are similar in production organization and technology realization. In the process of operation, both of them need to carry out internal collection, base map production, field verification and so on. It is operationally feasible to carry out cooperative production of national resources investigation and basic surveying and mapping. From the perspective of technical process and method, both of them are carried out by combination internal and field work. Firstly, based on remote sensing images and thematic geographic data, the internal work will perform image interpretation. Then, the field verification will be carried out to make judgments and adjustments. Finally, the results of the field verification will be transferred back to the internal work, and the data will be further edited and organized in the internal work to obtain the final data.This paper analyzes the technical methods and workflow of the cooperative update mechanism of national resources investigation and basic surveying and mapping. It will enable one-time acquisition of data needed for the national resources investigation and basic surveying and mapping. It is conducive to unifying the classification system, technical standards, survey methods, establishing a natural resource data service system, and improving the natural resource data sharing working mechanism. Realize the overall control of the land space, solve the contradictory problems such as multiple doors, uneven thickness, repeated crossover, etc., advance data integration and deep development and utilization by using big data technology and data analysis model.

Evaluation Model of College English Teaching Quality Based on Big Data Analysis

With the implementation of internationalization, the quality of English education has become more and more important. How to assess English Teaching Quality of contemporary college students has become one of the research hot spots. The widespread application of big data analysis is to solve the current English Teaching of college students. Evaluation issues provide new directions for resolution. Construction of College English TQA System Based on Big Data Analysis. It is based on the construction of big data of college students ‘English teaching quality, by constructing a model, visually presenting the college English teaching quality trajectory, so as to understand the students’ learning situation more intuitively. Aiming at the complex changes in the quality of English teaching, this paper designs a big data analysis model of English teaching quality for college students in order to obtain high-precision evaluation results of English teaching quality. This paper uses big data analysis technology to build a college English TQA model, and experimentally verifies the reliability of the model established in this paper. After experimental verification, it is found that the big data analysis of the college English TQA model proposed by this paper has an evaluation accuracy of 90.22% This fully demonstrates the reliability of the model and provides a good reference value for the evaluation of teaching quality.

Analysis in big data of satellite communication network based on machine learning algorithms

AbstractWith the development of satellite communication network technology, the amount of data generated every day and the rate of data growth are amazing. These different types of data (not necessarily structured) contain rich information. Based on this, a satellite for machine learning is proposed. First, a correlation analysis model is established, and a machine learning method is applied to the data prediction analysis of the satellite communication network. The basic idea and application process of the AdaBoost‐BP algorithm are introduced in detail. Second, combined with the data features after dimensionality reduction processing, an efficient big data analysis model is trained. Third, in order to quickly locate the abnormal behavior of users under large‐scale data, an algorithm for quantifying abnormal behaviors of users based on satellite communication network log information and quickly detecting and analyzing big data is proposed. Finally, experimental verification is performed. The experimental results verify that the method can improve the big data analysis capability of satellite communication networks.

Improved Feature Selection Model for Big Data Analytics

Although there are many attempts to build an optimal model for feature selection in Big Data applications, the complex nature of processing such kind of data makes it still a big challenge. Accordingly, the data mining process may be obstructed due to the high dimensionality and complexity of huge data sets. For the most informative features and classification accuracy optimization, the feature selection process constitutes a mandatory pre-processing phase to reduce dataset dimensionality. The exhaustive search for the relevant features is time-consuming. In this paper, a new binary variant of the wrapper feature selection grey wolf optimization and particle swarm optimization is proposed. The K-nearest neighbor classifier with Euclidean separation matrices is used to find the optimal solutions. A tent chaotic map helps in avoiding the algorithm from locked to the local optima problem. The sigmoid function employed for converting the search space from a continuous vector to a binary one to be suitable to the problem of feature selection. Cross-validation K-fold is used to overcome the overfitting issue. A variety of comparisons have been made with well-known and common algorithms, such as the particle swarm optimization algorithm, and the grey wolf optimization algorithm. Twenty datasets are used for the experiments, and statistical analyses are conducted to approve the performance and the effectiveness and of the proposed model with measures like selected features ratio, classification accuracy, and computation time. The cumulative features picked through the twenty datasets were 196 out of 773, as opposed to 393 and 336 in the GWO and the PSO, respectively. The overall accuracy is 90% relative to other algorithms ' 81.6 and 86.8. The total processing time for all datasets equals 184.3 seconds, wherein GWO and PSO equal 272 and 245.6, respectively.

Big Data Curation for Analytics within the Cyber-Physical Manufacturing Metrology Model (CPM3)

This paper presents recent research on enabling cloud-based model for big data analytics within the Cyber-Physical Manufacturing Metrology Model (CPM3). We will first briefly review a physics-based concept for converting optical metrology data into useful information that can easily be communicated and stored on the cloud for subsequent data mining. We also propose a novel organization of the compressed metrology data on the cloud, enabling logarithmically accelerated searching of databases and thus providing dramatic advantages for data mining. Capabilities of the new concepts of inspection data curation are demonstrated in defect detection using measurements of nanopatterned wafer surfaces.

Fog and Cloud Computing Assisted IoT Model Based Personal Emergency Monitoring and Diseases Prediction Services

Along with the rapid development of modern high-tech and the change of people's awareness of healthy life, the demand for personal healthcare services is gradually increasing. The rapid progress of information and communication technology and medical and bio technology not only improves personal healthcare services, but also brings the fact that the human being has entered the era of longevity. At present, there are many researches focused on various wearable sensing devices and implant devices and Internet of Things in order to capture personal daily life health information more conveniently and effectively, and significant results have been obtained, such as fog computing. To provide personal healthcare services, the fog and cloud computing is an effective solution for sharing health information. The health big data analysis model can provide personal health situation reports on a daily basis, and the gene sequencing can provide hereditary disease prediction. However, the injury mortality and emergency diseases since long ago caused death and great pain for the family. And there are no effective rescue methods to save precious lives and no methods to predict the disease morbidity likelihood. The purpose of this research is to capture personal daily health information based on sensors and monitoring emergency situations with the help of fog computing and mobile applications, and disease prediction based on cloud computing and big data analysis. Through the comparison of test results it was proved that the proposed emergency monitoring based on fog and cloud computing and the diseases prediction model based on big data analysis not only gain more of the rescue time than the traditional emergency treatment method, but they also accumulate lots of different personal healthcare related experience. The Taian 960 hospital of PLA and the Yanbian Hospital as IM testbed were joined to provide emergency monitoring tests, and to ensure the CVD and CVA morbidity likelihood medical big data analysis, the people around Taian city participated in personal health tests. Through the project, the five network layers architecture and integrated MAPE-K Model based EMDPS platform not only made the cooperation between hospitals feasible to deal with emergency situations, but also the Internet medicine for the disease prediction was built.

Redundancy Avoidance for Big Data in Data Centers: A Conventional Neural Network Approach

As the innovative data collection technologies are applying to every aspect of our society, the data volume is skyrocketing. Such phenomenon poses tremendous challenges to data centers with respect to enabling storage. In this paper, a hybrid-stream big data analytics model is proposed to perform multimedia big data analysis. This model contains four procedures, i.e., data pre-processing, data classification, data recognition and data load reduction. Specifically, an innovative multi-dimensional Convolution Neural Network (CNN) is proposed to assess the importance of each video frame. Thus, those unimportant frames can be dropped by a reliable decision-making algorithm. In order to ensure video quality, minimal correlation and minimal redundancy (MCMR) are combined to optimize the decision-making algorithm. Simulation results show that the amount of processed video is significantly reduced, and the quality of video is preserved due to the addition of MCMR. The simulation also proves that the proposed model performs steadily and is robust enough to scale up to accommodate the big data crush in data centers.