Optimization of University Library Services through Big Data and Multi-source Data Fusion

In the practical application of existing big data tourism prediction, there are some practical problems, such as complicated data sources and difficult fusion, low prediction accuracy and poor guiding practice effect. In view of this situation, this paper intends to build a tourism big data index prediction model suitable for the characteristics of tourism development through core data extraction, multi-source data fusion, complex data modeling and other key technologies. With the help of the improved tourism prediction model based on multi-source big data fusion technology, the tourist flow and consumption characteristics of Shandong province are more accurately identified and predicted. It can provide help for optimizing public service of tourism, strengthening early warning of tourist flow and improving marketing strategy of tourist destination. This study innovatively supplements the effective integration theory of multi-source tourism big data and the organic integration theory of big data and traditional sampling survey data. At the same time, the relevant methods of tourism big data forecasting model are extended.

This paper adopts the method of multisource big data fusion to conduct an in-depth study and analysis of precision poverty alleviation and uses big data statistical analysis model to explore and analyze it. Combining the characteristics of big data itself and the development of precision poverty alleviation, it focuses on the exploration of big data and introduces the background, development status, and achieved results of poverty alleviation with typical cases, followed by the analysis of the problems in the process of big data precision poverty alleviation and the study of the improvement path of big data technology precision poverty alleviation. Through the comparative analysis of the simulation accuracy of three models, the results show that the random forest model has the lowest error rate, after which the importance degree of indicators is derived using the model. In addition, the empirical analysis of the preprocessed sample data for multidimensional identification of poor households yields the contribution rate of each dimensional indicator that leads to multidimensional poverty of farm households, establishing scientific judging criteria to accurately judge whether farm households are poor on the one hand and selecting accurate identification methods to achieve accurate identification of poor households on the other hand. The tenfold crossover method is used to verify the errors in the test sample set. When the number of classification trees is greater than 100, it will gradually increase. Therefore, it is most appropriate to select the number of trees as 100. The multidimensional accurate identification model of farm household poverty constructed in this paper has an accuracy rate of 90.26% for the identification of poor households. By analyzing the accuracy rate of model identification and the contribution rate of multidimensional indicators leading to the poverty of farm households at the same time, the poverty degree of farm households under each dimensional indicator is derived, to accurately identify the poor households and their poverty status. The results show that the multidimensional accurate identification model of farm household poverty has the accurate identification ability and application value in the identification problem of poor households, and through the implementation of the model algorithm, a good application environment of accurate identification of poverty is created, which provides technical support to help poverty alleviation work and improve the accuracy of identification of poor households.

Aiming at the orbit floating or so called constellation rotation in navigation satellite autonomous orbit determination, an approach based on multi sources data fusion was introduced, that is to introduce angle observation from on board star sensor toward fixed star to fix the ascending node Ω, one of the six orbit elements so as to avoid constellation rotation. During data processing, a generalized measurement model based on matrix Cholesky decomposition and the method of measurement noises de-correlation was adopted. On the foundation of roundly analysis of present theories and methods of multi sources data fusion, and characteristics of multi sources measurement data fusion taken into account, two sorts of multi sources data fusion measurement models based on independent same distribution and correlation of measurement noises were conducted. Theoretical analysis and simulation experiment show that navigation satellite autonomous orbit determination based on multi sources data fusion can well solve the problem of orbit floating contrasting against that of only inter-satellite observations used.

Objective To establish an automatic staging model of hepatocellular carcinoma (HCC)in China based on big data platform. Methods Based on the information system structured by Primary Liver Cancer Big Data (PLCBD) platform of Big Data Institute of Southeast Hepatobiliary Health Information,Meng Chao Hepatobiliary Hospital of Fujian Medical University, the data for HCC staging, such as performance status (PS) score, Child-Pugh grading, extrahepatic metastasis, vascular invasion, number of tumor and tumor size, were rapidly extracted in database visualization mode. The China HCC automatic staging model of was constructed by using CASE-WHEN conditional judgment statement, and was visualized through web page developing. In total, 100 cases with complete PLCBD data were randomly selected for testing. The China HCC automatic staging model was employed for automatic staging. Manual staging for the tested patients was done by 4 attending physicians and 6 resident physicians from Department of Hepatobiliary Surgery. Multidisciplinary consultation was taken as the gold standard to observe the accuracy and practicability of the model. The results among automatic staging and manual staging of two groups were statistically compared by one-way ANOVA. Results Through the database visualization mode, the extraction of PS score, Child-Pugh grading, extrahepatic metastasis, vascular invasion, number of tumor, tumor size and staging-related indexes can be performed. Based on the big data of the above 6 aspects, China HCC automatic staging model was successfully established. The time for conducting automatic staging was 3 s, the average time of manual staging by attending physicians was (40±6) min, and (100±8) min for resident physicians with significant difference between them (F=227.90, P 0.05). Conclusions The China HCC automatic staging model can be successfully established based on the big data platform. The automatic staging model is highly efficient and accurate. Key words: Carcinoma, hepatocellular; Neoplasm staging; Big data; Database

Improving the level of intelligent fire protection construction is an important issue facing the current Chinese emergency rescue department. Among them, the fire rescue command platform is an important part of the intelligent fire protection This paper analyzes the current situation of big data platform of fire rescue command in China from the aspects of its connotation, data collection method, data transmission method and multi-source data fusion. Taking the “3.21” explosion accident in Yancheng, Jiangsu Province as an example, the application of fire rescue command big data technology in the emergency rescue of the explosion accident was analyzed. Finally, two methods of software and hardware construction are used to forecast the next step of China's fire rescue command platform.

The paper explores the application of multi-source spatial data fusion in archaeology and analyzes its future challenges. It shows that multi-source spatial data fusion can help archaeologists discover, analyze and protect archaeological sites and their surroundings more accurately. However, the heterogeneity of data, the complexity of processing and analyzing, and the challenge of interdisciplinary cooperation are still notable issues. The aim of this paper is to investigate the application and role of multi-source spatial data fusion, to explore the challenges it faces, and to propose methods to address these challenges.

Modelling and analysis of big data platform group adoption behaviour based on social network analysis

Since 1991, the Research and Development (R&D) group at Lockheed Martin Canada (LM Canada) has been developing and demonstrating the application of Multi-Source Data Fusion (MSDF) techniques for target tracking and identification within the Naval Command and Control (C2) for the HALIFAX Class frigates. The current C2 as well as the sensor suite of the HALIFAX Class were designed in the early 80s and based around a proprietary hardware architecture. The sensor data is pre-processed and provided to the C2 in real time. Considering the late 70s and 80s design of the sensor interfaces, where a data fusion within the C2 was not a commonality, not all of the information beneficial for a data fusion system is provided to the C2. After a sequence of simulation and modelling efforts for an MSDF capability within the HALIFAX Class C2, this project is now at a point where real data captured from a ship trial on the HALIFAX Class is being injected into the MSDF. This is an ongoing activity and a number of iterations are foreseen before the MSDF becomes part of HALIFAX Class C2. This paper provides a summary of lessons learned in this exercise.

Aiming at the problems of poor security and clustering accuracy in current data clustering algorithms, a controllable clustering algorithm for real-time streaming big data based on multi-source data fusion is proposed. The FIR filter structure model is used to suppress network interference, and ant colony algorithm is used to detect the abnormal data in the big data. By optimizing the iteration, the pheromone concentration is placed in the front position as the abnormal data point, and the filter is introduced. The fusion scope of multi-source data fusion is set. Combined with the data similarity function, the multi-source data fusion concept is used to construct the associated real-time streaming big data fusion device, and the data deduplication results are substituted into the fusion device to obtain the data clustering result. The experiments show that the proposed algorithm has high safety factor, good data clustering accuracy, high clustering efficiency, and low energy consumption.

Intelligence transportation system (ITS) and vehicular networks have attracted the research community in the recent years which generate the “big data” in traffic. However, the collection and application of the big traffic data is limited by the privacy of people who generate data. Besides, data-driven-based ITS only needs information that could reflect one or more types of vehicles at specific intersections, sections, and road networks, rather than that of each individual vehicle. Overall, intelligent analysis and data fusion of multi-source traffic data play an important role to reduce the phenomenon of privacy disclosure and ensure the quality of data. As a result, a complete method of multi-source traffic data analyzing and processing is proposed in this paper, including the data analysis method based on the spatio-temporal regression model and the data fusion method using evidence theory based on the confidence tensor. Finally, the practical data is used to conform the ways proposed before. And not only do the results show that the implicit privacy information has been removed but also present a higher accuracy of the proceed data.

With the development of research on multi-modal data fusion and its combination with online data management, the application of multi-modal big data fusion in information management systems is more and more extensive. How to integrate multi-modal big data effectively is the key technology to building an efficient information management system. In this paper, based on the combination of a multi-support vector machine and convolution neural network, the feature-level data fusion of multi-source heterogeneous big data is implemented, and it is applied to the real data set to test the relevant model. Experimental results show that this method can not only realize heterogeneous integration of big data, but also has high accuracy and reliability.

In the context of the information technology of logistics enterprises, the field of artificial intelligence empowers the logistics industry and brings revolutionary changes to it. The emergence of drones, self-driving cars and intelligent picking robots has dramatically changed the existing mode of warehousing, transport and logistics operations. Information technology based on big data mining and natural language processing has also made “data-driven logistics” a reality. In order to make full use of the rapidly growing big data in the logistics field and to solve the problem of efficiently querying the information of multiple logistics enterprises for comparison and extracting, integrating and querying multi-source data of logistics enterprises in the era of big data, the article combines the special vocabulary and special grammatical features in the logistics field. It proposes a method for extracting and constructing the entity relationship based on multi-source data fusion. The core method is to design and build stored procedures using the MySQL database to transform structured batches into triples. A dependency syntactic analysis model is designed, and a custom dictionary is added to extract triads from unstructured data to improve the efficiency and accuracy of traditional dependency syntactic analysis. Based on the triad extraction results, a knowledge graph in the logistics domain is constructed in the Neo4j graph database. The graph can be used to compare multiple logistics enterprises’ queries, uncover suspicious points of logistics enterprises, expose enterprise risks, effectively improve the efficiency of logistics information queries, and provide an innovative idea for logistics enterprises’ information construction. KeywordsKnowledge graphDependent syntactic analysisCustom dictionariesNeo4jTriples extracted

The rapid development of the Internet has produced massive amounts of data, and has promoted the development of various big data components in the big data field, such as Hadoop, Spark and other big data components. However, many big data components face many problems in actual industrial production, make the construction and maintenance cost of the big data platform high. Although there is an automated deployment platform for big data components on the market, it lacks comprehensive management and monitoring functions for the entire big data platform, resulting in users not being able to fully pay attention to all aspects of the big data platform, and the service and resource management is not flexible enough. Therefore, we have designed and implemented an open componentized big data platform, so that users can not only easily install and deploy big data components in the cluster, but also manage the resources and services of big data components conveniently and flexibly. Besides, complete monitoring information also provides the necessary guarantee for the stable running of the big data platform. The open componentized big data platform provides users with one-stop big data services.

On the bases of the OpenStack private cloud delivery big data platform, numerous entities yearn for attaining agile and standardized big data delivery platform, reclaiming the resources, managing the total cost of ownership (TCO) and adapting to multiple big data open source or commercial off-the-shelf (COTS) solutions. Nevertheless, as regards the big data platform running on cloud computing, the big data platform is disintegrated from the cloud computing system by virtual machines since neither being based on OpenStack private cloud nor on big data platform can achieve end-to-end resource delivery, together with ensuring that it is quite convenient for the long-term operations. Accordingly, establishing an across framework between private cloud and big data platform is quite essential. The big data on cloud agile provision framework could realize fast resource delivery based on predefined orchestration template of private cloud, operating system, big data platform, monitor, inspection system, etc. Through the deployment of this framework, it is capable of attaining the delivery of agile, low cost, standardized and high adaptability the big data on cloud, as well as the high-quality operation of the big data on cloud with the help of integration configuration management database (CMDB) with the automatic inspection system.

With the increase of the types of urban management objects, the intelligent management of the whole city has become a matter of concern in various countries, and it is also one of the indispensable links in urban development. In the construction of cities all over the world, the intelligent and scientific management system has been used innovatively. We provide excellent facilities for transportation development, information exchange, and resource progress. The research on urban fine management based on multisource spatial data fusion is proposed. Aiming at the traffic problems in urban fine management, this paper proposes a deep network architecture based on multisource data fusion. Multisource spatial data fusion technology is used to analyze urban traffic data. Deep network architecture is used to improve the precision management status of a smart city and the accuracy of traffic condition prediction. Then, the convolution neural network technology is explored in the data fusion technology strategy. The research results show that the framework has the ability to deal with heterogeneous data and urban big data and can effectively improve the traffic management state in the construction of a smart city and effectively solve the complexity of urban fine management and processing efficiency in the construction of a smart city.