Forthcoming and Online First Articles

International Journal of Information Technology and Management

International Journal of Information Technology and Management (IJITM)

Forthcoming articles have been peer-reviewed and accepted for publication but are pending final changes, are not yet published and may not appear here in their final order of publication until they are assigned to issues. Therefore, the content conforms to our standards but the presentation (e.g. typesetting and proof-reading) is not necessarily up to the Inderscience standard. Additionally, titles, authors, abstracts and keywords may change before publication. Articles will not be published until the final proofs are validated by their authors.

Forthcoming articles must be purchased for the purposes of research, teaching and private study only. These articles can be cited using the expression "in press". For example: Smith, J. (in press). Article Title. Journal Title.

Articles marked with this shopping trolley icon are available for purchase - click on the icon to send an email request to purchase.

Online First articles are published online here, before they appear in a journal issue. Online First articles are fully citeable, complete with a DOI. They can be cited, read, and downloaded. Online First articles are published as Open Access (OA) articles to make the latest research available as early as possible.

Open AccessArticles marked with this Open Access icon are Online First articles. They are freely available and openly accessible to all without any restriction except the ones stated in their respective CC licenses.

Register for our alerting service, which notifies you by email when new issues are published online.

We also offer which provide timely updates of tables of contents, newly published articles and calls for papers.

International Journal of Information Technology and Management (51 papers in press)

Regular Issues

  • Impact of E-commerce on supply chain management   Order a copy of this article
    by Saleeshya P.G, Rahul R 
    Abstract: E-commerce is web-enabled technology that brought significant changes in the supply chain activities of anindustry. Supply chain management has become a major strategy in manufacturing and service industry. An attempt has made in this paper on identifying the significant factors that affect the e-commerce adoption in the supply chain of a company, identifying the effects of e-commerce on different aspects of supply chain. The study also identifies the major performance parameters of a supply chain and effect of e-commerce adoption on these supply chain variables. An attempt has been made to propose a conceptual model for the study based on the existing literature and field study; the model is validated by academic experts and also experts in industry. Correlation analysis is being carried out to find gap between the ideal and actual situation.rnrn
    Keywords: supply chain; E-commerce; correlation; conceptual model.

  • Determinants of Success and Failure of Knowledge Transfer in Information Systems Offshoring: A Ranking-Type Delphi Study   Order a copy of this article
    by Artur Strasser, Susanne Strahringer, Markus Westner 
    Abstract: The transfer of knowledge from client to service provider poses major challenges in information systems (IS) offshoring projects. Knowledge transfer directly affects IS offshoring success. Therefore, associated challenges must be overcome. Our study examines the determinants of success and failure of knowledge transfer in IS offshoring projects based on a ranking-type Delphi study. We questioned 32 experts from Germany, each with more than ten years of experience in near- or offshore initiatives to seek a consensus among them. We identified 19 success and 20 failure determinants. These determinants are ranked in order of importance using best-worst scaling. Aspects of closer cooperation are critical for effective knowledge transfer. This includes regular collaboration, willingness to help and support, and mutual trust. In contrast, critical determinants of failure are concerned with fears and fluctuation of human resources. Hidden ambiguities or knowledge gaps, an unwillingness and disability to share knowledge, and high fluctuation of human resources negatively impact knowledge transfer.
    Keywords: best-worst scaling; BWS; delphi; determinants of success; determinants of failure; information systems; IS; information systems offshoring; knowledge transfer; ranking-type delphi.

  • How to evaluate brand extension in the mobile Internet environment   Order a copy of this article
    by Wenlong Zhu, Shiye Wang 
    Abstract: How to successfully implement a brand extension has been a common topic among global enterprises. Mobile Internet (M-Internet), a new information and communication technology, creates suitable conditions for enterprise brand extension. However, most researches related to brand extension evaluation focus on traditional information technologies presently. Little research has addressed M-Internet. From the perspective of consumer, this study constructs brand extension evaluation model based on the Task-Technology Fit (TTF) and Aaker and Keller Model (A & K Model), and analyzes the influencing mechanism of brand extension evaluation by using the Structural Equation Modeling (SEM). The final results show that technical characteristics of M-Internet produce a positive effect on attitude of parent brand. Furthermore, attitude of parent brand influences the brand extension evaluation, brand trust and perceived fit positively. Lastly, brand extension evaluation is subject to positive impact of brand trust and perceived fit besides attitude of parent brand. The theoretical and practical implications of this study are discussed lastly.
    Keywords: Mobile Internet; Brand extension evaluation; Structural Equation Modeling; Mediation effect.

  • QoE-based service differentiation: An analysis of the business implications for the mobile services market   Order a copy of this article
    by Luis Guillermo Martinez Ballesteros, Per Jonny Nesse, Jan Markendahl 
    Abstract: Mobile network operators (MNOs) face a future characterized with new challenges, such as growing data consumption, a slowdown in subscriber growth and reduced revenues due to the success of over-the-top providers. To remain competitive, MNOs must offer affordable services and provide innovative strategies to retain current customers. Quality of Experience (QoE) is a well-established methodology for measuring and understanding the overall level of customer satisfaction and has also been presented as a way to improve telecommunication services. Even though QoE can be used to solve problems, such as customer loyalty and optimization of network resources in mobile networks, there is still a lack of knowledge on how the MNOs can take advantage of QoE and its potential benefits. In this paper, we explored the implications of the incorporation of QoE feedback in mobile networks at the business level. The analysis, which is based on a combination of value network configuration and business model analysis of scenarios, shows that value-added offers of differentiated and personalized services can be seen as alternatives to generate new revenue streams in the mobile service market. An important finding from our study is that, due to the nature of the challenges facing the mobile services industry, a QoE analysis cannot be limited to only a technical discussion but needs to be combined with an informed analysis of the business implications of the proposed solution.
    Keywords: Quality of Experience; Business Models; Mobile Networks; Service Differentiation.

  • Research on Evaluation of Network Payment Security   Order a copy of this article
    by Xiang Xie, Ying Cui 
    Abstract: The paper collects the data about the network payment fraud through the questionnaire and then analyzes the data. We propose a prediction model based on the hybrid support degree Apriori algorithm, and find out the factors that are closely related to the success of cheating. Then we find out the nodes of the decision and their importance tree use the ID3 algorithm to construct the decision tree, construct and verify the evaluation index system of the network payment from the user's point of view, considering the results of association rules and decision tree, combined with principal component analysis and text mining results, and then determine the weight using entropy method. So we can determine the probability of being deceived according to the situation of different people, not only remind people to be vigilant, but also provide reference for the community.
    Keywords: Apriori algorithm; ID3 algorithm; Internet payment security; styling; Evaluation System; Principal component analysis; entropy method.

  • Scrutinizing medical practitioners twitter feeds analysis   Order a copy of this article
    by Arushi Jain, Vishal Bhatnagar, Nilanjan Dey, Amira Ashour, Fuqian Shi 
    Abstract: Mining of social media data has found widespread applications in recent times. Twitter feeds and facebook posts are being used to device product marketing strategies, sentiment analysis, financial predictions and forebode alarming situations. Twitter feeds analysis can be applied for analyzing the behavior and experiences of medical practitioners. Doctors informal conversations on Twitter can provide deep insights about their work experiences, their concerns about the profession, their feelings- pathos or excitement they feel and the affecting conditions. In the present work, twitter feed of Doctors along with the Twitter hashtags are used to collect data from tweets with hashtags such as #DoctorProblems. Afterward, data analysis was performed to determine the major problems faced by the members of the medical fraternity. These problems were categorized into five main categories. Further, based on these categories, the multi-label Na
    Keywords: Big data; Hadoop distributed file system; MapReduce; Naïve Bayes multilabel classifier; Tweets; Evaluation based measure; Label based measure.

  • Big Data Block Impact within Big Data Environment   Order a copy of this article
    by Ron Ziv, Oded Koren, Nir Perel 
    Abstract: Handling data is becoming more and more complex. A higher velocity of data is created as more people have access to data generating devices such as computers, mobile phones, medical devices, home appliances, etc. Data files, such as user activity logs, system logs and so on, are stored in HDFS big data platform in various sizes, considering the business requirements, infrastructure parameters, administration decisions, etc. Dividing the data files (in various volumes), without taking into consideration the HDFS predefined block size may create performance issues which can affect the systems activity. This paper presents how HDFS block design affects the performance of Apache Hadoop
    Keywords: architecture; HDFS; performance; big data.

  • A reliability and security enhanced framework for cloud-based storage systems   Order a copy of this article
    by Peng Xiao 
    Abstract: In cloud computing environments, reliable and secure data storage service plays a more and more important role in many data-intensive applications. However, existing storage systems either fail to provide them or provide them in a cost-ineffective manner. To provide better storage service in nowadays cloud environments, we propose a novel framework called Reliability and Security enhanced Cloud Storage (RSCS), which consists of several well-designed components to improve low-level data reliability as well as guarantee up-level data accessing security. In the RSCS framework, a simple yet effective file system scheme is proposed, which can mirror striped data among different nodes to improve the reliability while maintaining a high aggregated throughput. A centralized lease-based mechanism is designed to allow simultaneous accesses to different portions of a single file while maintaining the multiple-reader-single-writer semantics to each requested data portion. Finally, we provide a secure data accessing tunnel technology which allows the RSCS to establish secure communication channels between users and storage nodes without introducing too many extra costs. Extensive experiments are conducted in a real-world cloud storage platform, and the results indicate that the performance of the proposed RSCS framework can easily meet the requirements for most of current cloud systems.
    Keywords: cloud storage; data security; replication service; file system.

  • Openstack: a virtualization overview   Order a copy of this article
    by Pedro Martins, Faouzi Mechraoui, Filipe Cladeira 
    Abstract: The major cloud computing software companies offer a new concept, on which resources are virtualized to provide the service on the internet. Currently, there are multiple service providers, and additional options to virtualize services on premises. OpenStack is an open source alternative to create virtual local or cloud setups, which supports the petabytes of data, unlimited scale, and configurable networking. These features make this tool suitable for large scenarios virtualization, reducing maintenance costs and optimizing hardware resources utilization (e.g., schools, government). This paper presents an overview of the study of OpenStack software, oriented to build a scalable hosting architecture suitable for an educational setup. Functional and architectural details are discussed to implement unique cloud computing to fit the virtualization purposes. An experimental virtualization setup is described in the scope of an educational scenario. Finally, a guideline to configure OpenStack is given.
    Keywords: OpenStack; IaaS; Virtualization; Cloud computing; Open Source.

  • Consequential effects of leading technology-driven offensive strategy in a universal bank   Order a copy of this article
    by Asare Yaw Obeng, Alfred Coleman 
    Abstract: Globally, banking industry is saddled with intense competition. Management of banking firms are required to formulate effective strategies to drive their capabilities to compete, discover and defend their positions in a competitive industry. ?n Ghana, universal banks are leveraging the capabilities of information technology to devise technology-driven offensive strategies. The core of these strategies is embarking on innovative activities to enhance performance and respond to business challenges. A qualitative analysis was performed using primary data from 17 participants. Using NVivo, consequential effects of IS-technological innovation (ISTI) on business challenges, innovation performance, operational performance; and specific moderating factors of ISTI were assessed. Strategic-IS Project impacts strong (r=0.634601) and positive on ISTI than the other moderators. ISTI impacts strongly (r=0.644951) and positively on operational performance. With r=0.7422, innovation performance positively and strongly influences operational performance. ISTI impacts positively on business challenges.
    Keywords: Bank; Ghana; industry threats; information systems; linear regression; moderating factors; offensive strategy; technological innovation.

  • AQINM: an adaptive QoS management framework based on intelligent negotiation and monitoring in cloud   Order a copy of this article
    by Zeng Saifeng 
    Abstract: Recently, more and more federated cloud platforms have been constructed to deal with non-trivial large-scale applications, which typically require certain level of quality-of-service (QoS) guarantee. However, most of existing cloud-oriented QoS solutions are likely to introduce extra overheads on either resource allocation or task execution, which is especially true in federated cloud environments. In this paper, we present a lightweight QoS-enhancing middleware, namely Adaptive QoS Management based on Intelligent Negotiation and Monitoring (AQINM), which provides three QoS-enhancing services including policy management, service-layer-agreement (SLA) negotiation, and SLA monitoring. Unlike the conventional QoS-enable middleware, these services in the AQINM framework introduce several novel mechanisms to offer more cost-effective and efficient solutions to enforcing the QoS management in federated clouds. The implementation of our AQINM framework are tested in a campus federated cloud platform by using different applications as experimental benchmarks, and its performance are compared with other similar solutions. The experimental results indicate that the proposed AQINM can significantly reduce the costs of SLA negotiation and monitoring for large-scale cloud application that deployed in federated cloud environments.
    Keywords: cloud computing; quality of service; service layer agreement; resource virtualization.

  • Global Information Technology Outsourcing: Issues of Attractiveness of Some Regions in Eastern Europe   Order a copy of this article
    by Grigori Feigin, Anna Hayduk 
    Abstract: The article deals with the problem of the development of global information technology outsourcing. Based on the summary of main theoretical approaches used to explain the phenomenon of outsourcing, the conditions for making decisions on information technology outsourcing (ITO) nationally and globally are identified. The authors overview of the chances (positive effects for companies) arising from the ITO application specific to the national and global outsourcing is provided. The causes of the ITO insufficient spread at the present stage are indicated. A model classifying the factors that influence the attractiveness of the national economies of some countries for ITO is proposed. The attractiveness of the countries of the Eastern European region for ITO is assessed based on the example of a comparative analysis of Russia and Ukraine.
    Keywords: information technology outsourcing; supplier company; client company; chances and risks; factors of attractiveness of regions; Eastern Europe; comparative analysis; Russia; Ukraine.

  • Applying Machine Learning Algorithms To Determine And Predict The Reasons And Models For Employee Turnover   Order a copy of this article
    by Shardul Shankar, Ranjana Vyas, Vijayshri Tewari 
    Abstract: In recent years, organizations have struggled with the turnover of employees, which has become one of the biggest issues that not only have inadvertent consequences to an organizations growth, productivity, and performance; but also has negative implications on the intrinsic cost associated with it. To cater to this problem, one such method is the use of Machine Learning Algorithms. But one of the biggest issues in HR Information System (HRIS) analysis is the presence of noise in data, leading to inaccurate predictions. This paper tries to examine the efficiency of six such Algorithms, to determine the robustness, accuracy in real-time analysis of data, and then use that companys historical data to predict employee turnover for the present year. The dataset was mined from the HRIS database of a global organization in the US and Canada in the span of 10 years to compare these algorithms to examine voluntary turnover, using Python and RStudio analytical tools.
    Keywords: Employee Turnover; Machine Learning; Predictive Algorithms; Classification; Voluntary Turnover.

  • Industry 4.0 projects: a set of new individual competencies   Order a copy of this article
    by Tainá Alves Townsend, Cristiane Drebes Pedron, Rodrigo Menezes De Souza, Roberto Lima Ruas 
    Abstract: The current paper aims to identify the individual competencies of collaborators in industry 4.0 projects. We used the Delphi method with three rounds as a research methodology. Sixty-three experts engaged with industry 4.0 projects, professionals and academics, participated in the study. A set of individual competencies related to industry 4.0 was identified: (1) technical (technical skills, systemic process comprehension, IT security skills, project management tendency, analytical skills, and business knowledge), (2) personal (flexibility, learning motivation, decision-making, ambiguity tolerance, and ability to work under pressure), (3) methodological (creativity, digital mindset, and entrepreneur thinking) and (4) social aspects (communication skills, team-working skills, being committed and proactive, conflict resolution, and leadership skills). The findings led to a list of competencies for project managers and other team members in the industry 4.0' context. This result provides new insights related to personnel development in project-managed environments and educational guidance for the future workforce.
    Keywords: Industry 4.0; Competencies; Project management; Workforce; Skills; Individual Competencies; Digital Transformation; Delphi Method; Competences; Individual Competences.

  • If You Cannot Fly, Then Run: A Model of BIM Implementation Taxonomies and Thresholds   Order a copy of this article
    by Oluseye Olugboyega 
    Abstract: The barriers to BIM adoption are numerous and overwhelming. These barriers must be progressively overcome through a recursive BIM implementation strategy and assessment. The aim of this paper is to identify the key reduction indicators for tracking BIM adoption barriers and establish whether the key reduction indicators will provide a model of BIM implementation taxonomies and thresholds for assessing BIM implementation performance. Meta-Analysis methodology was used to synthesize the diverse findings. These key reduction indicators were categorized into three BIM implementation thresholds: BIM advanced industry, BIM emerging industry, and BIM frontier industry. It was found that BIM implementation taxonomies have different levels of the implementation plan, levels of market effectiveness, and levels of objectives The study concluded that the proposed model will help streamline the needs and advise on the BIM implementation needs of the various construction industry, most especially the developing construction industries.
    Keywords: BIM; BIM implementation; BIM adoption; BIM adaptation; BIM application; BIM utilization; BIM implementation taxonomies; BIM implementation thresholds.

Special Issue on: Intelligent Service Computing in Advanced Technology Management

  • Fine-grained sentiment classification based on semantic extension of target word   Order a copy of this article
    by Xindong You, Pengfei Guan, Xueqiang Lv, Baoan Lv 
    Abstract: Current existing fine-grained sentiment analysis method usually extract the context of the sentence while ignoring the semantic representation of the target words. We extent the target words in comments as the additional input parameters to the deep learning model in this paper. And the influence of the number of extended words on the models performance is also discussed thoroughly during the experimenting process. Main procedures of our proposed fine-grained sentiment classification method can be described as: (1) Firstly, target words are expanded by using the semantic distance of the word embedding, which used as the key information. (2) Bidirectional LSTM neural network is used to extract the semantic information afterwards. (3) Additionally, the attention mechanism is employed to learn the sentiment weight distribution of the target words among the text automatically. Experiments conducted on the SemEval 2014 Task 4 corpus showed that the proposed method outperforms the other LSTM model.
    Keywords: Fine-grained sentiment analysis; Target word extension; Bi-directional LSTM; Attention mechanism.

  • Research on Evaluation of Minimum Backbone Grid of Transmission Network Based on Differentiation Planning   Order a copy of this article
    by Xinyang Deng, Tao Wang, Yihe Wang, Na Zhang, Kai Liu, Fangyuan Yang 
    Abstract: The essence of the differential planning of transmission network is to evaluate the minimum backbone networks of transmission grids, and the evaluation of the backbone network of transmitting minimum network includes the evaluation of important nodes and the evaluation of important lines. In this paper, the important node evaluation of the transmission network takes into account the structural fragile nodes and the important load nodes, and the important line evaluation is based on the line number, which is considered synthetically from the point of view of the structural fragile line and the important load line. The minimum backbone network of transmission network is constructed by the structure backbone network and the important load backbone networks.
    Keywords: Electrical network architecture;The power system;The grid.

  • Research on Control Strategy of Grid-Connected Inverter Based on Three-loop Structure   Order a copy of this article
    by Yan Geng, Jianwei Ji, Bo Hu 
    Abstract: In this paper, a grid-connected inverter system is deeply researched based on the two-stage single-phase PV grid-connected inverter. Full bridge structure is adopted in the backend inverter circuit. In order to realize the balanced flow of power, to improve the system's response speed and to eliminate the influence of the resonance peak of LCL filter, the three loop control strategy is adopted in the inverter system. At the same time, the reason of generation of the dead-time and its influence on the output of the grid-connected inverter are analyzed in detail. And an improved dead-time compensation method is proposed for zero-current clamping phenomenon. The output voltage error of inverter is extended from two to seven in this method, which effectively solves the problems, such as zero-crossing distortion of the grid-connected current, more odd harmonic content, higher distortion rate and lower amplitude of fundamental wave.
    Keywords: Grid-Connected inverter; Dead-time Compensation; PV.

  • An Intelligent Image Denoising Method Using Weighted Multi-scale CB Morphological Filter Algorithm   Order a copy of this article
    by Yongjie Tan, Jie Qin 
    Abstract: In order to improve the accuracy of paper disease recognition in paper making process, a paper image denoising method based on multi-scale contour bougie (CB) element morphological filter is proposed. The small-scale structural elements in CB morphological filtering algorithm have better detail protection ability, and the large-scale structural elements have stronger noise suppression ability. By selecting several structural elements to filter the image, and then fusing the filtered images at different scales, the final denoising image can be obtained. The simulation results on the holes paper disease image with Gauss noise and salt and pepper noise show that the PSNR reaches more than 43dB and 38dB respectively, which proves that this method can suppress the noise in the image and keep the image details well.
    Keywords: image denoising; CB morphological filter; multi-scale structural elements; weighted fusion.

  • Network intrusion detection method based on improved ant colony algorithm combined with cluster analysis in cloud computing environment   Order a copy of this article
    by Xifeng Wang, Xiaoluan Zhang 
    Abstract: Aiming at the low detection accuracy of traditional clustering algorithm in intrusion detection under cloud computing platform, a network intrusion detection method based on improved ant colony algorithm combined with clustering analysis is proposed. In this paper, ant colony optimization clustering algorithm is proposed to improve the current mainstream clustering algorithm. This step mainly designs an ant colony clustering processing module suitable for intrusion detection, aiming at the improvement of the function parameters, objective function and calculation method of clustering center of ant colony algorithm. The purpose of the ant colony clustering module is to distinguish most of the clusters belonging to the same type again by clustering algorithm. Each feature vector is used as the clustering center to process and analyze them, so as to realize the separation of legal and illegal acts of network data as far as possible. Finally, the KDDcup99 data set which is recognized by the current research on intrusion detection algorithm is used to carry out experiments. In the experiment, cluster identification technology is used to identify a small number of anomalous intrusion data. Experiments show that the accuracy of the algorithm can achieve at 94.3% for DoS intrusion types and 94.1% for U2R intrusion types, which is higher than that of the contrast methods. It further proves that the proposed improved algorithm has a good clustering effect.
    Keywords: Network intrusion detection; Ant colony algorithm; Cluster analysis; Genetic algorithm; Abnormal data.

  • An Intelligent Image Detection Method Using Improved Canny Edge Detection Operator   Order a copy of this article
    by Qian Wang, Wenxia Chen, Haiyun Peng 
    Abstract: In order to meet the requirement of edge detection of paper disease image in papermaking process, a paper disease image detection method based on improved Canny operator is proposed. Firstly, according to the principle of Gauss filtering and the method of feature statistical analysis, the filtering function and window are selected adaptively. Then, in the gradient solution, the traditional 2?2 neighborhood is replaced by the 3?2 or 2?3 neighborhood which enhances the weight of the intermediate pixel, and the accuracy of edge detection is improved by enhancing the influence of the intermediate pixel. Finally, the iterative averaging method is used to determine the optimal threshold and reduce the error rate of image edge segmentation. The experimental results show that this method can effectively detect the edges of paper disease area and has good edge continuity.
    Keywords: Intelligent image detection; edge detection; improved Canny operator; Gauss filtering; feature statistical analysis; Adaptive.

Special Issue on: Information Management in the Information Age

  • Research on Integrated Management of Sales and Inventory Information in Circulation Enterprises based on Case-based Learning   Order a copy of this article
    by Ruirong Jing, Huilin Wang, Guohui Gao 
    Abstract: Aiming at the problems of low classification accuracy, low recall rate and low efficiency of comprehensive information management of circulation enterprises, a case-based integrated management method of sales and inventory information of circulation enterprises was proposed.Taking a circulation enterprise in hebei province as an example, this paper introduces the function of integrated management of sales and inventory information.This paper classifies the sales and inventory information of circulation enterprises, obtains the classification results of sales and inventory information by calculating the discriminant matrix, analyzes the risk management of sales and inventory information of circulation enterprises, and expounds the relationship between the risk management of sales and inventory information of circulation enterprises and other fields.The accuracy and recall rate of information classification of this method are good, which can correctly and completely complete the classification of enterprise inventory information.Comprehensive information management efficiency in more than 90%, with higher efficiency of comprehensive management.
    Keywords: Case study; Circulation enterprises; Sales and inventory information; Integrated management;.

  • Research on Efficiency Evaluation of Financial Refinement Management based on DEA   Order a copy of this article
    by Wenwen Lv, Zarina Abdul Salam 
    Abstract: Aiming at the low fitting degree of the traditional financial management performance evaluation method, a dea-based financial refinement management effectiveness evaluation method is proposed. This paper analyzes the overall structure of the financial department, takes the effectiveness evaluation index of financial management at home and abroad as the reference object, and constructs the effectiveness evaluation index system of financial fine management. According to the evaluation index system, CR model and BCC model in DEA method are adopted to evaluate the efficiency of financial delicacy management. Experimental results show that the method has small error, high fitting index and good practical performance.
    Keywords: DEA; Financial refinement management; Efficiency evaluation; Evaluation index system.

  • Mobile Payment Risk Prediction Of Communication Operators Under New Business Model   Order a copy of this article
    by Xiao-ying Shi 
    Abstract: In order to overcome the problems of low precision and high energy consumption existing in traditional methods, this paper studies the risk prediction of mobile payment of communication operators under the new business model. In this paper, the expert evaluation method is used to establish the mobile payment risk prediction index system of communication operators under the new business model. The analytic hierarchy process is used to calculate the weight of the prediction index through the structure of hierarchy, the construction of judgment matrix, the calculation of weight vector, the consistency test and the calculation of combined weight vector. The fuzzy comprehensive evaluation method is used to build the mobile payment risk prediction model. The prediction accuracy of the proposed method is always higher than 97%, the total CPU consumption is 34.64%, and the memory utilization is 12.36%, which has high prediction accuracy and low prediction energy consumption.
    Keywords: New business model; Communication operator; Mobile payment risk; Prediction model.

  • Establishment Of Business Risk Information Value Assessment Model Based On Raroc   Order a copy of this article
    by Nuan Wang 
    Abstract: Aiming at the problem of low precision of current enterprise risk assessment methods, a RAROC based enterprise risk information value assessment model is proposed. The crawler search method with topic search is adopted to collect the business information data, and the extended tree structure is introduced to clean up the collected data. Transformation of basic information data and business value. RAROC is used to process the information with commercial value and realize the value evaluation of commercial risk information. According to the model and KMV model, the risk adjustment coefficient was calculated. Reflect RAROC value evaluation results through statements. The experimental results show that the goodness of fit index, standard fit index and comparison fit index of the model are all close to 1, and the approximate root-mean-square error is less than 0.02, which proves the effectiveness and accuracy of the method.
    Keywords: RAROC; Business Risk; Assessment.

  • Research On Real-Time Acquisition Method Of Logistics Location Information Of Electric Commerce Based On Ranking Threshold   Order a copy of this article
    by M.E.I. MEI 
    Abstract: In order to overcome the problems of high energy consumption, poor real-time performance and low quality in current methods of collecting positioning information of e-commerce logistics, this paper proposes a real-time method of collecting positioning information of e-commerce logistics based on ranking threshold. By adjusting the mechanism of sensor nodes, the deployment of information acquisition nodes is realized. Redundant data in e-commerce logistics positioning information is removed by comparator, and sorting threshold method is introduced. The real-time collection of e-commerce logistics positioning information is completed by classifying and processing e-commerce logistics positioning information with mixed features. The experimental results show that the energy consumption factor of the proposed method is less than 1.8, the information transmission delay is less than 0.2, and the user satisfaction is more than 90%. It proves that the proposed method is more effective and robust.
    Keywords: Sorting Threshold; E-Commerce Logistics Positioning Information; Information Collection; Redundant Data;.

  • Research On Visualization Transmission Method For Business Innovation Strategy Data Based On Structural Characteristics   Order a copy of this article
    by Jing Hu 
    Abstract: In order to overcome the problems of low transfer accuracy and user satisfaction existing in the existing data visualization transfer methods, this paper proposes a data visualization transfer method of business innovation strategy based on structural features. The similarity calculation method of structure feature tree is used to realize the data structure feature processing. The sub trees of all non isomorphic patterns of K nodes are constructed. The number of isomorphic sub trees is calculated in the tree, and the transfer data division is completed. Based on the basic program of business intelligence, the original data of business innovation strategy is processed, converted into various types of visualization structure data, and transmitted to relevant personnel in online form to complete the visualization transmission of business innovation strategy data. The experimental results show that the proposed method is more accurate, up to 99.3%, and users are more satisfied.
    Keywords: Structural characteristics; Business innovation; Strategic data; Visualization transmission.

  • Early Warning Method For Enterprise Financial Informatization Caused By Tax Difference   Order a copy of this article
    by Guojian Lin, Weichuan Chen 
    Abstract: In order to overcome the problem that the traditional method only considers the financial report index when designing the early warning model, and ignores the influence of non-financial data on the early warning model, there is a low accuracy problem. Based on the discrete-time risk model, this paper proposes an early warning method of enterprise financial information caused by tax differences. Starting from the establishment of enterprise financial information early warning system, this paper analyzes the importance of tax indicators to enterprise financial information early warning. By studying the early warning system, we select index data in the model, add tax difference indicators, select multi period panel data, and use discrete-time risk model to build enterprise financial information early warning model. The experimental results show that the accuracy of this method is as high as 99.05%, and there is no multicollinearity among the variables in the model, which is reliable.
    Keywords: Tax differentials; Enterprise finance; Informatization; Early warning; Discrete time risk model;.

  • Research On Digital Management Method Of Market Information Based On Fusion Information   Order a copy of this article
    by Jing Li, Ming Yan 
    Abstract: In order to overcome the problems of low management efficiency and long management execution period of traditional market information management methods, this paper proposes a digital management method of market information based on fusion information. Firstly, the original market information is counted, and the chart information and Literature information in the original market information are digitized. By calculating the similarity of market information, the digital information is clustered and fused. Based on the results of clustering and fusion of digital information, the market information management database is constructed, and the comprehensive digital management of market information is realized from the aspects of confidentiality management, authority management, Literature information management and so on. The experimental results show that the management efficiency of this method is always over 96%, and the management efficiency is the highest; the management execution cycle is between 1.4min-1.9min, and the management cycle is the shortest.
    Keywords: Fusion Information; Market Information; Digital Information; Information Management Methods;rn.

  • Trajectory Information Acquisition Method For Library Borrowing Behavior Based On Rfid Technology   Order a copy of this article
    by Huan Zhou, Enjun Ding 
    Abstract: In order to overcome the low speed of the traditional methods of collecting the track information of library lending behavior, this paper proposes a new method of collecting the track information of library lending behavior based on RFID technology. In this method, access software is used to export the record data of borrowing behavior and classify them according to the types; the original data format is converted into the materialized data, and Apriori algorithm is used to analyze the association and mine the track information of library borrowing behavior; RFID reader is used as the main part, and the track information of library borrowing behavior is collected through the track estimation algorithm. The experimental results show that the information collection rate of this method is between 5.26s-6.39s, and the collection effect of library borrowing behavior track information is better.
    Keywords: RFID technology; Library borrowing behavior; Trajectory information acquisition; Borrowing behavior record data;.

  • Feature Extraction Modeling Of Enterprise Innovation Behavior Data Based On Morphological Gradient   Order a copy of this article
    by Shibiao Mu 
    Abstract: Aiming at the problem of slow speed and low accuracy of traditional feature extraction model for enterprise behavior data, a feature extraction model for enterprise innovation behavior data based on morphological gradient is constructed. The model is divided into two parts: the virtual method is used to integrate the data of enterprise innovation behavior, and the data are synthesized and filtered; the morphological gradient operator is used to extract the features of the integrated data of enterprise innovation behavior. The simulation results show that using the proposed model to extract the characteristics of enterprise innovation behavior data, the extraction process only takes 15.68 min, and the average extraction accuracy can reach 96.68%. This result is much better than the three traditional models and achieves the expected goal.
    Keywords: Morphological gradient; Enterprise innovation behavior; Data characteristics; Feature extraction model.

  • Information Supervisory Model For Financial Risk Prevention And Control Based On Twin-Svm   Order a copy of this article
    by Qiong Kang 
    Abstract: Aiming at the problems of poor effect and low accuracy of traditional financial market risk prevention and control methods, a financial risk prevention and control information monitoring model based on double support vector machine is proposed.The improved support vector machine and asymmetric COvAR data were combined with covariance operation to reduce the actual tail risk overflow.Through financial aggregation and covariance tail data of current characteristic financial system, the spillover effect of financial risk is obtained.According to the extreme value statistical analysis theorem, it is determined that the current financial risk gradually obeys the extreme value.In order to verify the effectiveness of the method, the financial data from 2012 to 2018 provided by a bank were used as experimental samples to conduct simulation experiments.Experimental data show that the proposed method has lower boundary cost and higher market arbitrage, and has a strong market applicability.
    Keywords: Financial risk; Data set; Support vector machine;.

  • Integration Technology Of Logistics Information Resources In Electric Power Enterprises Based On Web Services   Order a copy of this article
    by Zijian Zhang, Yu Liang, Yu Cui, Junyu Liu 
    Abstract: In order to overcome the problems of high data access delay and poor security in current logistics management of electric power enterprises, the integration technology of logistics information resources in electric power enterprises based on Web services is proposed. ID3 algorithm is used to rank the attributes of logistics information resources in power enterprises. Based on Web services, three-dimensional mapping space is constructed by using attributes and management patterns of information resources. The best integration mode is obtained by combining rules, to realize the integration of information sources to resources storage and transmission. The experimental results show that the data access delay of the proposed technology is less than 10 seconds, the security of data integration and the satisfaction of integration results are higher than 95%, which proves that the proposed technology is more reliable and effective.
    Keywords: Web services; Power enterprises; Logistics; Information resource integration; ID3 algorithm.

  • Optimization Decision Model of Enterprise Financial Risk Management Combining Stochastic Demand   Order a copy of this article
    by Dandan Zhao, Lin Li 
    Abstract: The Corporate financial management has certain risks. The influencing factors include the laws of economy, politics, and the market itself. Constructing a suitable enterprise financial risk management model based on the market mechanism can effectively reduce the enterprises financial risks and increase the investment return rate. The random demand is a kind of artificial intelligence optimization decision model with better optimization ability, but sometimes will fall into a local optimal solution. Combining random demand with optimization decision and adding optimization decision random number can make the algorithm jump out of the local optimal solution and get the global optimum so as to improve the accuracy of the algorithm. Then the random demand is used to optimize the enterprise financial risk management model. Experiments show that the random demand, which has better convergence accuracy and convergence speed, can achieve a better optimization effect on the enterprise financial risk management model, reduce the risks, and increase the income.
    Keywords: Optimization Decision Model; Enterprise Financial Risk Management; Optimum; Accuracy of the algorithm.

Special Issue on: Artificial Intelligence and Big data used on Business Management

  • Optimization of Outlier Data Mining Algorithm for Large Dataset Based on Unit   Order a copy of this article
    by Yizhi Li, Xiangming Zhou 
    Abstract: The purpose of this paper is to study and optimize the cell-based outlier data mining algorithm for large data sets, and further improve the profit group data mining algorithm. In this experiment, within the scope of the experiment, first use mathematical statistical analysis to investigate the unit-based large data set outlier data mining algorithm optimization, the data mining proportion of each category of the Internet of Things; and then use the data statistical method to classify statistical analysis and detect unit-based Of outlier data mining optimization algorithms for large data sets, research the outlier data mining speed of the optimized algorithm, study the ability to obtain outliers after optimization algorithm; and use a single variable method to compare and investigate distance-based outlier data mining algorithms and cell-based large data sets Speed comparison of outlier data mining algorithm optimization; Finally, use big data analysis method to fit and analyze the data.
    Keywords: Key words: Outlier Data; Algorithm Optimization; Big Data Set; Intelligent Internet of Things; Mining Speed.

  • Scheduling and Monitoring on Engineering Vehicles Based on IoTs   Order a copy of this article
    by Li Wan 
    Abstract: with the development of information technology, the traditional logistics industry meets a new opportunity in information time. In this paper, we design an intelligent logistics platform based on Internet of Things (IoTs). The locations and dynamic data of vehicles are collected using intelligent equipment on the platform. Moreover, we build a mathematical model based on collected data for a transportation problem, which is solved by Lingo to intend to obtain an intelligent schedule. Our solution of scheduling and monitoring of engineering vehicles based on IoTs can help enterprises reduce operational cost and improve service quality.
    Keywords: Scheduling1;Monitoring2;Engineering3;Vehicles4;IoT5;Intelligent6;Logistics7;logistics8; service9,etc.

  • Precision Advertising and Optimization Strategy Based on Big Data Algorithm   Order a copy of this article
    by Hailan Pan, Shi Yin 
    Abstract: This article first proposes the reference method, the case study method, the data analysis method and the comparison method, to estimate and approximate the quantitative analysis of the placement of high-precision data advertisements, and to clarify the current situation and characteristics of the accuracy of big data. Secondly, the advertising platform discussed in this article is an independent B/S system written in Java to follow J2EE specifications. The entire platform includes a back-end system that maintains advertising materials and advertising, a user behavior collection system, user behavior analysis, and recommendations for advertising based on interest. system. For third-party sites to use this system, they only need to access the Client Js Library, and the corresponding advertisements will be automatically pushed to the front-end page when consumers browse the page.
    Keywords: Big Data Algorithm;Accurate Advertising;Optimization Strategy;Collaborative Filtering Algorithm.

  • Parallel machine scheduling optimization based on improved multi-objective artificial bee colony algorithm   Order a copy of this article
    by Li Jun Yang 
    Abstract: Aiming at the scheduling model of the same kind of machine, considering that low carbon emission is an urgent problem to be solved in the manufacturing industry, a mathematical model containing the maximum completion time and maximum processing energy consumption was established. In order to balance the local development ability and global search ability of artificial bee colony algorithm, and improve the convergence speed of the algorithm, a scheduling optimization method of parallel machine based on improved multi-objective artificial bee colony algorithm was proposed. Firstly, a chaotic image initialization method is proposed to ensure the diversity and excellence of the initial population. Then, the individual threshold is used to dynamically adjust the search radius to improve the search accuracy and convergence speed. Finally, considering the development times of the external archive solution, the evolution is guided by selecting the elite solution reasonably. In order to verify the effectiveness of the algorithm, comparative experiments and performance analysis of the algorithm are carried out on several examples. The results show that the proposed algorithm can solve the scheduling problem of the same kind of machine effectively in practical scenarios.
    Keywords: parallel1;machine2;artificial3;bee4;colony5;scheduling6;optimization7;multi-objective8,etc.

  • Application of multi-channel attention mechanism in text classification of new media   Order a copy of this article
    by Wei-Xian Wang 
    Abstract: Sentiment analysis of new media text has become a research hotspot in recent years. In order to more effectively analyze the emotional polarity of new media text, this paper proposes a text classification algorithm based on multi-channel attention mechanism. First, channels based on bidirectional gating recurrent unit (BiGRU) neural network are used to extract semantic features, while channels based on fully connected neural network are used to extract emotional features. In order to extract the key information better, the attention mechanism is introduced into the two channels respectively, and the bidirectional encoder representation technology based on converter is used to provide the word vectors. Then, the real emotional semantics are embedded into the model through the dynamic adjustment of the word vector by the context. Finally, the semantic features and emotional features of the double channels are fused to obtain the final semantic expression. In the experiment part, NLPCC2014 data set and microblog data captured by crawler are used for comparative experiment. The experimental results show that the proposed multi-channel attention mechanism method can enhance the ability of emotion semantic capture, improve the performance of emotion classification.
    Keywords: new1,media2,sentiment3,analysis4,multi-channel5,attention6,mechanism7,etc.

  • Innovation and Entrepreneurship Orientation and Suggestions for New Engineering Computer Majors under the Background of Artificial Intelligence   Order a copy of this article
    by Hongjun Jia 
    Abstract: This article uses a variety of methods such as literature data method, questionnaire survey method, mathematical statistics, etc. to design an experiment on innovation and entrepreneurship education for new engineering computer under the background of artificial intelligence, to provide directions and suggestions for innovative and entrepreneurial talents in modern society and industry needs. This article has analyzed the current problems in the computer major training program in colleges and universities, and has mastered the degree of understanding, difficulties and needs of computer students on innovation and entrepreneurship. Among the interviewees, 51.63% of students think that starting a business is a good choice, and 23.48% of students are starting a business or have experienced a business. Among the needs of computer professional employability, the frequency of selection of practical ability and innovation ability is as high as 97.59% and 95.58%, which is enough to show the importance of practical ability and innovation ability.
    Keywords: Artificial Intelligence;Computer Science;New Engineering;Innovation and Entrepreneurship.

  • A prediction and analysis model of complex system based on extension neural network-Taking the prediction and analysis of terrorist events in the big data environment as an example   Order a copy of this article
    by Yachun Tang 
    Abstract: Predictive analysis of terrorist incidents often exists problems such as large data volume, large data types, large redundancy, and difficulty in dealing with multiple constraints, making it difficult to obtain effective prediction results for terrorist event prediction. Therefore, the methods of analyzing and predicting terrorist events in big data environment are analyzed, and a big data prediction analysis model for terrorist events based on improved extension neural network is presented. Firstly, a meta-element model for predicting and analyzing terrorist events is established, the preliminary cluster analysis of the terrorist event prediction analysis based on the extension transformation is performed, and a terror event prediction extension principal component analysis model is established; Then, based on the prediction of the extension principal component analysis in the terrorist incident, an improved extension neural network structure is constructed, and the extension neurons based on different extensions are established; Furthermore, the predictive analysis model of the terrorist network extension neural network is formed, and the corresponding model and algorithm implementation steps are given. Finally, the algorithm and the model are illustrated and compared by specific case analysis, which shows the validity and feasibility of the model and algorithm.
    Keywords: Predictive analysis model1; Extension neural network2; Extension theory3; Big data4; Terrorist incidents5,etc.

  • Embedded System Architecture-Computer Embedded Software Defect Prediction Based on Genetic Optimization Algorithm   Order a copy of this article
    by Aiju Wang 
    Abstract: With the rapid development of electronic measurement technology, people have put forward higher requirements for the diversity of oscilloscope functions and abundant peripheral interfaces. This paper aims to use genetic optimization algorithm to detect embedded software defects, provide users with prepared defect information, and improve the efficiency and accuracy of detection. This paper proposes popular algorithms for moving target video detection, three genetic optimization algorithms, selection operator, crossover operator, and mutation operator, and establishes a complete system, deepening a virtual simulation environment for embedded software development development model. In addition, from hardware simulation to the detection of software defects such as memory leaks and uninitialized variables, they are all included in the system and run through the entire process of embedded software development.
    Keywords: Embedded system architecture; genetic optimization algorithm; computer embedded; software defect.

  • O2O Customer Big Data Analysis System Based on Embedded Technology   Order a copy of this article
    by Fan Zhang, Yu Su 
    Abstract: The application of data acquisition systems is extremely common. People use data acquisition systems to obtain many signals that they need. However, for the special group of customers, data analysis is still needed. In order to study the operability of the new embedded technology applied to big data analysis, this article uses big data query method, system construction method and data export method to collect samples, analyze the data analysis collection system, and streamline the algorithm. And then it will create a system that can analyze customer big data. If you want to analyze, you have to collect first. In the introduction of the method of collecting data in the article, first calculate the absolute error of a single measurement. The analysis results of the two gauge blocks of 1.0mm and 1.1mm show that when 4 measurements are taken, the absolute errors of the results are all less than 0.5um.
    Keywords: Embedded Technology; O2O Customers Introduction; Big Data Technology; Data Mining; Analysis System.

  • Research on Application of Optimal Particle Swarm Optimization Algorithm in Logistics Route Improvement   Order a copy of this article
    by Xianyu Wang 
    Abstract: Aiming at the logistics path optimization model, the author converts the logistics path optimization problem into a classical traveling salesman problem in the field of mathematics. The adaptive particle swarm optimization algorithm is used to dispose of the model problem. In the algorithm, each particle has four behavior evolution strategies, and the individual speed and position are updated by selecting the strategy with the highest probability. An adaptive particle swarm optimization algorithm is proposed. The algorithm improves the speed of individual optimization by using probabilistic mutation algorithm of policy behavior, which avoids falling into local optimal solution. For the purpose of demonstrating the effectiveness and performance of the method, comparative experiments are conducted on the open source Oliver30 data set. Experimental results show that the average path length achieved by the proposed method is closer to the optimal value, and the convergence speed is fast.
    Keywords: convergence1;particle2;swarm3;optimization4;adaptive5;multi-strategy6,etc.

  • Artificial Intelligence and Big Data in the Production Process Optimize the Parameters of the Cut Tobacco Making Process   Order a copy of this article
    by Wenlong Jin, Liujing Wang, Chengting Zhang 
    Abstract: This article aims to use big data and artificial intelligence energy systems to optimize the parameters in the cut tobacco making process. This paper designs a production process detection system based on artificial intelligence, and uses a database to store big data. It analyzes the data through the database, and selects an important step in the cut tobacco making process, and optimizes the parameters of threshing and redrying. The speed of beater, hot air temperature and moisture regain temperature in the threshing and redrying process were compared and analyzed. Finally, the leaf emergence rate and stem emergence rate are compared between the tobacco shreds with optimized parameters and the unoptimized shredded tobacco. The results show that the optimized parameters are 550, hot air temperature 90
    Keywords: Artificial Intelligence and Big Data; Cut Tobacco Making Process; Parameter Optimization; Optimization Process.

  • Design and Implementation of Corporate Governance Automated Decision Model based on WEB Data   Order a copy of this article
    by Qiang Ma 
    Abstract: As a global, dynamic interactive and cross platform distributed graphic information system based on the hypertext and HTTP, WEB provides a graphical and easy to access intuitive interface for users to find information, and organizes the information nodes into an interrelated network structure. In corporate governance, information mining and processing is particularly important. WEB data can provide a large amount of high-dimensional structured and unstructured data for corporate decision-makers to make more effective management decisions. Therefore, this paper attempts to build a model to help managers improve their decision-making ability and corporate governance. Through the integration of WEB data, this paper tests the impact of executives ME on perks. The results show that the background characteristics of executives could affect their decision-making, and the model can be established under certain constraints. This paper enriches the application of decision-making model to improve the level of corporate governance.
    Keywords: WEB; Automated Decision; Corporate Governance; Decision Support System; Marketization.

  • Development of Regional Agricultural E-commerce in China Based on CAS   Order a copy of this article
    by Bahao Li 
    Abstract: The paper makes a exploration of the mode of agricultural production and operation. Based on the analysis of the demand of the farmers to the e-commerce system, the intelligent sensor is connected to the Internet of things, attempt to propose the solution of \"Internet plus agricultural business\" is put forward. main regional agricultural products in China are aquatic products. In 2016, the total output of aquatic products was 2.853 million tons, of which the output of pelagic fishery and mariculture were 449000 tons and 167000 tons respectively. The total agricultural output value of crops ranked second, including 152000 tons of grain, 37000 tons of vegetables and 24000 tons of fruits. E-commerce of agricultural products effectively introduces e-commerce into traditional trade of agricultural products and realizes the organic combination of the two. It avoids the shortcomings of the traditional agricultural products trading system.
    Keywords: Intelligent Systems; Regional Agricultural Products; E-commerce Development; Intelligent Sensors.

  • Design and Implementation of Big Data Analysis and Visualization Platform for Smart City   Order a copy of this article
    by Kai Sun, Naidi Liu, Xinghua Sun, Yuxin Zhang 
    Abstract: Through the construction of smart cities, the modernization of urban governance systems and governance capacities can be improved. However, the constructions of smart cities face the challenges of data failure, lack of relevance, information fragmentation, fundamental data without accepting new data and innovative concepts. Business big data are extracted, converted from different departments, and these structured, semi-structured, and non-structured data are extracted and transformed to load in data warehouse by ETL. Through the data sharing and exchange platforms, then use joint databases and element searches to create Multi-department data business views to support specific applications in smart cities. This research realizes the smart city big data visual analysis system. The system architecture includes data access layer, data management layer, data analysis layer and release management layer. The system mainly includes four modules: People's livelihood service, citizen big data, urban operation and big data map. This system helps break data barriers, connect data islands, and digitize many municipal businesses, so as to perform data analysis and data visualization, and provide support for refined governance decision-making. The system realizes the access, integration, transformation, visualization and interactive decision analysis of various data of urban life.
    Keywords: Smart City; Big Data; Urban Governance; Data Visualization.

  • Real-time Prediction Algorithm and Simulation of Sports Results Based on Internet of Things and Machine Learning   Order a copy of this article
    by Yibing Ma, Hongyu Guo, Yuqi Sun, Fang Liu 
    Abstract: In the field of sports prediction, the prediction results must be processed, because many events in large-scale sports events are linked to funds. Through inquiries on the Internet, more and more sports-related data can be obtained. Using these data, people continue to develop intelligent models and prediction systems, optimize and innovate these models and systems, and then more accurately predict the results of the game. This article is mainly based on basketball technical time series statistics, using a three-layer feedforward back-propagation neural network, and adopting a rotation prediction method to predict the most important technical and statistical indicators of the team. According to the teams forecast data, the average field goal percentage is 46.03%, the 3-point field goal percentage is 37.48%, the assists are 12.95, and the backcourt rebounds are 25.4.
    Keywords: Machine Learning; Exercise Results; Real-Time Prediction; Internet of Things.

Special Issue on: LISS 2017 Emerging Trends, Issues and Challenges in Big Data and Its Implementation

  • Evolution of intellectual structure of data mining research based on keywords   Order a copy of this article
    by Yue Huang 
    Abstract: Data mining has made rapid progress in the past decade and detecting intellectual structure of data mining research is of great help to researchers. We retrieved 5380 papers, published in 11 leading journals of data mining defined by Google Scholar, from SCIE under Web of Science and Scopus databases between 2007 and 2016 to carry out bibliometric analysis. As indicated by the analysis on the evolution of keyword frequency, the research focus of data mining has shifted from such topics as association rule mining to large-scale complex networks. Matrices of high-frequency keywords were also built for different time periods, namely 2007 to 2016 for the whole picture during these years, 2007 to 2011 and 2012 to 2016 for two periods. Clustering results show there are four main data mining topics and the attention has been paid more to graph data mining and complex network analysis in the past 5 years.
    Keywords: data mining; intellectual structure; co-word analysis; clustering; evolution analysis.

  • The Effects of Relationship Quality and Knowledge Sharing on Service Innovation Performance: Organizational learning as a mediator   Order a copy of this article
    by Zhaoquan Jian, MOHAMED A.L.I. OSMAN, L.E.I. LI 
    Abstract: Drawing on RBV and service dominant logic and using data collected from 243 companies, this paper aims at examining the interplays between relationship quality, knowledge sharing, organizational learning, and service innovation performance. This empirical research found that knowledge sharing and relationship quality were significantly related to organizational learning, that in turn significantly affected service innovation performance. Moreover, better relationship quality would yield improved knowledge sharing. Furthermore, we propose that organizational learning is a significant mediator through which knowledge sharing influences firm performance, and that relationship quality is also a critical factor that facilitates service innovation.
    Keywords: Relationship Quality; Knowledge Sharing; Organizational Learning; Service Innovation Performance.