International Journal of Information Technology and Management

Includes bibliographical references.

Analysis of the multi-agent's relationship in collaborative innovation network for science and technology SEMs based on evolutionary game theory -- Research on the measuring method and structure mining of organisation conflict -- Electric vehicle range estimation based on the road congestion level classification -- A decision support system for identification of technology innovation risk based on sequential CBR -- The research on the selection of the rice transfer machine -- Dataset replica placement strategy under a response time constraint in the cloud -- Sampling method based on improved C4.5 decision tree and its application in prediction of telecom customer churn -- An improved reversible data hiding scheme based on pixel permutation.

[Article Title: Analysis of the multi-agent's relationship in collaborative innovation network for science and technology SEMs based on evolutionary game theory/ Guangyou Nan, Jinyu Wei and Haiju Hu, p. 1-15] Abstract: The construction of a collaborative innovation network for the science and technology small and middle enterprises (SMEs) is an attempt to effectively combine the advantages of science and technology SMEs. In this paper, the evolutionary game theory is used to establish the three party game model including the government, science and technology SMEs, and college and research institutions. Then, the interaction mechanism among them is analysed. On the basis of analysing each party's cost and benefit under different strategic portfolios of three parties, the stable strategy of the evolutionary game is derived. The research results show that the government can effectively mobilise the enthusiasm of enterprises and the college and research institutions by setting up reasonable subsidies or fines for them, and could also influence and promote the cooperation relations between enterprises and the college and research institutions.;[Article Title: Research on the measuring method and structure mining of organisation conflict/ Lei Liu and Xinan Zhao, p. 16-31] Abstract: Jehn (1995) divides organisation conflict into task conflict and relationship conflict to grasp the degree and structure of organisation conflict, which can provide effective decision-making basis for dealing with conflict. The authors establish measurement model of organisation conflict, give the weight with the methods of distinguishing individual advantage characteristic and use intergroup conflict scale to measure conflict situation. According to the measurement results, there are three subsequent applications: analysing the conflict intensity, analysing the conflict types and finding the common features of high conflict members. The authors choose market service department and property management department of a company in Shenyang. In those departments, the authors apply the proposed method to analyse the organisation conflict and find out the causes for conflict of high conflict group members.;[Article Title: Electric vehicle range estimation based on the road congestion level classification/ Hong Liang, Wenjiao Wang, Yunlei Sun, Min Zhong, Yuan Gao, Xiao Sun and Jianhang Liu, p. 32-46] Abstract: Electric vehicles have been an emerging industry in recent years even though the remaining driving range bothers the drivers. To strengthen the user acceptance and relieve the range anxiety, an efficient and accurate estimation approach of remaining driving range would be a solution. In this paper, a road congestion level classification based on support vector machines is proposed and an electric vehicle power model is implemented based on the real-world dataset collected from LF620 battery vehicles. The experiment includes data pre-processing, best parameters searching, support vector machine model training and remaining driving range calculation. The results show the significant influence of considering the big data analysis results on range estimation.;[Article Title: A decision support system for identification of technology innovation risk based on sequential CBR/ Quan Xiao, p. 47-62] Abstract: To identify risks in the increasingly complex market is an important issue for the development of technology innovation enterprises. But it is contended that there is still a lack of effective methods to support the dynamic characteristics and knowledge reuse of the problem. In front of a variety of risk sources, utilisation of IT is necessary, and we introduce case-based reasoning (CBR) technique to identify new risks from cases in the past. However, extant CBR method has limitations on problems with dynamic characteristics. This paper provides insights into the dynamic nature of technology innovation risk identification, and designs a decision support system for identification of technology innovation risk, which contributes a novel extension of CBR to sequential CBR. In our framework, cases are represented as sequences of risk events, and similarity between cases is measured based on weighted event sequence pattern mining. The effectiveness of this work is finally illustrated with a case.;[Article Title: The research on the selection of the rice transfer machine/ Xin Yang, Zhenxiang Zeng, Jinyu Wei and Xinjiang Cai, p. 63-73] Abstract: This article sets the fuel consumption index and the working efficiency index as the main basis for the rice transfer machine. Through the simulation experiment of different load transfer machine models, it reaches their fuel law in the rice field. Finally it determines the best model by the optimal ratio and the working efficiency, which extremely satisfies the requirement of the short payback period and the long service life. The transfer machine reduces the labour intensity of the future agriculture field, improves the production efficiency and reduces the labour cost. And it also has an important role in improving business efficiency.;[Article Title: Dataset replica placement strategy under a response time constraint in the cloud/ Xiuguo Wu and Wei Su, p. 74-92] Abstract: In cloud computing environment, especially data-intensive systems, large amounts of datasets are stored in distributed data centres, and are often retrieved by users in different regions. To reduce the users' response time, replicating the popular datasets to multiple suitable data centres is an advisable choice, as tasks can access the datasets from a nearby site. Nevertheless, the dataset replicas' suitable storage placement selection is still an important issue that should be solved urgently from the response time constraint view, for the reason that too many replicas are infeasible in practice. In this paper, we first propose a comprehensive dataset response time estimation model, then present a replica placement model based on Steiner tree. After that, an approximate replica placement algorithm under a response time constraint in the cloud is given using Kruskal minimum spanning tree. At last, a practical and reasonable performance evaluation is designed and implemented. Both the theoretical analysis and simulations conducted on general (random) datasets show the efficiency and effectiveness of the proposed strategy in the cloud.;[Article Title: Sampling method based on improved C4.5 decision tree and its application in prediction of telecom customer churn/ Weibin Deng, Linsen Deng, Jin Liu and Jie Qi, p. 93-109] Abstract: Nowadays, customer churn prediction is quite important for telecom operators to reduce churn rate and remain competitive. However, the imbalance between the retained customers and the churners affects the prediction accuracy. For solving this problem, a new sampling method based on improved C4.5 decision tree is proposed. Firstly, an initial weight is set for each sample according to the data scale of each class. Then, the samples' weight is adjusted through several rounds of alternative training by the improved C4.5 decision tree algorithm. Both the gain ratio and the misclassification cost are considered for splitting criterion. Besides, the boundary minority examples and the centre majority examples are found according to their weights. Furthermore, over-sampling is conducted for the boundary minority examples by synthetic minority over-sampling technique (SMOTE) and under-sampling is executed for the majority examples. Experiments on UCI public data and telecom operator data show the efficiency of the new method.;[Article Title: An improved reversible data hiding scheme based on pixel permutation/ Jilin Wang, Xiao Sun and Xiaoqing Feng, p. 110-125] Abstract: Low payload capacity is a flaw in pixel exchange-based reversible data hiding schemes. In order to improve it, this paper proposes a triangular pixel pair structure, which requires fewer pixels than a traditional 2 × 2 pixel block. At the same time, the corresponding embedding conditions are also proposed to screen out those pixel pairs that may reduce image visual quality seriously after data embedding. Embeddable pixel pair is binarised by its feature. And, Huffman coding method is used to create free space for secret data while ensuring reversibility. Eventually, data is embedded into a cover image by switching embeddable pixel pair features.

The experimental results show that the greyscale histogram of the cover image is never modified by the proposed scheme. Consequently, secret data cannot be detected by the statistical steganalysis based on the greyscale histogram. Both payload capacity and imperceptibility get enhanced obviously, and PSNR is at the same level as the schemes that do not provide robustness of the greyscale histogram.