Template-Type: ReDIF-Article 1.0 Author-Name: Guangyou Nan Author-X-Name-First: Guangyou Author-X-Name-Last: Nan Author-Name: Jinyu Wei Author-X-Name-First: Jinyu Author-X-Name-Last: Wei Author-Name: Haiju Hu Author-X-Name-First: Haiju Author-X-Name-Last: Hu Title: Analysis of the multi-agent's relationship in collaborative innovation network for science and technology SEMs based on evolutionary game theory 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. Journal: Int. J. of Information Technology and Management Pages: 1-15 Issue: 1 Volume: 18 Year: 2019 Keywords: collaborative innovation network; government; science and technology SMEs; college and research institution; innovation management; evolutionary game theory. File-URL: http://www.inderscience.com/link.php?id=97881 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijitma:v:18:y:2019:i:1:p:1-15 Template-Type: ReDIF-Article 1.0 Author-Name: Lei Liu Author-X-Name-First: Lei Author-X-Name-Last: Liu Author-Name: Xinan Zhao Author-X-Name-First: Xinan Author-X-Name-Last: Zhao Title: Research on the measuring method and structure mining of organisation conflict 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. Journal: Int. J. of Information Technology and Management Pages: 16-31 Issue: 1 Volume: 18 Year: 2019 Keywords: organisation conflict; structure mining; individual advantage characteristic; clustering analysis. File-URL: http://www.inderscience.com/link.php?id=97882 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijitma:v:18:y:2019:i:1:p:16-31 Template-Type: ReDIF-Article 1.0 Author-Name: Hong Liang Author-X-Name-First: Hong Author-X-Name-Last: Liang Author-Name: Wenjiao Wang Author-X-Name-First: Wenjiao Author-X-Name-Last: Wang Author-Name: Yunlei Sun Author-X-Name-First: Yunlei Author-X-Name-Last: Sun Author-Name: Min Zhong Author-X-Name-First: Min Author-X-Name-Last: Zhong Author-Name: Yuan Gao Author-X-Name-First: Yuan Author-X-Name-Last: Gao Author-Name: Xiao Sun Author-X-Name-First: Xiao Author-X-Name-Last: Sun Author-Name: Jianhang Liu Author-X-Name-First: Jianhang Author-X-Name-Last: Liu Title: Electric vehicle range estimation based on the road congestion level classification 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. Journal: Int. J. of Information Technology and Management Pages: 32-46 Issue: 1 Volume: 18 Year: 2019 Keywords: electric vehicle; driving range estimation; support vector machine; python. File-URL: http://www.inderscience.com/link.php?id=97883 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijitma:v:18:y:2019:i:1:p:32-46 Template-Type: ReDIF-Article 1.0 Author-Name: Quan Xiao Author-X-Name-First: Quan Author-X-Name-Last: Xiao Title: A decision support system for identification of technology innovation risk based on sequential CBR 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. Journal: Int. J. of Information Technology and Management Pages: 47-62 Issue: 1 Volume: 18 Year: 2019 Keywords: risk identification; case-based reasoning; technology innovation; sequential data; decision support system. File-URL: http://www.inderscience.com/link.php?id=97884 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijitma:v:18:y:2019:i:1:p:47-62 Template-Type: ReDIF-Article 1.0 Author-Name: Xin Yang Author-X-Name-First: Xin Author-X-Name-Last: Yang Author-Name: Zhenxiang Zeng Author-X-Name-First: Zhenxiang Author-X-Name-Last: Zeng Author-Name: Jinyu Wei Author-X-Name-First: Jinyu Author-X-Name-Last: Wei Author-Name: Xinjiang Cai Author-X-Name-First: Xinjiang Author-X-Name-Last: Cai Title: The research on the selection of the rice transfer machine 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. Journal: Int. J. of Information Technology and Management Pages: 63-73 Issue: 1 Volume: 18 Year: 2019 Keywords: rice mechanisation; transfer machine; BOM; fuel consumption efficiency ratio. File-URL: http://www.inderscience.com/link.php?id=97885 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijitma:v:18:y:2019:i:1:p:63-73 Template-Type: ReDIF-Article 1.0 Author-Name: Xiuguo Wu Author-X-Name-First: Xiuguo Author-X-Name-Last: Wu Author-Name: Wei Su Author-X-Name-First: Wei Author-X-Name-Last: Su Title: Dataset replica placement strategy under a response time constraint in the cloud 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. Journal: Int. J. of Information Technology and Management Pages: 74-92 Issue: 1 Volume: 18 Year: 2019 Keywords: cloud computing; cloud storage; data; replicas placements; response time constraint; wait access latency; average wait access latency; data transfer time; Kruskal minimum spanning tree; Steiner tree. File-URL: http://www.inderscience.com/link.php?id=97886 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijitma:v:18:y:2019:i:1:p:74-92 Template-Type: ReDIF-Article 1.0 Author-Name: Weibin Deng Author-X-Name-First: Weibin Author-X-Name-Last: Deng Author-Name: Linsen Deng Author-X-Name-First: Linsen Author-X-Name-Last: Deng Author-Name: Jin Liu Author-X-Name-First: Jin Author-X-Name-Last: Liu Author-Name: Jie Qi Author-X-Name-First: Jie Author-X-Name-Last: Qi Title: Sampling method based on improved C4.5 decision tree and its application in prediction of telecom customer churn 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. Journal: Int. J. of Information Technology and Management Pages: 93-109 Issue: 1 Volume: 18 Year: 2019 Keywords: telecom customer churn; imbalanced data; under-sampling; over-sampling; decision tree; data mining. File-URL: http://www.inderscience.com/link.php?id=97887 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijitma:v:18:y:2019:i:1:p:93-109 Template-Type: ReDIF-Article 1.0 Author-Name: Jilin Wang Author-X-Name-First: Jilin Author-X-Name-Last: Wang Author-Name: Xiao Sun Author-X-Name-First: Xiao Author-X-Name-Last: Sun Author-Name: Xiaoqing Feng Author-X-Name-First: Xiaoqing Author-X-Name-Last: Feng Title: An improved reversible data hiding scheme based on pixel permutation 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. Journal: Int. J. of Information Technology and Management Pages: 110-125 Issue: 1 Volume: 18 Year: 2019 Keywords: data hiding; reversibility; pixel pair; Huffman coding; pixel permutation. File-URL: http://www.inderscience.com/link.php?id=97903 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijitma:v:18:y:2019:i:1:p:110-125 Template-Type: ReDIF-Article 1.0 Author-Name: Kaixu Liu Author-X-Name-First: Kaixu Author-X-Name-Last: Liu Author-Name: Gianmario Motta Author-X-Name-First: Gianmario Author-X-Name-Last: Motta Author-Name: Tianyi Ma Author-X-Name-First: Tianyi Author-X-Name-Last: Ma Author-Name: Ke Fan Author-X-Name-First: Ke Author-X-Name-Last: Fan Title: Threefold similarity analysis: a case study on crowdsourcing feeds Abstract: Crowdsourcing is a valuable social sensing for the smarter city. We present a framework of crowdsourcing feeds similarity analysis from a threefold point of view, namely image, text, and geography, which is based on similarity analysis, founded on a sequence that goes from coarse to thinner similarity filters. The main idea is to extract feeds within a specific geographic range, and then to analyse similarity of image colour and text in clustered feed sets. The framework enables to identify feeds that report the same issue, and hence to filter redundant information. Based on proved methods and algorithms, such framework has been implemented in a software application, called CITY FEED, which is used by the Municipality of Pavia. Journal: Int. J. of Information Technology and Management Pages: 327-345 Issue: 2/3 Volume: 18 Year: 2019 Keywords: crowdsourcing; smart city; image similarity analysis; text similarity analysis; clusters; text semantic analysis. File-URL: http://www.inderscience.com/link.php?id=99807 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijitma:v:18:y:2019:i:2/3:p:327-345 Template-Type: ReDIF-Article 1.0 Author-Name: Haijun Zhang Author-X-Name-First: Haijun Author-X-Name-Last: Zhang Author-Name: Jingxuan Li Author-X-Name-First: Jingxuan Author-X-Name-Last: Li Author-Name: Bin Luo Author-X-Name-First: Bin Author-X-Name-Last: Luo Author-Name: Yan Li Author-X-Name-First: Yan Author-X-Name-Last: Li Title: Needle in a haystack: an empirical study on mining tags from Flickr user comments Abstract: In the Web2.0 era, user generated content has become the main source of information of many popular photo-sharing websites such as Flickr. In Flickr, many photos have very few or even no tags, because only the uploader can mark tags for a photo. Meanwhile, the user can deliver his/her comment on the photo, which he/she is browsing. Therefore, it is possible to recommend new tags or enrich the existing tag set based on user comments. The work of this paper contains two phases, i.e., the tag generation, and the ranking algorithm. In the phase of candidate tags generation, two methods are introduced relying on natural language processing (NLP) techniques, namely word-based and phrase-based. In ranking and recommending tags, we proposed an algorithm by jointly modelling the location information of candidate tags, statistical information of candidate tags and semantic similarity between candidate tags. Extensive experimental results demonstrate the effectiveness of our method. Journal: Int. J. of Information Technology and Management Pages: 297-326 Issue: 2/3 Volume: 18 Year: 2019 Keywords: tag recommendation; user comment; Flickr; image annotation. File-URL: http://www.inderscience.com/link.php?id=99808 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijitma:v:18:y:2019:i:2/3:p:297-326 Template-Type: ReDIF-Article 1.0 Author-Name: Xiaolin Du Author-X-Name-First: Xiaolin Author-X-Name-Last: Du Author-Name: Dan Wang Author-X-Name-First: Dan Author-X-Name-Last: Wang Author-Name: Yunming Ye Author-X-Name-First: Yunming Author-X-Name-Last: Ye Author-Name: Yan Li Author-X-Name-First: Yan Author-X-Name-Last: Li Author-Name: Yueping Li Author-X-Name-First: Yueping Author-X-Name-Last: Li Title: SGP: a social network sampling method based on graph partition Abstract: A representative sample of a social network is essential for many internet services that rely on accurate analysis. A good sampling method for social network should be able to generate small sample network with similar structures and distributions as its original network. In this paper, a sampling algorithm based on graph partition, sampling based on graph partition (SGP), is proposed to sample social networks. SGP firstly partitions the original network into several sub-networks, and then samples in each sub-network evenly. This procedure enables SGP to effectively maintain the topological similarity and community structure similarity between the sampled network and its original network. Finally, we evaluate SGP on several well-known datasets. The experimental results show that SGP method outperforms seven state-of-the-art methods. Journal: Int. J. of Information Technology and Management Pages: 227-242 Issue: 2/3 Volume: 18 Year: 2019 Keywords: sampling algorithms; social networks; graph partition; community structure; topology structure. File-URL: http://www.inderscience.com/link.php?id=99809 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijitma:v:18:y:2019:i:2/3:p:227-242 Template-Type: ReDIF-Article 1.0 Author-Name: Xiaoyi Yang Author-X-Name-First: Xiaoyi Author-X-Name-Last: Yang Author-Name: Qian Wu Author-X-Name-First: Qian Author-X-Name-Last: Wu Author-Name: Xinmei Deng Author-X-Name-First: Xinmei Author-X-Name-Last: Deng Title: Study on image feature recognition algorithm and its application in public security management Abstract: Public security is the topic of common concern of the government and the common people. In order to solve the puzzle of image distortion, being complex in algorithm and being difficult to take into account of the overall structure and details of the image in the image recognition algorithm of public security management system, the paper presented a fusion algorithm of texture consistency measure based on bi-orthogonal wavelet transform. By means of the orthogonal wavelet transform, the wavelet transform is used to decompose the source image, and then the low frequency and high frequency wavelet coefficient matrix of the fused image is determined according to a certain proportion and texture measure, thus the fusion image is obtained. The experimental results show that the algorithm can not only distinguish the false edges of the image, but also enrich the details of the image and take into account the overall visual image, so it can better improve the recognition effect of the image in the public security management system. Journal: Int. J. of Information Technology and Management Pages: 284-296 Issue: 2/3 Volume: 18 Year: 2019 Keywords: public security; security management system; public security management; government concern; image distortion; overall structure; details information; orthogonal wavelet transform; wavelet coefficient matrix; texture measure; false edges; enriching details. File-URL: http://www.inderscience.com/link.php?id=99814 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijitma:v:18:y:2019:i:2/3:p:284-296 Template-Type: ReDIF-Article 1.0 Author-Name: Haibo Li Author-X-Name-First: Haibo Author-X-Name-Last: Li Author-Name: Mengxia Liang Author-X-Name-First: Mengxia Author-X-Name-Last: Liang Title: Identifying inter-organisational resource-service sequences based on similarity for collaborative tasks Abstract: To improve the efficiency of a collaborative task, collaboration of resource services in a business process is important. From the business process viewpoint, the resource services should be provided as service flows to business processes. Resource services are selected and used by different organisations. This reduces the efficiency of the collaboration of resource services among different organisations. To solve this problem, a similarity based approach is proposed to identify the resource service sequences in an inter-organisational business process. Manufacturing is used as an example to discuss the problem. First, a modelling method, resource service temporal relationship modelling (RSTM), is presented. In RSTM, the temporal relationship of resource services is described, which is resolved according to the big data of business. Then, based on the RSTM, all resource service sequences are obtained directly. Next, an algorithm of similarity is presented to calculate the isomorphic resource service sequences with inter-organisation consideration. Finally, the proposed approach is tested with a simulation experiment, and the results show that it is very promising. Journal: Int. J. of Information Technology and Management Pages: 156-170 Issue: 2/3 Volume: 18 Year: 2019 Keywords: collaborative task; inter-organisation; resource service sequence; big data. File-URL: http://www.inderscience.com/link.php?id=99815 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijitma:v:18:y:2019:i:2/3:p:156-170 Template-Type: ReDIF-Article 1.0 Author-Name: Fulin Nan Author-X-Name-First: Fulin Author-X-Name-Last: Nan Author-Name: Hui Tian Author-X-Name-First: Hui Author-X-Name-Last: Tian Author-Name: Tian Wang Author-X-Name-First: Tian Author-X-Name-Last: Wang Author-Name: Yiqiao Cai Author-X-Name-First: Yiqiao Author-X-Name-Last: Cai Author-Name: Yonghong Chen Author-X-Name-First: Yonghong Author-X-Name-Last: Chen Title: A collusion-resistant public auditing scheme for shared cloud data Abstract: With the increasing popularity of collaboration in the cloud, shared data have become a new branch of cloud data, which also brings new challenges for remote integrity auditing. To address the concerns, this paper presents a novel public auditing scheme for shared data. Differing from the existing works, we introduce a new entity called local authentication server to finalise the block tags of shared data, which can thereby prevent the collusion attack effectively. Moreover, thanks to the new mechanism of tag generation, our scheme relieves the user manager of the burden of management and largely reduces the computation and communication overheads. In addition, we extend the scheme to support batch auditing by employing the aggregate BLS signature technique. The theoretical proof and experimental evaluation demonstrate that the proposed scheme can provide excellent security and outperform the previous ones in computational costs in the user revocation phase. Journal: Int. J. of Information Technology and Management Pages: 195-212 Issue: 2/3 Volume: 18 Year: 2019 Keywords: cloud storage; shared data; public auditing; collusion attack; user revocation; local authentication server. File-URL: http://www.inderscience.com/link.php?id=99816 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijitma:v:18:y:2019:i:2/3:p:195-212 Template-Type: ReDIF-Article 1.0 Author-Name: Jiacheng Jiang Author-X-Name-First: Jiacheng Author-X-Name-Last: Jiang Author-Name: Yingbo Wu Author-X-Name-First: Yingbo Author-X-Name-Last: Wu Author-Name: De Xiang Author-X-Name-First: De Author-X-Name-Last: Xiang Author-Name: Keqin Yu Author-X-Name-First: Keqin Author-X-Name-Last: Yu Author-Name: Tianhui Wang Author-X-Name-First: Tianhui Author-X-Name-Last: Wang Title: Cost and green aware workload migration on geo-distributed datacentres Abstract: With the development of the inter-datacentre (inter-DC) virtual machine migration technology, it is possible to reduce the cost of electricity and the environment by using the workload migration across the datacentre. This paper presents a solution - cost and green aware workload migration algorithm (CGWM) that utilising the difference of electricity prices, CO2 emissions and water consumption between different geographical locations to manage the workload. CGWM attempts to reduce electricity costs, carbon emissions and water consumption. When the three optimisation goals conflict, CGWM first to ensure the reduction of electricity cost, and then by adjusting the weight factor to make CGWM more biased to optimise the carbon dioxide or water consumption. Simulation results show CGWM can reduce electricity costs while controlling carbon dioxide emissions and water consumption. Journal: Int. J. of Information Technology and Management Pages: 213-226 Issue: 2/3 Volume: 18 Year: 2019 Keywords: cloud computing; VM migration; geographical datacentres; green datacentres; carbon dioxide emissions; greedy algorithm. File-URL: http://www.inderscience.com/link.php?id=99817 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijitma:v:18:y:2019:i:2/3:p:213-226 Template-Type: ReDIF-Article 1.0 Author-Name: Shiqi Wen Author-X-Name-First: Shiqi Author-X-Name-Last: Wen Author-Name: Cheng Wang Author-X-Name-First: Cheng Author-X-Name-Last: Wang Author-Name: Haibo Li Author-X-Name-First: Haibo Author-X-Name-Last: Li Author-Name: Guoqi Zheng Author-X-Name-First: Guoqi Author-X-Name-Last: Zheng Title: Parallel naïve Bayes regression model-based collaborative filtering recommendation algorithm and its realisation on Hadoop for big data Abstract: Collaborative filtering (CF) algorithms are widely used in a lot of recommender systems. However, space-time overhead and high computational complexity hinder their use in large-scale systems. This paper implements the parallel naïve Bayes regression model based collaborative filtering recommendation algorithm on Hadoop computing platform to scalability problem of CF. Firstly, this paper analysis the inherent parallelism of the naive Bayesian regression model and constructs the theoretical model of naive Bayesian parallelisation. Secondly, the parallel naïve Bayes regression model-based collaborative filtering recommendation algorithm is realised on Hadoop platform with distributed Hadoop distributed file system (HDFS) and MapReduce as the transparent distributed infrastructure. And its temporal-spatial overhead, speedup is discussed. Finally, applying parallel the naïve Bayes regression model-based collaborative filtering recommendation algorithm to a large dataset. The experiment results on Netflix dataset show that this method has high scalability and less space-time overhead, which is suitable for real-time recommendation on large dataset. Journal: Int. J. of Information Technology and Management Pages: 129-142 Issue: 2/3 Volume: 18 Year: 2019 Keywords: parallel naïve Bayes regression model; model-based collaborative filtering; big data; Hadoop; MapReduce. File-URL: http://www.inderscience.com/link.php?id=99818 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijitma:v:18:y:2019:i:2/3:p:129-142 Template-Type: ReDIF-Article 1.0 Author-Name: Yihao Zhang Author-X-Name-First: Yihao Author-X-Name-Last: Zhang Author-Name: Junhao Wen Author-X-Name-First: Junhao Author-X-Name-Last: Wen Author-Name: Zhi Liu Author-X-Name-First: Zhi Author-X-Name-Last: Liu Author-Name: Changpeng Zhu Author-X-Name-First: Changpeng Author-X-Name-Last: Zhu Title: A semi-supervised approach of graph-based with local and global consistency Abstract: An approach of graph-based semi-supervised learning is proposed that consider the local and global consistency of data. Like most graph-based semi-supervised learning, the algorithm mainly focused on two key issues: the graph construction and the manifold regularisation framework. In the graph construction, these labelled and unlabelled data are represented as vertices encoding edges weights with the similarity of instances, which means that not only the local geometry information but also the class information are utilised. In manifold regularisation framework, the cost function contains two terms of smoothness constraint and fitting constraint, it is sufficiently smooth with respect to the intrinsic structure revealed by known labelled and unlabelled instances. Specifically, we design the algorithm that uses the normalised Laplacian eigenvectors, which ensure the cost function can converge to closed form expression and then, we provide the convergence proof. Experimental results on various datasets and entity relationship classification show that the proposed algorithm mostly outperforms the popular classification algorithm. Journal: Int. J. of Information Technology and Management Pages: 243-255 Issue: 2/3 Volume: 18 Year: 2019 Keywords: semi-supervised learning; graph construction; data consistency; manifold regularisation. File-URL: http://www.inderscience.com/link.php?id=99819 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijitma:v:18:y:2019:i:2/3:p:243-255 Template-Type: ReDIF-Article 1.0 Author-Name: Yao Wang Author-X-Name-First: Yao Author-X-Name-Last: Wang Author-Name: Dianhui Chu Author-X-Name-First: Dianhui Author-X-Name-Last: Chu Author-Name: Mingqiang Song Author-X-Name-First: Mingqiang Author-X-Name-Last: Song Title: Diabetes index evaluation framework based on data mining technology: a genetic factor involved solution for predicting diabetes risk Abstract: With the development of data mining, scientists began to apply information technology to solve medical problems. In this context, the idea of auxiliary medical service emerged. The purpose of this study is to propose a new framework predicting the probability of suffering from diabetes via diabetes index (DI), which is defined as a score to assess the diabetes-related risk of the participant. DI is calculated based on a diabetic clinical dataset and the SVM model is applied as well. Particularly, genetic feature is innovatively introduced as an important factor in view of the fact that people with family history are more vulnerable to diabetes. The framework is applied to implement a diabetes auxiliary evaluation system. After a set of comprehensive experiments, the assessment result is supposed to identify risk of the disease at an early stage, which contributes to a deeper understanding of one's own health conditions. Journal: Int. J. of Information Technology and Management Pages: 256-267 Issue: 2/3 Volume: 18 Year: 2019 Keywords: data mining; diabetes evaluation framework; genetic feature; SVM; diabetes auxiliary evaluation system; diabetes index. File-URL: http://www.inderscience.com/link.php?id=99820 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijitma:v:18:y:2019:i:2/3:p:256-267 Template-Type: ReDIF-Article 1.0 Author-Name: Shalini Goel Author-X-Name-First: Shalini Author-X-Name-Last: Goel Author-Name: Vipul Garg Author-X-Name-First: Vipul Author-X-Name-Last: Garg Author-Name: Deepak Garg Author-X-Name-First: Deepak Author-X-Name-Last: Garg Author-Name: Manshiv Kathait Author-X-Name-First: Manshiv Author-X-Name-Last: Kathait Title: Voice transmission through WiFi Abstract: In an era of digital communication, one of the key requirements is of free connectivity. In addition, one of the most anticipated issues is poor connectivity in most of the areas and it is not possible to install infrastructure-based networks due to cost-effectiveness or non-vulnerability terrains (cellular blind spots like a desert, battlefields, forests, etc.). In the light of the above-mentioned discussion, an android application has been developed in the ongoing project for Android-based wireless devices named WiFi_Intercom. WiFi_Intercom uses classes which allow its user to connect with other connected users through WiFi wireless standard using point to point (P2P) or WLAN connection as a means of communication between Android-based wireless devices. The application will also allow the mobile user to search and call other connected users within the WiFi range through the application. Each mobile device connects to a WLAN router and identifies itself in the routing table. Journal: Int. J. of Information Technology and Management Pages: 268-283 Issue: 2/3 Volume: 18 Year: 2019 Keywords: point to point; P2P; protocols; wireless standards; connectivity; WLAN; wireless infrastructure; mobile devices. File-URL: http://www.inderscience.com/link.php?id=99821 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijitma:v:18:y:2019:i:2/3:p:268-283 Template-Type: ReDIF-Article 1.0 Author-Name: Roney Thomas Author-X-Name-First: Roney Author-X-Name-Last: Thomas Author-Name: Priya Govindaraj Author-X-Name-First: Priya Author-X-Name-Last: Govindaraj Author-Name: Jaisankar Natarajan Author-X-Name-First: Jaisankar Author-X-Name-Last: Natarajan Title: A fuzzy inference-based trust model estimation system for service selection in cloud computing Abstract: Cloud computing assures to be the fundamental changeover in the evolution of the computing world. The cloud computing helps the users to have no Capex, which is making a lot of businesses and individuals to it. Many services are provided by the cloud, for users to meet their application's functional as well as non-functional. Due to the vast number of available services, ambiguous requirements, security and trust measures and efficiency provided by different cloud providers, it is often difficult for the users to select the cloud services. This paper proposes a system that assesses trust of cloud services by providers using a fuzzy-based inference system for selecting the services dynamically. Journal: Int. J. of Information Technology and Management Pages: 143-155 Issue: 2/3 Volume: 18 Year: 2019 Keywords: cloud computing; trust; service selection; fuzzy inference; FCL; jFuzzyLogic. File-URL: http://www.inderscience.com/link.php?id=99822 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijitma:v:18:y:2019:i:2/3:p:143-155 Template-Type: ReDIF-Article 1.0 Author-Name: Xiaoyi Deng Author-X-Name-First: Xiaoyi Author-X-Name-Last: Deng Author-Name: Feifei Huangfu Author-X-Name-First: Feifei Author-X-Name-Last: Huangfu Title: Facilitating social recommendation with collaborative topic regression and social trust Abstract: Social networks make users more dependent on online information regarding purchasing decision making. Networks which make users more dependent on online information regarding purchasing decision making. Therefore, social network information can be utilised to improve the performance of recommender systems that aim to mitigate information overload and provide users with the most attractive and relevant items. To improve recommender systems by incorporating social network information, this paper exploits multi-sourced information to predict ratings and make recommendations. An improved collaborative topic regression model that incorporates social trust, in which users' decisions regarding ratings are affected by their preferences and the favours of trusted friends, is proposed. In addition, an approach to calculating the maximum a posteriori estimates is proposed to learn model parameters. Empirical experiments using two real-world datasets are conducted to evaluate the performance of our model. The results indicate that the proposed model has better accuracy and robustness than other methods for making recommendations. Journal: Int. J. of Information Technology and Management Pages: 182-194 Issue: 2/3 Volume: 18 Year: 2019 Keywords: collaborative topic regression; matrix factorisation; social trust; trust propagation; recommender system. File-URL: http://www.inderscience.com/link.php?id=99826 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijitma:v:18:y:2019:i:2/3:p:182-194 Template-Type: ReDIF-Article 1.0 Author-Name: Yuanyuan Xu Author-X-Name-First: Yuanyuan Author-X-Name-Last: Xu Author-Name: Tianhe Yao Author-X-Name-First: Tianhe Author-X-Name-Last: Yao Author-Name: Genke Yang Author-X-Name-First: Genke Author-X-Name-Last: Yang Title: An EMD-SVM model with error compensation for short-term wind speed forecasting Abstract: In this paper, we propose an empirical mode decomposition-support vector machine (EMD-SVM) model with error compensation in order to reduce the cumulative error and improve the prediction accuracy of short-term wind speed forecasting. The essential idea behind the proposed approach is that the error of the current prediction is highly correlated with the previous prediction errors, and the forecasted speed should be compensated in terms of the errors incurred from previous predictions. Specifically, we first predict the historical data by the EMD-SVM model so as to obtain the corresponding prediction errors. Then, we establish the error compensation mechanism. Finally, we combine the EMD-SVM model with error compensation to obtain the final prediction results. The error compensation strategy is validated by a series of actual 10 min wind speed data collected from New Zealand. Experimental results demonstrate that the proposed EMD-SVM model with error compensation can be successfully applied to short-term wind speed forecasting, and it has higher accuracy and stronger robustness compared with the method without error compensation. Journal: Int. J. of Information Technology and Management Pages: 171-181 Issue: 2/3 Volume: 18 Year: 2019 Keywords: wind speed forecasting; EMD-SVM model; wind speed prediction; error compensation. File-URL: http://www.inderscience.com/link.php?id=99827 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijitma:v:18:y:2019:i:2/3:p:171-181 Template-Type: ReDIF-Article 1.0 Author-Name: Mark I. Hwang Author-X-Name-First: Mark I. Author-X-Name-Last: Hwang Title: Top management support and information systems implementation success: a meta-analytical replication Abstract: Factors that contribute to the success or failure of information systems implementation have received extensive attention in the literature. Top management support is considered one of the most, if not the most, critical factors for implementation success. However, the positive effect of top management support is not always borne out in empirical data, prompting a quest for moderator variables. A classic meta-analysis shows that the effect of top management support on implementation success is moderated by task interdependence, a claim refuted in several more recent meta-analyses. Drawing from the lessons learned from these meta-analyses, the current research reanalysed the top management support literature with a larger sample while controlling for the effect of common method variance and systems success measurement issues. The results reaffirm the significant and substantial effect of top management support on systems success. At the same time, evidence also supports the moderating role of task interdependence, common method variance, and how systems success is measured. Implications for systems implementation are discussed. Journal: Int. J. of Information Technology and Management Pages: 347-361 Issue: 4 Volume: 18 Year: 2019 Keywords: top management support; task interdependence; IS implementation; IT project; meta-analysis; common method variance; IS success. File-URL: http://www.inderscience.com/link.php?id=103050 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijitma:v:18:y:2019:i:4:p:347-361 Template-Type: ReDIF-Article 1.0 Author-Name: Rupak Rauniar Author-X-Name-First: Rupak Author-X-Name-Last: Rauniar Author-Name: Greg Rawski Author-X-Name-First: Greg Author-X-Name-Last: Rawski Author-Name: Ronald J. Salazar Author-X-Name-First: Ronald J. Author-X-Name-Last: Salazar Author-Name: Donald Hudson Author-X-Name-First: Donald Author-X-Name-Last: Hudson Title: User engagement in social media - empirical results from Facebook Abstract: Theory building and better understanding of user engagement behaviour are fundamental to developing future approaches and effective organisational deployment of social media technologies. Based on the theory of reasoned action (TRA), predictors of intention to engage on social media sites were empirically examined with 389 users of Facebook - the most popular online social media site. Our results suggest that perceived value, social presence, interactivity, and trustworthiness are positively related to the user's attitude towards social media. The research model shows promise for use by managers and organisations to predict and understand the usage of social media in a target population. Journal: Int. J. of Information Technology and Management Pages: 362-388 Issue: 4 Volume: 18 Year: 2019 Keywords: theory of reasoned action; social media; Facebook. File-URL: http://www.inderscience.com/link.php?id=103051 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijitma:v:18:y:2019:i:4:p:362-388 Template-Type: ReDIF-Article 1.0 Author-Name: Pablo Ortiz Bochard Author-X-Name-First: Pablo Ortiz Author-X-Name-Last: Bochard Author-Name: Thomas Schwarz Author-X-Name-First: Thomas Author-X-Name-Last: Schwarz Title: Evaluation of mean and variance approximations in three point estimation of task completion times using the beta and the Kumaraswamy distribution Abstract: Estimation of task and project completion times within IT projects remains one of the most error-prone, but also most critical duties of an IT project manager. Various three-point methods of PERT have been evaluated by assuming that the true distribution is a beta-distribution. We evaluate PERT methods by comparing additionally with the Kumaraswamy distribution, which has an equal claim to be the true a-priori distribution for project completion times. We use skew and kurtosis in order to define test sets instead of simply choosing a range of shape parameters. We validate various approximations proposed in the literature and show that valid approximations are possible. Journal: Int. J. of Information Technology and Management Pages: 389-406 Issue: 4 Volume: 18 Year: 2019 Keywords: project management; expert judgement; mean and variance approximations; PERT; three-point estimations; task completion times; beta distribution; Kumaraswamy distribution. File-URL: http://www.inderscience.com/link.php?id=103053 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijitma:v:18:y:2019:i:4:p:389-406 Template-Type: ReDIF-Article 1.0 Author-Name: Xiao Peng Author-X-Name-First: Xiao Author-X-Name-Last: Peng Title: CPPM: a lightweight performance prediction middleware for cloud platforms Abstract: As more and more commercial clouds have been applied in various areas, how to evaluate the performance of a cloud platform has become an important issue that needs to be addressed. Furthermore, an effective performance prediction mechanism is of significant value for improving the current cloud services, such as resource allocation and task scheduling. In the paper, we present the design and prototype implementation of a performance prediction system, namely <i>cloud performance prediction middleware</i> (CPPM), which is aiming at providing a set of lightweight and flexible services on existing cloud infrastructure so as to allow cloud providers monitoring, estimating and predicting the runtime performance from various aspects. The CPPM enables cloud providers to make more efficient and fine-grained resource management and scheduling policies based on their short-term workload prediction mechanism; also it provides an application-level performance prediction service which uses skeleton approach to capture execution characteristics of the running applications so as to predict their actual runtime performance and efficiency. Extensive experiments are conducted to examine the effectiveness and efficiency of the CPPM. Journal: Int. J. of Information Technology and Management Pages: 419-434 Issue: 4 Volume: 18 Year: 2019 Keywords: cloud computing; performance evaluation; workload; quality of service. File-URL: http://www.inderscience.com/link.php?id=103055 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijitma:v:18:y:2019:i:4:p:419-434 Template-Type: ReDIF-Article 1.0 Author-Name: Aidas Vasilis Vasiliauskas Author-X-Name-First: Aidas Vasilis Author-X-Name-Last: Vasiliauskas Author-Name: Virgilija Vasilienė-Vasiliauskienė Author-X-Name-First: Virgilija Author-X-Name-Last: Vasilienė-Vasiliauskienė Author-Name: Ieva Meidutė-Kavaliauskienė Author-X-Name-First: Ieva Author-X-Name-Last: Meidutė-Kavaliauskienė Title: Impact of communication on the collaboration between 3PL service providers and their clients. Case of Lithuania Abstract: Production enterprises constantly are trying to add more value to their products and secure their competitive advantage. One of the possible ways in achieving this goal is to get rid of the uncommon activities to intermediaries, which take control over the process of distribution of goods. However, due to intense change on the market, intermediaries responsible for provision of third-party logistics (3PL) services, sometimes fall short to adapt to shifted manufacturer's needs. Because of the insufficient exchange of information, 3PL service providers start to render inadequate services and are not able to assure efficiency of manufacturer's logistics system. This article discusses importance of exchange of information between production enterprises and their logistics intermediaries based on the results of study on the situation of communication problems between 3PL service providers and their clients in Lithuania. Journal: Int. J. of Information Technology and Management Pages: 407-418 Issue: 4 Volume: 18 Year: 2019 Keywords: collaboration; exchange of information; 3PL services; logistics intermediaries; communication; Lithuania. File-URL: http://www.inderscience.com/link.php?id=103064 File-Format: text/html File-Restriction: Access to full text is restricted to subscribers. Handle: RePEc:ids:ijitma:v:18:y:2019:i:4:p:407-418