Search Article (Advanced Search)

Search for Article,Author or ...

Current Issue

No 19
Vol. 5 No. 3
Summer 2017
|

Most Visited


Last Published Articles

Prediction of the collaboration of two authors by their research interests is one of the issues to enhance group researches. One of the main topics in the analysis of social networks is link prediction. One type of social networks as co-authors social network is one of the highly applied datasets. If we denote a social network by a graph, link prediction means the prediction of the edges between the nodes of network in future. The output of link prediction algorithms is used in different fields as recommender systems. There are a few studies on link prediction using the content issued by nodes to predict the link. In this study, a new link prediction algorithm is developed based on the interest of people. By extracting the working fields of the authors via the analysis of published papers by them, this algorithm predicts their ties in future. The results of tests on SID dataset as co-author dataset show that the presented algorithm outperforms all the structure-based link prediction algorithms. Finally, the reasons of efficiency of algorithm are analyzed and presented.
hosna solaimannezhad - omid fatemi
DOI : 0
Keywords : Link prediction ، Social networks ، Content-based ، Interest
In today's competitive world, the competition is not between companies, rather than it is between their supply chains. Therefore, supply chain plays an important role in companies' success in competition with other companies and their competitors and it is very important for companies to find ways to increase supply chain performance. The purpose of present study was to create an alignment and coordination structure between the strategies of information systems and supply chain strategies in order to improve the performance of supply chain. Two structures have been specially investigated. In the first structure, the alignment between strategy of efficient information systems (supporting interagency effectiveness and inter-organizational effectiveness) and pure strategy (based on cost reduction and a focus on improving processes) has been investigated. In the other structure, alignment between flexible Information System Strategy (empower companies to achieve rapid market and strategic decision support) and the agile strategies (effective presence in the competitive market and the ability to cost-effective rapid response to unpredictable changes in the market) has been investigated. In the study, it has been showed how efficient information systems (flexible) lead to improvement and enhancement of the relationship between pure supply chain strategy (agile) and supply chain performance. Finally it has been showed how supply chain improvement leads to improvement of company performance.
abbas zareian - Iraj Mahdavi - Hamed Fazlollahtabar
DOI : 0
Keywords : Functional informational systems ، flexible informational systems ، supply chain performance
In today's competitive environment, customers are the most important asset to any company. Therefore companies should understand what the retention and value drivers are for each customer. An approach that can help consider customers’ different value dimensions is the value network. This paper aims to introduce a new approach using data mining techniques for mapping and analysing customers’ value network. Besides, this approach is applied in a real case study. This research contributes to develop and implement a methodology to identify and define network entities of a value network in the context of B2B relationships. To conduct this work, we use a combination of methods and techniques designed to analyse customer data-sets (e.g. RFM and customer migration) and to analyse value network. As a result, this paper develops a new strategic network view of customers and discusses how a company can add value to its customers. The proposed approach provides an opportunity for marketing managers to gain a deep understanding of their business customers, the characteristics and structure of their customers’ value network. This paper is the first contribution of its kind to focus exclusively on large data-set analytics to analyse value network. This new approach indicates that future research of value network can further gain the data mining tools.
forough farazzmanesh - Monireh Hosseini
DOI : 0
Keywords : Business-to-business Marketing, ، Business Customers’ Value Network, ، Market Segmentation, ، Data Mining, ، Telecommunication Industry, ، Value Network Analysis
Nowadays, with the advent of social networks, a big change has occurred in the structure of web-based services. Online community(OC) enable their users to access different type of Information, through the internet based structure anywhere any time. OC services are among the strategies used for production and repost of information by users interested in a specific area. In this respect, users become members in a particular domain at will and begin posting. Considering the networking structure, one of the major challenges these groups face is the lack of reposting behavior. Most users of these systems take up a lurking position toward the posts in the forum. One of the proposed ways to increase information reposts is the selection and display of influential posts for each individual. Influential posts are so selected as to be more likely reposted by users based on each user's interests, knowledge and characteristics. The present article intends to introduce a new method for selecting k influential posts to ensure increased repost of information. In terms of participation in OCs, users are divided into two groups of posters and lurkers. Some solutions are proposed to encourage lurking users to participate in reposting the contents. Based on actual data from Twitter and actual blogs with respect to reposts, the assessments indicate the effectiveness of the proposed method.
Omid R. B. Speily
DOI : 0
Keywords : Information Propagation ، Post similarity ، Lurker ، Online Community
This paper will be discussed about the relay channels polarization in order to achieve more capacity region and will be shown that if the inputs of two different relay channels followed the Arikans' polarization structure, then one can categorized these channels to good channel and bad channel. Encoding and decoding complexity for these codes are like to original polar code, O (N.log⁡〖N)〗, and the error probability for them is O (〖2^(-(N) )〗^β ). As, a new scheme for choosing good indices for sending the information in polarized relay channel is presented. The relay channel, introduced by Van der Meulen in [1], is a communication channel and it has a sender and a receiver that assisted in communication by another way, which is a relay node. A memoryless relay channel is specified by probability distribution W(Y_r,Y|〖X,X〗_r ), where X is the transmitted symbol by the source, X_r is the transmitted symbol by the relay, Y_r is the received symbol by the relay and Y is the received symbol by the destination according to figure (1). One can assume that the message M is uniformly distributed over the message set and the average probability of error is defined as P_e^((n))=Pr{M ̂≠M}, where M ̂ is the estimation of decoder. Rate R is said to be achievable if there exist a sequence of 〖(2〗^NR,N) codes, N is the length of the code, such that 〖lim〗_(N→∞) P_e^((n))=0.
Hassan Tavakoli - saeid Pakravan
DOI : 0
Keywords : Relay channel ، Polar code ، Channel polarization ، Capacity ، Relay channel polarization ، Good index of relay channel
Today, increased competition between organizations has led them to seek a better understanding of customer behavior through innovative ways of storing and analyzing their information. Moreover, the emergence of new computing technologies has brought about major changes in the ability of organizations to collect, store and analyze macro-data. Therefore, over thousands of data can be stored for each customer. Hence, customer satisfaction is one of the most important organizational goals. Since all customers do not represent the same profitability to an organization, understanding and identifying the valuable customers has become the most important organizational challenge. Thus, understanding customers’ behavioral variables and categorizing customers based on these characteristics could provide better insight that will help business owners and industries to adopt appropriate marketing strategies such as up-selling and cross-selling. Since the variety of products is one of the main parameters of assessing customer behavior, studying this factor in the field of business-to-business (B2B) communication represents a vital new approach. Hence, this study aims to cluster customers based on a developed RFM model, namely RFMV, by adding a variable of variety of products (V). Therefore, CRISP-DM and K-mean algorithm was used for clustering. The results of the study indicated that the variable V, variety of products, is effective in calculating customers’ value. Moreover, the results indicated the better customers clustering and valuation by using the RFMV model. As a whole, the results of modeling indicate that the variety of products along with other behavioral variables provide more accurate clustering than RFM model.
Saman Qadaki Moghaddam - Neda Abdolvand - Saeedeh Rajaee Harandi
DOI : 0
Keywords : Clustering ، Data Mining ، Customer Relationship Management ، Product Variety ، RFM Model ،
Effective low-level visual features are crucial factors for the semantic concept detection in images. In this paper, new static features (namely, right singular feature vector, left singular feature vector, and also singular value feature vector) are proposed. These features are derived by applying singular value decomposition (SVD) "directly" to the "raw" images. The proposed SVD features are different from features which are obtained from the principal component analysis (PCA) or the latent semantic analysis (LSA). The advantage of the proposed SVD features is that in which edge, color and texture information is integrated simultaneously and this information is sorted based on their importance for concept detection. Feature extraction is performed in a multi-granularity partitioning manner. Since SVD features have the high dimensionality, classification is carried out with the K-nearest neighbor (K-NN) algorithm which utilizes a new distance function, namely, multiplicative distance. This distance is "stable" in the high-dimensional space. Classification is carried out for each grid partition of each granularity separately (in contrast to the existing systems in which classification is performed just for the whole image, not for each partition). Therefore, if some partitions do not contain the target concept, the results of classifications on these partitions do not affect the results of classifications on partitions containing that concept. This leads to the performance improvement. Experimental results on PASCAL VOC and TRECVID datasets show the effectiveness of the proposed SVD features and multi-granularity partitioning and classification method.
Kamran Farajzadeh - Esmail Zarezadeh - Jafar Mansouri
DOI : 0
Keywords : High-dimensional data ، multi-granularity partitioning and classification ، multiplicative distance ، semantic concept detection ، static visual features ، SVD

About Journal

Affiliated to :ICT Research Institute of ACECR
Manager in Charge :Habibollah Asghari
Editor in Chief :Masood Shafiei
Editorial Board :
Abdolali Abdipoor
Mahmoud Naghibzadeh
Zabih Ghasemlooy
Mahmoud Moghavemi
Aliakbar Jalali
Ramazan Ali Sadeghzadeh
Hamidreza Sadegh Mohammadi
Saeed Ghazimaghrebi
Ahmad Khademzadeh
Shaban Elahi
Abbasali Lotfi
Alireza Montazemi
Ali Mohammad Djafari
Rahim Saeidi
ISSN :2322-1437
eISSN :2345-2773

Indexed In