@article{ author = {Geravanchizadeh, Masoud and Ghalamiosgouei, Si}, title = {A New Fractional Adaptive Filtering Method and its Application in Speech Enhancement}, abstract ={In this paper, a modified version of an adaptive filtering technique, called fractional affine projection algorithm, is proposed for the dual-channel speech enhancement problem. The new adaptive filtering approach uses the fractional derivative together with the conventional first-order derivative of the mean-square error in its update equation. The update rule shows nonlinear behavior of step-size with respect to input signal. The proposed method is compared with the conventional methods of the least-mean-squares, normalized least-mean-squares, fractional least-mean-squares, normalized fractional least-mean-squares, and affine projection algorithms, both subjectively and objectively. The quality of noisy speech processed by applying different algorithms is evaluated objectively through the SNR and PESQ test measurements, and subjectively by conducting listening tests. Experimental results show that the fractional affine projection algorithm outperforms the conventional adaptive filtering methods in the sense of mean-square-error and quality of enhanced speech.}, Keywords = {Speech Enhancement, Dual Channel speech Enhancement, Adaptive Filtering, Fractional Signal Processing, Affine Projection Algorithms }, volume = {7}, Number = {2}, pages = {1-9}, publisher = {ICT Research Institute(ITRC)}, title_fa = {}, abstract_fa ={}, keywords_fa = {}, url = {http://ijict.itrc.ac.ir/article-1-96-en.html}, eprint = {http://ijict.itrc.ac.ir/article-1-96-en.pdf}, journal = {International Journal of Information and Communication Technology Research}, issn = {2251-6107}, eissn = {2783-4425}, year = {2015} } @article{ author = {Meymanatabadi, Saber and MuseviNiya, Jav}, title = {A New Method for SLM-Based OFDM Systems without Side Information}, abstract ={One of the most well-known techniques to reduce the problem of PAPR in orthogonal frequency division multiplexing (OFDM) systems is selected mapping (SLM). The chief drawback of this method is transmission of several additional bits, side information (SI), for each data block. Such side information causes bandwidth efficiency to be decreased; in addition, incorrect detection of SI in the receiver side make whole data block be lost. In this paper, we propose a technique by which side information bits are not explicitly sent. We exhibit the example of our method for an OFDM system by using 16-QAM modulation. It is shown that our proposed scheme, from the view point of bit error rate, probability of detection failure and PAPR reduction, performs very well.}, Keywords = {Orthogonal frequency division multiplexing (OFDM), peak-to-average power ratio (PAPR), selected mapping (SLM), side information }, volume = {7}, Number = {2}, pages = {11-17}, publisher = {ICT Research Institute(ITRC)}, title_fa = {}, abstract_fa ={}, keywords_fa = {}, url = {http://ijict.itrc.ac.ir/article-1-97-en.html}, eprint = {http://ijict.itrc.ac.ir/article-1-97-en.pdf}, journal = {International Journal of Information and Communication Technology Research}, issn = {2251-6107}, eissn = {2783-4425}, year = {2015} } @article{ author = {KhodadadiAzadboni, Mohammad and Behrad, Alirez}, title = {Text Localization, Extraction and Inpainting in Color Images using Combined Structural and Textural Features}, abstract ={In this article, a new approach is proposed for text detection, extraction and inpainting in color images. The proposed algorithm includes three stages. In the first stage, several gradient based operators and image corners are utilized to localize text blocks. We use a new block split and merging algorithm to enhance the accuracy of text localization algorithm. An SVM based text verification algorithm is then employed with a new set of features to reject non-text blocks. To inpaint text areas, we cluster different colors in the text blocks using k-means clustering algorithm and estimate background and text colors. Then a color segmentation algorithm is employed to detect characters’ pixels accurately. In the third stage, the proposed inpainting algorithm is applied to restore initial image contents. The inpainting algorithm is based on a matching algorithm that considers the priority for inpainting the pixels. Experimental results and a comparison of the results with those of other methods show the efficiency of the proposed algorithm.}, Keywords = {text detection, text localization, image inpainting, structural and textural features, color segmentation }, volume = {7}, Number = {2}, pages = {19-31}, publisher = {ICT Research Institute(ITRC)}, title_fa = {}, abstract_fa ={}, keywords_fa = {}, url = {http://ijict.itrc.ac.ir/article-1-99-en.html}, eprint = {http://ijict.itrc.ac.ir/article-1-99-en.pdf}, journal = {International Journal of Information and Communication Technology Research}, issn = {2251-6107}, eissn = {2783-4425}, year = {2015} } @article{ author = {AbdiGhavidel, Hadi and Khosravizadeh, Parvaneh and Rahimi, Afshi}, title = {Impact of Topic Modeling on Rule-Based Persian Metaphor Classification and its Frequency Estimation}, abstract ={The impact of several topic modeling techniques have been well established in many various aspects of Persian language processing. In this paper, we choose to investigate the influence of Latent Dirichlet Allocation technique in the metaphor processing aspect and show this technique helps measure metaphor frequency effectively. In the first step, we apply LDA on Persian or so-called Bijankhan corpus to extract classes containing the words which share the most natural semantic proximity. Then, we develop a rule-based classifier for identifying natural and metaphorical sentences. The underlying assumption is that the classifier allocates a topic for each word in a sentence. If the overall topic of the sentence diverges from the topic of one of the words in the sentence, metaphoricity is detected. We run the classifier on whole the corpus and observed that roughly at least two and at most four sentence in the corpus carries metaphoricity. This classifier with an f-measure of 68.17% in a randomly 100 selected sentences promises that a LDA-based metaphoricty analysis seems efficient for Persian language processing.}, Keywords = {Impact, LDA, Persian language, Metaphoricity }, volume = {7}, Number = {2}, pages = {33-40}, publisher = {ICT Research Institute(ITRC)}, title_fa = {}, abstract_fa ={}, keywords_fa = {}, url = {http://ijict.itrc.ac.ir/article-1-100-en.html}, eprint = {http://ijict.itrc.ac.ir/article-1-100-en.pdf}, journal = {International Journal of Information and Communication Technology Research}, issn = {2251-6107}, eissn = {2783-4425}, year = {2015} } @article{ author = {Divsalar, Mehrnoush and AbdollahiAzgomi, Mohammad and Ashtiani, Mehr}, title = {A Computational Trust Model for E-Commerce Systems: Concepts, Definitions and Evaluation Method}, abstract ={Trust is a complex and multidimensional concept, which plays a key role in the success of electronic commerce. Assessing trust, specifically in the beginning of a commercial relation and the formulation of trust in general is a complex and difficult task. The researchers are often focused on a specific context for trust formulation and the relevant literature does not clearly distinguish between the factors involving in trust decision making process. With the aim of providing a basis for computational trust models and by consolidating a large body of studied contexts in the trust literature, this paper first tries to present a conceptual trust model for electronic commerce. Four types of trust that are used in the conceptual trust model are as follows: (1) institutional trust, (2) technological trust, (3) trading party trust, and (4) propensity trust. Then, a computational trust model is proposed in which the agents involved in a commercial transaction can consult with a trust manager agent (TMA), which is considered in a distributed fashion in the network. The proposed model is capable of evaluating a broad range of trust contexts and has two main features: (1) trust is evaluated dynamically (i.e., a change in any of the trust’s parameters will result in the re-calculation of trust values) and (2) the proposed model is capable of making partial studies for the trust contexts presented in the conceptual model of trust. Finally, the proposed model is evaluated and the results are presented in this paper.}, Keywords = {Trust model, trust evaluation, computational trust model, electronic commerce, trust manager agent (TMA) }, volume = {7}, Number = {2}, pages = {41-58}, publisher = {ICT Research Institute(ITRC)}, title_fa = {}, abstract_fa ={}, keywords_fa = {}, url = {http://ijict.itrc.ac.ir/article-1-101-en.html}, eprint = {http://ijict.itrc.ac.ir/article-1-101-en.pdf}, journal = {International Journal of Information and Communication Technology Research}, issn = {2251-6107}, eissn = {2783-4425}, year = {2015} } @article{ author = {Keyvanpour, Mohammadreza and Tavoli, Reza and Mozaffari, Saee}, title = {HWS: A Hierarchical Word Spotting Method for Farsi Printed Words Through Word Shape Coding}, abstract ={Word shape coding (WSC) is a method of document image retrieval (DIR) based on keyword spotting. By using this method, a word can be recognized in the document image, only by identifying some of the features of the word. In this paper, a hierarchical word spotting method, namely HWS, is presented for Farsi document image retrieval through WSC. In HWS method, document images are retrieved by using a new indexing method. In HWS, at first the words in the document images are shape coded based on topological properties. These features include number of sub-words, ascenders, descenders, and holes.A new feature that has been used for this paper is dot's position in word. Six features are obtained which are one top dot, two top dots, three top dots and one bottom dot, two bottom dots, and three bottom dots. Precision of retrieval increases by using these features. Then, all of the shape codes are indexed by building a tree. Retrieval is done based on keyword query in the tree. The results show that the proposed technique is very fast for large volumes of documents. Time complexity for successful and non-successful searching is O(logkn) .This value is better than values in ordinal method. Also, time complexity for indexing is O(logkn) . The HWS method is tested on Bijankhan database. 87867 common words from this database are used for building the dictionary. Test results show that average of precision is 0.83 and average recall is 0.94.}, Keywords = { Tree indexing, Information Retrieval, Document Image, word shape coding, Farsi document }, volume = {7}, Number = {2}, pages = {59-70}, publisher = {ICT Research Institute(ITRC)}, title_fa = {}, abstract_fa ={}, keywords_fa = {}, url = {http://ijict.itrc.ac.ir/article-1-102-en.html}, eprint = {http://ijict.itrc.ac.ir/article-1-102-en.pdf}, journal = {International Journal of Information and Communication Technology Research}, issn = {2251-6107}, eissn = {2783-4425}, year = {2015} } @article{ author = {Nekooei, Arezoo and Tarokh, Mohammad Jafar}, title = {Customer Clustering Based on Customer Lifetime Value: A Case Study of an Iranian Bank}, abstract ={Customer lifetime value (CLV) as a quantifiable parameter plays an important role in customer clustering. Clustering based on CLV helps organizations to form distinct customer groups, reveal buying patterns, and create longterm relationships with their customers. Our research aims at the synthesis of a CLV model and a clustering algorithm in a new comprehensive framework. First, a model for calculation of CLV is suggested, which is called Group LRFM or GLRFM briefly. In this model, four parameters, Length, Recency, Frequency, and Monetary, are determined according to the products/services used by customers. Then, a novel framework based upon the model is presented in eight steps for customer clustering. In traditional methods, the customers of valuable cluster are treated the same. But in proposed framework, company can design different and proper strategies for each cluster based on the use of products/services. The experimental results in banking industry verify that proposed approach allows an accurate and efficient cluster analysis; it provides appropriate information to create clear sales and marketing policies for three identified segments.}, Keywords = {clustering, data mining, customer relationship management (CRM), customer lifetime value (CLV) }, volume = {7}, Number = {2}, pages = {71-90}, publisher = {ICT Research Institute(ITRC)}, title_fa = {}, abstract_fa ={}, keywords_fa = {}, url = {http://ijict.itrc.ac.ir/article-1-103-en.html}, eprint = {http://ijict.itrc.ac.ir/article-1-103-en.pdf}, journal = {International Journal of Information and Communication Technology Research}, issn = {2251-6107}, eissn = {2783-4425}, year = {2015} }