---

  Accepting differences between knowledge-based organizations and other organizations with respect to the philosophy of existence, nature of the activities and their differentiated employees, we intend to present a proper model with surveying existing models. The presented model should be applicable in the compensation system in knowledge based organizations. Components Influencing compensation systems identified and classified into two main groups of financial and non-financial and four sub-division categories through studying existing models. According to the experts, 8 main effective components in compensation of these organizations were identified. Finally, based on 8 selected components and with the exploiting of the experts opinion and using of Interpretive Structural Modeling (ISM) technique, a prioritizing and leveling model for compensation system of knowledge-based organizations was developed. In this designed model, nonfinancial factors such as job-related factors (job challenge and growth opportunities) and factors related to the job environment (having a floating work hours and workplace conditions) have higher priority. This means that these Factors in compensation system are more important and have more influence.  

---

  Present a model for analyzing agents’ behaviors and determining their efficiency factor, while responding to calls in call centers is the main goal of this study. The aim of this model is to identify the strengths and weaknesses of the agents providing these services to customers. The proposed process defines three criteria namely F, U and Q which represent the number of responding, duration of responding to a unit call and the quality of responding to calls. After obtaining experts’ opinions, parameters were weighted. Then, based on the number of optimum clusters provided by Davis we tried to cluster the factors using K-Means. In the next stage criterion to measure the efficiency of agents were defined, and results were analyzed.  The use case carried out on 3401535 records of 158 answering agents in the call center for one of the companies affiliated to automobile industry. The results show that efficiency of agents is not relation to gender. The company does not use enough “best agents” for answering customer calls; whereas one of the highlights of Human Resource Management is the efficient use of an expert. On the other hand the results show that company should pay attention to the education and skills of hired agents who answer customer calls.    

---

In cyberspace, Social networks have been born as a new type of websites and have gained an enormous range of users and fans. Social networks are one type of social media and are places for forming virtual communities of interested users. Internet users have been classified in different ways based on their type of using social networks. This study seeks to provide a mechanism to predict patterns of behavior in social networks. Due to the expansion of social networks, the selected network requires a model based on the new strategic decisions or policies for better serve users. This study uses data mining techniques for classification and analysis of social network users for better understanding of their behavior and improving services and developing appropriate strategies. Understanding behavioral patterns of users of social networks lead to better adaptation to user needs. The user population applied for analysis includes 31033 users that use a specific Iranian Social Network regularly. A method for clustering and orientation analysis based on past users behavior using CRISP-DM and data mining software is deeply analyzed and described. A full perception of users’ behavior will result in a better match of social network features with users’ needs as well as a high value added for users and profitability for social network owners.

---

Todays, websites have great importance in the field of information and do a lot of services. In this regard, webometrics studies has been the attention of many researchers at various aspects. The aim of this study is to evaluate and cluster the Iranian banks and financial institutions based on website traffic indicators. In research process, 31 banks and financial institutions were evaluated in the form of 6 of the most important website traffic indicators include the average number of pages visited, average time to browse the site, the percentage of visitors within the country, the percentage of visitors from abroad, the number of links, and the speed of loading, based on the Alexa website and search engine. Then, the similar banks and institutions were classified in the form of homogeneous groups using by the Hierarchical Clustering Analysis (HCA). The quality and validity of each of the clusters created was confirmed by using Discriminant Analysis (DA) and finally, were discussed the characteristics of each of these clusters. The findings suggest that there is not a significant difference in terms of speed of loading between the clusters, but in other indexes, the difference between clusters is significant.

---

Integrated complaints management system designed to give organizations the opportunity to learn from customer feedback information and use information to reduce weaknesses in business performance, efficient use of resources and maintain satisfactory capital base long term relationship with their customers. Therefore in this paper, a model is provided that could clear weak points first, in other words, discover and understand the Working patterns and factors affecting it. Second, it can provide solutions to the problem. As a case study customer relationship management data unit of Ayandeh private Bank is used. This data related to customer complaints in one of the call centers in Tehran. In order to provide a descriptive model, the data is clustered by using data mining tools, optimal clusters based on Davis– Bouldin Indicator is determined and based on the analysis obtained, the architecture of response system is designed. Next, in order to provide a prediction model, support vector machine is used. The result is validated and suggestions to improve complaints management system are presented

---

Knowing customer behavior patterns, clustering and assigning them is one of the most important purpose for banks. In this research, the five criteria of each customer, including Recency, Frequency, Monetary, Loan and Deferred, were extracted from the bank database during one year, and then clustered using the customer's K-Means algorithm. Then, the multi-objective model of bank service allocation was designed for each of the clusters. The purpose of the designed model was to increase customer satisfaction, reduce costs, and reduce the risk of allocating services. Given the fact that the problem does not have an optimal solution, and each client feature has a probability distribution function, simulation was used to solve it. In order to determine the neighbor optimal solution of the Simulated Anneling algorithm, neighboring solutions were used and a simulation model was implemented. The results showed a significant improvement over the current situation. In this research, we used Weka and R-Studio software for data mining and Arena for simulation for optimization. The results of this research were used to develop Business Intelligence software for customers in one of the private banks of Iran.

---

E-Banking is a new type of banking service where banking services are provided using -environments. This kind of banking activity has spread throughout the world since 1991. Customers are migrating from traditional banking to modern banking with the increase of e-banking services and the provision of various tools for banking transactions. Accordingly, it is important to examine the progress of banks in these tools and the level of customer satisfaction. This study first analyzes the extent of customer satisfaction with these tools by examining customer transactions in Branch, ATM, Internet Bank and Mobile Bank Which has conducted this survey for a hundred thousand customers. After an initial analysis of the use of tools, Customers were clustered using k-Mean Method and Imperialist Competitive Algorithm with MATLAB software and grouped into seven clusters. Then the characteristics of each cluster are examined and strategies for each cluster are presented. In the final stage, we analyzed the strategies proposed by the Shapely value-based game theory approach and the most important strategies proposed.

---

Abstract In current settlement planning settlements are either rural or urban. In reality human settlements are more diverse than this dichotomy and current definitions of rural and urban settlements are not comprehensive from political, administrative and scientific points of view and show lack of attention to various factors that shape human settlements and their status. In other words changing the status of a settlement based on public demand might not change the real status of a settlement. Application of models based on fuzzy logic as a relative approach in identification and classification of human settlements provides a better and more diverse framework for human settlement grouping based on various social, environmental and economic factors. Changing the status of a settlement from rural to urban without considering the role of such factors will not only increase the public expenditures, but also will increase public expectations and demand for inefficient services. Identification of those rural settlements with higher membership degree to urban settlements will help planners and policy makers to make better decisions when trying to accept or reject the status of a settlement. The main aim of this study is to assess the use fuzzy logic to identify rural settlements that are suitable for getting the city status. Rural settlement in Tehran province, Iran, has been selected as case study.

---

---

Prospective sales policies are one of the essential components of short- and medium-term planning in any business. The correct and accurate formulation of sales policies can play an effective role in managing cash flows and allocating resources. In general, the above statement indicates the fact that in today's competitive world, customer satisfaction and increased market share is vital, estimating the issues about customer buying behavior and decision making is the main theme of any organization that this can be improved by using advanced prospective analysis in the field of sales policy. The purpose of this study is to provide a model for customer clustering, extract the product portfolio of each cluster and allocate the appropriate sales policies for them. Finally, the results were confirmed by experts. Apart from current customers and with the entrance of new customers, using clustering algorithms, the appropriate policies for different categories of these customers are provided to improve their loyalties.

---

This paper presents a novel approach for driving stress assessment by fuzzy clustering. In previous researches, stress during real-world driving tasks has been detected in discrete levels, but in this study, we demonstrated that considering fixed-levels for stress in long periods is not authentic.  Without employing discrete levels of stress, data remains unlabeled. So a clustering method has been proposed to compensate for the lack of the feasibility of classification. Due to uncertainties, the clusters can be defined in terms of fuzzy sets. Furthermore, using fuzzy clustering methods, data overlap is considered. In the proposed algorithm, utilizing membership values generated by fuzzy c-means, and weights assigned by fuzzy inference system (FIS), we present automatic continuous criteria for stress in the short time intervals. The continuous scale is defined between 0and100, where higher values represent higher stress levels. Our findings not only confirm rough results of previous studies, but also indicate improvements in precision and accuracy of stress assessment.    

---

Aims: The aim of the research is to use and apply the artificial intelligence network and data mining of the non-form pattern in the ten valuable landmark buildings of Tehran (1330s to 1350s) in the direction of modernization.

Methods: In the present study, the research method used in terms of purpose is applied-developmental and the method of study is descriptive-survey in terms of method and nature. In this research, the MLP (Multilayer perceptron) artificial intelligence network and clustering have been used to validate the non-form analysis of residential building plans in the period 1330-1350. The data were randomly divided into three sets, 70% of the data were used for training, 15% for validation, and 15% for testing.

Results: According to the analysis and matching with non-formal analysis, the results show that plans have 15, 14, 13 and 11 components in terms of non-form. which exactly corresponds to the plan's amorphous analytical tables. Therefore, the results of the non-form analysis of the plans have been validated by artificial intelligence.

Conclusion: Modernization of buildings and preservation of historical buildings are important for the majority of people and the results of this research showed that by using modern technology such as creating an artificial intelligence network, it is possible to find the invisible and hidden components in the plans of the mentioned period and use them in today's residential plans. The use of modern technologies such as artificial intelligence in order to cluster and identify the hidden relationships of plans can be very helpful.

---

 
In recent years using wireless sensor networks (WSNs) in applications, such as disaster management and security surveillance have been increased. A lot of sensors in these applications are expected to be remotely deployed in unattended environments autonomously. To support scalability, nodes are often grouped into disjointed and mostly non-overlapping clusters. Every cluster has a leader that is known as a cluster-head (CH). The CH may be selected by the sensors in the network or pre-assigned by the network designer. These networks require effective communication protocols to be energy efficient and increase network quality. In this paper, a self-organization routing protocol for wireless sensor networks is presented by using hierarchical protocols and considering the position of CHs regarding to each other which is called “Probabilistic Selection of Cluster-head based on the Nearest possible Distance of Cluster-head”. In addition to increase network lifetime, it causes to increase scalability of the network, optimal use of communication bandwidth and improve some of qualitative parameters of the sensor networks. Proposed method has little overhead control and can find appropriate CHs with local information. In this paper, simulation is done by the NS-2 simulator, and simulation results show this protocol could lead to increase environment monitoring, improve network lifetime, throughput and some qualitative sensor network parameters by improving the clustering process of all the routing protocol. WSNs that aren’t considered CHs distribution (LEACH protocol here).

---

Mesh segmentation and partitioning of 3D models have always been significant as one of the most structural tools used in many applications of CAD and computer graphics. One of the most versatile of these algorithms, which is capable of optimum segmentation of model, is the iterative algorithm. It is a parametric method based on Lloyd algorithm, which segments the model in an optimized way by plotting the voronoi diagram through the points cloud data. The main disadvantage of this method, which confines its application, is the time-consuming problem. In this paper, employing the nature of fuzzy segmentation, a solution has been proposed to specify the number of regions required for model’s partitioning and to carry out the nonparametric segmentation with no need for user’s initial settings. Additionally, utilizing the approximate voronoi diagram and fuzzy regions construction, a novel method for obtaining the optimized segmentation in a shorter time interval in comparison with other iterative algorithms has been presented. The proposed method has been implemented in a standard model for validation. It has been observed that the obtained results have remarkable improvements relative to the results from the iterative algorithm, which demonstrates the efficiency of this method in segmentation of 3D models.

---

Financial Service Providers (FSPs) like other organizations can use ‎Customer Lifetime Value (CLV) as an instrument to achieve their targets in ‎Customer Relationship Management (CRM). Although various studies have ‎been done about this concept, CLV case studies are scarce in banking ‎industry. In this research, in order to present a model to determine CLV in ‎banking industry, customers with current account in a bank in Iran were ‎studied. Determining the relative importance of R, F and M variables that are ‎used to cluster customers, ranking the clusters of customers according to ‎their CLV and understanding the best strategies for bank to treat with each ‎cluster are among the other goals of this study. Three main variables were ‎used to apply the model; a) Recency: the length of time since the last ‎transaction (in days), b) Frequency: number of positive transactions and c) ‎Monetary: balance of account (in Rials). Also wR , wF and wM were used as ‎the relative importance of R,F and M variables. We used the ideas of experts ‎and marketing managers and the data of transactions from the random ‎samples of 382 corporate customers and 5113 individual customers, who had ‎current account in 33 branches of a bank in Tehran. The analytical Hierarchy ‎Process (AHP) was applied to determine wR , wF and wM in evaluating CLV. ‎Then WRFM model was used to cluster the customers and rank them based ‎on their CLV for two groups of corporate and individual clients Clustering ‎and Discriminant Analysis techniques were implemented for this section. ‎Finally, the best strategies for bank to treat with each cluster of the ‎customers was determined.‎ Keywords:

---

This paper presents a novel approach for driving stress assessment by fuzzy clustering. In previous researches, stress during real- world driving tasks has been detected in discrete levels, but in this study, we demonstrated that considering fixed-levels for stress in long periods is not authentic.  Without employing discrete levels of stress, data remains unlabeled, so a clustering method has been proposed to compensate for the lack of feasibility of classification. Due to uncertainties, the clusters can be defined in terms of fuzzy sets. Furthermore, using fuzzy clustering methods, data overlap is considered. In the proposed algorithm, using membership values generated by fuzzy c-means, and weights assigned by fuzzy inference system (FIS), we present an automatic continuous criteria for stress in short time intervals. The continuous scale is defined between 0 and 100, where higher values represent higher stress levels. Our findings not only confirm rough results of previous studies, but also indicate improvements in precision and accuracy of stress assessment. 

---

The purpose of this paper is to propose an integrated model of clustering, AHP and Kano approaches. Based on customer segmentation and value achievement of each segment, the new model is expected to recommend appropriate service for each segment. Statistical population of this research includes customers of Saman Bank of Qom. After random sampling, 144 questionnaires have been used for data analysis. After data collection, the clustering approah has been used and clusters have been prioritized by the AHP approach and finally, the needs of each cluster have been determined using with the Kano methodology and appropriate service has been recommended for each cluster. The number of clusters has been addressed as four and the clusters have been prioritzed as the second, the third, the first and the fourth cluster. In the first cluster, customers' needs are distinguished as more, one-dimensional, attractive and indifferent; in the second and third clusters as more must-be; and in the fourth cluster as more one-dimensional. The results imply that the integratoin of the three approaches forms an empowered technique by which, an organization can achieve competitive advantage through market segmentation, valueable customer recognition/satisfaction

---

Due to the rapid growth of manufacturing industry and increased competition among companies, the need to produce parts with free-form surfaces with lower cost and higher accuracy is felt. Nowadays beside all of the great benefits of 5-axis CNC machines the use of 3-axis CNC machines are more common in industry because of the high capital investment, high operating and maintenance cost, the low dynamic stability and their complex programming in 5-axis machining. Therefore it is preferred using 3-axis machines in industry where it’s possible. Since the inability of machining some complex parts by 3-axis machines, the 3+2-axis machining technology has been proposed. In this paper, a new method has been used to determine the tool appropriate orientation for 3+2-axis machining. In the proposed method, visible and invisible points of the surface and the shortest tool length are calculated for the workpiece and finally performed surface partitioning. The minimum number of tool orientation result from this methods reducing overall machining time and the boundaries between machining partitions to improves the surface quality. A 3+2-axis machining of an impeller perform and evaluate the efficiency and surface accuracy by the use of a coordinate measuring machine.

---

Apples are an important source of polyphenols in the human diet and the consumption of this fruit has been linked to the prevention of degenerative diseases. This study deliberation of the physicochemical and antioxidant properties of some cultivars of apples cultivated in Zanjan province were measured as a suitable strategy for their evaluation in 2017. The total phenol content, total flavonoid, anthocyanin, chlorophyll, carotenoid, antioxidant properties, pectin, soluble solids, total acid and flavor index in the skin and pomace of nine apple cultivars (Malus domastica) including "Top Red", "Granny Smith", "Dellbar Stewal", "Golden Primorz", "Idared", "Red Delecious", "Red Starking", "Jonagold" and "Golden Delicious" were evaluated and clustered. According to the cluster analysis based on the accumulation of phenolic substances in the skin of fruits, there was no significant difference between Granny Smith and Red Delecious cultivars and had at least a significant difference with Top Red. The results showed that the amount of phenolic compounds in fruit skin was higher than pomace, and the amount of these compounds were distinct in various cultivars. The highest amount of total phenol, chlorophyll, carotenoid, flavonoids and anthocyanin was measured in fruit skin. As the final result, the highest amount of skin phenol (6.4 mg.kg^-1), pectin (2.31%), skin chlorophyll (80.82 mg.g^-1) and antioxidant properties (83.73%) were observed in Granny Smith variety compared to the others.

---

This paper explores the empirical evidence of the nature of intra-metropolitan supply linkages and industrial clustering and searches for the driving forces that enhances the learning processes and innovation capacities hence; contributing to competitive advantage within the Tehran metropolitan. The research points to accelerating growth in the automotive sector since the late 1980s and early 1990s which has been the driving force of the Tehran’s economy. This growth appears to be related to industrial clustering and systemic linkages with actors such as suppliers, sub-contractors and so on. The analysis of empirical evidences from the sample industrial cluster indicates a considerable number of interesting findings from strong degrees of industrial clustering. However, there are some weak evidences of industrial clustering such as weak institutional environment in the cluster.