@article { author = {asghari beirami, behnam and Mokhtarzade, mehdi}, title = {Spatial-Spectral Classification of Hyperspectral Images Based on Extended Morphological Profiles and Guided Filter}, journal = {Computer and Knowledge Engineering}, volume = {2}, number = {2}, pages = {2-8}, year = {2020}, publisher = {Ferdowsi University of Mashhad}, issn = {2538-5453}, eissn = {2717-4123}, doi = {10.22067/cke.v2i2.81519}, abstract = {Previous studies show that the incorporation of spatial features in the classification process of hyperspectral images (HSI) improves classification accuracy. Although different spatial-spectral methods are proposed in the literature for the classification of the HSI, they almost have a slow, complex, and parameter-dependent structure. This paper proposes, a simple, fast and efficient two-stage spatial-spectral method for the classification of the HSI based on extended morphological profiles (EMP) and the guided filter. The proposed method consists of four major stages. In the first stage, principal component analysis (PCA) is used to smooth the HSI to extract the low-dimensional informative features. In the second stage, EMP is produced from the first three PCs. Stacked feature vectors, consisting of PCs and EMP, are classified via support vector machines (SVM) in the third step. Finally, a post-processing stage based on a guided filter is applied to classified maps to further improve the classification accuracy and to refine the noisy classified pixels. Experimental results on two famous hyperspectral images named Indian Pines and Pavia University in a very small training sample size situation show that the proposed method can reach the high level of accuracies which are superior to some recent state-of-the-art methods.}, keywords = {Extended Morphological Profiles,Guided Filter,Support vector machine,Principal Components Analysis,Hyperspectral,Classification}, url = {https://cke.um.ac.ir/article_26881.html}, eprint = {https://cke.um.ac.ir/article_26881_5286deaa9b483514f796e7a625c642be.pdf} } @article { author = {Karimi Zandian, Zahra and Keyvanpour, Mohammad Reza}, title = {SSLBM: A New Fraud Detection Method Based on Semi- Supervised Learning}, journal = {Computer and Knowledge Engineering}, volume = {2}, number = {2}, pages = {10-18}, year = {2020}, publisher = {Ferdowsi University of Mashhad}, issn = {2538-5453}, eissn = {2717-4123}, doi = {10.22067/cke.v2i2.82152}, abstract = {The increment of computer technology usage and rapid development of the Internet and electronic business lead to an increase in financial transactions. With the increase of these banking activities, fraudsters also use different methods to boost their fraudulent activities. One of the ways to cope their damages is fraud detection. Although, in this field, some methods have been proposed, there are essential challenges on the way. For example, it is necessary to propose methods that detect fraud accurately and fast, simultaneously. Lack of non-fraud labeled data and little fraud labeled data for learning is another challenge in this field particularly in banking. Therefore, we propose a new fraud detection method for bank accounts called SSLBM. In this method, after preprocessing phase, a helpful learning method called SSEV is used that is based on semi-supervised learning and evolutionary algorithm. The results imply improvement of detection by using SSLBM with 68% accuracy and acceptable speed.  }, keywords = {Fraud,Fraud detection,Semi-supervised learning,Evolutionary algorithm,Feature extraction}, url = {https://cke.um.ac.ir/article_26805.html}, eprint = {https://cke.um.ac.ir/article_26805_53d140da9787bd951a7585a5df2cd3fe.pdf} } @article { author = {Kianian, sahar and Farzi, saeed}, title = {Assessment of Customer Credit Risk using an Adaptive Neuro-Fuzzy System}, journal = {Computer and Knowledge Engineering}, volume = {2}, number = {2}, pages = {19-28}, year = {2020}, publisher = {Ferdowsi University of Mashhad}, issn = {2538-5453}, eissn = {2717-4123}, doi = {10.22067/cke.v2i2.80359}, abstract = {Given the financial crises in the world, one of the most important issues of banking industry is the assessment of customers' credit to distinguish bad credit customers from good credit customers. The problem of customer credit risk assessment is a binary classification problem, which suffers from the lack of data and sophisticated features as main challenges. In this paper, an adaptive neuro-fuzzy inference system is exploited to tackle the customer credit risk assessment problem regarding the mentioned challenges. First of all, a SOMTE-based algorithm is introduced to overcome the data imbalancing problem. Then, several efficient features are identified using a MEMETIC meta-heuristic algorithm, and finally an adaptive neuro-fuzzy system is exploited for distinguishing bad credit customers from good ones. To evaluate and compare the performance of the proposed system, the standard German credit data dataset and the well-known classification algorithms are utilized. The results indicate the superiority of the proposed system compared to some well-known algorithms in terms of precision, accuracy, and Type II errors.}, keywords = {Banking,Customer credit risk,Risk Assessment,Fuzzy system}, url = {https://cke.um.ac.ir/article_26988.html}, eprint = {https://cke.um.ac.ir/article_26988_5be4c31c509baea7f0a5c61a50f9a93a.pdf} } @article { author = {Keyvanpour, Mohammad reza and Mehrmolaei, Soheila and Etaati, Atekeh}, title = {PLI-X: Temporal Association Rules Mining in Customer Relationship Management Systems}, journal = {Computer and Knowledge Engineering}, volume = {2}, number = {2}, pages = {29-48}, year = {2020}, publisher = {Ferdowsi University of Mashhad}, issn = {2538-5453}, eissn = {2717-4123}, doi = {10.22067/cke.v2i2.81586}, abstract = {The temporal association rules mining has recently become an important technology in the field of the Customer Relationship Management (CRM), which can be useful for improving the customer enterprise relationship. Also, the dynamic nature of the CRM systems is made necessity of using efficient and rapid algorithms in order to extract valid patterns in this field. Hence, this paper proposes an efficient algorithm of incremental mining for temporal association rules in CRM entitled PLI-X. The four significant features that are considered for this algorithm are:(1) generating  valid temporal association rules after adding the new transactions to the database, (2) performing algorithm on the whole temporal database instead of a small section of it, (3) performing the temporal transactional databases of the non-numeric, and (4) quickly generating the temporal association rules and reducing the run time by partitioning the candidate itemsets based on the previous partitions and scanning database when scan is necessary. Experimental result is the valid proof for the correctnessof this assertion. It seems that the PLI-X algorithm can be used as a strong tool in order to extract valid patterns and discover useful temporal association rules in the field of CRM.}, keywords = {Temporal Database,CRM,Incremental Mining,Pre-large Itemsets}, url = {https://cke.um.ac.ir/article_26843.html}, eprint = {https://cke.um.ac.ir/article_26843_1d05e0d72b3a0546ac1317a47aaf5a12.pdf} } @article { author = {Soleimanian Gharehchopogh, Farhad and Mousavi, Seyyed Keyvan}, title = {A New Feature Selection in Email Spam Detection by Particle Swarm Optimization and Fruit Fly Optimization Algorithms}, journal = {Computer and Knowledge Engineering}, volume = {2}, number = {2}, pages = {49-62}, year = {2020}, publisher = {Ferdowsi University of Mashhad}, issn = {2538-5453}, eissn = {2717-4123}, doi = {10.22067/cke.v2i2.81750}, abstract = {With the advent of the internet, along with email, and social networking, there are some new issues that have caused vulnerability of users against attackers. Internet users face a lot of undesirable emails and their data privacy and security is in danger. Spammers are often sent to users by intruders and sales markets, and most of the time they target spam, harassment, and abuse of user data. With increasing attacks on computer networks, attempts to rebuild computer networks and detect spam emails are important. Hackers use the identities of users by obtaining their personal information and account of users for malicious and subversive actions. Intruders are attempting to expose, remove, or change user information by opening encrypted information. Therefore, it is very important to detect spam in the early stages. In this paper, a new approach is proposed based on a hybridization of Particle Swarm Optimization (PSO) with Fruit Fly Optimization (FFO) to email spam detection. This paper shows a Feature Selection (FS) based on PSO, which decreases dimensionality and improves the accuracy of email spam classification. The PSO searches the feature space for the best feature subsets. Experiments results on the public spambase dataset show that the accuracy of the proposed model is 92.21%, which is better in comparison with others models, such as PSO, Genetic Algorithm (GA), and Ant Colony Optimization (ACO).  }, keywords = {Email spam detection,Feature selection,Particle swarm optimization,Fruit fly optimization}, url = {https://cke.um.ac.ir/article_26945.html}, eprint = {https://cke.um.ac.ir/article_26945_1b3689a326ca43622e5fd63f64234b74.pdf} } @article { author = {Mostafavi, Seyedakbar and Hakami, Vesal and Paydar, Fahimeh}, title = {Performance Evaluation of Software-Defined Networking Controllers: A Comparative Study}, journal = {Computer and Knowledge Engineering}, volume = {2}, number = {2}, pages = {63-73}, year = {2020}, publisher = {Ferdowsi University of Mashhad}, issn = {2538-5453}, eissn = {2717-4123}, doi = {10.22067/cke.v2i2.84917}, abstract = {Software-Defined Networking (SDN) is a viable approach for management of large and extensive networks with flexible quality of service requirements and huge data traffic. Due to the central role of SDN controllers in traffic engineering and performance of software-defined networks on one hand, and diversity of available SDN controllers on the other hand, an evaluation framework is required to study and compare the architectural choices and performance of distributed and centralized SDN controllers in action. In this paper, we propose a comprehensive framework for performance evaluation of OpenFlow SDN controllers. In this simulation platform, we analyze both centralized and decentralized architectures for controller deployment. Performance of controllers is evaluated based on Quality of Service (QoS) measures including delay and throughput in different network topologies under different workloads. The impact of routing protocols on controller performance in data center networks is also analyzed. Our results can provide valuable insights for scalable design and proper deployment of SDN controllers in the real world scenarios.  }, keywords = {Software-Defined Networking (SDN),OpenFlow Controllers,Performance Evaluation,Quality of Service}, url = {https://cke.um.ac.ir/article_26917.html}, eprint = {https://cke.um.ac.ir/article_26917_da95ba5d3cef75cc048fef4ec4fd6772.pdf} }