Pattern Analysis and Intelligent Systems
shahrzad Oveisi
Articles in Press, Accepted Manuscript, Available Online from 02 June 2022
Abstract
Nowadays, we are witnessing the growth of financial theft cases and thereby a high degree of financial losses concomitant with the growth of IoT technology, as well as development and utilization of this technology in banking and financial fields along with the increase in the volume of transactions. ...
Read More
Nowadays, we are witnessing the growth of financial theft cases and thereby a high degree of financial losses concomitant with the growth of IoT technology, as well as development and utilization of this technology in banking and financial fields along with the increase in the volume of transactions. Financial fraud detection represents the challenge of finding anomalies in networks of financial transactions. In general, anomaly detection is the problem of distinguishing between normal data samples and well-defined patterns or signatures with those that do not conform to the expected profiles. Various methods have been introduced to identify, detect and prevent such thefts. This paper presents a LSTM based approach for detecting fraudulent transactions. I express the fraud detection problem as a sequence classification task and employ LSTM based method to incorporate transaction sequences. Then, the results are assessed using two classifier methods, namely random forest and decision tree and Mean Square Error. In the second case, because the data are imbalanced, undersampling and oversampling techniques have been used, after which I employ LSTM neural network and results assessed with MSE. Finally, the results of the two groups were compared with confusion matrix. According to the evaluations, my proposed method with Random forest classifier gives the best results.
Pattern Analysis and Intelligent Systems
Zahra narimani; Farhad Soleimanian Gharehchopogh
Articles in Press, Accepted Manuscript, Available Online from 07 July 2022
Abstract
One of the most critical issues in studying complex networks is detecting communities widely used in sociology, social media (such as Instagram, Twitter, or email networks), biology, physics, data networks, and information technology. Graphs usually implement complex network modelling. In a graph, nodes ...
Read More
One of the most critical issues in studying complex networks is detecting communities widely used in sociology, social media (such as Instagram, Twitter, or email networks), biology, physics, data networks, and information technology. Graphs usually implement complex network modelling. In a graph, nodes represent objects, and edges represent connections between objects. Communities are groups of nodes that have many internal connections and few intergroup connections. Although in social network research, the detection of communities has attracted much attention, most of them face functional weaknesses because the structure of the community is not clear or the characteristics of nodes in a community are not the same. Besides, many existing algorithms have complex and costly calculations. In this paper, a model based on Harris Hawk Optimization (HHO) algorithm and Opposition-based Learning (OBL) is proposed for Community Detection (CD). The proposed model uses an OBL to balance exploration and exploitation. The balance between exploration and exploitation is effective in achieving optimal solutions. The evaluation of the proposed model is performed on four different datasets based on modularity criteria and NMI (Normalized Mutual Information). The results show that the proposed model has higher modularity, NMI, and generalizability compared to other methods.
Pattern Analysis and Intelligent Systems
Ehsan Soleimani; Kamal Mirzaie
Articles in Press, Accepted Manuscript, Available Online from 30 July 2022
Abstract
With the increasing use of online services in the form of platforms or websites, as well as the growth of users in online spaces, it seems necessary to study and analyze these networks. One of the areas of interest for social media analysts is Community Detection (CD) in these networks. The purpose of ...
Read More
With the increasing use of online services in the form of platforms or websites, as well as the growth of users in online spaces, it seems necessary to study and analyze these networks. One of the areas of interest for social media analysts is Community Detection (CD) in these networks. The purpose of CD is to discover subcommunities within the original networks. Identifying these groups in social networks has many applications in discovering new groups, and extracting common points between users. The main challenge in CD is to find the relationships between the nodes and form clusters in them. In particular, the use of CD techniques makes it possible to identify similar nodes that have common features. Because user data does not belong to a specific category and there is a lot of data in the community and a similar relationship should be established between them based on the type of data. In this paper, a new method for CD using an Adaptive Genetic Algorithm (AGA) is proposed. The evaluation of the proposed model was performed on the Enron Email suite using Normalized Mutual Information (NMI), Variation Information (VI) and Cross Common Fraction (CCF) criteria. The results show that with increasing the number of generations, the accuracy of the proposed model increases and also the rate of crossover and mutation are very effective in the accuracy of detection. The accuracy of NMI, VI and CCF criteria with 800 iterations is 82.17, 72.95 and 75.16, respectively.
Computer Networks and Distributed Systems
Saeed Banaeian Far; Maryam Rajabzadeh Asaar; Afrooz Haghbin
Articles in Press, Accepted Manuscript, Available Online from 19 August 2022
Abstract
Privacy is a matter of considerable public concern in internet-based communications. In other words, it is sensed more with the growth of internet-based communications and the increasing number of connected users. This paper focuses on the blockchain-based retail markets. It presents a framework that ...
Read More
Privacy is a matter of considerable public concern in internet-based communications. In other words, it is sensed more with the growth of internet-based communications and the increasing number of connected users. This paper focuses on the blockchain-based retail markets. It presents a framework that allows retail market owners to change their retail markets' pseudonyms to a new ones and transfer their accumulated reputations to their new pseudonyms in an untraceable way so that no one can find a link between the transferred reputation and the previous retail market. The main idea is to assign the retail market reputation to a Non-Fungible Token (NFT) and anonymously transfer the NFT ownership to another owner. The presented method is named blockchain-based reputation transfer (BB-RT) and is designed using the two concepts of NFT and Signature of Knowledge (SoK) for providing an unknown and unlinkable transfer. The BB-RT framework provides security for retail markets, including unlinkable reputation transfer for removing retail markets' adversaries. Each retail market owner can prove its retail market's previous reputation in its new retail market. It is believed that the BB-RT framework can be applied in Distributed Autonomous Organization (DAO)-based markets (businesses) since markets' reputations are transferred without the help of a central manager. Finally, the mentioned BB-RT framework properties are analyzed.
Software Engineering and Information Systems
Narges Akhound; Sahar Adabi; Ali Rezaee; Amir masoud Rahmani
Articles in Press, Accepted Manuscript, Available Online from 27 September 2022
Abstract
The advent of the Internet of Things (IoT) technology has made it possible for different devices to be widely connected to the Internet and interact. It has led to the production of large amounts of heterogeneous data. On the other hand, cloud computing is a convenient and efficient processing model ...
Read More
The advent of the Internet of Things (IoT) technology has made it possible for different devices to be widely connected to the Internet and interact. It has led to the production of large amounts of heterogeneous data. On the other hand, cloud computing is a convenient and efficient processing model for storing and processing data. Still, the increasing demand for real-time and delay-sensitive applications is increasing day by day. Due to network bandwidth limitations, these problems cannot be solved using cloud computing alone. A fog layer located between the IoT devices and the cloud computing layer has been proposed to overcome the problem of resource constraints in mobile devices. delay-sensitive applications run that require more volume and power resources. In this paper, end-to-end architecture for integrating IoT, fog, and cloud layers into a large-scale dispatched application is proposed to support high availability to make efficient use of fog-cloud resources and achieve the appropriate quality of service (QoS) in terms of delay and failure probability criteria. The mentioned architecture consists of three hierarchal layers: IoT devices, fog nodes, and cloud data centers. Depending on the processing power of each layer's resources, user requests may be executed on the same layer or sent to a higher layer. Then, quality characteristics such as availability, performance, and interoperability for the proposed architecture are evaluated by the ATAM scenario-based method. The basis of architectural evaluation and analysis in this method is the study of the requirements and the quality characteristics of the system architecture.
Computer Networks and Distributed Systems
Mohsen Raji; Saeed Keshavarzi; Mehran Farvardin
Articles in Press, Accepted Manuscript, Available Online from 07 November 2022
Abstract
A Wireless Sensor Network (WSN) is consisted of thousands of sensor nodes to monitor environmental conditions. Energy plays a major role in these networks because nodes are worked with batteries and are sometimes placed in an inconsistent environment where their battery cannot be charged or replaced. ...
Read More
A Wireless Sensor Network (WSN) is consisted of thousands of sensor nodes to monitor environmental conditions. Energy plays a major role in these networks because nodes are worked with batteries and are sometimes placed in an inconsistent environment where their battery cannot be charged or replaced. In this paper, a new dynamic clustering method is presented for WSNs with moving targets. In this method, target tracking is carried out using the speed and direction of target movement as well as selection of the optimal cluster-head (CH) using the artificial bee colony (ABC) meta-heuristic algorithm with fuzzy TOPSIS. In the proposed CH selection method, three criteria are considered; i.e. the remaining energy of the node, the cost of selecting each node as the CH, and the risk of hardware failure of each node. Since each of these criteria should be assigned with a suitable weight, ABC optimization algorithm is used to find the best weights for ranking decisions. After specifying the objective function in the ABC algorithm and weighting the criteria, fuzzy TOPSIS algorithm is used and each of the nodes is fuzzified in each of the criteria that are normalized and weighted. The results show that in addition to maintaining the accuracy of tracking the moving target, the proposed method achieves a 5.4% improvement in network energy consumption in comparison with a state-of-the-art method called EEAC.
Computer Networks and Distributed Systems
Sara Mohammadi; Parvaneh Asghari; Amir Masoud Rahmani
Articles in Press, Accepted Manuscript, Available Online from 02 December 2022
Abstract
As a new technology, cloud computing is a key part of making systems more efficient and better and improving the Internet of Things. One of the significant challenges in fog computing is trust management, taking into account the processing, storage, and network constraints of fog devices. This study ...
Read More
As a new technology, cloud computing is a key part of making systems more efficient and better and improving the Internet of Things. One of the significant challenges in fog computing is trust management, taking into account the processing, storage, and network constraints of fog devices. This study suggests that a multi-objective imperialist competitive optimization algorithm be used to increase trust and decrease response time in fog environments. After formulating trust, delay, and accuracy, the multi-objective imperialist competitive optimization algorithm is developed and evaluated for fog server selection. Evaluations show that the proposed method is more efficient and works well in terms of accuracy, delay, and trust than other algorithms.