A Multi-Agent Based Decentralized Algorithm for Social Network Community Mining

2009 ◽  
Author(s):  
Bo Yang ◽  
Jing Huang ◽  
Dayou Liu ◽  
Jiming Liu
Keyword(s):  
Social Network ◽  
Agent Based ◽  
Network Community ◽  
Multi Agent ◽  
Community Mining

scholarly journals Distributed recommender system using multi-agent for social networks

2021 ◽  
Author(s):  
Lubaid Ahmed
Keyword(s):  
Social Networks ◽  
Social Network ◽  
Recommender Systems ◽  
Recommender System ◽  
Network Simulator ◽  
Clustering Methods ◽  
Agent Based Simulation ◽  
Agent Based ◽  
Data Mining Algorithms ◽  
Multi Agent

Social networks have become significant tools due to the vast and useful information existing in them. The social platforms also act as the storage of entered choices of millions of users for various applications such as political surveys, research studies, marketing product preferences and many more. Social network recommender systems exploit this information and direct users in selecting their choices. It is clear that recommender systems should be efficient enough to be able to process the huge magnitude of data that has been generated in recent years by social network users. This research proposes a foundation of an efficient and scalable recommender system to be able to process large amount of data (i.e. Big data) in a short amount of time. The main goal is providing scalability and efficiency of the recommender system. The simulation of the prototype of such a distributed recommender system by using multi-agent based technologies shows promising results. These prototypes provide recommendations to users about other users with the similar interests in online and distributed manner as real recommender systems. The agents can simulate users or can be used as the containers of algorithms for comparing the similarity between users by different approaches, such as cosine similarity and clustering methods for testing and examining real scenarios. To be able to test these prototypes in agent-based simulation environment an agent-based framework is developed. This framework has three modules named social network crawler, social network simulator and employed prototype of the distributed recommender system that use different text and data mining algorithms. Finally, newly developed performance metric (called Scalability Factor) is introduced that shows the minimum number of servers needed to be able to run the agent systems in parallel. This thesis shows using a distributed and parallel model for recommender systems is the key to increase the speed of recommendation convergence and as a result to provide scalability. Multi-agent based simulation results, coupled with numerical analysis affirm that the proposed solution provides scalability and efficiency for recommender systems.

scholarly journals Distributed recommender system using multi-agent for social networks

2021 ◽  
Author(s):  
Lubaid Ahmed
Keyword(s):  
Social Networks ◽  
Social Network ◽  
Recommender Systems ◽  
Recommender System ◽  
Network Simulator ◽  
Clustering Methods ◽  
Agent Based Simulation ◽  
Agent Based ◽  
Data Mining Algorithms ◽  
Multi Agent

Social networks have become significant tools due to the vast and useful information existing in them. The social platforms also act as the storage of entered choices of millions of users for various applications such as political surveys, research studies, marketing product preferences and many more. Social network recommender systems exploit this information and direct users in selecting their choices. It is clear that recommender systems should be efficient enough to be able to process the huge magnitude of data that has been generated in recent years by social network users. This research proposes a foundation of an efficient and scalable recommender system to be able to process large amount of data (i.e. Big data) in a short amount of time. The main goal is providing scalability and efficiency of the recommender system. The simulation of the prototype of such a distributed recommender system by using multi-agent based technologies shows promising results. These prototypes provide recommendations to users about other users with the similar interests in online and distributed manner as real recommender systems. The agents can simulate users or can be used as the containers of algorithms for comparing the similarity between users by different approaches, such as cosine similarity and clustering methods for testing and examining real scenarios. To be able to test these prototypes in agent-based simulation environment an agent-based framework is developed. This framework has three modules named social network crawler, social network simulator and employed prototype of the distributed recommender system that use different text and data mining algorithms. Finally, newly developed performance metric (called Scalability Factor) is introduced that shows the minimum number of servers needed to be able to run the agent systems in parallel. This thesis shows using a distributed and parallel model for recommender systems is the key to increase the speed of recommendation convergence and as a result to provide scalability. Multi-agent based simulation results, coupled with numerical analysis affirm that the proposed solution provides scalability and efficiency for recommender systems.

A Multi-agent based Micro Grid Operation Method

2013 ◽  
Vol 133 (9) ◽  
pp. 1652-1657 ◽  
Author(s):  
Takeshi Nagata ◽  
Kosuke Kato ◽  
Masahiro Utatani ◽  
Yuji Ueda ◽  
Kazuya Okamoto ◽  
...  
Keyword(s):  
Agent Based ◽  
Operation Method ◽  
Multi Agent ◽  
Micro Grid ◽  
Grid Operation

Browser Security Attacks and Detection Techniques: A Case of Tabnabbing

2020 ◽  
Vol 8 (1) ◽  
pp. 33-41
Author(s):  
Dr. S. Sarika ◽  
Keyword(s):  
Credit Card ◽  
State Of The Art ◽  
Experimental Results ◽  
Detection Technique ◽  
Security Attacks ◽  
Agent Based ◽  
Detection Techniques ◽  
Browser Security ◽  
Cyber Threats ◽  
Multi Agent

Phishing is a malicious and deliberate act of sending counterfeit messages or mimicking a webpage. The goal is either to steal sensitive credentials like login information and credit card details or to install malware on a victim’s machine. Browser-based cyber threats have become one of the biggest concerns in networked architectures. The most prolific form of browser attack is tabnabbing which happens in inactive browser tabs. In a tabnabbing attack, a fake page disguises itself as a genuine page to steal data. This paper presents a multi agent based tabnabbing detection technique. The method detects heuristic changes in a webpage when a tabnabbing attack happens and give a warning to the user. Experimental results show that the method performs better when compared with state of the art tabnabbing detection techniques.

Sign in / Sign up

Export Citation Format

Share Document