2020 Innovations in Intelligent Systems and Applications Conference (ASYU)
A network security simulation system is useful as a network security application in network secur... more A network security simulation system is useful as a network security application in network security training exercises. Also, the simulation system enables the system administrator to observe how changing different parameters and security restrictions can affect the security of a network. This paper presents a simulation system for security risk assessment for companies. An agent-based modeling paradigm is used for the implementation of the proposed simulation system. An agent-based system can estimate network security risks and provide a guide for effective policies in order to protect the network from attacks. The proposed system allows security professionals to simulate varying network environments, attacker and defender scenarios in accordance with different situations. Therefore, the proposed agent-based system captures companies’ network system dynamics that consist of interactions of multiple agents, including attackers and defenders that the system can use. The proposed model is evaluated through a case study in order to assess security risks for various security policies in a representative company’s network.
2018 26th Signal Processing and Communications Applications Conference (SIU), 2018
Analytical solutions are not possible due to the complexity and large-scale data sets of complex ... more Analytical solutions are not possible due to the complexity and large-scale data sets of complex systems. In order to facilitate the examination of these systems, agent based modeling and simulation techniques are often used. When studies done in recent years are examined, it is seen that meta-heuristic algorithms are often used for optimization with modeling and simulation. In this study, Artificial Bee Colonies algorithm is investigated for meta-heuristic algorithms for parameter calibration in complex systems with an optimization problem. The success of the parameter calibration process of complex systems has been tested with the Modified Artificial Bee Colonies Algorithm, which has been proven in this work.
The major problem encountered when modeling complex systems with agent-based modeling and simulat... more The major problem encountered when modeling complex systems with agent-based modeling and simulation techniques is the existence of large parameter spaces. A complex system model cannot be expected to reflect the whole of the real system, but by specifying the most appropriate parameters, the actual system can be represented by the model under certain conditions. When the studies conducted in recent years were reviewed, it has been observed that there are few studies for parameter tuning problem in agent based simulations, and these studies have focused on tuning parameters of a single model. In this study, an approach of parameter tuning is proposed by using metaheuristic algorithms such as Genetic Algorithm (GA), Particle Swarm Optimization (PSO), Artificial Bee Colonies (ABC), Firefly (FA) algorithms. With this hybrid structured study, the parameter tuning problems of the models in the different fields were solved. The new approach offered was tested in two different models, and ...
Agent-based modeling is a new computational model for social sciences. Computational models are f... more Agent-based modeling is a new computational model for social sciences. Computational models are formulated as computer programs which represent the processes that exist in the social world. When simulations of these computational models for social sciences are performed, it is possible to gather information about real systems' processes and predict future outcomes of the processes. The agent-based model includes a set of agents that represent real actors in a real system in the simulated environment. The simulated environment represents the environment in which the agents contain their resources and perform their actions. Agents interact with other agents and entities in the environment while they try to achieve their individual goals. In the present study, it is aimed to imitate the school environment in a simulation environment by using the Repast Simphony 2.4 simulation tool and observe the impact of science education on undesirable behaviors of students represented by agents...
In this study, parameter optimization studies in modeling and simulations performed in different ... more In this study, parameter optimization studies in modeling and simulations performed in different areas are examined. The common feature of all works are the modeling of systems which are difficult to observe their results in real environment and the problem of setting up large parameter space. The goal is to reflect the real system of the generated model, and it is necessary to select the most suitable parameters in the large parameter space. This is an important issue and is beyond the limits of human problem solving. From the work done, different classifications were developed to categorize the methods of parameter adjustment and to evaluate the existing work. This helps model developers to find the algorithm that produce the optimal solution for the parameter tunning problem that will arise in future modeling studies.
Agent Based Modelling and Simulation(ABMS) is increasingly used in order to analyze and model com... more Agent Based Modelling and Simulation(ABMS) is increasingly used in order to analyze and model complex systems. ABMS is a method in order to model and simulate Complex Systems which is very difficult to observe and analyze in environment. The main goal in ABMS is to analyze components of real systems, create models which show behaviours of real systems and includes minimum number of real systems’ properties, and uncover expected behaviours in real systems. Today, we know that cooperation of basic components of a system may result in complex phenomena's. Adaptive Multi Agent System (AMAS) theory has been developed to use cooperation as an engine for designing complex systems. While modelling a complex system in an agent based environment, the main goal of AMAS theory is to model interaction between agents and/or between agents and the environment in a cooperative manner. Moreover, the AMAS Theory enables a system to find its right configuration in an environment for its functional...
2017 9th International Conference on Computational Intelligence and Communication Networks (CICN), 2017
Modeling and simulation of real-world environments has in recent times being widely used. The mod... more Modeling and simulation of real-world environments has in recent times being widely used. The modeling of environments whose examination in particular is difficult and the examination via the model becomes easier. The parameters of the modeled systems and the values they can obtain are quite large, and manual tuning is tedious and requires a lot of effort while it often it is almost impossible to get the desired results. For this reason, there is a need for the parameter space to be set. The studies conducted in recent years were reviewed, it has been observed that there are few studies for parameter tuning problem in modeling and simulations. In this study, work has been done for a solution to be found to the problem of parameter tuning with swarm intelligence optimization algorithms Particle swarm optimization and Firefly algorithms. The performance of these algorithms in the parameter tuning process has been tested on 2 different agent based model studies. The performance of the ...
2016 Intl IEEE Conferences on Ubiquitous Intelligence & Computing, Advanced and Trusted Computing, Scalable Computing and Communications, Cloud and Big Data Computing, Internet of People, and Smart World Congress (UIC/ATC/ScalCom/CBDCom/IoP/SmartWorld), 2016
In this paper, we present an approach for adaptive replication to support fault tolerance. This a... more In this paper, we present an approach for adaptive replication to support fault tolerance. This approach uses a feedback control theory methodology within an adaptive replication infrastructure to determine replication degrees of replica groups. We implemented this approach in a multi-agent system to survive Byzantine failures. At the end of the paper, we also provide some experimental results to show
2012 International Symposium on Innovations in Intelligent Systems and Applications, 2012
ABSTRACT Adaptive replication increases the system's response time due to the need for mo... more ABSTRACT Adaptive replication increases the system's response time due to the need for monitoring in fault tolerant multi-agent systems. The sampling period is one of the key factors that could influence the cost of adaptive replication. In this paper, we show how to select an appropriate sampling period in a heuristic manner to decrease the cost incurred by adaptive replication.
2020 Innovations in Intelligent Systems and Applications Conference (ASYU)
A network security simulation system is useful as a network security application in network secur... more A network security simulation system is useful as a network security application in network security training exercises. Also, the simulation system enables the system administrator to observe how changing different parameters and security restrictions can affect the security of a network. This paper presents a simulation system for security risk assessment for companies. An agent-based modeling paradigm is used for the implementation of the proposed simulation system. An agent-based system can estimate network security risks and provide a guide for effective policies in order to protect the network from attacks. The proposed system allows security professionals to simulate varying network environments, attacker and defender scenarios in accordance with different situations. Therefore, the proposed agent-based system captures companies’ network system dynamics that consist of interactions of multiple agents, including attackers and defenders that the system can use. The proposed model is evaluated through a case study in order to assess security risks for various security policies in a representative company’s network.
2018 26th Signal Processing and Communications Applications Conference (SIU), 2018
Analytical solutions are not possible due to the complexity and large-scale data sets of complex ... more Analytical solutions are not possible due to the complexity and large-scale data sets of complex systems. In order to facilitate the examination of these systems, agent based modeling and simulation techniques are often used. When studies done in recent years are examined, it is seen that meta-heuristic algorithms are often used for optimization with modeling and simulation. In this study, Artificial Bee Colonies algorithm is investigated for meta-heuristic algorithms for parameter calibration in complex systems with an optimization problem. The success of the parameter calibration process of complex systems has been tested with the Modified Artificial Bee Colonies Algorithm, which has been proven in this work.
The major problem encountered when modeling complex systems with agent-based modeling and simulat... more The major problem encountered when modeling complex systems with agent-based modeling and simulation techniques is the existence of large parameter spaces. A complex system model cannot be expected to reflect the whole of the real system, but by specifying the most appropriate parameters, the actual system can be represented by the model under certain conditions. When the studies conducted in recent years were reviewed, it has been observed that there are few studies for parameter tuning problem in agent based simulations, and these studies have focused on tuning parameters of a single model. In this study, an approach of parameter tuning is proposed by using metaheuristic algorithms such as Genetic Algorithm (GA), Particle Swarm Optimization (PSO), Artificial Bee Colonies (ABC), Firefly (FA) algorithms. With this hybrid structured study, the parameter tuning problems of the models in the different fields were solved. The new approach offered was tested in two different models, and ...
Agent-based modeling is a new computational model for social sciences. Computational models are f... more Agent-based modeling is a new computational model for social sciences. Computational models are formulated as computer programs which represent the processes that exist in the social world. When simulations of these computational models for social sciences are performed, it is possible to gather information about real systems' processes and predict future outcomes of the processes. The agent-based model includes a set of agents that represent real actors in a real system in the simulated environment. The simulated environment represents the environment in which the agents contain their resources and perform their actions. Agents interact with other agents and entities in the environment while they try to achieve their individual goals. In the present study, it is aimed to imitate the school environment in a simulation environment by using the Repast Simphony 2.4 simulation tool and observe the impact of science education on undesirable behaviors of students represented by agents...
In this study, parameter optimization studies in modeling and simulations performed in different ... more In this study, parameter optimization studies in modeling and simulations performed in different areas are examined. The common feature of all works are the modeling of systems which are difficult to observe their results in real environment and the problem of setting up large parameter space. The goal is to reflect the real system of the generated model, and it is necessary to select the most suitable parameters in the large parameter space. This is an important issue and is beyond the limits of human problem solving. From the work done, different classifications were developed to categorize the methods of parameter adjustment and to evaluate the existing work. This helps model developers to find the algorithm that produce the optimal solution for the parameter tunning problem that will arise in future modeling studies.
Agent Based Modelling and Simulation(ABMS) is increasingly used in order to analyze and model com... more Agent Based Modelling and Simulation(ABMS) is increasingly used in order to analyze and model complex systems. ABMS is a method in order to model and simulate Complex Systems which is very difficult to observe and analyze in environment. The main goal in ABMS is to analyze components of real systems, create models which show behaviours of real systems and includes minimum number of real systems’ properties, and uncover expected behaviours in real systems. Today, we know that cooperation of basic components of a system may result in complex phenomena's. Adaptive Multi Agent System (AMAS) theory has been developed to use cooperation as an engine for designing complex systems. While modelling a complex system in an agent based environment, the main goal of AMAS theory is to model interaction between agents and/or between agents and the environment in a cooperative manner. Moreover, the AMAS Theory enables a system to find its right configuration in an environment for its functional...
2017 9th International Conference on Computational Intelligence and Communication Networks (CICN), 2017
Modeling and simulation of real-world environments has in recent times being widely used. The mod... more Modeling and simulation of real-world environments has in recent times being widely used. The modeling of environments whose examination in particular is difficult and the examination via the model becomes easier. The parameters of the modeled systems and the values they can obtain are quite large, and manual tuning is tedious and requires a lot of effort while it often it is almost impossible to get the desired results. For this reason, there is a need for the parameter space to be set. The studies conducted in recent years were reviewed, it has been observed that there are few studies for parameter tuning problem in modeling and simulations. In this study, work has been done for a solution to be found to the problem of parameter tuning with swarm intelligence optimization algorithms Particle swarm optimization and Firefly algorithms. The performance of these algorithms in the parameter tuning process has been tested on 2 different agent based model studies. The performance of the ...
2016 Intl IEEE Conferences on Ubiquitous Intelligence & Computing, Advanced and Trusted Computing, Scalable Computing and Communications, Cloud and Big Data Computing, Internet of People, and Smart World Congress (UIC/ATC/ScalCom/CBDCom/IoP/SmartWorld), 2016
In this paper, we present an approach for adaptive replication to support fault tolerance. This a... more In this paper, we present an approach for adaptive replication to support fault tolerance. This approach uses a feedback control theory methodology within an adaptive replication infrastructure to determine replication degrees of replica groups. We implemented this approach in a multi-agent system to survive Byzantine failures. At the end of the paper, we also provide some experimental results to show
2012 International Symposium on Innovations in Intelligent Systems and Applications, 2012
ABSTRACT Adaptive replication increases the system's response time due to the need for mo... more ABSTRACT Adaptive replication increases the system's response time due to the need for monitoring in fault tolerant multi-agent systems. The sampling period is one of the key factors that could influence the cost of adaptive replication. In this paper, we show how to select an appropriate sampling period in a heuristic manner to decrease the cost incurred by adaptive replication.
Uploads
Papers by Şebnem Bora