Ravie Chandren Muniyandi

Improving Bee Algorithm Based Feature Selection in Intrusion Detection System Using Membrane Computing

Despite the great benefits accruable from the debut of computer and the internet, efforts are constantly being put up by fraudulent and mischievous individuals to compromise the integrity, confidentiality or availability of electronic information systems. In Cyber-security parlance, this is termed ‘intrusion’. Hence, this has necessitated the introduction of Intrusion Detection Systems (IDS) to help detect and curb different types of attack. However, based on the high volume of data traffic involved in a network system, effects of redundant and irrelevant data should be minimized if a qualitative intrusion detection mechanism is genuinely desirous. Several attempts, especially feature subset selection approach using Bee Algorithm (BA), Linear Genetic Programming (LGP), Support Vector Decision Function Ranking (SVDF), Rough, Rough-DPSO, and Mutivariate Regression Splines (MARS) have been advanced in the past to measure the dependability and quality of a typical IDS. The observed problem among these approaches has to do with their general performance. This has therefore motivated this research work. We hereby propose a new but robust algorithm called membrane algorithm to improve the Bee Algorithm based feature subset selection technique. This Membrane computing paradigm is a class of parallel computing devices. Data used were taken from KDD-Cup 99 Dataset which is the acceptable standard benchmark for intrusion detection. When the final results were compared to those of the existing approaches, using the three standard IDS measurements-Attack Detection, False Alarm and Classification Accuracy Rates, it was discovered that Bee Algorithm-Membrane Computing (BA-MC) approach is a better technique. This is because our approach produced very high attack detection rate of 89.11%, classification accuracy of 95.60% and also generated a reasonable decrease in false alarm rate of 0.004. Receiver Operating Characteristic (ROC) curve was used for results interpretation.

MEMBRANE COMPUTING INSPIRED GENETIC ALGORITHM ON MULTI-CORE PROCESSORS

Membrane computing is a branch of natural computing. Several studies have recently attempted to utilize the structure of membrane computing to improve intelligent algorithms. These studies have applied communication rules in membrane models to facilitate information exchange between membranes, thereby improving the performance of those algorithms. However, parallel membrane computing has not yet been considered. This study proposes a membrane computing-inspired genetic algorithm. Similar to previous studies, the algorithm also uses communication rules to facilitate information exchange. In this study, an appropriate membrane computing-inspired genetic algorithm is defined, in which each membrane can be executed over different cores in a parallel manner. The proposed algorithm can be executed over different cores and uses multi-core processing to implement parallel membrane computation. Simulation with a Colville minimization problem shows that the membrane computing inspired genetic algorithm has improved performance, with a mean error of the solution 61.9 times better than genetic algorithm.

A parallel membrane inspired harmony search for optimization problems

Display Omitted Harmony Search is enhanced by improving the speed of convergence while preventing premature convergence to a local minimum.Membrane computing model is employed to execute parallelized HS efficiently to increase the diversity of HS and improving the performance of HS.Simulation results showed that the application of the proposed approach to different variants of harmony search yielded better performance than previous approaches.We applied the parallel membrane-inspired HS to the flexible job shop scheduling problem and well-known benchmark instances to demonstrate the effectiveness of the proposed algorithm. Harmony search is an emerging meta-heuristic optimization algorithm that is inspired by musical improvisation processes, and it can solve various optimization problems. Membrane computing is a distributed and parallel model for solving hard optimization problems. First, we employed some previously proposed approaches to improve standard harmony search by allowing its parameters to be adaptive during the processing steps. Information from the best solutions was used to improve the speed of convergence while preventing premature convergence to a local minimum. Second, we introduced a parallel framework based on membrane computing to improve the harmony search. Our approach utilized the parallel membrane computing model to execute parallelized harmony search efficiently on different cores, where the membrane computing communication characteristics were used to exchange information between the solutions on different cores, thereby increasing the diversity of harmony search and improving the performance of harmony search. Our simulation results showed that the application of the proposed approach to different variants of harmony search yielded better performance than previous approaches. Furthermore, we applied the parallel membrane inspired harmony search to the flexible job shop scheduling problem. Experiments using well-known benchmark instances showed the effectiveness of the algorithm.

Accelerated execution of P systems with active membranes to solve the N-queens problem

The N-queens problem has attracted increasing attention because of its potential applications in different areas, such as parallel memory storage approaches, image processing, and physical and chemical studies. Local search is a powerful method for solving real problems, such as the N-queens problem. Recently, models of P systems with active membranes have been used for local search to solve the N-queens problem. However, there have been insufficient studies of the parallelism of the P-system models with active membranes. In addition, the active membrane systems defined for N queens have several individual membranes that contain one object and no internal rules in each membrane, as well as several communication rules among membranes, which reduce the execution speed. In this study, a new P system model with active membranes is defined for solving the N-queens problem, and multi-core simulation of the proposed membrane system allows the execution of alternative computations in parallel, thus reducing the average time for finding a successful computation. The speed of the proposed model was compared with previous models that used P systems with active membranes for local search. The model contains two membranes, but the inclusion of several objects and rules within each membrane increases the parallelism and performance. This model reduces the number of communication rules required among membranes, and increases the execution speed. This model also increases the parallelism of previous P systems with active membranes when several rules evolve concurrently and more than one queen is exchanged during each step to reach a solution. Multi-core processing has been used to decrease the probability of restarting the P systems and to decrease processing time by distributing the processing of the active membrane on the multi-core. The speed of the proposed model when solving N = 200 queens was almost 1000 times faster than previous methods.

Parallel and distributed computing models on a graphics processing unit to accelerate simulation of membrane systems

Abstract Membrane systems are parallel distributed computing models that are used in a wide variety of areas. Use of a sequential machine to simulate membrane systems loses the advantage of parallelism in Membrane Computing. In this paper, an innovative classification algorithm based on a weighted network is introduced. Two new algorithms have been proposed for simulating membrane systems models on a Graphics Processing Unit (GPU). Communication and synchronization between threads and thread blocks in a GPU are time-consuming processes. In previous studies, dependent objects were assigned to different threads. This increases the need for communication between threads, and as a result, performance decreases. In previous studies, dependent membranes have also been assigned to different thread blocks, requiring inter-block communications and decreasing performance. The speedup of the proposed algorithm on a GPU that classifies dependent objects using a sequential approach, for example with 512 objects per membrane, was 82×, while for the previous approach ( Algorithm 1 ), it was 8.2×. For a membrane system with high dependency among membranes, the speedup of the second proposed algorithm ( Algorithm 3 ) was 12×, while for the previous approach ( Algorithm 1 ) and the first proposed algorithm ( Algorithm 2 ) that assign each membrane to one thread block, it was 1.8×.

Accelerated Simulation of Membrane Computing to Solve the N-queens Problem on Multi-core

Membrane computing or P Systems are distributed and parallel computing device that inspired their computation from cell biology. In this study, a new model of membrane computing with active membranes is defined for solving the N-queens problem. The model contains two membranes, but the inclusion of several objects and rules within each membrane. This model increases the parallelism of previous Membrane computing with active membranes because several rules can evolve concurrently and more than one queen can be exchanged during each step. Number of communication rules are also decreased. Communication rules decrease speed on multi-core processing because communications and synchronizations between threads and cores that are necessary for communication rules are very time consuming process. Multi-core processing is used to exploit the parallelism of membrane computing for solving N-queens problem.

Converting differential-equation models of biological systems to membrane computing

This paper presents a method to convert the deterministic, continuous representation of a biological system by ordinary differential equations into a non-deterministic, discrete membrane computation. The dynamics of the membrane computation is governed by rewrite rules operating at certain rates. That has the advantage of applying accurately to small systems, and to expressing rates of change that are determined locally, by region, but not necessary globally. Such spatial information augments the standard differentiable approach to provide a more realistic model. A biological case study of the ligand-receptor network of protein TGF-β is used to validate the effectiveness of the conversion method. It demonstrates the sense in which the behaviours and properties of the system are better preserved in the membrane computing model, suggesting that the proposed conversion method may prove useful for biological systems in particular.

A Hybrid Membrane Computing and Honey Bee Mating Algorithm as an Intelligent Algorithm for Channel Assignment Problem

Membrane computing is a model of computation inspired by the structure and functioning of cells as living organisms. Membrane computing naturally has parallel structure. Also, it uses communication rules to exchange information between membranes. This paper first proposes Hybrid Honey Bee Mating (HHBM) then uses parallelism advantage of membrane to parallelize and divide the HHBM algorithm as an evolutionary algorithm to different membranes (parts). These membranes can be executed in parallel way on different cores or CPUs. Simulation shows that when number of membrane increases performance of this algorithm increases.

A Membrane Computing Model for Generation of Picture Arrays

In the bio-inspired area of membrane computing, P system is a versatile model providing a rich framework for many computational problems. Array P system and its variant with parallel rewriting facilitate the study of picture languages within this area of membrane computing. Here another variant of array P system, called tabled parallel array P system (TPAP), is introduced, by endowing it with the features of parallel rewriting and tables of array-rewriting rules. The generative power of TPAP as well as the ability of this system in describing picture patterns are investigated.

DETECTING ABNORMAL BEHAVIOR IN SOCIAL NETWORK WEBSITES BY USING A PROCESS MINING TECHNIQUE

Detecting abnormal user activity in social network websites could prevent from cyber-crime occurrence. The previous research focused on data mining while this research is based on user behavior process. In this study, the first step is defining a normal user beh avioral pattern and the second step is detecting ab normal behavior. These two steps are applied on a case stu dy that includes real and syntactic data sets to ob tain more tangible results. The chosen technique used to define the pattern is process mining, which is an affordable, complete and noise-free event log. The proposed model discovers a normal behavior by genetic process mining technique and abnormal activities ar e detected by the fitness function, which is based on Petri Net rules. Although applying genetic mining is time consuming process, it can overcome the risk s of noisy data and produces a comprehensive normal model in Petri net representation form.