| الإنجليزية | العربية | الرئسية | تسجيل الدخول |

البحوث العلمية

2021

Oversampling Method Based on Gaussian Distribution and K-Means Clustering

2021-06
Computers, Materials and Continua (القضية : 1) (الحجم : 69)
Learning from imbalanced data is one of the greatest challenging problems in binary classification, and this problem has gained more importance in recent years. When the class distribution is imbalanced, classical machine learning algorithms tend to move strongly towards the majority class and disregard the minority. Therefore, the accuracy may be high, but the model cannot recognize data instances in the minority class to classify them, leading to many misclassifications. Different methods have been proposed in the literature to handle the imbalance problem, but most are complicated and tend to simulate unnecessary noise. In this paper, we propose a simple oversampling method based on Multivariate Gaussian distribution and K-means clustering, called GK-Means. The new method aims to avoid generating noise and control imbalances between and within classes. Various experiments have been carried out with six classifiers and four oversampling methods. Experimental results on different imbalanced datasets show that the proposed GK-Means outperforms other oversampling methods and improves classification performance as measured by F1-score and Accuracy.

Rule Mining Using Particle Swarm Optimization for Intrusion Detection Systems

2021-04
Uludağ University Journal of The Faculty of Engineering (القضية : 1) (الحجم : 26)
Traditional data mining techniques are commonly used to build the Intrusion Detection Systems IDSs. They are designed on the basis of some probabilistic methods that still do not take into account some of the important properties of each feature in the dataset. We believe that each feature in the dataset has its own crucial role for its characteristics, which should be taken into consideration. In this work, instead of using the traditional technique or applying feature selection methods we proposed max and min boundary mining approach to solve Anomaly Intrusion Detection System AIDS problem. The main idea of the proposed method is to handle each feature in the dataset independently extracting two important properties represented by max-boundary and min-boundary. First, Particle Swarm Optimization PSO is used to search for the optimal max and min boundary for each feature in each class from the train data set. Second, the generated max and min boundaries are used as detection rules in order to detect anomalies from normal behavior using test dataset. KDD Cup 99 and the new version of KDD Cup 99 called NSL-KDD datasets are used to test the proposed model and its performance is compared with four well-known techniques such as J48, Naïve Bayes, PART and SMO. In addition, performance is also compared with some recent work. Experiment results show that the proposed model is outperformed all other algorithms in all terms (true positive rate, false positive rate, f-measure, Recall, Precision, MCC and AUC).

Face Recognition Based on Gabor Feature Extraction Followed by FastICA and LDA

2021-04
Computers, Materials and Continua (القضية : 2) (الحجم : 68)
Over the past few decades, face recognition has become the most effective biometric technique in recognizing people's identity, as it is widely used in many areas of our daily lives. However, it is a challenging technique since facial images vary in rotations, expressions, and illuminations. To minimize the impact of these challenges, exploiting information from various feature extraction methods is recommended since one of the most critical tasks in face recognition system is the extraction of facial features. Therefore, this paper presents a new approach to face recognition based on the fusion of Gabor-based feature extraction, Fast Independent Component Analysis (Fas-tICA), and Linear Discriminant Analysis (LDA). In the presented method, first, face images are transformed to grayscale and resized to have a uniform size. After that, facial features are extracted from the aligned face image using Gabor, FastICA, and LDA methods. Finally, the nearest distance classifier is utilized to recognize the identity of the individuals. Here, the performance of six distance classifiers, namely Euclidean, Cosine, Bray-Curtis, Mahalanobis, Correlation, and Manhattan, are investigated. Experimental results revealed that the presented method attains a higher rank-one recognition rate compared to the recent approaches in the literature on four benchmarked face datasets: ORL, GT, FEI, and Yale. Moreover, it showed that the proposed method not only helps in better extracting the features but also in improving the overall efficiency of the facial recognition system.
2020

OPTIMIZATION ALGORITHMS FOR INTRUSION DETECTION SYSTEM: A REVIEW

2020-08
International Journal of Research-GRANTHAALAYAH (القضية : 8) (الحجم : 8)
With the growth and development of the Internet, the devices and the hosts connected to the Internet have become the target for attackers and intruders. Consequently, the integrity of systems and data has become more sophisticated. Meanwhile, many institutions suffer from money-losing or other losses due to attacks on computer systems. Accordingly, the detection of intrusion and attacks has become a challenge and a vital necessity at the same time. Many different methods were used to build intrusion detection systems (IDSs), and all these methods seek to a plus the efficiency of intrusion detection systems. This paper is a survey which tries to covers some of the optimization algorithms used in the field of intrusion detection in past ten years such as Artificial Bee Colony (ABC), Genetic Algorithm (GA), Cuttlefish Algorithms (CFA), and Particle Swarm Optimization (PSO). It is hoped that this review will provide useful insights about the intrusion detection literature and is a good source for anyone interested in applying one of the used optimization algorithms in the field of intrusion detection.

Rule Mining Using Particle Swarm Optimization for Intrusion Detection Systems

2020-08
Academic Journal of Nawroz University (القضية : 2) (الحجم : 9)
Traditional data mining techniques are commonly used to build the Intrusion Detection Systems IDSs. They are designed on the basis of some probabilistic methods that still do not take into account some of the important properties of each feature in the dataset. We believe that each feature in the dataset has its own crucial role for its characteristics, which should be taken into consideration. In this work, instead of using the traditional technique or applying feature selection methods we proposed max and min boundary mining approach to solve Anomaly Intrusion Detection System AIDS problem. The main idea of the proposed method is to handle each feature in the dataset independently extracting two important properties represented by max-boundary and min-boundary. First, Particle Swarm Optimization PSO is used to search for the optimal max and min boundary for each feature in each class from the train data set. Second, the generated max and min boundaries are used as detection rules in order to detect anomalies from normal behavior using test dataset. KDD Cup 99 and the new version of KDD Cup 99 called NSL-KDD datasets are used to test the proposed model and its performance is compared with four well-known techniques such as J48, Naïve Bayes, PART and SMO. In addition, performance is also compared with some recent work. Experiment results show that the proposed model is outperformed all other algorithms in all terms (true positive rate, false positive rate, f-measure, Recall, Precision, MCC and AUC).
2019

A new clustering method based on the bio-inspired cuttlefish optimization algorithm

2019-12
Expert Systems
Most of the well-known clustering methods based on distance measures, distance metrics and similarity functions have the main problem of getting stuck in the local optima and their performance strongly depends on the initial values of the cluster centers. This paper presents a new approach to enhance the clustering problems with the bio-inspired Cuttlefish Algorithm (CFA) by searching the best cluster centers that can minimize the clustering metrics. Various UCI Machine Learning Repository datasets are used to test and evaluate the performance of the proposed method. For the sake of comparison, we have also analysed several algorithms such as K-means, Genetic Algorithm and the Particle Swarm Optimization (PSO) Algorithm. The simulations and obtained results demonstrate that the performance of the proposed CFAClustering method is superior to the other counterpart algorithms in most cases. Therefore, the CFA can be considered as an alternative stochastic method to solve clustering problems.

New Data Hiding Approach Based on Biological Functionality of DNA Sequence

2019-12
Science Journal of University of Zakho (القضية : 4) (الحجم : 7)
Data hiding or steganography has been used ever since a secret message was needed to be transferred. Data hiding methods need a medium to be cover for secret message that is to be sent. Different mediums are used such as image, video, audio, and last decade the deoxyribose nucleic acid (DNA). In this paper, a new data hiding approach based on the DNA sequence is proposed. Unlike many existing methods, the proposed method does not change the biological functionality of the DNA reference sequence when the sequence is translated into amino acids. The proposed method is consisting of two steps: the first step is encrypting the message using the Toffoli quantum gate. The second step is embedding the encrypted message into DNA sequence by taking one codon at a time and considering amino acids' biological functionality during the embedding process. Experimental results show that the proposed method outperforms the existing schemes preserving biological functionality in terms of cracking probability, and hiding capacity for bit per nucleotide.
2018

Publication Preview Source A New Message Encryption Method based on Amino Acid Sequences and Genetic Codes

2018-01
International Journal of Advanced Computer Science and Applications, (القضية : 9) (الحجم : 8)
As the use of technology is increasing rapidly, the amount of shared, sent, and received information is also increasing in the same way. As a result, this necessitates the need for finding techniques that can save and secure the information over the net. There are many methods that have been used to protect the information such as hiding information and encryption. In this study, we propose a new encryption method making use of amino acid and DNA sequences. In addition, several criteria including data size, key size and the probability of cracking are used to evaluate the proposed method. The results show that the performance of the proposed method is better than many common encryption methods, such as RSA in terms of evaluation criteria.

A New Message Encryption Method based on Amino Acid Sequences and Genetic Codes

2018-01
International Journal of Advanced Computer Science and Applications (القضية : 8) (الحجم : 9)
As the use of technology is increasing rapidly, the amount of shared, sent, and received information is also increasing in the same way. As a result, this necessitates the need for finding techniques that can save and secure the information over the net. There are many methods that have been used to protect information such as hiding information and encryption. In this study, we propose a new encryption method making use of amino acid and DNA sequences. In addition, several criteria including data size, key size and the probability of cracking are used to evaluate the proposed method. The results show that the performance of the proposed method is better than many common encryption methods, such as RSA in terms of evaluation criteria.
2017

A DIDS Based on The Combination of Cuttlefish Algorithm and Decision Tree

2017-12
Science Journal of University of Zakho (القضية : 4) (الحجم : 5)
Different Distributed Intrusion Detection Systems (DIDS) based on mobile agents have been proposed in recent years to protect computer systems from intruders. Since intrusion detection systems deal with a large amount of data, keeping the best quality of features that represent the whole data and removing the redundant and irrelevant features are important tasks in these systems. In this paper, a novel DIDS based on the combination of Cuttlefish Optimization Algorithm (CFA) and Decision Tree (DT) is proposed. The proposed system uses an agent called Rule and Feature Generator Agent (RFGA)for reducing the dimensionality of the data by generating a subset of features with their corresponding rules. RFGA agent uses CFA to search for the optimal subset of features, while DT is used as a measurement on the selected features. The proposed model is tested on the KDD Cup 99 dataset. The obtained results show that the proposed system gives a better performance even with a small subset of 5 features when compared with the using all 41 features.

Normalization Methods For Backpropagation: A Comparative Study

2017-12
Science Journal of University of Zakho (القضية : 4) (الحجم : 5)
Neural Networks (NN) have been used by many researchers to solve problems in several domains including classification and pattern recognition, and Backpropagation (BP) which is one of the most well-known artificial neural network models. Constructing effective NN applications relies on some characteristics such as the network topology, learning parameter, and normalization approaches for the input and the output vectors. The Input and the output vectors for BP need to be normalized properly in order to achieve the best performance of the network. This paper applies several normalization methods on several UCI datasets and comparing between them to find the best normalization method that works better with BP. Norm, Decimal scaling, Mean-Man, Median-Mad, Min-Max, and Z-score normalization are considered in this study. The comparative study shows that the performance of Mean-Mad and Median-Mad is better than all remaining methods. On the other hand, the worst result is produced with Norm method.
2015

A novel feature-selection approach based on the cuttlefish optimization algorithm for intrusion detection systems

2015-04
Expert Systems with Applications (القضية : 5) (الحجم : 42)
This paper presents a new feature-selection approach based on the cuttlefish optimization algorithm which is used for intrusion detection systems (IDSs). Because IDSs deal with a large amount of data, one of the crucial tasks of IDSs is to keep the best quality of features that represent the whole data and remove the redundant and irrelevant features. The proposed model uses the cuttlefish algorithm (CFA) as a search strategy to ascertain the optimal subset of features and the decision tree (DT) classifier as a judgment on the selected features that are produced by the CFA. The KDD Cup 99 dataset is used to evaluate the proposed model. The results show that the feature subset obtained by using CFA gives a higher detection rate and accuracy rate with a lower false alarm rate when compared with the obtained results using all features.

A new feature selection model based on ID3 and bees algorithm for intrusion detection system

2015-02
Turkish Journal of Electrical Engineering & Computer Sciences (القضية : 2) (الحجم : 23)
Intrusion detection systems (IDSs) have become a necessary component of computers and information security framework. IDSs commonly deal with a large amount of data traffic and these data may contain redundant and unimportant features. Choosing the best quality of features that represent all of the data and exclude the redundant features is a crucial topic in IDSs. In this paper, a new combination approach based on the ID3 algorithm and the bees algorithm (BA) is proposed to select the optimal subset of features for an IDS. The BA is used to generate a subset of features, and the ID3 algorithm is used as a classi er. The proposed model is applied to KDD Cup 99 dataset. The obtained results show that the feature subset generated by the proposed ID3-BA gives a higher accuracy and detection rate with a lower false alarm rate when compared to the results obtained by using all features.
2011

Intrusion Detection System Based on Neural Networks Using Bipolar Input with Bipolar Sigmoid Activation Function

2011-12
af. J. of Comp. & Math’s (القضية : 2) (الحجم : 8)
Vulnerabilities in common security components such as firewalls are inevitable. Intrusion Detection Systems (IDS) are used as another wall to protect computer systems and to identify corresponding vulnerabilities. The purpose of this paper is to use the Backpropagation algorithm for IDS by applying bipolar input “input is represented as (1, -1)”, and bipolar sigmoid activation function. The KDD Cup 99 dataset is used in this paper. The number of train dataset is 4947 connection records, and the number of test dataset is 3117 connection records. The results of the proposed method show that the PSP is 88.32 and CPT equal to 0.286.

Intrusion Detection System Based on Decision Tree and Clustered Continuous Inputs

2011-11
Raf. J. of Comp. & Math’ (القضية : 1) (الحجم : 8)
With the rapid expansion of computer networks during the past decade, security has become a crucial issue for computer systems. Different soft-computing based methods have been proposed in recent years for the development of intrusion detection systems (IDSs). The purpose of this paper is to use ID3 algorithm for IDS and extend it to deal not only with discrete values but also with continuous ones, by using K_mean algorithm to partition each continuous attribute values to three clusters. The full 10% KDD Cup 99 train dataset and the full Correct test dataset are used. The results of the proposed method show an improvement in the performance as compared to standard ID3 using classical partition method.

Intrusion Detection and Attack Classifier Based on Three Techniques: A Comparative Study

2011-01
Eng. & Tech. Journal, (القضية : 2) (الحجم : 29)
Different soft-computing based methods have been proposed in recent years for the development of intrusion detection systems. The purpose of this work is to develop, implement and evaluate an anomaly off-line based intrusion detection system using three techniques; data mining association rules, decision trees, and artificial neural network, then comparing among them to decide which technique is better in its performance for the intrusion detection system. Several methods have been proposed to modify these techniques to improve the classification process. For association rules, the majority vote classifier was modified to build a new classifier that can recognize anomalies. With decision trees, ID3 algorithm was modified to deal not only with discrete values but also to deal with numerical values. For neural networks, a back-propagation algorithm has been used as the learning algorithm with a different number of input patterns (118, 51, and 41) to introduce the important knowledge about the intruder to the neural networks. Different types of normalization methods were applied to the input patterns to speed up the learning process. The full 10% KDD Cup 99 train dataset and the full correct test dataset are used in this work. The results of the proposed techniques show that there is an improvement in the performance compared to the standard techniques, furthermore, the Percentage of Successful Prediction (PSP) and Cost Per Test (CPT) of neural networks and decision trees are better than association rules. On the other hand, the training time for the neural network takes longer time than the decision trees.
2009

Cuttlefish Algorithm – A Novel Bio-InspiredOptimization Algorithm

2009-09
International Journal of Scientific & Engineering Research (القضية : 9) (الحجم : 4)
In this paper, a new meta-heuristic bio-inspired optimization algorithm, called Cuttlefish Algorithm (CFA) is presented. The algorithm mimics the mechanism of color changing behavior used by the cuttlefish to solve numerical global optimization problems. The patterns and colors seen in cuttlefish are produced by reflected light from different layers of cells including (chromatophores, leucophores, and iridophores) stacked together, and it is the combination of certain cells at once that allows cuttlefish to possess such a large array of patterns and colors. The proposed algorithm considers two main processes: reflection and visibility. Reflection process is proposed to simulate the light reflection mechanism used by these three layers, while the visibility is proposed to simulate the visibility of matching pattern used by the cuttlefish. These two processes are used as a search strategy to find the global optimal solution. The efficiency of this algorithm is also tested with some other popular biology inspired optimization algorithms such as Genetic Algorithms (GA), Particle Swarm Optimization (PSO) and Bees Algorithm (BA) that have been previously proposed in the literature. Simulations and obtained results indicate that the proposed CFA is superior to other algorithms.
2008

Reduction of Associated noise of hiding in sound file

2008-01
Raf. J. of Comp. & Math’s (القضية : 9) (الحجم : 9)
Nois

الرجوع