Unsupervised Binary BAT algorithm based Network Intrusion Detection System using enhanced multiple classifiers

Nowadays, along with network development, due to the threats of unknown sources, information communication is more vulnerable, and thus, more secured information is required. Intrusion Detection System (IDS) is very important for cybersecurity with the presence in particular of various networked computers' foundation. An efficient IDS apply machine learning method as computational technics to increase rates of detection to gain the high accuracy and low false alarms rate within the huge amounts of data. To increase the rate of detection, researcher usually implements the optimizer. Thus, in this research, a comprehensive experimental study is presented based on various binary to optimize the rate of detection and decrease the error. Moreover, Numerous researches have been conducted about intrusion detection systems with the old dataset such as Kddcup'99 dataset, and due to this reason, most of them did not get the potential accuracy to detect intrusion with the current intrusion as the old dataset is not covering the current attacks. Therefore, this research aims to A hybrid Anomaly Classification of IDS with Deep Learning (DL) and Binary Algorithms (BA) as Optimizer with the most updated dataset named "CICIDS2017" which can be used for the intrusion detection evaluation. Moreover, this research conducts the anomaly classification of IDS based on the deep neural network (DNN) as the Deep Learning (DL) platform and Binary Algorithms (BA) in terms of Binary Bat Algorithm (BBA), Binary Genetic Algorithm (BGA), Binary Gravitational Search Algorithm (BGSA) as optimizer to enhance the rates of detection. Some of the results which had been considered and achieved for DNN and the hybrid version (DNN and Binary Algorithms) are in terms of: Accuracy, Recall, Precision, Confusion Matrix, Sensitivity, Specificity, and Cost Error.

Feature selection is selecting a subset of optimal features. Feature selection is being used in high dimensional data reduction and it is being used in several applications like medical, image processing, text mining, etc. Several methods were introduced for unsupervised feature selection. Among those methods some are based on filter approach and some are based on wrapper approach. In the existing work, unsupervised feature selection methods using Genetic Algorithm, Particle Swarm Optimization with Relative Reduct, Quick Reduct and Ant Colony Optimization have been introduced. These methods yield better performance for unsupervised feature selection. In this paper we proposed a novel method to select subset of features from unlabeled data using binary bat algorithm with sum of squared error as the fitness function. The proposed method is then tested with various classification algorithms like decision tree, multilayer perceptron, support vector machine and clustering quality measures like sum of squared error. The results show that our proposed method gives more accuracy when compared with other optimization algorithm.

One of the important assets in a company is customers. Customers determine the company's stability because they are source of income and determine the company's competitiveness. It shows the importance of predicting which customers have the potential to switch to another company. These predictions can be done using Machine Learning (ML). One of ML methods is the Extreme Learning Machine (ELM). The advantages of ELM compared to other methods are fast computing time, ease of use, and can reach a global optimum. However, ELM has weaknesses when solving problems with high-dimensional datasets, so feature selection is required. The Binary Bat Algorithm (BBA) is a swarm intelligence method that can be used to optimize ELM performance. The advantages of BBA compared to other are few parameters and much better in effectiveness or accuracy. This research was carried out with preprocessing data, training data and testing data. The research results showed that ELM-BBA is better than ELM and ELM-Binary Particle Swarm Optimization (BPSO) in evaluation metric values. However, ELM-BBA tended to be slower than ELM-BPSO. The best results on evaluation metrics achieved by ELM-BBA were 0.97, 0.97, 0.96, and 0.97 in accuracy, precision, recall, and F1 score, respectively.

Data classification is a challenging problem. Data classification is very sensitive to the noise and high dimensionality of the data. Being able to reduce the model complexity can help to improve the accuracy of the classification model performance. Therefore, in this research, we propose a novel feature selection technique based on Binary Harris Hawks Optimizer with Time-Varying Scheme (BHHO-TVS). The proposed BHHO-TVS adopts a time-varying transfer function that is applied to leverage the influence of the location vector to balance the exploration and exploitation power of the HHO. Eighteen well-known datasets provided by the UCI repository were utilized to show the significance of the proposed approach. The reported results show that BHHO-TVS outperforms BHHO with traditional binarization schemes as well as other binary feature selection methods such as binary gravitational search algorithm (BGSA), binary particle swarm optimization (BPSO), binary bat algorithm (BBA), binary whale optimization algorithm (BWOA), and binary salp swarm algorithm (BSSA). Compared with other similar feature selection approaches introduced in previous studies, the proposed method achieves the best accuracy rates on 67% of datasets.

The quality of service (QoS) multicast routing problem is one of the main issues for transmission in communication networks. It is known to be an NP-hard problem, so many heuristic algorithms have been employed to solve the multicast routing problem and find the optimal multicast tree which satisfies the requirements of multiple QoS constraints such as delay, delay jitter, bandwidth and packet loss rate. In this paper, we propose an improved chaotic binary bat algorithm to solve the QoS multicast routing problem. We introduce two modification methods into the binary bat algorithm. First, we use the two most representative chaotic maps, namely the logistic map and the tent map, to determine the parameter [Formula: see text] of the pulse frequency [Formula: see text]. Second, we use a dynamic formulation to update the parameter α of the loudness [Formula: see text]. The aim of these modifications is to enhance the performance and the robustness of the binary bat algorithm and ensure the diversity of the solutions. The simulation results reveal the superiority, effectiveness and efficiency of our proposed algorithms compared with some well-known algorithms such as Genetic Algorithm (GA), Particle Swarm Optimization (PSO), Jumping Particle Swarm Optimization (JPSO), and Binary Bat Algorithm (BBA).

In this study, the binary bat algorithm (BBA) for structural topology optimization is implemented. The problem is to find the stiffest structure using a certain amount of material and some constraints using the bit-array representation method. A new filtering algorithm is proposed to make BBA find designs with no separated objects, no checkerboard patterns, less unusable material, and higher structural performance. A volition penalty function for topology optimization is also proposed to accelerate the convergence toward the optimal design. The main effect of using the BBA lies in the fact that the BBA is able to handle a large number of design variables in comparison with other well-known metaheuristic algorithms. Based on the numerical results of four benchmark problems in structural topology optimization for minimum compliance, the following conclusions are made: (1) The BBA with the proposed filtering algorithm and penalty function are effective in solving large-scale numerical topology optimization problems (fine finite elements mesh). (2) The proposed algorithm produces solid-void designs without gray areas, which makes them practical solutions that are applicable in manufacturing.

<p>Classification aims to identify a class label of an instance according to the information from its characteristics or features. Unfortunately, many classification problems have a large feature set containing irrelevant and redundant features, which reduce the classification performance. In order to address the above problem, feature selection is proposed to select a small subset of relevant features. There are three main types of feature selection methods, i.e. wrapper, embedded and filter approaches. Wrappers use a classification algorithm to evaluate candidate feature subsets. In embedded approaches, the selection process is embedded in the training process of a classification algorithm. Different from the other two approaches, filters do not involve any classification algorithm during the selection process. Feature selection is an important process but it is not an easy task due to its large search space and complex feature interactions. Because of the potential global search ability, Evolutionary Computation (EC), especially Particle Swarm Optimization (PSO), has been widely and successfully applied to feature selection. However, there is potential to improve the effectiveness and efficiency of EC-based feature selection. The overall goal of this thesis is to investigate and improve the capability of EC for feature selection to select small feature subsets while maintaining or even improving the classification performance compared to using all features. Different aspects of feature selection are considered in this thesis such as the number of objectives (single-objective/multi-objective), the fitness function (filter/wrapper), and the searching mechanism. This thesis introduces a new fitness function based on mutual information which is calculated by an estimation approach instead of the traditional counting approach. Results show that the estimation approach works well on both continuous and discrete data. More importantly, mutual information calculated by the estimation approach can capture feature interactions better than the traditional counting approach. This thesis develops a novel binary PSO algorithm, which is the first work to redefine some core concepts of PSO such as velocity and momentum to suit the characteristics of binary search spaces. Experimental results show that the proposed binary PSO algorithm evolve better solutions than other binary EC algorithms when the search spaces are large and complex. Specifically, on feature selection, the proposed binary PSO algorithm can select smaller feature subsets with similar or better classification accuracies, especially when there are a large number of features. This thesis proposes surrogate models for wrapper-based feature selection. The surrogate models use surrogate training sets which are subsets of informative instances selected from the training set. Experimental results show that the proposed surrogate models assist PSO to reduce the computational cost while maintaining or even improving the classification performance compared to using only the original training set. The thesis develops the first wrapper-based multi-objective feature selection algorithm using MOEA/D. A new decomposition strategy using multiple reference points for MOEA/D is designed, which can deal with different characteristics of multi-objective feature selection such as highly discontinuous Pareto fronts and complex relationships between objectives. The experimental results show that the proposed algorithm can evolve more diverse non-dominated sets than other multi-objective algorithms. This thesis introduces the first PSO-based feature selection algorithm for transfer learning. In the proposed algorithm, the fitness function uses classification performance to reduce the differences between domains while maintaining the discriminative ability on the target domain. The experimental results show that the proposed algorithm can select feature subsets which achieve better classification performance than four state-of-the-art feature-based transfer learning algorithms.</p>

Monitoring network traffic and detecting security threats is a vital task in today's world, and intrusion detection systems (IDS) have become an essential tool for this purpose. However, IDSs have to analyze large volumes of data, which often contain irrelevant and redundant features. This makes the job of IDSs more challenging, as they must sift through all available features to identify attack patterns, leading to longer processing time and reduced detection accuracy. To address this, we propose a new wrapper approach for solving the feature selection (FS) problem. Our proposed approach uses a novel multi‐objective binary bat algorithm (MBBA‐FS) with a decision tree classifier. The MBBA‐FS aims to produce a set of non‐dominated solutions that minimize the number of features used while maintaining a high detection accuracy. Then, we use a frequency ranking method to identify a single subset of relevant features from the resulting set of non‐dominated solutions. We tested the feasibility and performance of our approach against other leading FS methods using various datasets, including KDD CUP 1999, NLS‐KDD, UNSW‐NB15, and several synthetic benchmarks. The experimental results show that MBBA‐FS outperforms existing FS approaches in terms of classification accuracy and number of selected features.

Voltage dips represent a significant power quality problem. The main cause of voltage dips and short-term interruptions is an electrical short circuit that occurs in transmission or distribution networks. Faults in the power system are stochastic by nature and the main cause of voltage dips. As faults in the transmission system can affect more customers than faults in the distribution system, to reduce the number of dips, it is not enough to invest in a small part of the transmission or distribution system. Only targeted investment in the whole (or a large part of the) power system will reduce voltage dips. Therefore, monitoring parts of the power system is very important. The ideal solution would be to cover the entire system so that a power quality (PQ) monitor is installed on each bus, but this method is not economically justified. This paper presents an advanced method for determining the optimal location and the optimal number of voltage dip measuring devices. The proposed algorithm uses a monitor reach area matrix created by short-circuit simulations, and the coefficient of the exposed area. Single-phase and three-phase short circuits are simulated in DIgSILENT software on the IEEE 39 bus test system, using international standard IEC 60909. After determining the monitor reach area matrix of all potential monitor positions, the binary bat algorithm with a coefficient of the exposed area of the system bus is used to minimize the proposed objective function, i.e., to determine the optimal location and number of measuring devices. Performance of the binary bat algorithm is compared to the mixed-integer linear programming algorithm solved by using the GNU Linear Programming Kit (GLPK).

In this paper, we study machine learning methods for recognizing the motion context of a user of an infrastructure-free navigation system. Motion context is information about whether the user is running, crawling, or lying down, for instance. This can be valuable information for the command and control of a tactical or rescue operation, and it can also be used to adapt the positioning algorithm accordingly in order to improve the positioning result. We test our approach in collaboration with the Finnish Defence Forces. With only about 5 min of training data, we are able to detect the users motion context over 93% of the time using a random forest classifier. However, our tests show that the performance of the classifier is highly dependent on the user of the system. For this reason, we experiment with different classification algorithms in order to find a user-independent classifier providing a good compromise between accuracy and computational complexity. With a naïve Bayesian classifier, we achieve 85% detection rate in case when the training data is not produced by the user. In addition, we demonstrate how the motion recognition can be used to adjust the zero velocity update threshold in order to improve the performance of a foot-mounted inertial navigation algorithm.

A new feature selection based on comprehensive measurement both in inter-category and intra-category for text categorization

In this article, a novel hybrid binary bat algorithm named HBBA is proposed for global optimization problems. First, to avoid simultaneous updating of bat velocity's dimensional components, i.e., elements of velocity vector, a random black hole model is modified to adapt to binary algorithm for updating in unknown spaces for each dimensional component individually. Through this way, the search ability of bats around the current group best is increased greatly. Second, a time-varying v-shaped transfer function, rather than a time-invariant one as in closely related works, is proposed to map velocity in continuous search space to a binary one. This accelerates the speed to switch individuals' positions, i.e., solutions in binary space. Third, a chaotic map is utilized to replace monotonous parameters in original binary bat algorithm, which is beneficial for avoiding premature convergence. Simulation results demonstrate the effectiveness of the proposed algorithm by three types of benchmark functions and unit commitment problem.

This research introduces innovative approaches to enhance intrusion detection systems (IDSs) by addressing critical challenges in existing methods. Various machine-learning techniques, including nature-inspired metaheuristics, Bayesian algorithms, and swarm intelligence, have been proposed in the past for attribute selection and IDS performance improvement. However, these methods have often fallen short in terms of detection accuracy, detection rate, precision, and F-score. To tackle these issues, the paper presents a novel hybrid feature selection approach combining the Bat metaheuristic algorithm with the Residue Number System (RNS). Initially, the Bat algorithm is utilized to partition training data and eliminate irrelevant attributes. Recognizing the Bat algorithm's slower training and testing times, RNS is incorporated to enhance processing speed. Additionally, principal component analysis (PCA) is employed for feature extraction. In a second phase, RNS is excluded for feature selection, allowing the Bat algorithm to perform this task while PCA handles feature extraction. Subsequently, classification is conducted using naive bayes, and k-Nearest Neighbors. Experimental results demonstrate the remarkable effectiveness of combining RNS with the Bat algorithm, achieving outstanding detection rates, accuracy, and F-scores. Notably, the fusion approach doubles processing speed. The findings are further validated through benchmarking against existing intrusion detection methods, establishing their competitiveness.

The past ten years have seen notable research activity and significant advancements in multiuser multiple-input multiple-output (MU-MIMO) antennas. An MU-MIMO antenna system must accommodate many subscribers without additional bandwidth or energy. User scheduling becomes a critical strategy to take advantage of multiuser heterogeneity and acquire maximum gain in systems where the total number of recipients exceeds the number of transmitting antennas. Due to their high computational cost, many user selection methods currently in use, such as greedy algorithms and exhaustive search are unsuitable for MU-MIMO systems. A suitable scheduling mechanism is essential for the various users in an MU-MIMO system to utilise bandwidth and enhance the system’s total rate effectively. In this article, we proposed a user and antenna scheduling with a population-based meta-heuristic approach, namely the binary salp swarm algorithm (binary SSA), to increase the system sum rate with low computing complexity. We specifically used a population-based meta-heuristics optimisation technique to simulate the user scheduling problem in MU-MIMO systems, characterising complicated issues with binary decisions. Additionally, binary SSA significantly outperforms existing population-based models, such as the binary bat algorithm (binary BA), PSO, SSA, FPA and binary flower pollination algorithm (binary FPA), regarding system throughput/sum rate. The proposed binary SSA technique also effectively achieves a system sum rate compared to a random search scheme and other existing suboptimal scheduling methods. Compared to binary BA and binary FPA approaches, the binary SSA has a higher convergence rate and superior searching capabilities. The simulation outcomes show the proposed binary SSA-based scheduling scheme delivers noticeable performance benefits.

Biometric authentication systems play a crucial role in ensuring secure access control in the era of the Internet of Things (IoT). Iris recognition, in particular, offers a highly accurate and reliable means of authentication. However, the success of iris recognition heavily relies on the accurate segmentation of the iris region from the surrounding areas. This research article presents a novel approach to iris segmentation using the Binary Bat Algorithm (BAT) in the context of biometric authentication in IoT. The proposed methodology involves preprocessing the iris images, defining an objective function to evaluate the quality of the iris segmentation, encoding the candidate solutions using binary encoding, initializing the population of bat solutions, and incorporating local search mechanisms within the BAT algorithm to fine-tune the segmentation. Experimental evaluations are conducted using a publicly available iris dataset, comparing the proposed BAT algorithm with existing segmentation methods. The performance of the BAT algorithm is assessed using evaluation metrics such as segmentation accuracy, completeness, and computational efficiency. Additionally, the robustness of the BAT algorithm is analyzed under various challenging conditions, including varying lighting conditions, occlusions, and noise. The results demonstrate that the BAT algorithm outperforms existing segmentation methods in terms of accuracy and completeness. The proposed approach shows promising potential for efficient iris segmentation in biometric authentication systems in the IoT domain.