A new approach for intrusion detection system based on training multilayer perceptron by using enhanced Bat algorithm

Enhanced multi-layer perceptron for CO2 emission prediction with worst moth disrupted moth fly optimization (WMFO)

This study introduces the Worst Moth Disruption Strategy (WMFO) to enhance the Moth Fly Optimization (MFO) algorithm, specifically addressing challenges related to population stagnation and low diversity. The WMFO aims to prevent local trapping of moths, fostering improved global search capabilities. Demonstrating a remarkable efficiency of 66.6 %, WMFO outperforms the MFO on CEC15 benchmark test functions. The Friedman and Wilcoxon tests further confirm WMFO's superiority over state-of-the-art algorithms. Introducing a hybrid model, WMFO-MLP, combining WMFO with a Multi-Layer Perceptron (MLP), facilitates effective parameter tuning for carbon emission prediction, achieving an outstanding total accuracy of 97.8 %. Comparative analysis indicates that the MLP-WMFO model surpasses alternative techniques in precision, reliability, and efficiency. Feature importance analysis reveals that variables such as Oil Efficiency and Economic Growth significantly impact MLP-WMFO's predictive power, contributing up to 40 %. Additionally, Gas Efficiency, Renewable Energy, Financial Risk, and Political Risk explain 26.5 %, 13.6 %, 8 %, and 6.5 %, respectively. Finally, WMFO-MLP performance offers advancements in optimization and predictive modeling with practical applications in carbon emission prediction.

Multi-Layer Perception model with Elastic Grey Wolf Optimization to predict student achievement

This study proposes a Grey Wolf Optimization (GWO) variant named Elastic Grey Wolf Optimization algorithm (EGWO) with shrinking, resilient surrounding, and weighted candidate mechanisms. Then, the proposed EGWO is used to optimize the weights and biases of Multi-Layer Perception (MLP), and the EGWO-MLP model for predicting student achievement is thus obtained. The training and verification of the EGWO-MLP prediction model are conducted based on the thirty attributes from the University of California (UCI) Machine Learning Repository dataset's student performance dataset, including family features and personal characteristics. For the Mathematics (Mat.) subject achievement prediction, the EGWO-MLP model outperforms one model's prediction accuracy, and the standard deviation possesses the stable ability to predict student achievement. And for the Portuguese (Por.) subject, the EGWO-MLP outperforms three models' Mathematics (Mat.) subject achievement prediction through the training process and takes first place through the testing process. The results show that the EGWO-MLP model has made fewer test errors, indicating that EGWO can effectively feedback weights and biases due to the strong exploration and local stagnation avoidance. And the EGWO-MLP model is feasible for predicting student achievement. The study can provide reference for improving school teaching programs and enhancing teachers' teaching quality and students' learning effect.

Intrusion Detection System Based on Pattern Recognition

Artificial intelligence has been developed to be able to solve difficult problems that involve huge amounts of data and that require rapid decision-making in most branches of science and business. Machine learning is one of the most prominent areas of artificial intelligence, which has been used heavily in the last two decades in the field of network security, especially in Intrusion Detection Systems (IDS). Pattern recognition is a machine learning method applied in medical applications, image processing, and video processing. In this article, two layers' IDS is proposed. The first layer classifies the network connection according to the used service. Then, a minimum number of features that optimize the detection accuracy of malicious activities on that service are identified. Using those features, the second layer classifies each network connection as an attack or normal activity based on the pattern recognition method. In the training phase, two multivariate normal statistical models are created: the normal behavior model and the attack behavior model. In the testing and running phases, a maximum likelihood estimation function is used to classify a network connection into attack or normal activity using the two multivariate normal statistical models. The experimental results prove that the proposed IDS has superiority over related IDSs for network intrusion detection. Using only four features, it successfully achieves DR of 97.5%, 0.001 FAR, MCC 95.7%, and 99.8% overall accuracy.

Multiclass feature selection with metaheuristic optimization algorithms: a review

Selecting relevant feature subsets is vital in machine learning, and multiclass feature selection is harder to perform since most classifications are binary. The feature selection problem aims at reducing the feature set dimension while maintaining the performance model accuracy. Datasets can be classified using various methods. Nevertheless, metaheuristic algorithms attract substantial attention to solving different problems in optimization. For this reason, this paper presents a systematic survey of literature for solving multiclass feature selection problems utilizing metaheuristic algorithms that can assist classifiers selects optima or near optima features faster and more accurately. Metaheuristic algorithms have also been presented in four primary behavior-based categories, i.e., evolutionary-based, swarm-intelligence-based, physics-based, and human-based, even though some literature works presented more categorization. Further, lists of metaheuristic algorithms were introduced in the categories mentioned. In finding the solution to issues related to multiclass feature selection, only articles on metaheuristic algorithms used for multiclass feature selection problems from the year 2000 to 2022 were reviewed about their different categories and detailed descriptions. We considered some application areas for some of the metaheuristic algorithms applied for multiclass feature selection with their variations. Popular multiclass classifiers for feature selection were also examined. Moreover, we also presented the challenges of metaheuristic algorithms for feature selection, and we identified gaps for further research studies.

Recent advances of bat-inspired algorithm, its versions and applications

Bat-inspired algorithm (BA) is a robust swarm intelligence algorithm that finds success in many problem domains. The ecosystem of bat animals inspires the main idea of BA. This review paper scanned and analysed the state-of-the-art researches investigated using BA from 2017 to 2021. BA has very impressive characteristics such as its easy-to-use, simple in concepts, flexible and adaptable, consistent, and sound and complete. It has strong operators that incorporate the natural selection principle through survival-of-the-fittest rule within the intensification step attracted by local-best solution. Initially, the growth of the recent solid works published in Scopus indexed articles is summarized in terms of the number of BA-based Journal articles published per year, citations, top authors, work with BA, top institutions, and top countries. After that, the different versions of BA are highlighted to be in line with the complex nature of optimization problems such as binary, modified, hybridized, and multiobjective BA. The successful applications of BA are reviewed and summarized, such as electrical and power system, wireless and network system, environment and materials engineering, classification and clustering, structural and mechanical engineering, feature selection, image and signal processing, robotics, medical and healthcare, scheduling domain, and many others. The critical analysis of the limitations and shortcomings of BA is also mentioned. The open-source codes of BA code are given to build a wealthy BA review. Finally, the BA review is concluded, and the possible future directions for upcoming developments are suggested such as utilizing BA to serve in dynamic, robust, multiobjective, large-scaled optimization as well as improve BA performance by utilizing structure population, tuning parameters, memetic strategy, and selection mechanisms. The reader of this review will determine the best domains and applications used by BA and can justify their BA-related contributions.

A Comprehensive Comparison of the Performance of Metaheuristic Algorithms in Neural Network Training for Nonlinear System Identification

Many problems in daily life exhibit nonlinear behavior. Therefore, it is important to solve nonlinear problems. These problems are complex and difficult due to their nonlinear nature. It is seen in the literature that different artificial intelligence techniques are used to solve these problems. One of the most important of these techniques is artificial neural networks. Obtaining successful results with an artificial neural network depends on its training process. In other words, it should be trained with a good training algorithm. Especially, metaheuristic algorithms are frequently used in artificial neural network training due to their advantages. In this study, for the first time, the performance of sixteen metaheuristic algorithms in artificial neural network training for the identification of nonlinear systems is analyzed. It is aimed to determine the most effective metaheuristic neural network training algorithms. The metaheuristic algorithms are examined in terms of solution quality and convergence speed. In the applications, six nonlinear systems are used. The mean-squared error (MSE) is utilized as the error metric. The best mean training error values obtained for six nonlinear systems were 3.5×10−4, 4.7×10−4, 5.6×10−5, 4.8×10−4, 5.2×10−4, and 2.4×10−3, respectively. In addition, the best mean test error values found for all systems were successful. When the results were examined, it was observed that biogeography-based optimization, moth–flame optimization, the artificial bee colony algorithm, teaching–learning-based optimization, and the multi-verse optimizer were generally more effective than other metaheuristic algorithms in the identification of nonlinear systems.

CNN-based severity prediction of neurodegenerative diseases using gait data

Neurodegenerative diseases occur because of degeneration in brain cells but can manifest as impairment of motor functions. One of the side effects of this impairment is an abnormality in walking. With the development of sensor technologies and artificial intelligence applications in recent years, the disease severity of patients can be estimated using their gait data. In this way, decision support applications for grading the severity of the disease that the patient suffers in the clinic can be developed. Thus, patients can have treatment methods more suitable for the severity of the disease. The presented research proposes a deep learning-based approach using gait data represented by a Quick Response code to develop an effective and reliable disease severity grading system for neurodegenerative diseases such as amyotrophic lateral sclerosis, Huntington's disease, and Parkinson's disease. The two-dimensional Quick Response data set was created by converting each one-dimensional gait data of the subjects with a novel representation approach to a Quick Response code. This data set was regressed with the convolutional neural network deep learning method, and a solution was sought for the problem of grading disease severity. Further, to demonstrate the success of the results obtained with the novel approach, native machine learning approaches such as Multilayer Perceptron, Random Forest, Extremely Randomized Trees, and K-Nearest Neighbours, and ensemble machine learning methods, such as voting and stacking, were applied on one-dimensional data. Finally, the results obtained on the prediction of disease severity by testing one-dimensional gait data with a convolutional neural network architecture that operates on one-dimensional data were included. The results showed that, in most cases, the two-dimensional convolutional neural network approach performed the best among all methods.

Intrusion detection in mobile ad-hoc network using Hybrid Reactive Search and Bat algorithm

Purpose

The mischievous nodes that defy the standard corrupt the exhibition of good nodes considerably. Therefore, an intrusion discovery mechanism should be included to the mobile ad-hoc network (MANET). In this paper, worm-hole and other destructive malignant attacks are propelled in MANET.

Design/methodology/approach

A wireless ad-hoc network also called as mobile ad-hoc network (MANET) is a gathering of hubs that utilizes a wireless channel to exchange information and coordinate together to establish information exchange among any pair of hubs, without any centralized structure. The security issue is a major difficulty while employing MANETs.

Findings

Consequently, the attacks due to the malicious node activity are detected using Hybrid Reactive Search and Bat (HRSB) mechanism to prevent the mischievous nodes from entering the network beneath the untruthful information. Moreover, the attack detection rate and node energy are predicted for determining the lifetime of the node.

Originality/value

The simulation outcomes of the proposed HRSB technique are evaluated with the prevailing methods. The comparison studies have proven the efficacy of the current research model by attaining high attack detection rate and achieving more network lifetime.

A systematic review of emerging feature selection optimization methods for optimal text classification: the present state and prospective opportunities

Specialized data preparation techniques, ranging from data cleaning, outlier detection, missing value imputation, feature selection (FS), amongst others, are procedures required to get the most out of data and, consequently, get the optimal performance of predictive models for classification tasks. FS is a vital and indispensable technique that enables the model to perform faster, eliminate noisy data, remove redundancy, reduce overfitting, improve precision and increase generalization on testing data. While conventional FS techniques have been leveraged for classification tasks in the past few decades, they fail to optimally reduce the high dimensionality of the feature space of texts, thus breeding inefficient predictive models. Emerging technologies such as the metaheuristics and hyper-heuristics optimization methods provide a new paradigm for FS due to their efficiency in improving the accuracy of classification, computational demands, storage, as well as functioning seamlessly in solving complex optimization problems with less time. However, little details are known on best practices for case-to-case usage of emerging FS methods. The literature continues to be engulfed with clear and unclear findings in leveraging effective methods, which, if not performed accurately, alters precision, real-world-use feasibility, and the predictive model's overall performance. This paper reviews the present state of FS with respect to metaheuristics and hyper-heuristic methods. Through a systematic literature review of over 200 articles, we set out the most recent findings and trends to enlighten analysts, practitioners and researchers in the field of data analytics seeking clarity in understanding and implementing effective FS optimization methods for improved text classification tasks.

MQTTset, a New Dataset for Machine Learning Techniques on MQTT

IoT networks are increasingly popular nowadays to monitor critical environments of different nature, significantly increasing the amount of data exchanged. Due to the huge number of connected IoT devices, security of such networks and devices is therefore a critical issue. Detection systems assume a crucial role in the cyber-security field: based on innovative algorithms such as machine learning, they are able to identify or predict cyber-attacks, hence to protect the underlying system. Nevertheless, specific datasets are required to train detection models. In this work we present MQTTset, a dataset focused on the MQTT protocol, widely adopted in IoT networks. We present the creation of the dataset, also validating it through the definition of a hypothetical detection system, by combining the legitimate dataset with cyber-attacks against the MQTT network. Obtained results demonstrate how MQTTset can be used to train machine learning models to implement detection systems able to protect IoT contexts.