Now showing 1 - 10 of 25
  • Publication
    Multiclass feature selection with metaheuristic optimization algorithms: a review
    ( 2022) ;
    Olatunji O. Akinola
    ;
    Absalom E. Ezugwu
    ;
    Jeffrey O. Agushaka
    ;
    Latih Abualigah
    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.
      18
  • Publication
    An intelligent cybersecurity system for detecting fake news in social media websites
    ( 2022) ;
    Mughaid, Ala
    ;
    Al-Zu'bi, Shadi
    ;
    Arjan, A
    ;
    Al-Amrat, Rula
    ;
    Alajmi, Rathaa
    ;
    Abualigah, Laith
    ;
    Maalej, Ahmed
    People worldwide suffer from fake news in many life aspects, healthcare, transportation, education, economics, and many others. Therefore, many researchers have considered seeking techniques for automatically detecting fake news in the last decade. The most popular news agencies use e-publishing on their websites; even websites can publish any news they want. However, thus before quotation any news from a website, there should be a close look at news resource ranking by using a trusted websites classifier, such as the website world rank, which reflects the repute of these websites. This paper uses the world rank of news websites as the main factor of news accuracy by using two widespread and trusted websites ranking. Moreover, a secondary factor is proposed to compute the news accuracy similarity by comparing the current news with fakes news and getting the possible news accuracy. Experiments results are conducted on several benchmark datasets. The results showed that the proposed method got promising results compared to other comparative methods in defining the news accuracy.
      19  8Scopus© Citations 2
  • Publication
    Review on COVID-19 diagnosis models based on machine learning and deep learning approaches
    COVID-19 is the disease evoked by a new breed of coronavirus called the severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2). Recently, COVID-19 has become a pandemic by infecting more than 152 million people in over 216 countries and territories. The exponential increase in the number of infections has rendered traditional diagnosis techniques inefficient. Therefore, many researchers have developed several intelligent techniques, such as deep learning (DL) and machine learning (ML), which can assist the healthcare sector in providing quick and precise COVID-19 diagnosis. Therefore, this paper provides a comprehensive review of the most recent DL and ML techniques for COVID-19 diagnosis. The studies are published from December 2019 until April 2021. In general, this paper includes more than 200 studies that have been carefully selected from several publishers, such as IEEE, Springer and Elsevier. We classify the research tracks into two categories: DL and ML and present COVID-19 public datasets established and extracted from different countries. The measures used to evaluate diagnosis methods are comparatively analysed and proper discussion is provided. In conclusion, for COVID-19 diagnosing and outbreak prediction, SVM is the most widely used machine learning mechanism, and CNN is the most widely used deep learning mechanism. Accuracy, sensitivity, and specificity are the most widely used measurements in previous studies. Finally, this review paper will guide the research community on the upcoming development of machine learning for COVID-19 and inspire their works for future development. This review paper will guide the research community on the upcoming development of ML and DL for COVID-19 and inspire their works for future development.
      95  2Scopus© Citations 48
  • Publication
    Light and Secure Encryption Technique Based on Artificially Induced Chaos and Nature-Inspired Triggering Method
    ( 2022) ;
    Muhammed J. Al-Muhammed
    Encryption is the de facto method for protecting information, whether this information is locally stored or on transit. Although we have many encryption techniques, they have problems inherited from the computational models that they use. For instance, the standard encryption technique suffers from the substitution box syndrome—the substitution box does not provide enough confusion. This paper proffers a novel encryption method that is both highly secure and lightweight. The proposed technique performs an initial preprocessing on its input plaintext, using fuzzy substitutions and noising techniques to eliminate relationships to the input plaintext. The initially encrypted plaintext is next concealed in enormously complicated codes that are generated using a chaotic system, whose behavior is controlled by a set of operations and a nature-inspired triggering technique. The effectiveness of the security of the proposed technique is analyzed using rigorous randomness tests and entropy.
      34  4
  • Publication
    Economic load dispatch using memetic sine cosine algorithm
    ( 2022) ;
    Mohammed Azmi Al-Betar
    ;
    Mohammed A. Awadallah
    ;
    Khaled Assaleh
    In this paper, the economic load dispatch (ELD) problem which is an important problem in electrical engineering is tackled using a hybrid sine cosine algorithm (SCA) in a form of memetic technique. ELD is tackled by assigning a set of generation units with a minimum fuel costs to generate predefined load demand with accordance to a set of equality and inequality constraints. SCA is a recent population based optimizer turned towards the optimal solution using a mathematical-based model based on sine and cosine trigonometric functions. As other optimization methods, SCA has main shortcoming in exploitation process when a non-linear constraints problem like ELD is tackled. Therefore, β-hill climbing optimizer, a recent local search algorithm, is hybridized as a new operator in SCA to empower its exploitation capability to tackle ELD. The proposed hybrid algorithm is abbreviated as SCA-βHC which is evaluated using two sets of real-world generation cases: (i) 3-units, two versions of 13-units, and 40-units, with neglected Ramp Rate Limits and Prohibited Operating Zones constraints. (ii) 6-units and 15-units with Ramp Rate Limits and Prohibited Operating Zones constraints. The sensitivity analysis of the control parameters for SCA-βHC is initially studied. The results show that the performance of the SCA-βHC algorithm is increased by tuning its parameters in proper value. The comparative evaluation against several state-of-the-art methods show that the proposed method is able to produce new best results for some tested cases as well as the second-best for others. In a nutshell, hybridizing βHC optimizer as a new operator for SCA is very powerful algorithm for tackling ELD problems.
      25  4Scopus© Citations 4
  • Publication
    Hybrid encryption technique: Integrating the neural network with distortion techniques
    ( 2022) ;
    Al-Muhammed, Muhammed J.
    ;
    Chakchai So-In
    This paper proposes a hybrid technique for data security. The computational model of the technique is grounded on both the nonlinearity of neural network manipulations and the effective distortion operations. To accomplish this, a two-layer feedforward neural network is trained for each plaintext block. The first layer encodes the symbols of the input block, making the resulting ciphertext highly uncorrelated with the input block. The second layer reverses the impact of the first layer by generating weights that are used to restore the original plaintext block from the ciphered one. The distortion stage imposes further confusion on the ciphertext by applying a set of distortion and substitution operations whose functionality is fully controlled by random numbers generated by a key-based random number generator. This hybridization between these two stages (neural network stage and distortion stage) yields a very elusive technique that produces ciphertext with the maximum confusion. Furthermore, the proposed technique goes a step further by embedding a recurrent neural network that works in parallel with the first layer of the neural network to generate a digital signature for each input block. This signature is used to maintain the integrity of the block. The proposed method, therefore, not only ensures the confidentiality of the information but also equally maintains its integrity. The effectiveness of the proposed technique is proven through a set of rigorous randomness testing.
      4
  • Publication
    An enhanced binary Rat Swarm Optimizer based on local-best concepts of PSO and collaborative crossover operators for feature selection
    ( 2022) ;
    Awadallah, Mohammed A.
    ;
    Al-Betar, Mohammed Azmi
    ;
    Braik, Malik Shehadeh
    ;
    Hammouri, Abdelaziz I.
    ;
    Abu Doush, Iyad
    In this paper, an enhanced binary version of the Rat Swarm Optimizer (RSO) is proposed to deal with Feature Selection (FS) problems. FS is an important data reduction step in data mining which finds the most representative features from the entire data. Many FS-based swarm intelligence algorithms have been used to tackle FS. However, the door is still open for further investigations since no FS method gives cutting-edge results for all cases. In this paper, a recent swarm intelligence metaheuristic method called RSO which is inspired by the social and hunting behavior of a group of rats is enhanced and explored for FS problems. The binary enhanced RSO is built based on three successive modifications: i) an S-shape transfer function is used to develop binary RSO algorithms; ii) the local search paradigm of particle swarm optimization is used with the iterative loop of RSO to boost its local exploitation; iii) three crossover mechanisms are used and controlled by a switch probability to improve the diversity. Based on these enhancements, three versions of RSO are produced, referred to as Binary RSO (BRSO), Binary Enhanced RSO (BERSO), and Binary Enhanced RSO with Crossover operators (BERSOC). To assess the performance of these versions, a benchmark of 24 datasets from various domains is used. The proposed methods are assessed concerning the fitness value, number of selected features, classification accuracy, specificity, sensitivity, and computational time. The best performance is achieved by BERSOC followed by BERSO and then BRSO. These proposed versions are comparatively assessed against 25 well-regarded metaheuristic methods and five filter-based approaches. The obtained results underline their superiority by producing new best results for some datasets.
      42
  • Publication
    A hybrid Harris Hawks optimizer for economic load dispatch problems
    ( 2022) ;
    Al-Betar, Mohammed Azmi
    ;
    Awadallah, Mohammed A.
    ;
    Makhadmeh, Sharif Naser
    ;
    Abu Doush, Iyad
    ;
    Alshathri, Samah
    ;
    Abd Elaziz, Mohamed
    This paper proposes a hybridized version of the Harris Hawks Optimizer (HHO) with adaptive-hill-climbing optimizer to tackle economic load dispatch (ELD) problems. ELD is an important problem in power systems that is tackled by finding the optimal schedule of the generation units that minimize fuel conceptions under a set of constraints. Due to the complexity of ELD search space, as it is rigid and deep, the exploitation of HHO is improved by hybridizing it with a recent local search method called adaptive-hill climbing. The HHO can navigate several potential search space regions, while adaptive-hill climbing is used to deeply search for the local optimal solution in each potential region. To evaluate the proposed approach, six versions of ELD cases with various complexities and constraints have been used which are the 6 generation units with 1263 MW of load demand, 13 generation units with 1800 MW of load demand, 13 generation units with 2520 MW of load demand, 15 generation units with 2630 MW of load demand, 40 generation units with 10500 MW of load demand, and 140 generation units with 49342 MW of load demand. Furthermore, the proposed algorithm is evaluated on two ELD real-world cases which are 6 units-1263 MW and 15units-2630 MW. The results show that the proposed algorithm can achieve a significant performance for the majority of the experimented cases. It can achieve the best-reported solution for the ELD case with 15 generation units when compared to 15 well-established methods. Additionally, it obtains the second-best for the ELD case with 140 generation units when compared to 10 well-established methods. In conclusion, the proposed method can be an alternative to solve ELD problems which is efficient.
      7  1
  • Publication
    A Novel Deep Learning Technique for Detecting Emotional Impact in Online Education
    ( 2022) ;
    AlZu’bi, Shadi
    ;
    Hawashin, Bilal
    ;
    Abu Shanab, Samia
    ;
    Zraiqat, Amjed
    ;
    Mughaid, Ala
    ;
    Almotairi, Khaled H.
    ;
    Abualigah, Laith
    Emotional intelligence is the automatic detection of human emotions using various intelligent methods. Several studies have been conducted on emotional intelligence, and only a few have been adopted in education. Detecting student emotions can significantly increase productivity and improve the education process. This paper proposes a new deep learning method to detect student emotions. The main aim of this paper is to map the relationship between teaching practices and student learning based on emotional impact. Facial recognition algorithms extract helpful information from online platforms as image classification techniques are applied to detect the emotions of student and/or teacher faces. As part of this work, two deep learning models are compared according to their performance. Promising results are achieved using both techniques, as presented in the Experimental Results Section. For validation of the proposed system, an online course with students is used; the findings suggest that this technique operates well. Based on emotional analysis, several deep learning techniques are applied to train and test the emotion classification process. Transfer learning for a pre-trained deep neural network is used as well to increase the accuracy of the emotion classification stage. The obtained results show that the performance of the proposed method is promising using both techniques, as presented in the Experimental Results Section.
      36  5
  • Publication
    Development of Lévy flight-based reptile search algorithm with local search ability for power systems engineering design problems
    ( 2022) ;
    Ekinci, Serdar
    ;
    Izci, Davut
    ;
    Alsoud, Anas Ratib
    ;
    Abualigah, Laith
    The need for better-performing algorithms to solve real-world power systems engineering problems has always been a challenging topic. Due to their stochastic nature, metaheuristic algorithms can provide better results. Thus, they have a rising trend in terms of investigation. This paper is a further attempt to offer a better optimizing structure, therefore, aims to provide a better-performing algorithm both for designing an appropriate proportional-integral-derivative (PID) controller to effectively operate an automatic voltage regulator (AVR) system and extracting the optimum parameters of a power system stabilizer (PSS) employed in a single-machine infinite-bus (SMIB) power system. Therefore, the paper discusses the development of the Lévy flight-based reptile search algorithm with local search capability and evaluates its potential against challenging power systems engineering optimization problems. The Lévy flight concept is used for better exploration capability in the proposed algorithm, whereas the Nelder-Mead simplex search algorithm is integrated for further exploitation. The latter case is confirmed through 23 benchmark functions with different features using statistical and nonparametric tests. The superiority of the proposed Lévy flight-based reptile search and Nelder-Mead (L-RSANM) algorithm-based PID controller for the AVR system is demonstrated comparatively using convergence, statistical and nonparametric tests along with transient and frequency responses. Besides, it is also assessed against previously reported and different methods, showing further superiority for AVR system control. Furthermore, the extraordinary ability of the L-RSANM algorithm to design an efficient PSS employed in the SMIB power system is demonstrated, as well. In conclusion, the proposed L-RSANM algorithm is shown to be more capable to solve the challenging power systems engineering design problems.
      49  1