Article
Engineering, Marine
Yin Zhang, Jun Guo, Qian Zhou, Shuang Wang
Summary: This paper proposes an indirect damage identification method based on Probabilistic Neural Network, utilizing natural frequency changes to indirectly identify damage and improve the identification accuracy and efficiency through optimization algorithms. Results show that Genetic Algorithm has higher iterative efficiency and the optimized PNN has higher damage identification accuracy.
Article
Computer Science, Information Systems
Zaid Abdi Alkareem Alyasseri, Mohammed Azmi Al-Betar, Mohammed A. Awadallah, Sharif Naser Makhadmeh, Ammar Kamal Abasi, Iyad Abu Doush, Osama Ahmad Alomari
Summary: This paper proposes a hybrid method that combines the beta-hill climbing optimizer with the flower pollination algorithm for local refinement in global optimization problems. The experimental results show that the proposed method outperforms the flower pollination algorithm in convergence behavior and performs better than other methods in multiple dimensions.
JOURNAL OF KING SAUD UNIVERSITY-COMPUTER AND INFORMATION SCIENCES
(2022)
Article
Computer Science, Information Systems
T. Sree Kala, A. Christy
Summary: The rapid advancement in web and system technologies has led to an increase in attacks and intrusions, making intrusion detection frameworks crucial for security. The HFFPNN technique, a hybrid classifier, shows promising results in intrusion detection classification, surpassing existing techniques and expanding the scope of research.
MULTIMEDIA TOOLS AND APPLICATIONS
(2021)
Article
Computer Science, Artificial Intelligence
Shameem Ahmed, Kushal Kanti Ghosh, Laura Garcia-Hernandez, Ajith Abraham, Ram Sarkar
Summary: This study discusses optimization methods for high-dimensional feature vector classification problems, proposes an improved version of the CRO algorithm, and evaluates it on multiple datasets, showing superior performance.
NEURAL COMPUTING & APPLICATIONS
(2021)
Article
Computer Science, Artificial Intelligence
Maciej Kusy, Piotr A. Kowalski
Summary: This paper presents a method for reducing the architecture of the probabilistic neural network (PNN) by clustering data and selecting nearest neighbors. Experimental results show that the reduced PNN achieves higher accuracy than the original network and existing methods in most classification tasks.
APPLIED SOFT COMPUTING
(2022)
Article
Computer Science, Artificial Intelligence
Edgar S. Garcia-Trevino, Pu Yang, Javier A. Barria
Summary: This article proposes a novel wavelet probabilistic neural network (WPNN) that relies on wavelet-based estimation of class probability densities for generative learning. The new neural network approach overcomes the limitation of traditional probabilistic neural networks by not being dependent on the number of data inputs. It is particularly suitable for data stream classification and anomaly detection in offline and online environments, and achieves significant performance improvements compared to existing algorithms.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2022)
Article
Computer Science, Information Systems
Ashwini Kumar Pradhan, Debahuti Mishra, Kaberi Das, Mohammad S. Obaidat, Manoj Kumar
Summary: The classification of medical images is crucial for early identification and clinical treatment of diseases. However, traditional classifiers face challenges in feature extraction. To overcome this, researchers propose a new deep learning method called Convolution Neural Network (CNN). This paper presents a test-bed analysis comparing various pre-trained CNN models and introduces a nature-inspired optimization method to enhance the performance. Experimental results show the potential superiority of the proposed CNN model in classifying chest X-ray images and the CNN-HCA model performs better than existing hybrid approaches.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Article
Green & Sustainable Science & Technology
Pisut Pongchairerks
Summary: This paper proposes a probabilistic hill-climbing algorithm, called PH, for the single-source transportation problem (STP). PH is a tree search algorithm that converts the STP into assignment problems (AP) and uses the Hungarian method to find the optimal solution for each node. The algorithm generates child nodes by modifying the AP of the parent node, and selects the current node in a probabilistic way to diversify the search.
Article
Computer Science, Information Systems
Bibi Aamirah Shafaa Emambocus, Muhammed Basheer Jasser
Summary: Optimization problems are commonly solved using heuristic algorithms, and the Dragonfly Algorithm has been found to be more effective than other swarm intelligence algorithms. However, it still suffers from low exploitation. In this paper, the authors propose using hill climbing as a local search technique to enhance the performance of the Dragonfly Algorithm. The optimized algorithm shows improved results in training artificial neural networks for classification problems.
Article
Geochemistry & Geophysics
Zhuo Chen, Kunjia Liu, Qi Zhang, Zhongyan Liu, Dixiang Chen, Mengchun Pan, Jiafei Hu, Yujing Xu
Summary: Traditional geomagnetic vector matching methods based on a single correlation criterion are unable to distinguish the nonlinear mapping of the geomagnetic field and geographical position. This study proposes a vector pattern recognition matching method based on a probabilistic neural network (PNN) to achieve geomagnetic navigation. The proposed method demonstrates higher matching rates and better accuracy compared to traditional algorithms in simulation experiments.
IEEE TRANSACTIONS ON GEOSCIENCE AND REMOTE SENSING
(2023)
Article
Computer Science, Information Systems
Alexandr Kuznetsov, Emanuele Frontoni, Luca Romeo, Nikolay Poluyanenko, Sergey Kandiy, Kateryna Kuznetsova, Eleonora Benova
Summary: Nonlinear substitutions or S-boxes are crucial for modern symmetric ciphers as they complicate the relationship between plaintext and ciphertext. The design of S-boxes should consider factors such as bijectivity, nonlinearity, algebraic immunity, delta uniformity, and linear redundancy to enhance cryptographic strength. Generating S-boxes with high nonlinearity has been the focus of research, but the complexity remains challenging. This article introduces a hill-climbing algorithm with optimized parameters to significantly reduce complexity and improve the generation of S-boxes with various cryptographic indicators.
Article
Geosciences, Multidisciplinary
Soumi Chaki, Aurobinda Routray, William K. Mohanty
Summary: This paper proposes a framework based on Probabilistic Neural Network (PNN) for lithology classification using seismic attributes. The framework is compared with existing supervised classifiers in terms of performance measures such as classification accuracy, sensitivity, and specificity. The study also investigates the selection of appropriate parameters for the classifiers and the importance of individual seismic predictors. The framework is shown to be helpful in estimating the probability of hydrocarbon presence in a large study area.
JOURNAL OF APPLIED GEOPHYSICS
(2022)
Article
Engineering, Electrical & Electronic
Ruofei Wang, Heng Zhao, Dengxin Hua, Jiaqi Li, Xingbo Wang, Feng Ji
Summary: This study proposes a new method for particle property identification based on probabilistic neural network and designs a new portable light scattering sensor for particle signal acquisition. The experimental results show that the proposed method achieves a 99% correct classification rate.
IEEE SENSORS JOURNAL
(2023)
Article
Multidisciplinary Sciences
T. Pandu Ranga Vital, Janmenjoy Nayak, Bighnaraj Naik, D. Jayaram
Summary: Parkinson's disease is an aging neurological disease characterized by dopamine deficiencies, ranking second in the world after Alzheimer's. Early identification of PD is advanced but costly. Voice analysis is an effective approach for PD identification, and a novel probabilistic neural network-based approach is proposed in this study for accurate classification of PD using sound records.
ARABIAN JOURNAL FOR SCIENCE AND ENGINEERING
(2021)
Article
Computer Science, Artificial Intelligence
Xinglong Ju, Victoria C. P. Chen, Jay M. Rosenberger, Feng Liu
Summary: The paper discusses the importance of knot positioning in the MARS model and proposes two methods for knot positioning, demonstrating that the PHCM method using prior change in RSS information performs best in terms of accuracy and computational speed through experiments.
EXPERT SYSTEMS WITH APPLICATIONS
(2021)
Article
Computer Science, Artificial Intelligence
Zaid Abdi Alkareem Alyasseri, Ahamad Tajudin Khader, Mohammed Azmi Al-Betar, Xin-She Yang, Mazin Abed Mohammed, Karrar Hameed Abdulkareem, Seifedine Kadry, Imran Razzak
Summary: A multi-objective flower pollination algorithm is proposed in this study to solve the EEG signal denoising problem using wavelet transform. The algorithm optimizes the denoising parameters based on two measurement criteria, minimum mean squared error and maximum signal-to-noise ratio. Experimental results show that the proposed method achieves good performance.
NEURAL COMPUTING & APPLICATIONS
(2023)
Article
Computer Science, Artificial Intelligence
Bilal H. Abed-alguni, Noor Aldeen Alawad, Mohammed Azmi Al-Betar, David Paul
Summary: This paper proposes improved binary versions of the Sine Cosine Algorithm (SCA) for the Feature Selection (FS) problem. By introducing Opposition Based Learning (OBL), Variable Neighborhood Search (VNS), Laplace distribution, and Refraction Learning (RL), the binary SCA algorithm has been successfully improved. The experimental results show that the improved IBSCA3 algorithm performs well in terms of classification accuracy and fitness values, outperforming other algorithms.
APPLIED INTELLIGENCE
(2023)
Article
Engineering, Environmental
Fadl A. Essa, Mohamed Abd Elaziz, Mohammed Azmi Al-Betar, Ammar H. Elsheikh
Summary: The study investigated the performance of a reverse osmosis unit integrated with a recovery energy system, under different operating system pressures and recovery ratios. A hybrid machine learning model using LSTM neural network optimized by AHA was developed to predict permeate flow and power saving of the reverse osmosis unit. The optimized model showed significantly improved prediction accuracy compared to the pure model, with high coefficient of determination values.
PROCESS SAFETY AND ENVIRONMENTAL PROTECTION
(2023)
Article
Computer Science, Artificial Intelligence
Malik Sh. Braik, Mohammed A. Awadallah, Mohammed Azmi Al-Betar, Abdelaziz I. Hammouri, Raed Abu Zitar
Summary: An Enhanced Chameleon Swarm Algorithm (ECSA) is proposed to solve non-convex Economic Load Dispatch (ELD) problems by integrating roulette wheel selection and Levy flight methods. The performance of ECSA is shown to outperform other methods on complex benchmark functions.
APPLIED INTELLIGENCE
(2023)
Review
Computer Science, Interdisciplinary Applications
Sharif Naser Makhadmeh, Mohammed Azmi Al-Betar, Ammar Kamal Abasi, Mohammed A. Awadallah, Iyad Abu Doush, Zaid Abdi Alkareem Alyasseri, Osama Ahmad Alomari
Summary: This paper reviews and summarizes the studies that utilize the butterfly optimization algorithm (BOA) for optimization problems. It introduces the basic concepts, inspiration, and mathematical model of BOA, and categorizes the studies into different adaptation forms. The advantages, drawbacks, and future directions of BOA in dealing with optimization problems are analyzed and summarized.
ARCHIVES OF COMPUTATIONAL METHODS IN ENGINEERING
(2023)
Article
Geosciences, Multidisciplinary
Muhammad Nabih, Ashraf Ghoneimi, Ahmed Bakry, Samia Allaoua Chelloug, Mohammed Azmi Al-Betar, Mohamed Abd Elaziz
Summary: This study aims to predict Poisson's ratio using ordinary well log and seismic data through machine learning algorithms. The Wild Geese Algorithm is used to determine the best configuration, enhancing the prediction process. Rock physics templates are used to interpret lithology and pore-fluid.
MARINE AND PETROLEUM GEOLOGY
(2023)
Article
Computer Science, Artificial Intelligence
Kwok Tai Chui, Brij B. Gupta, Rutvij H. Jhaveri, Hao Ran Chi, Varsha Arya, Ammar Almomani, Ali Nauman
Summary: This paper proposes a multiround transfer learning and modified generative adversarial network (MTL-MGAN) algorithm for lung cancer detection. The algorithm maximizes transferability through a multiround transfer learning process and avoids negative transfer through customized loss functions. The proposed algorithm significantly improves accuracy compared to related works.
INTERNATIONAL JOURNAL OF INTELLIGENT SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Meena Malik, Chander Prabha, Punit Soni, Varsha Arya, Wadee Alhalabi Alhalabi, Brij B. Gupta, Aiiad A. Albeshri, Ammar Almomani
Summary: Machine learning and deep learning have diverse applications in areas such as education, genetics, and space engineering. The development of smart cities is still in its early stage, with a major challenge being effective waste management. Smart city experts play a crucial role in formulating efficient waste management schemes that can be integrated into the city's overall development plan. This study proposes an automated classification model for urban waste using Convolutional Neural Networks, which can be implemented with low-cost resources and scaled up to address the issue of healthy living provisions across cities. The key aspects of developing such models involve using pre-trained models and employing transfer learning for fine-tuning.
INTERNATIONAL JOURNAL ON SEMANTIC WEB AND INFORMATION SYSTEMS
(2023)
Article
Materials Science, Multidisciplinary
Ghazi S. Alsoruji, A. M. Sadoun, Mohamed Abd Elaziz, Mohammed Azmi Al-Betar, A. W. Abdallah, A. Fathy
Summary: This study presents a machine learning model based on long-short term memory model and beluga whale optimizer to predict the mechanical properties of ultrafine grain Al-TiO2 nanocomposites. The model shows excellent accuracy in predicting the yield and ultimate strengths, elongation, and hardness of the composites tested.
JOURNAL OF MATERIALS RESEARCH AND TECHNOLOGY-JMR&T
(2023)
Article
Computer Science, Interdisciplinary Applications
Qinghua Liu, Guojiang Xiong, Xiaofan Fu, Ali Wagdy Mohamed, Jing Zhang, Mohammed Azmi Al-Betar, Hao Chen, Jun Chen, Sheng Xu
Summary: This study proposes a new hybrid method, GSK-DE, to solve large-scale ED problems by integrating the advantages of GSK and DE algorithms. By dividing the population into two subpopulations, one performing GSK and the other executing DE, and combining the updated individuals, GSK-DE improves the searching efficiency. Simulation results demonstrate that GSK-DE achieves quicker global convergence, higher quality dispatch schemes, and greater robustness.
JOURNAL OF COMPUTATIONAL DESIGN AND ENGINEERING
(2023)
Article
Business
Ammar Almomani
Summary: This paper proposes a new method using machine learning to analyze and classify darknet traffic, which demonstrates high accuracy and precision in distinguishing between malicious and benign traffic.
INFORMATION SYSTEMS AND E-BUSINESS MANAGEMENT
(2023)
Article
Computer Science, Information Systems
Mohammed Azmi Al-Betar, Iyad Abu Doush, Sharif Naser Makhadmeh, Ghazi Al-Naymat, Osama Ahmad Alomari, Mohammed A. Awadallah
Summary: This survey paper comprehensively analyzes the performance and applications of Equilibrium Optimizer (EO), comparing it with eight other well-established methods. Different versions and applications of EO are discussed, highlighting their pros and cons, and suggesting future research directions.
MULTIMEDIA TOOLS AND APPLICATIONS
(2023)
Review
Computer Science, Information Systems
Kwok Tai Chui, Brij B. Gupta, Jiaqi Liu, Varsha Arya, Nadia Nedjah, Ammar Almomani, Priyanka Chaurasia
Summary: The smart city vision has driven the rapid development of IoT and CPS. This paper surveys various aspects of IoT and CPS from 2013 to May 2023. It discusses industry standards, big data utilization, machine learning algorithms, advanced security techniques, and research challenges. The focus has shifted towards advanced algorithms, such as deep learning, transfer learning, and data generation algorithms, to provide more accurate models.
Article
Computer Science, Information Systems
Ammar Almomani, Mohammed Alweshah, Waleed Alomoush, Mohammad Alauthman, Aseel Jabai, Anwar Abbass, Ghufran Hamad, Meral Abdalla, Brij B. Gupta
Summary: Voice classification is essential for creating intelligent systems that assist with student exams, criminal identification, and security systems. The research aims to develop a system that can predict and classify gender, age, and accent, resulting in the proposal of a new system called Classifying Voice Gender, Age, and Accent (CVGAA). By incorporating rhythm-based features and using backpropagation and bagging algorithms, the voice recognition system's accuracy is significantly improved, with the Bagging algorithm achieving the highest accuracy of 55.39% in the voice common dataset and 78.94% in speech accent for age classification and accent accuracy.
CMC-COMPUTERS MATERIALS & CONTINUA
(2023)
Proceedings Paper
Computer Science, Artificial Intelligence
Ghazi Al-Naymat, Mariam Khader, Mohammed Azmi Al-Betar, Raghda Hriez, Ali Hadi
Summary: This paper introduces a parallel approximated variant called MR-VDENCLUE, which is capable of discovering clusters with varying densities and can handle big datasets.
INTELLIGENT SYSTEMS AND APPLICATIONS, VOL 1
(2023)
