Hybrid Dipper Throated and Grey Wolf Optimization for Feature Selection Applied to Life Benchmark Datasets DOI Open Access
Doaa Sami Khafaga,

El-Sayed M. El-kenawy,

Faten Khalid Karim

et al.

Computers, materials & continua/Computers, materials & continua (Print), Journal Year: 2022, Volume and Issue: 74(2), P. 4531 - 4545

Published: Oct. 31, 2022

Selecting the most relevant subset of features from a dataset is vital step in data mining and machine learning. Each feature has 2n possible subsets, making it challenging to select optimum collection using typical methods. As result, new metaheuristics-based selection method based on dipper-throated grey-wolf optimization (DTO-GW) algorithms been developed this research. Instability can result when subject metaheuristics, which lead wide range results. Thus, we adopted hybrid our optimizing, allowed us better balance exploration harvesting chores more equitably. We propose utilizing binary DTO-GW search approach previously devised for selecting optimal attributes. In proposed method, number selected minimized, while classification accuracy increased. To test method’s performance against eleven other state-of-the-art approaches, eight datasets UCI repository were used, such as grey wolf (bGWO), wolf, particle swarm (bGWO-PSO), bPSO, stochastic fractal (bSFS), whale algorithm (bWOA), modified (bMGWO), multiverse (bMVO), bowerbird (bSBO), hysteresis (bHy), (bHWO). The suggested superior successful handling problem selection, according results experiments.

Language: Английский

Detecting COVID-19 in chest CT images based on several pre-trained models DOI Creative Commons

Esraa Hassan,

Mahmoud Y. Shams, Noha A. Hikal

et al.

Multimedia Tools and Applications, Journal Year: 2024, Volume and Issue: 83(24), P. 65267 - 65287

Published: Jan. 15, 2024

Abstract This paper explores the use of chest CT scans for early detection COVID-19 and improved patient outcomes. The proposed method employs advanced techniques, including binary cross-entropy, transfer learning, deep convolutional neural networks, to achieve accurate results. COVIDx dataset, which contains 104,009 images from 1,489 patients, is used a comprehensive analysis virus. A sample 13,413 this dataset categorised into two groups: 7,395 individuals with confirmed 6,018 normal cases. study presents pre-trained learning models such as ResNet (50), VGG (19), (16), Inception V3 enhance DCNN classifying input images. cross-entropy metric compare cases based on predicted probabilities each class. Stochastic Gradient Descent Adam optimizers are employed address overfitting issues. shows that accuracies 99.07%, 98.70%, 98.55%, 96.23%, respectively, in validation set using optimizer. Therefore, work demonstrates effectiveness enhancing accuracy DCNNs image classification. Furthermore, provides valuable insights development more efficient diagnostic tools COVID-19.

Language: Английский

Citations

17
AI Adoption and Educational Sustainability in Higher Education in the UAE DOI
Fanar Shwedeh, Said A. Salloum, Ahmad Aburayya

et al.

Studies in big data, Journal Year: 2024, Volume and Issue: unknown, P. 201 - 229

Published: Jan. 1, 2024

Language: Английский

Citations

17
Network Intrusion Detection Based on Feature Selection and Hybrid Metaheuristic Optimization DOI Open Access
Reem Alkanhel,

El-Sayed M. El-kenawy,

Abdelaziz A. Abdelhamid

et al.

Computers, materials & continua/Computers, materials & continua (Print), Journal Year: 2022, Volume and Issue: 74(2), P. 2677 - 2693

Published: Oct. 31, 2022

Applications of internet-of-things (IoT) are increasingly being used in many facets our daily life, which results an enormous volume data. Cloud computing and fog computing, two the most common technologies IoT applications, have led to major security concerns. Cyberattacks on rise as a result usage these since present measures insufficient. Several artificial intelligence (AI) based solutions, such intrusion detection systems (IDS), been proposed recent years. Intelligent that require data preprocessing machine learning algorithm-performance augmentation use feature selection (FS) techniques increase classification accuracy by minimizing number features selected. On other hand, metaheuristic optimization algorithms widely decades. In this paper, we hybrid algorithm for IDS. The is grey wolf (GW), dipper throated (DTO) referred GWDTO. has better balance between exploration exploitation steps process thus could achieve performance. employed IoT-IDS dataset, performance GWDTO was assessed using set evaluation metrics compared approaches literature validate its superiority. addition, statistical analysis performed assess stability effectiveness approach. Experimental confirmed superiority approach boosting IoT-based networks.

Language: Английский

Citations

31
Wind speed forecasting using optimized bidirectional LSTM based on dipper throated and genetic optimization algorithms DOI Creative Commons
Amel Ali Alhussan,

El-Sayed M. El-kenawy,

Abdelaziz A. Abdelhamid

et al.

Frontiers in Energy Research, Journal Year: 2023, Volume and Issue: 11

Published: June 1, 2023

Accurate forecasting of wind speed is crucial for power systems stability. Many machine learning models have been developed to forecast accurately. However, the accuracy these still needs more improvements achieve accurate results. In this paper, an optimized model proposed boosting prediction speed. The optimization performed in terms a new algorithm based on dipper-throated (DTO) and genetic (GA), which referred as (GADTO). used optimize bidrectional long short-term memory (BiLSTM) parameters. To verify effectiveness methodology, benchmark dataset freely available Kaggle employed conducted experiments. first preprocessed be prepared further processing. addition, feature selection applied select significant features using binary version GADTO algorithm. selected are utilized learn best configuration BiLSTM model. predict future values speed, resulting predictions analyzed set evaluation criteria. Moreover, statistical test study difference approach compared other approaches analysis variance (ANOVA) Wilcoxon signed-rank tests. results tests confirmed approach’s its robustness with average root mean square error (RMSE) 0.00046, outperforms performance recent methods.

Language: Английский

Citations

22
A Review of the Chat GBT Technology Role in Marketing Research DOI
Mahmoud Alghizzawi

Studies in big data, Journal Year: 2024, Volume and Issue: unknown, P. 497 - 507

Published: Jan. 1, 2024

Language: Английский

Citations

7
EEG-based optimization of eye state classification using modified-BER metaheuristic algorithm DOI Creative Commons
Ahmed M. Elshewey, Amel Ali Alhussan, Doaa Sami Khafaga

et al.

Scientific Reports, Journal Year: 2024, Volume and Issue: 14(1)

Published: Oct. 18, 2024

This article introduces the Modified Al-Biruni Earth Radius (MBER) algorithm, which seeks to improve precision of categorizing eye states as either open (0) or closed (1). The evaluation proposed algorithm was assessed using an available EEG dataset that applied preprocessing techniques, including scaling, normalization, and elimination null values. MBER algorithm's binary format is specifically designed select features can significantly enhance accuracy classification. competing ones, namely, (BER), Particle Swarm Optimization (PSO), Whale Algorithm (WAO), Grey Wolf Optimizer (GWO) Genetic (GA) were evaluated predefined sets assessment criteria. statistical analysis employed ANOVA Wilcoxon signed-rank tests effectiveness significance compared other five algorithms. Furthermore, A series visual depictions presented validate robustness algorithm. Thus, outperformed optimizers on majority unimodal benchmark functions due these considerations. Different ML models used for classification, e.g., DT, RF, KNN, SGD, GNB, SVC, LR. KNN model achieved highest values Precision (PPV) (0.959425), Negative Predictive Value (NPV) (0.964969), FScore (0.963431), (0.9612), Sensitivity (0.970578) Specificity (0.949711). serves a fitness function optimized by utilization earth radius (MBER). Finally, state classification 96.12%

Language: Английский

Citations

7
Green hydrogen production ensemble forecasting based on hybrid dynamic optimization algorithm DOI Creative Commons
Amel Ali Alhussan,

El-Sayed M. El-kenawy,

Mohammed A. Saeed

et al.

Frontiers in Energy Research, Journal Year: 2023, Volume and Issue: 11

Published: June 29, 2023

Solar-powered water electrolysis can produce clean hydrogen for sustainable energy systems. Accurate solar generation forecasts are necessary system operation and planning. Al-Biruni Earth Radius (BER) Particle Swarm Optimization (PSO) used in this paper to ensemble forecast generation. The suggested method optimizes the dynamic hyperparameters of deep learning model recurrent neural network (RNN) using BER metaheuristic search optimization algorithm PSO algorithm. We data from HI-SEAS weather station Hawaii 4 months (September through December 2016). will level production next season our simulations compare results those other forecasting approaches. Regarding accuracy, resilience, computational economy, show that BER-PSO-RNN has great potential as a useful tool generation, which important ramifications planning execution such accuracy proposed is confirmed by two statistical analysis tests, Wilcoxon’s rank-sum one-way variance (ANOVA). With use excels processing time-series data, we discovered with algorithm, Solar System could produce, on average, 0.622 kg/day during comparison algorithms.

Language: Английский

Citations

16
The Role of ChatGpt in Knowledge Sharing and Collaboration Within Digital Workplaces: A Systematic Review DOI

Sheikh Abdulaziz Fahad,

Said A. Salloum, Khaled Shaalan

et al.

Studies in big data, Journal Year: 2024, Volume and Issue: unknown, P. 259 - 282

Published: Jan. 1, 2024

Language: Английский

Citations

4
Role of metaheuristic algorithms in healthcare: a comprehensive investigation across clinical diagnosis, medical imaging, operations management, and public health DOI Creative Commons
Aiman Lameesa, Mahfara Hoque, Md. Sakib Bin Alam

et al.

Journal of Computational Design and Engineering, Journal Year: 2024, Volume and Issue: 11(3), P. 223 - 247

Published: May 1, 2024

Abstract Metaheuristic algorithms have emerged in recent years as effective computational tools for addressing complex optimization problems many areas, including healthcare. These can efficiently search through large solution spaces and locate optimal or near-optimal responses to issues. Although metaheuristic are crucial, previous review studies not thoroughly investigated their applications key healthcare areas such clinical diagnosis monitoring, medical imaging processing, operations management, well public health emergency response. Numerous also failed highlight the common challenges faced by metaheuristics these areas. This thus offers a comprehensive understanding of domains, along with future development. It focuses on specific associated data quality quantity, privacy security, complexity high-dimensional spaces, interpretability. We investigate capacity tackle mitigate efficiently. significantly contributed decision-making optimizing treatment plans resource allocation improving patient outcomes, demonstrated literature. Nevertheless, improper utilization may give rise various complications within medicine despite numerous benefits. Primary concerns comprise employed, challenge ethical considerations concerning confidentiality well-being patients. Advanced optimize scheduling maintenance equipment, minimizing operational downtime ensuring continuous access critical resources.

Language: Английский

Citations

4
Classification of monkeypox images using Al-Biruni earth radius optimization with deep convolutional neural network DOI Creative Commons
Amal H. Alharbi

AIP Advances, Journal Year: 2024, Volume and Issue: 14(6)

Published: June 1, 2024

There is a connection that has been established between the virus responsible for monkeypox and formation of skin lesions. This detected in Africa many years. Our research centered around detection lesions as potential indicators during pandemic. primary objective to utilize metaheuristic optimization techniques improve performance feature selection classification algorithms. In order accomplish this goal, we make use deep learning transfer technique extract attributes. The GoogleNet network, framework, used carry out extraction. Furthermore, process conducted using binary version dynamic Al-Biruni earth radius (DBER). After that, convolutional neural network assign labels selected features from collection. To accuracy, adjustments are made by utilizing continuous DBER algorithm. We range metrics analyze different assessment methods, including sensitivity, specificity, positive predictive value (P-value), negative (N-value), F1-score. They were compared each other. All metrics, F1-score, P-value, N-value, achieved high values 0.992, 0.991, 0.993, respectively. outcomes combining with network. optimizing parameters proposed method an impressive overall accuracy rate 0.992.

Language: Английский

Citations

4