Marwa Radwan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Marwa Radwan has a total of 16 co-authors. Here are the top co-authors by number of shared publications:
Amel Ali Alhussan
Department of Computer Sciences, College of Computer and Information Sciences, Princess Nourah bint Abdulrahman University, Riyadh, 11671, P.O. Box 84428, Saudi Arabia
4 shared publicationsAbdelhameed Ibrahim
Computer Engineering and Control Systems Department, Faculty of Engineering, Mansoura University, Mansoura, 35516, Egypt
2 shared publicationsDoaa Sami Khafaga
Department of Computer Sciences, College of Computer and Information Sciences, Princess Nourah Bint Abdulrahman University, Riyadh, Saudi Arabia
2 shared publicationsEbrahim A. Mattar
College of Engineering, University of Bahrain, Sakhir, Bahrain
2 shared publications- El-Sayed M. El-Kenawy
Bahrain Polytechnic
2 shared publications Abdelaziz A. Abdelhamid
Department of Computer Science, College of Computing and Information Technology, Shaqra University, Shaqra, Saudi Arabia
1 shared publication
Latest Publications
- Open Access
- 1 September 2026
- Published by Springer Nature in Journal of Big Data
- Vol. 13 (1) , 148
Comment feedback optimization algorithm (CFOA)-optimized spatio-temporal graph networks for biomass forecasting and predictive maintenance support in renewable energy systems
- 1 September 2026
- Published by Springer Nature in Journal of Big Data
- Vol. 13 (1) , 148
Open AccessComment feedback optimization algorithm (CFOA)-optimized spatio-temporal graph networks for biomass forecasting and predictive maintenance support in renewable energy systems
- Top Cited PapersOpen Access
- 10 March 2026
- Published by Springer Nature in Scientific Reports
- Vol. 16 (1)
Optimizing solar and wind forecasting with iHow optimization algorithm and multi-scale attention networks
Deep learning models often encounter two key challenges in developing intelligent and scalable forecasting frameworks for renewable energy systems: input feature space dimensionality and sensitivity to hyperparameter settings. These limitations increase computational cost and compromise generalization and robustness. This paper presents a hybrid deep learning–optimization framework that leverages cognitively inspired metaheuristics to address these challenges, employing the Binary iHow Optimization Algorithm (biHOW) for feature selection and its continuous counterpart, iHOW , for hyperparameter tuning. Both variants emulate human cognitive phases—data absorption, information analysis, reinstitution, and adaptive knowledge development enabling efficient traversal of complex search spaces. Using the Multi-Scale Attention Network (MSAN) as the forecasting backbone, which is well suited for modeling renewable energy time series due to its ability to capture multi-scale temporal dependencies ranging from short-term fluctuations to long-term seasonal patterns, the proposed framework achieved high accuracy for wind and solar generation prediction. The MSAN model attained Mean Squared Errors (MSE) of 0.0105 for wind and 0.0976 for solar forecasting. Applying biHOW for feature selection reduced the average misclassification rate to 0.3925 (wind) and 0.4161 (solar) while identifying compact, interpretable feature subsets. The iHOW optimizer further fine-tuned architectural and training parameters, decreasing MSE to $$1.10883\times 10^{-6}$$ for wind and $$7.08664\times 10^{-6}$$ for solar, outperforming state-of-the-art metaheuristics including HHO, GWO, PSO, and JAYA. These findings demonstrate the effectiveness of iHOW-based optimization in enhancing forecasting accuracy and computational scalability. The proposed hybrid framework supports adaptive forecasting for intelligent energy management within modern smart grids.- 10 March 2026
- Published by Springer Nature in Scientific Reports
- Vol. 16 (1)
Top Cited PapersOpen AccessOptimizing solar and wind forecasting with iHow optimization algorithm and multi-scale attention networks
Deep learning models often encounter two key challenges in developing intelligent and scalable forecasting frameworks for renewable energy systems: input feature space dimensionality and sensitivity to hyperparameter settings. These limitations increase computational cost and compromise generalization and robustness. This paper presents a hybrid deep learning–optimization framework that leverages cognitively inspired metaheuristics to address these challenges, employing the Binary iHow Optimization Algorithm (biHOW) for feature selection and its continuous counterpart, iHOW , for hyperparameter tuning. Both variants emulate human cognitive phases—data absorption, information analysis, reinstitution, and adaptive knowledge development enabling efficient traversal of complex search spaces. Using the Multi-Scale Attention Network (MSAN) as the forecasting backbone, which is well suited for modeling renewable energy time series due to its ability to capture multi-scale temporal dependencies ranging from short-term fluctuations to long-term seasonal patterns, the proposed framework achieved high accuracy for wind and solar generation prediction. The MSAN model attained Mean Squared Errors (MSE) of 0.0105 for wind and 0.0976 for solar forecasting. Applying biHOW for feature selection reduced the average misclassification rate to 0.3925 (wind) and 0.4161 (solar) while identifying compact, interpretable feature subsets. The iHOW optimizer further fine-tuned architectural and training parameters, decreasing MSE to $$1.10883\times 10^{-6}$$ for wind and $$7.08664\times 10^{-6}$$ for solar, outperforming state-of-the-art metaheuristics including HHO, GWO, PSO, and JAYA. These findings demonstrate the effectiveness of iHOW-based optimization in enhancing forecasting accuracy and computational scalability. The proposed hybrid framework supports adaptive forecasting for intelligent energy management within modern smart grids. - 3 February 2026
- Published by Springer Nature in Potato Research
- Vol. 69 (2) , 36
Towards Intelligent Agricultural Forecasting: Quantum Temporal Models for Potato Yield Prediction
- 3 February 2026
- Published by Springer Nature in Potato Research
- Vol. 69 (2) , 36
Towards Intelligent Agricultural Forecasting: Quantum Temporal Models for Potato Yield Prediction
- Open Access
- 8 October 2024
- Published by Springer Nature in Scientific Reports
- Vol. 14 (1) , 1-16
Optimized classification of diabetes using dynamic waterwheel plant optimization algorithm
The classification of chronic diseases has been a prominent research focus in public health, extensively leveraging machine learning algorithms. One of these chronic diseases that has significant rates of occurrence all around the world is diabetes, which is a disease by itself. Many academics are working to construct robust machine-learning algorithms for accurate categorization, given the prevalence of this chronic disease. A revolutionary methodology that can accurately categorize diabetic disease is the focus of this study, which aims to provide new methods. The proposed technique in this work is based on developing a novel feature selection method, DWWPA, which stands for dynamic waterwheel plant algorithm. The DWWPA algorithm is utilized in the process of optimizing the K-nearest neighbors (KNN) model in order to improve the accuracy of its classification. In the feature selection process, a binary representation of this method is called binary DWWPA (bDWWPA). Several different machine learning models and optimization techniques are compared to the strategy that has been presented. When categorizing diabetes cases in the dataset, the findings demonstrate the superiority and success of the proposed method. Furthermore, several different statistical analysis techniques, such as Analyses of variance (ANOVA) and Wilcoxon signed-rank test, are carried out to investigate the statistical difference and importance of the suggested strategy in contrast to the other ways at the same level of competition. The conclusions of these tests were consistent with what was anticipated they would be. Based on the suggested feature selection and the optimization of the KNN model, the proposed method has an accuracy of 98.9% when taken as an entire. The suggested method was useful in accurately classifying diabetic disease, as evidenced by the fact that it achieved a higher level of accuracy than the contemporary approaches.
- 8 October 2024
- Published by Springer Nature in Scientific Reports
- Vol. 14 (1) , 1-16
Open AccessOptimized classification of diabetes using dynamic waterwheel plant optimization algorithm
The classification of chronic diseases has been a prominent research focus in public health, extensively leveraging machine learning algorithms. One of these chronic diseases that has significant rates of occurrence all around the world is diabetes, which is a disease by itself. Many academics are working to construct robust machine-learning algorithms for accurate categorization, given the prevalence of this chronic disease. A revolutionary methodology that can accurately categorize diabetic disease is the focus of this study, which aims to provide new methods. The proposed technique in this work is based on developing a novel feature selection method, DWWPA, which stands for dynamic waterwheel plant algorithm. The DWWPA algorithm is utilized in the process of optimizing the K-nearest neighbors (KNN) model in order to improve the accuracy of its classification. In the feature selection process, a binary representation of this method is called binary DWWPA (bDWWPA). Several different machine learning models and optimization techniques are compared to the strategy that has been presented. When categorizing diabetes cases in the dataset, the findings demonstrate the superiority and success of the proposed method. Furthermore, several different statistical analysis techniques, such as Analyses of variance (ANOVA) and Wilcoxon signed-rank test, are carried out to investigate the statistical difference and importance of the suggested strategy in contrast to the other ways at the same level of competition. The conclusions of these tests were consistent with what was anticipated they would be. Based on the suggested feature selection and the optimization of the KNN model, the proposed method has an accuracy of 98.9% when taken as an entire. The suggested method was useful in accurately classifying diabetic disease, as evidenced by the fact that it achieved a higher level of accuracy than the contemporary approaches.
- Open Access
- 24 July 2024
- Published by Springer Nature in Potato Research
- Vol. 68 (2) , 897-921
Potato Leaf Disease Classification Using Optimized Machine Learning Models and Feature Selection Techniques
The diseases that particularly affect potato leaves are early blight and the late blight, and they are dangerous as they reduce yield and quality of the potatoes. In this paper, different machine learning (ML) models for predicting these diseases are analysed based on a detailed database of more than 4000 records of weather conditions. Some of the critical factors that have been investigated to determine correlations with disease prevalence include temperature, humidity, wind speed, and atmospheric pressure. These types of data relationships were comprehensively identified through sophisticated means of analysis such as K-means clustering, PCA, and copula analysis. To achieve this, several machine learning models were used in the study: logistic regression, gradient boosting, multilayer perceptron (MLP), and support vector machine (SVM), as well as K-nearest neighbor (KNN) models both with and without feature selection. Feature selection methods such as the binary Greylag Goose Optimization (bGGO) were applied to improve the predictive performance of the models by identifying feature sets pertinent to the models. Results demonstrated that the MLP model, with feature selection, achieved an accuracy of 98.3%, underscoring the critical role of feature selection in improving model performance. These findings highlight the importance of optimized ML models in proactive agricultural disease management, aiming to minimize crop loss and promote sustainable farming practices.
- 24 July 2024
- Published by Springer Nature in Potato Research
- Vol. 68 (2) , 897-921
Open AccessPotato Leaf Disease Classification Using Optimized Machine Learning Models and Feature Selection Techniques
The diseases that particularly affect potato leaves are early blight and the late blight, and they are dangerous as they reduce yield and quality of the potatoes. In this paper, different machine learning (ML) models for predicting these diseases are analysed based on a detailed database of more than 4000 records of weather conditions. Some of the critical factors that have been investigated to determine correlations with disease prevalence include temperature, humidity, wind speed, and atmospheric pressure. These types of data relationships were comprehensively identified through sophisticated means of analysis such as K-means clustering, PCA, and copula analysis. To achieve this, several machine learning models were used in the study: logistic regression, gradient boosting, multilayer perceptron (MLP), and support vector machine (SVM), as well as K-nearest neighbor (KNN) models both with and without feature selection. Feature selection methods such as the binary Greylag Goose Optimization (bGGO) were applied to improve the predictive performance of the models by identifying feature sets pertinent to the models. Results demonstrated that the MLP model, with feature selection, achieved an accuracy of 98.3%, underscoring the critical role of feature selection in improving model performance. These findings highlight the importance of optimized ML models in proactive agricultural disease management, aiming to minimize crop loss and promote sustainable farming practices.
- Open Access
- 28 May 2024
- Published by Springer Nature in Potato Research
- p. 1-25
Optimized Deep Learning for Potato Blight Detection Using the Waterwheel Plant Algorithm and Sine Cosine Algorithm
Potato blight, sometimes referred to as late blight, is a deadly disease that affects Solanaceae plants, including potato. The oomycete Phytophthora infestansis causal agent, and it may seriously damage potato crops, lowering yields and causing financial losses. To ensure food security and reduce economic losses in agriculture, potato diseases must be identified. The approach we have proposed in our study may provide a reliable and efficient solution to improve potato late blight classification accuracy. For this purpose, we used the ResNet-50, GoogLeNet, AlexNet, and VGG19Net pre-trained models. We used the AlexNet model for feature extraction, which produced the best results. After extraction, we selected features using ten optimization algorithms in their binary format. The Binary Waterwheel Plant Algorithm Sine Cosine (WWPASC) achieved the best results amongst the ten algorithms, and we performed statistical analysis on the selected features. Five machine learning models—Decision Tree (DT), Random Forest (RF), Multilayer Perceptron (MLP), Support Vector Machine (SVM), andK-Nearest Neighbour (KNN)—were used to train the chosen features. The most accurate model was the MLP model. The hyperparameters of the MLP model were optimized using the Waterwheel Plant Algorithm Sine Cosine (WWPASC). The results indicate that the suggested methodology (WWPASC-MLP) outperforms four other optimization techniques, with a classification accuracy of 99.5%.
- 28 May 2024
- Published by Springer Nature in Potato Research
- p. 1-25
Open AccessOptimized Deep Learning for Potato Blight Detection Using the Waterwheel Plant Algorithm and Sine Cosine Algorithm
Potato blight, sometimes referred to as late blight, is a deadly disease that affects Solanaceae plants, including potato. The oomycete Phytophthora infestansis causal agent, and it may seriously damage potato crops, lowering yields and causing financial losses. To ensure food security and reduce economic losses in agriculture, potato diseases must be identified. The approach we have proposed in our study may provide a reliable and efficient solution to improve potato late blight classification accuracy. For this purpose, we used the ResNet-50, GoogLeNet, AlexNet, and VGG19Net pre-trained models. We used the AlexNet model for feature extraction, which produced the best results. After extraction, we selected features using ten optimization algorithms in their binary format. The Binary Waterwheel Plant Algorithm Sine Cosine (WWPASC) achieved the best results amongst the ten algorithms, and we performed statistical analysis on the selected features. Five machine learning models—Decision Tree (DT), Random Forest (RF), Multilayer Perceptron (MLP), Support Vector Machine (SVM), andK-Nearest Neighbour (KNN)—were used to train the chosen features. The most accurate model was the MLP model. The hyperparameters of the MLP model were optimized using the Waterwheel Plant Algorithm Sine Cosine (WWPASC). The results indicate that the suggested methodology (WWPASC-MLP) outperforms four other optimization techniques, with a classification accuracy of 99.5%.