Hanaa Salem Marie

Prof. Dr. Hanaa Salem Marie

Delta University for Science and Technology
+1
orcid

Research Focus & Metrics

Academic Career Length

12Years (2015-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 January 2017 in Applied Soft Computing
Verified
Journal Article
Closed access
Hanaa Salem MarieHanaa Salem Marie
Hanaa Salem Marie
GAGamal Attiya
Gamal Attiya
NENawal El-Fishawy
Nawal El-Fishawy

4 February 2022 in Sensors
Verified
Journal Article
Open access
PDF file
IHibrahim hesin
ibrahim hesin
OEOmar Elzeki
Omar Elzeki
AAAli Alshehri
Ali Alshehri
Hanaa Salem MarieHanaa Salem Marie
Hanaa Salem Marie
The rapid growth and adaptation of medical information to identify significant health trends and help with timely preventive care have been recent hallmarks of the modern healthcare data system. Heart disease is the deadliest condition in the developed world. Cardiovascular disease and its complications, including dementia, can be averted with early detection. Further research in this area is needed to prevent strokes and heart attacks. An optimal machine learning model can help achieve this goal with a wealth of healthcare data on heart disease. Heart disease can be predicted and diagnosed using machine-learning-based systems. Active learning (AL) methods improve classification quality by incorporating user–expert feedback with sparsely labelled data. In this paper, five (MMC, Random, Adaptive, QUIRE, and AUDI) selection strategies for multi-label active learning were applied and used for reducing labelling costs by iteratively selecting the most relevant data to query their labels. The selection methods with a label ranking classifier have hyperparameters optimized by a grid search to implement predictive modelling in each scenario for the heart disease dataset. Experimental evaluation includes accuracy and F-score with/without hyperparameter optimization. Results show that the generalization of the learning model beyond the existing data for the optimized label ranking model uses the selection method versus others due to accuracy. However, the selection method was highlighted in regards to the F-score using optimized settings.

15 June 2022 in Healthcare
Verified
Journal Article
Open access
PDF file
eman ashraf rashademan ashraf rashad
eman ashraf rashad
NANihal Areed
Nihal Areed
Hanaa Salem MarieHanaa Salem Marie
Hanaa Salem Marie
EAEhab Hany Abdelhay
Ehab Hany Abdelhay
Ahmed FaroukAhmed Farouk
Ahmed Farouk
Recently, there has been considerable growth in the internet of things (IoT)-based healthcare applications; however, they suffer from a lack of intrusion detection systems (IDS). Leveraging recent technologies, such as machine learning (ML), edge computing, and blockchain, can provide suitable and strong security solutions for preserving the privacy of medical data. In this paper, FIDChain IDS is proposed using lightweight artificial neural networks (ANN) in a federated learning (FL) way to ensure healthcare data privacy preservation with the advances of blockchain technology that provides a distributed ledger for aggregating the local weights and then broadcasting the updated global weights after averaging, which prevents poisoning attacks and provides full transparency and immutability over the distributed system with negligible overhead. Applying the detection model at the edge protects the cloud if an attack happens, as it blocks the data from its gateway with smaller detection time and lesser computing and processing capacity as FL deals with smaller sets of data. The ANN and eXtreme Gradient Boosting (XGBoost) models were evaluated using the BoT-IoT dataset. The results show that ANN models have higher accuracy and better performance with the heterogeneity of data in IoT devices, such as intensive care unit (ICU) in healthcare systems. Testing the FIDChain with different datasets (CSE-CIC-IDS2018, Bot Net IoT, and KDD Cup 99) reveals that the BoT-IoT dataset has the most stable and accurate results for testing IoT applications, such as those used in healthcare systems.

8 January 2024 in EURASIP Journal on Image and Video Processing
Verified
Journal Article
Open access
PDF file
LAlobna m abouelmagd
lobna m abouelmagd
Mahmoud Y. ShamsMahmoud Y. Shams
Mahmoud Y. Shams
Hanaa Salem MarieHanaa Salem Marie
Hanaa Salem Marie
Abou ELLa HassanienAbou ELLa Hassanien
Abou ELLa Hassanien
Plant diseases have a significant impact on leaves, with each disease exhibiting specific spots characterized by unique colors and locations. Therefore, it is crucial to develop a method for detecting these diseases based on spot shape, color, and location within the leaves. While Convolutional Neural Networks (CNNs) have been widely used in deep learning applications, they suffer from limitations in capturing relative spatial and orientation relationships. This paper presents a computer vision methodology that utilizes an optimized capsule neural network (CapsNet) to detect and classify ten tomato leaf diseases using standard dataset images. To mitigate overfitting, data augmentation, and preprocessing techniques were employed during the training phase. CapsNet was chosen over CNNs due to its superior ability to capture spatial positioning within the image. The proposed CapsNet approach achieved an accuracy of 96.39% with minimal loss, relying on a 0.00001 Adam optimizer. By comparing the results with existing state-of-the-art approaches, the study demonstrates the effectiveness of CapsNet in accurately identifying and classifying tomato leaf diseases based on spot shape, color, and location. The findings highlight the potential of CapsNet as an alternative to CNNs for improving disease detection and classification in plant pathology research.

18 January 2022 in Applied Sciences
Verified
Journal Article
Open access
PDF file
Hanaa Salem MarieHanaa Salem Marie
Hanaa Salem Marie
Mahmoud Y. ShamsMahmoud Y. Shams
Mahmoud Y. Shams
OEOmar Elzeki
Omar Elzeki
MAMohamed Abdelfattah
Mohamed Abdelfattah
JAJehad Faisal Al Amri
Jehad Faisal Al Amri
SEShaima abd el kader mohamed Elnazer
Shaima abd el kader mohamed Elnazer
Diabetes, a metabolic disease in which the blood glucose level rises over time, is one of the most common chronic diseases at present. It is critical to accurately predict and classify diabetes to reduce the severity of the disease and treat it early. One of the difficulties that researchers face is that diabetes datasets are limited and contain outliers and missing data. Additionally, there is a trade-off between classification accuracy and operational law for detecting diabetes. In this paper, an algorithm for diabetes classification is proposed for pregnant women using the Pima Indians Diabetes Dataset (PIDD). First, a preprocessing step in the proposed algorithm includes outlier rejection, imputing missing values, the standardization process, and feature selection of the attributes, which enhance the dataset’s quality. Second, the classifier uses the fuzzy KNN method and modifies the membership function based on the uncertainty theory. Third, a grid search method is applied to achieve the best values for tuning the fuzzy KNN method based on uncertainty membership, as there are hyperparameters that affect the performance of the proposed classifier. In turn, the proposed tuned fuzzy KNN based on uncertainty classifiers (TFKNN) deals with the belief degree, handles membership functions and operation law, and avoids making the wrong categorization. The proposed algorithm performs better than other classifiers that have been trained and evaluated, including KNN, fuzzy KNN, naïve Bayes (NB), and decision tree (DT). The results of different classifiers in an ensemble could significantly improve classification precision. The TFKNN has time complexity O(kn2d), and space complexity O(n2d). The TFKNN model has high performance and outperformed the others in all tests in terms of accuracy, specificity, precision, and average AUC, with values of 90.63, 85.00, 93.18, and 94.13, respectively. Additionally, results of empirical analysis of TFKNN compared to fuzzy KNN, KNN, NB, and DT demonstrate the global superiority of TFKNN in precision, accuracy, and specificity.

15 February 2021 in Pattern Analysis and Applications
Verified
Journal Article
Closed access
PDF file
MAMostafa Atlam
Mostafa Atlam
HTHanaa Torkey
Hanaa Torkey
NENawal El-Fishawy
Nawal El-Fishawy
Hanaa Salem MarieHanaa Salem Marie
Hanaa Salem Marie