Amira Abdelwahab

Dr. Amira Abdelwahab

King Faisal University, Al Hufūf, Ash Sharqīyah, Saudi Arabia
orcid

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

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

Representative Publications

View All Publications
24 December 2020 in Plants
Verified
Journal Article
Open access
PDF file
AAAhmed Zaher Afifi
Ahmed Zaher Afifi
AAAbdulaziz Alhumam
Abdulaziz Alhumam
AAAmira Abdelwahab
Amira Abdelwahab
Automated identification of plant diseases is very important for crop protection. Most automated approaches aim to build classification models based on leaf or fruit images. These approaches usually require the collection and annotation of many images, which is difficult and costly process especially in the case of new or rare diseases. Therefore, in this study, we developed and evaluated several methods for identifying plant diseases with little data. Convolutional Neural Networks (CNNs) are used due to their superior ability to transfer learning. Three CNN architectures (ResNet18, ResNet34, and ResNet50) were used to build two baseline models, a Triplet network and a deep adversarial Metric Learning (DAML) approach. These approaches were trained from a large source domain dataset and then tuned to identify new diseases from few images, ranging from 5 to 50 images per disease. The proposed approaches were also evaluated in the case of identifying the disease and plant species together or only if the disease was identified, regardless of the affected plant. The evaluation results demonstrated that a baseline model trained with a large set of source field images can be adapted to classify new diseases from a small number of images. It can also take advantage of the availability of a larger number of images. In addition, by comparing it with metric learning methods, we found that baseline model has better transferability when the source domain images differ from the target domain images significantly or are captured in different conditions. It achieved an accuracy of 99% when the shift from source domain to target domain was small and 81% when that shift was large and outperformed all other competitive approaches.

1 January 2021 in International Journal of Engineering Business Management
Verified
Journal Article
Open access
PDF file
MSMohamed Salama
Mohamed Salama
HKHatem Abdul Kader
Hatem Abdul Kader
AAAmira Abdelwahab
Amira Abdelwahab
The use of social media networks is becoming a current phenomenon in the world today where people are sharing posts and tweets, connect with different groups, and share their opinions about things. This data is extremely heterogeneous and so it is hard to analyze and derive information from this data that is considered an indispensable source for decision-makers. New techniques are therefore needed to handle these huge amounts of data to find the hidden information thus improve the results of the analysis. We are developing a framework for the analysis of heterogeneous data using machine learning (ML) techniques. In contrast to most of the literature frameworks that focus on a specific type of heterogeneous data for evaluating the proposed framework, we have analyzed 15k tweets data from six American airlines. These tweets are collected from the open stream of Twitter, also predict, classify each tweet as a negative or positive review, and test the ability of deep learning (DL) algorithms by comparing it with traditional ML algorithms. The findings confirmed the validity of the proposed framework and helped to achieve the study objective by providing excellent analysis performance and provide insights into additional aspects of information extraction from heterogeneous data.

30 December 2023 in Electronics
Verified
Journal Article
Open access
PDF file
AAAmira Abdelwahab
Amira Abdelwahab
AAAhmed Zaher Afifi
Ahmed Zaher Afifi
MSMohamed Salama
Mohamed Salama
The integration of active learning (AL) and deep learning (DL) presents a promising avenue for enhancing the efficiency and performance of deep learning classifiers. This article introduces an approach that seamlessly integrates AL principles into the training process of DL models to build robust image classifiers. The proposed approach employs a unique methodology to select high-confidence unlabeled data points for immediate labeling, reducing the need for human annotation and minimizing annotation costs. Specifically, by combining uncertainty sampling with the pseudo-labeling of confident data, the proposed approach expands the training set efficiently. The proposed approach uses a hybrid active deep learning model that selects the most informative data points that need labeling based on an uncertainty measure. Then, it iteratively retrains a deep neural network classifier on the newly labeled samples. The model achieves high accuracy with fewer manually labeled samples than traditional supervised deep learning by selecting the most informative samples for labeling and retraining in a loop. Experiments on various image classification datasets demonstrate that the proposed model outperforms conventional approaches in terms of classification accuracy and reduced human annotation requirements. The proposed model achieved accuracy of 98.9% and 99.3% for the Cross-Age Celebrity and Caltech Image datasets compared to the conventional approach, which achieved 92.3% and 74.3%, respectively. In summary, this work presents a promising unified active deep learning approach to minimize the human effort in manually labeling data while maximizing classification accuracy by strategically labeling only the most valuable samples for the model.

15 December 2020
Verified
Conference Paper
Closed access
MEMohamed Elsayed
Mohamed Elsayed
HAHatem Abdelkader
Hatem Abdelkader
AAAmira Abdelwahab
Amira Abdelwahab
in recent times, Big data is modifying the style life of workplaces and thinking by improved performance in knowledge discovering and decision making ever-greater volumes of data are being produced data due to the network of sensors and communication technologies Heterogeneous data is a category of unstructured data with an unknown pace in several ways. Current data analysis techniques are inadequate to handle the huge volumes of data produced, this data difficult to manage, store, handle, interpret, analyze using traditional techniques. Deep learning (DL) is extremely popular among many data scientists and experts thanks to the high precision in speech recognition, image handling, and data analytics. DL has become much more important because it can be used for largescale heterogeneous data. DL has been applied efficiently in several fields and has exceeded most of the traditional techniques, DL algorithmic can study large unclassified data with the ability to select features. This study concentrates on the discussion of a variety of new algorithms that handle this data and DL models that provide greater accuracy for heterogeneous data.

21 May 2022 in Applied Sciences
Verified
Journal Article
Open access
PDF file
AAAmira Abdelwahab
Amira Abdelwahab
NYNesma Youssef
Nesma Youssef
Data mining techniques are useful in discovering hidden knowledge from large databases. One of its common techniques is sequential rule mining. A sequential rule (SR) helps in finding all sequential rules that achieved support and confidence threshold for help in prediction. It is an alternative to sequential pattern mining in that it takes the probability of the following patterns into account. In this paper, we address the preferable utilization of sequential rule mining algorithms by applying them to databases with different features for improving the efficiency in different fields of application. The three compared algorithms are the TRuleGrowth algorithm, which is an extension sequential rule algorithm of RuleGrowth; the top-k non-redundant sequential rules algorithm (TNS); and a non-redundant dynamic bit vector (NRD-DBV). The analysis compares the three algorithms regarding the run time, the number of produced rules, and the used memory to nominate which of them is best suited in prediction. Additionally, it explores the most suitable applications for each algorithm to improve the efficiency. The experimental results proved that the performance of the algorithms appears related to the dataset characteristics. It has been demonstrated that altering the window size constraint, determining the number of created rules, or changing the value of the minSup threshold can reduce execution time and control the number of valid rules generated.

23 June 2022 in Applied Sciences
Verified
Journal Article
Open access
PDF file
AAAmira Abdelwahab
Amira Abdelwahab
MMMohamed Mostafa
Mohamed Mostafa
The social network is considered a part of most user’s lives as it contains more than a billion users, which makes it a source for spammers to spread their harmful activities. Most of the recent research focuses on detecting spammers using statistical features. However, such statistical features are changed over time, and spammers can defeat all detection systems by changing their behavior and using text paraphrasing. Therefore, we propose a novel technique for spam detection using deep neural network. We combine the tweet level detection with statistical feature detection and group their results over meta-classifier to build a robust technique. Moreover, we embed our technique with initial text paraphrasing for each detected tweet spam. We train our model using different datasets: random, continuous, balanced, and imbalanced. The obtained experimental results showed that our model has promising results in terms of accuracy, precision, and time, which make it applicable to be used in social networks.