Mahnoor Jamil

Ms. Mahnoor Jamil


Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

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

Representative Publications

View All Publications

30 May 2025 in Applied Sciences
Verified
Journal Article
Open access
PDF file
Mahnoor JamilMahnoor Jamil
Mahnoor Jamil
HTHristina Mihajloska Trpcheska
Hristina Mihajloska Trpcheska
APAleksandra Popovska-Mitrovikj
Aleksandra Popovska-Mitrovikj
VDVesna Dimitrova
Vesna Dimitrova
RCReiner Creutzburg
Reiner Creutzburg
Image-based spam poses a significant challenge for traditional text-based filters, as malicious content is often embedded within images to bypass keyword detection techniques. This study investigates and compares the performance of six machine learning models—ResNet50, XGBoost, Logistic Regression, LightGBM, Support Vector Machine (SVM), and VGG16—using a curated dataset containing 678 legitimate (ham) and 520 spam images. The novelty of this research lies in its comprehensive side-by-side evaluation of diverse models on the same dataset, using standardized dataset preprocessing, balanced data splits, and validation techniques. Model performance was assessed using evaluation metrics such as accuracy, receiver operating characteristic (ROC) curve, precision, recall, and area under the curve (AUC). The results indicate that ResNet50 achieved the highest classification performance, followed closely by XGBoost and Logistic Regression. This work provides practical insights into the strengths and limitations of traditional, ensemble-based, and deep learning models for image-based spam detection. The findings can support the development of more effective and generalizable spam filtering solutions in multimedia-rich communication platforms.


25 June 2024
Verified
Conference Paper
Closed access
PDF file
Mahnoor JamilMahnoor Jamil
Mahnoor Jamil
JIJohn Chukwu Ikechukwu
John Chukwu Ikechukwu
RCReiner M. Creutzburg
Reiner M. Creutzburg
The global impact of the COVID-19 pandemic has significantly disrupted healthcare systems worldwide. Amidst challenges, there is a crucial demand for efficient methodologies to expedite disease detection. This research underscores the potential of Deep Neural Networks in enhancing pandemic management over the past five years. Focusing on Artificial Intelligence (AI) application in COVID-19 detection through X-ray imaging, this research advocates using Visual Geometry Group (VGG’16), a Convolutional Neural Network (CNN) used for image classification with multiple layers. These CNNs act as classifier-based systems, treating images as structured data arrays to identify and learn patterns. Quantifying the model’s effectiveness through the accuracy score, this research reveals a 0.90% accuracy, indicating the model’s accurate detection of COVID-19 cases in X-ray images. Additionally, the study highlights a significant achievement with a less than 10% false positive rate, crucial for reliable and prompt COVID-19 diagnoses in the healthcare industry. In conclusion, this research presents an AI-driven approach, utilizing VGG’16 and convolutional neural networks to enhance the efficiency and accuracy of COVID-19 detection in X-ray imaging. The high accuracy score and low false positive rate positions this methodology as a valuable contribution, offering robust pandemic management and healthcare decision-making.