SMSumbal Maqsood

Sumbal Maqsood

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Sumbal Maqsood has a total of 22 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Top Cited Papers

    Lightweight large language model based hierarchical federated learning for B5G enabled IoT intrusion detection networks

    by Rami Mohawesh, Haitham Al-Obiedollah, Sumbal Maqsood, Haythem Bany Salameh


  • Open Access

    Cybersecurity challenges and solutions in 5G-enabled internet of things

    by Rami Mohawesh, Ali Al-Yousef, Tariq Daradkeh, Noor Aldeen Alawad, Moy’aWiah A. Al-Shannaq, Ahmad A. Saifan, Rafat Hammad, Yanal N. Alahmad, Sumbal Maqsood

    Due to the growing interconnection and sensitive nature of IoT applications, this article provides a comprehensive overview of cybersecurity in 5G-enabled Internet of Things (IoT) networks. The review highlights the significant potential of 5G technology while also emphasizing the need for ongoing work to mitigate its weaknesses and fully harness its advantages. In this context, prospective research avenues are crucial to enhance the resilience and security of 5G-enabled systems. The future directions outlined in this document are diverse and seek to tackle significant deficiencies in 5G-IoT cybersecurity research. A primary objective is to align theoretical analyses with practical implementations by examining specific assaults in IoT contexts, thus improving the comprehension of real-world vulnerabilities. Furthermore, as the 5G standard progresses through its implementation, continuous research must remain synchronized with improvements, focusing on components and features that are currently in development. Formulating effective protection and mitigation strategies to address sophisticated threats is essential for safeguarding this integrated environment. Furthermore, enhancing standards and regulatory frameworks is essential to ensure uniform security procedures across various businesses and areas, especially considering the global nature of 5G-IoT applications. Ultimately, investigating sophisticated attack scenarios that leverage the interaction between IoT devices and 5G infrastructure would enhance understanding of vulnerabilities and aid in the development of more resilient security measures. These directives underscore the necessity for ongoing, flexible research to guarantee the robustness and safety of 5G-enabled IoT networks.


  • Open Access

    Temporal attention to estimate continuous blood pressure using photoplethysmography signals

    by Sumbal Maqsood, Shuxiang Xu, Matthew Springer, Rami Mohawesh, Haythem Bany Salameh, Shivangi Gheewala

    Continuous blood pressure (BP) monitoring plays a crucial role in preventative health care because it provides invaluable assessment of an individual’s cardiovascular health. However, achieving accurate and non-invasive BP estimation remains a significant challenge. Motivated by the need for improved accuracy in BP estimation, this research proposes a novel deep-learning technique to estimate blood pressure from photoplethysmography (PPG) signals based on the temporal attention mechanism by selecting optimal features to improve the estimation accuracy. The proposed deep learning model consists of an embedded temporal attention employed to learn the temporal sequence and selects the optimal competitive features using bidirectional encoder and decoder. PPG features are extracted from traditional feature extraction techniques such as statistical, frequency, time domain-based analysis and chaotic features using two publicly available datasets MIMIC II and PPG-BP. The comparison of proposed model experimental results with the state-of-the-art models demonstrates the advancement of optimal feature selection technique for blood pressure measurement. The mean absolute error (MAE) and standard deviation SD for optimal feature extraction with the temporal attention mechanism model are 2.31 ± 3.16 mmHg and 1.13 ± 2.32 mmHg utilising MIMIC II data and 3.43 ± 3.08 mmHg and 3.29 ± 2.19 mmHg for PPG-BP dataset for SBP and DBP respectively. The proposed model results satisfied the standard requirements published by the British Hypertension Society (BHS) and US Association for the Advancement of Medical Instrumentation (AAMI) standards. The proposed solution can offer continuous BP estimation and can significantly enhance healthcare by helping individuals manage their cardiovascular health more effectively.


  • Factitious or fact? Learning textual representations for fake online review detection

    by Rami Mohawesh, Muna Al-Hawawreh, Sumbal Maqsood, Omar Alqudah


  • Open Access

    An explainable ensemble of multi-view deep learning model for fake review detection

    by Rami Mohawesh, Shuxiang Xu, Matthew Springer, Yaser Jararweh, Muna Al-Hawawreh, Sumbal Maqsood


  • Open Access

    Exploiting deep transformer models in textual review based recommender systems

    by Shivangi Gheewala, Shuxiang Xu, Soonja Yeom, Sumbal Maqsood


  • Multilingual deep learning framework for fake news detection using capsule neural network

    by Rami Mohawesh, Sumbal Maqsood, Qutaibah Althebyan

    Fake news detection is an essential task; however, the complexity of several languages makes fake news detection challenging. It requires drawing many conclusions about the numerous people involved to comprehend the logic behind some fake stories. Existing works cannot collect more semantic and contextual characteristics from documents in a particular multilingual text corpus. To bridge these challenges and deal with multilingual fake news detection, we present a semantic approach to the identification of fake news based on relational variables like sentiment, entities, or facts that may be directly derived from the text. Our model outperformed the state-of-the-art methods by approximately 3.97% for English to English, 1.41% for English to Hindi, 5.47% for English to Indonesian, 2.18% for English to Swahili, and 2.88% for English to Vietnamese language reviews on TALLIP fake news dataset. To the best of our knowledge, our paper is the first study that uses a capsule neural network for multilingual fake news detection.


  • Open Access

    A Benchmark Study of Machine Learning for Analysis of Signal Feature Extraction Techniques for Blood Pressure Estimation Using Photoplethysmography (PPG)

    by Sumbal Maqsood, Shuxiang Xu, Matthew Springer, Rami Mohawesh

    Cardiovascular related diseases are the most significant health concern around the globe. The most crucial health indicator is blood pressure because it gives essential information about the health of a patient’s heart. Cardiovascular diseases can be detected early and prevented if blood pressure is monitored continuously and regularly. Blood pressure cuffs, which are widely used to control blood flow in the arm or wrist when measuring blood pressure, are not practical for continuous blood pressure measurement. However, biosignals can be used for blood pressure estimation; but it is still critical and challenging. In this paper, we conducted a comprehensive analysis of feature extraction techniques for blood pressure estimation by using PPG signals. The feature extraction techniques were further divided into three subgroups to analyse the significance of each group. Group A includes time-based features; group B presents statistical feature extraction, and group C presents frequency domain-based features. The analysis employed several machine learning algorithms and compared their performance from many perspectives for the first time, to the best of our knowledge. The experimental results from two publicly available datasets demonstrated that the set of features belonging to group A were more reliable than other techniques for blood pressure estimation. We found that deep learning models achieved better performance than all traditional machine learning methods. We also found that the GRU model and Bi-LSTM achieved the best performance for time-domain features for blood pressure estimation. We believe the findings of this benchmark study will help researchers choose the most appropriate method for feature extraction and machine learning algorithms.