Sadaf Nazneen Syed

Sadaf Nazneen Syed

Auto-generated profile, based on publicly available information

Sadaf Nazneen Syed

School of Computing and Engineering, University of Huddersfield, Huddersfield, U.K.

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications
15 August 2023 in IEEE Access
Verified
Journal Article
Open access
SSSadaf Nazneen Syed
Sadaf Nazneen Syed
Pavlos LazaridisPavlos Lazaridis
Pavlos Lazaridis
FKFaheem Khan
Faheem Khan
Qasim Zeeshan AhmedQasim Zeeshan Ahmed
Qasim Zeeshan Ahmed
MHMaryam Hafeez
Maryam Hafeez
Zaharias ZaharisZaharias Zaharis
Zaharias Zaharis
As we advance towards 6G communication systems, the number of network devices continues to increase resulting in spectrum scarcity. With the help of Spectrum Sensing (SS), Cognitive Radio (CR) exploits the frequency spectrum dynamically by detecting and transmitting in underutilized bands. The performance of 6G networks can be enhanced by utilizing Deep Neural Networks (DNNs) to perform SS. This paper provides a detailed survey of several Deep Learning (DL) algorithms used for SS by classifying them as Multilayer Perceptrons (MLPs), Convolutional Neural Networks (CNNs), Long Short-Term Memory (LSTM) networks, combined CNN-LSTM architectures and Autoencoders (AEs). The works are discussed in terms of the input provided to the DL algorithm, data acquisition technique used, data pre-processing technique used, architecture of each algorithm, evaluation metrics used, results obtained, and comparison with standard SS detectors. This survey further provides an overview of traditional ML algorithms and simple Artificial Neural Networks (ANNs) while highlighting the drawbacks of conventional SS approaches for completeness. A description of some publicly available Radio Frequency (RF) datasets is included and the need for comprehensive RF datasets and Transfer Learning (TL) is discussed. Furthermore, the research challenges related to the use of DL for SS are highlighted along with potential solutions.

30 October 2022
Verified
Conference Paper
Closed access
SSSadaf Nazneen Syed
Sadaf Nazneen Syed
Pavlos LazaridisPavlos Lazaridis
Pavlos Lazaridis
FKFaheem Khan
Faheem Khan
Qasim Zeeshan AhmedQasim Zeeshan Ahmed
Qasim Zeeshan Ahmed
MHMaryam Hafeez
Maryam Hafeez
Zaharias ZaharisZaharias Zaharis
Zaharias Zaharis
The number of network devices continues to rise as we advance towards 6G communication systems. A new range of frequencies is allocated while the earlier resources remain underutilized. Cognitive Radio (CR) enables the dynamic spectrum management of frequencies while detecting the unoccupied bands with the aid of spectrum sensing. By adopting Deep Learning (DL) for spectrum sensing, the performance of the 6G networks can be made more robust. This paper presents a survey of several DL algorithms such as, Multilayer Perceptrons (MLPs), Convolutional Neural Networks (CNNs), Long Short-Term Memory (LSTM) networks and combination of CNNs and LSTMs that have been applied for performing spectrum sensing. The application of DL to spectrum sensing is then demonstrated by considering it as a binary classification problem. An MLP with its hyperparameters optimized by using Grid Search algorithm is proposed to classify a dataset consisting of RadioML 2018.01A and noise samples with high accuracy.

3 February 2026 in IEEE Sensors Journal
Verified
Journal Article
Closed access
SSSadaf Nazneen Syed
Sadaf Nazneen Syed
Antoni IvanovAntoni Ivanov
Antoni Ivanov
FKFaheem Khan
Faheem Khan
Qasim Zeeshan AhmedQasim Zeeshan Ahmed
Qasim Zeeshan Ahmed
Vladimir PoulkovVladimir Poulkov
Vladimir Poulkov
Pavlos LazaridisPavlos Lazaridis
Pavlos Lazaridis
Spectrum sensing enables Secondary Users (SUs) in cognitive radio networks to opportunistically access underutilized spectrum without causing interference to Primary Users (PUs). While deep neural networks have shown strong potential for this task, most existing approaches rely heavily on simulated datasets, limiting their applicability in real-world environments. In this work, we present a real-world dataset collected using two Universal Software Radio Peripheral (USRP) B210 devices, where one emulates the PU and the other acts as the SU. Additionally, a baseline additive white Gaussian noise dataset is collected using a wired setup. We further propose a lightweight convolutional neural network with dilated convolutions that achieves the highest sensing accuracy across all modulation schemes. At a signal-to-noise ratio of -6 dB, it outperforms the second-best method by 19.35% while being 40.5% smaller in size and requiring 85.18% fewer floating-point operations. Experiments using our real-world datasets and synthetic datasets derived from the widely used RadioML2016.10A and RML22 datasets reveal a significant drop in model performance on real-world data, highlighting the limitations of simulation-based evaluations and the importance of realistic datasets in spectrum sensing research.