David R. Siddle

David R. Siddle

Auto-generated profile, based on publicly available information

David R. Siddle

Department of Engineering University of Leicester Leicester UK

Research Focus & Metrics

Academic Career Length

20Years (2007-Present)

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

Representative Publications

View All Publications
1 July 2025 in IEEE Access
Verified
Journal Article
Open access
AUAmadi Gabriel Udu
Amadi Gabriel Udu
MSMarwah T. Salman
Marwah T. Salman
MGMaryam K. Ghalati
Maryam K. Ghalati
ALAndrea Lecchini-Visintini
Andrea Lecchini-Visintini
DSDavid R. Siddle
David R. Siddle
Hongbiao DongHongbiao Dong
Hongbiao Dong
Class imbalance is a pervasive challenge in real-world machine learning (ML) applications, where the minority class, often the class of interest, is significantly underrepresented. This imbalance can degrade model performance, result in misleading evaluation metrics, and complicate validation processes. Two prominent data-augmentation techniques to address class imbalance are the Synthetic Minority Oversampling Technique (SMOTE) and Generative Adversarial Networks (GAN). However, both techniques have inherent limitations, motivating the emergence of novel variants designed to overcome these challenges. While previous reviews have typically focused on specific domains, conventional methodologies, or broad strategy overviews, this review presents a unified taxonomy that outlines the causes, types, and implications of class imbalance across diverse ML tasks. It further examines emerging trends in the application of SMOTE and GAN techniques, their limitations, and hybrid adaptations. By categorising imbalance types and analysing models, metrics, datasets, and comparative approaches, this review provides actionable insights and identifies future research directions for practitioners and researchers working to address class imbalance in real-world ML tasks.

8 January 2025 in IEEE Access
Verified
Journal Article
Open access
MSMarwah T. Salman
Marwah T. Salman
DSDavid R. Siddle
David R. Siddle
AUAmadi Gabriel Udu
Amadi Gabriel Udu
Multilevel quadrature amplitude modulation (M-QAM) combined with DC-bias in optical orthogonal frequency division multiplexing (DCO-OFDM) offers a spectrally efficient solution and adaptive transmission rates for indoor light-fidelity (Li-Fi) systems. However, a significant challenge posed by the DCO-OFDM scheme is the additional power of the DC bias required to ensure that the amplitudes of the transmitted signals are nonnegative. These biased signals are clipped according to optical power constraints, imposing clipping noise that affects the transmission bit error rate (BER). This performance degradation is conditioned by the adjustments made to the DC bias, which requires continuous modification to support adaptive transmission. Therefore, simultaneously addressing DC bias optimization and clipping mitigation is essential to provide reliable and power-efficient transmissions. This paper proposes a machine learning (ML) approach to predict the optimum DC bias based on the statistical properties of the OFDM signal and system characteristics. A robust ML regressor selection process using LazyPredict algorithm (LPA) was employed to identify the optimal regressors for developing the predictive model. The model demonstrated significant prediction accuracy for DC bias across a wide range of transmission settings. In particular, the models built on variants of gradient boosting regressor (GBR) and support vector regressor (SVR) demonstrated superior performance, with R-squared evaluation scores of 0.9792 and 0.9225, respectively, for two different set of features. Furthermore, the BER performance of our adaptive DC bias approach was compared to a fixed DC bias in adaptive DCO-OFDM transmission, demonstrating the superiority of our approach in effectively mitigating clipping noise at high transmission rates while maintaining power efficiency at lower rates. These results provide a promising solution for the future practical deployment of Li-Fi systems in indoor applications.

8 August 2007 in Radio Science
Verified
Journal Article
Open access
PDF file
DSD. R. Siddle
D. R. Siddle
EWE. M. Warrington
E. M. Warrington
SGS. D. Gunashekar
S. D. Gunashekar
Measurements of signal strength are reported for a study of UHF propagation on three transhorizon sea paths in the British Channel Islands. Enhancements of up to 30 dB from the mean occur for periods of hours or days, especially in the summer, and constitute about 5% of the overall data. The probability distribution of received power is tabulated for the three paths and various antenna heights, and is compared with predictions of signal strength using ITU‐R Recommendation P.1546‐2. The difference between median and upper decile in the data is much less than predicted, whereas the difference between upper decile and the upper percentile is much greater than predicted.

3 September 2018 in Radio Science
Verified
Journal Article
Open access
PDF file
ASA. J. Stocker
A. J. Stocker
DSD. R. Siddle
D. R. Siddle
EWE. M. Warrington
E. M. Warrington
GMG. Mariotti
G. Mariotti
DSD. Silvestri
D. Silvestri
MMM. Mercolino
M. Mercolino
Spacecraft communication systems operating at X band are strongly affected when the propagation path passes close to the Sun (which can be characterized by the Sun‐Earth‐Probe, SEP, angle). In this paper, a channel model that can generate a time series of signal amplitude and phase, and hence the signal in‐phase and quadrature values, is presented. For X band, the channel model reproduces the observations well for SEP > 0.8°. While the model has not been experimentally validated at SEP angles below 0.8°, the behavior is consistent with measurements reported in the literature and is therefore likely to be suitable for use, with caution, in that region too.

10 November 2025 in PLOS ONE
Verified
Journal Article
Open access
PDF file
MSMarwah Salman
Marwah Salman
DSDavid Siddle
David Siddle
YGYuan Gao
Yuan Gao
The direct current (DC) in optical orthogonal frequency division multiplexing (DCO-OFDM) scheme is commonly adopted in light fidelity (Li-Fi) technology as it offers a spectrally efficient solution. A prior study adopted a machine learning (ML)-based solution to predict the optimum DC bias using key parameters, including the statistical properties of the OFDM transmitted signal and a polynomial regression model. However, the model’s robustness decreased when the data structure was shuffled, indicating limited generalization to unseen data. This study builds upon that work by utilizing the same dataset and improving the prediction model with advanced ML tools, such as the LazyPredict algorithm (LPA), to systematically evaluate and select a regression model. A robust ML regressor selection process is proposed to ensure the reliability of predictions. Additionally, a comprehensive data analysis is conducted to assess the importance of features affecting the optimum DC bias. The results demonstrate that the ensemble learning algorithm, Random Forest (RF), outperforms other models with an R-squared of 0.953 and an RMSE of 0.233. A Friedman statistical test was applied to validate the results over five iterations of model training. Furthermore, hyperparameter tuning and bootstrap sampling were employed to conduct a deeper investigation into the model’s performance and stability. The proposed model significantly enhances the accuracy and robustness of DC bias prediction compared to previous approaches, ensuring consistent performance across different data distributions.

26 August 2026 in Radio Science
Verified
Journal Article
Open access
PDF file
AZA. Zeqaj
A. Zeqaj
Paolo TortoraPaolo Tortora
Paolo Tortora
EPE. Paolini
E. Paolini
ASA. J. Stocker
A. J. Stocker
DSD. R. Siddle
D. R. Siddle
MMM. Mercolino
M. Mercolino
During deep space missions, maintaining reliable communication between a spacecraft and Earth becomes particularly challenging during superior solar conjunctions, when the spacecraft passes behind the Sun relative to Earth. The highly ionized solar corona and solar wind create plasma inhomogeneities that severely affect radio signals, leading to phase scintillation, amplitude fading, and signal loss. These effects intensify as the Sun‐Earth‐Probe (SEP) angle decreases, resulting in frequent disruption of phase‐locking techniques crucial for successful signal demodulation. This paper comprehensively analyzes the communication subsystem to ensure reliable tracking, telemetry, and command (TT&C) links during superior solar conjunctions. By analyzing the effects of solar plasma on radio links, the paper proposes new operational methods and subsystem architectures that enhance the robustness of RF communication even in very harsh conditions. The solutions include modulation, coding, non‐coherent demodulation methods, and alternative channel models to mitigate scintillation effects and maintain stable communication links, particularly at low SEP angles. These strategies offer promising ways to improve data transmission reliability and maximize mission success during challenging solar conjunction phases.