Daniel Robert Franklin
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Daniel Robert Franklin has a total of 196 co-authors. Here are the top co-authors by number of shared publications:
- Mehran Abolhasan
School of Electrical and Data Engineering, University of Technology Sydney, Ultimo, NSW, Australia
48 shared publications - Farzad Safaei
University of Wollongong, Wollongong, NSW, Australia
31 shared publications - Mitra Safavi-Naeini
Australian Nuclear Science and Technology Organisation (ANSTO), Lucas Heights, Australia
23 shared publications - Anatoly B. Rosenfeld
Centre for Medical Radiation Physics, University of Wollongong
17 shared publications - Susanna Guatelli
University of Wollongong
11 shared publications - Marco Petasecca
Centre for Medical Radiation Physics, University of Wollongong
10 shared publications
Latest Publications
- Open Access
- 26 August 2026
- Published by IOP Publishing in Physics in Medicine & Biology
- Vol. 71 (16) , 16TR01
Laser-driven particle accelerators for cancer therapy: a review of state-of-the-art techniques, challenges and opportunities
Charged particle radiation therapy (such as electron, proton and heavy ion therapies) is presently delivered via large linear or circular electromagnetic particle accelerators. There is growing interest in laser plasma accelerators as an alternative source for therapeutic charged particle radiation, including protons, carbon ions, and very high energy electrons. Laser plasma accelerators offer the potential for extremely high dose rates in a very compact physical footprint. While these radiation sources advancing rapidly, there remain many technical challenges to be overcome prior to clinical translation. In this work, we outline the current state of the art in laser-plasma accelerators for proton, carbon ion and very high energy electron radiation therapy, discuss recent in vitro and in vivo experimental results, and identify the key challenges and opportunities offered by this promising family of technologies.
- 26 August 2026
- Published by IOP Publishing in Physics in Medicine & Biology
- Vol. 71 (16) , 16TR01
Open AccessLaser-driven particle accelerators for cancer therapy: a review of state-of-the-art techniques, challenges and opportunities
Charged particle radiation therapy (such as electron, proton and heavy ion therapies) is presently delivered via large linear or circular electromagnetic particle accelerators. There is growing interest in laser plasma accelerators as an alternative source for therapeutic charged particle radiation, including protons, carbon ions, and very high energy electrons. Laser plasma accelerators offer the potential for extremely high dose rates in a very compact physical footprint. While these radiation sources advancing rapidly, there remain many technical challenges to be overcome prior to clinical translation. In this work, we outline the current state of the art in laser-plasma accelerators for proton, carbon ion and very high energy electron radiation therapy, discuss recent in vitro and in vivo experimental results, and identify the key challenges and opportunities offered by this promising family of technologies.
- Open Access
- 13 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 75719-75734
In-Band Network Telemetry for End-to-End Service Performance Monitoring in Broadband Networks: A Survey and Deployment Feasibility Analysis
End-to-end performance monitoring is essential for ensuring service reliability and operational visibility in modern telecommunications networks. Traditional monitoring techniques often rely on out-of-band measurements, which provide limited visibility into real-time packet behavior across complex network infrastructures. In-band telemetry has emerged as a promising approach that enables performance information to be collected directly from packets as they traverse the network. This article presents a comprehensive survey of in-band telemetry techniques and evaluates their applicability to end-to-end performance monitoring in broadband networks. The survey first examines header stamping approaches, including mechanisms such as In-band Network Telemetry (INT), In-situ Operations, Administration, and Maintenance (IOAM), and related implementations. It then reviews packet marking and selective sampling techniques that aim to reduce measurement overhead while maintaining monitoring accuracy. Hybrid approaches that combine multiple telemetry mechanisms are also discussed. Building on this taxonomy, the paper analyzes the feasibility of deploying in-band telemetry across multi-segment telecommunications environments using broadband services as a representative use case. The analysis highlights several limitations in current mechanisms, including the absence of standardized Layer-2 telemetry support, the assumption of single-domain deployment, and the lack of mechanisms for sharing telemetry information across adjacent network segments. Finally, the paper identifies key open challenges and research directions required to enable scalable, interoperable, and operationally viable end-to-end telemetry solutions for future broadband networks.
- 13 May 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 75719-75734
Open AccessIn-Band Network Telemetry for End-to-End Service Performance Monitoring in Broadband Networks: A Survey and Deployment Feasibility Analysis
End-to-end performance monitoring is essential for ensuring service reliability and operational visibility in modern telecommunications networks. Traditional monitoring techniques often rely on out-of-band measurements, which provide limited visibility into real-time packet behavior across complex network infrastructures. In-band telemetry has emerged as a promising approach that enables performance information to be collected directly from packets as they traverse the network. This article presents a comprehensive survey of in-band telemetry techniques and evaluates their applicability to end-to-end performance monitoring in broadband networks. The survey first examines header stamping approaches, including mechanisms such as In-band Network Telemetry (INT), In-situ Operations, Administration, and Maintenance (IOAM), and related implementations. It then reviews packet marking and selective sampling techniques that aim to reduce measurement overhead while maintaining monitoring accuracy. Hybrid approaches that combine multiple telemetry mechanisms are also discussed. Building on this taxonomy, the paper analyzes the feasibility of deploying in-band telemetry across multi-segment telecommunications environments using broadband services as a representative use case. The analysis highlights several limitations in current mechanisms, including the absence of standardized Layer-2 telemetry support, the assumption of single-domain deployment, and the lack of mechanisms for sharing telemetry information across adjacent network segments. Finally, the paper identifies key open challenges and research directions required to enable scalable, interoperable, and operationally viable end-to-end telemetry solutions for future broadband networks.
- Open Access
- 2 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 34011-34029
Graph-Transformer for Spatiotemporal Soil Moisture Forecasting Using Multimodal Remote Sensing Data
Soil moisture is a key variable in the hydrological cycle, essential for drought monitoring, water resource management, and agriculture decision-making. However, accurate forecasting of soil moisture remains a challenge due to the nonlinear nature of soil water dynamics and the complex influencing factors. While deep learning models such as Long Short-Term Memory and Transformers have advanced temporal modelling, they struggle with spatial dependencies across diverse geographic locations, as their architecture primarily focuses on temporal dynamics. To address this limitation, we propose a novel hybrid framework that integrates graph neural networks with state-of-the-art time series models. We introduce a Graph-Transformer architecture for improved soil moisture forecasting by jointly modelling spatiotemporal dependencies. Our model forecasts soil moisture at two depths including 0–7 cm, referred to as surface soil moisture (SSM), and 7–28 cm, representing the root-zone soil moisture (RZSM). Evaluation using four years of multimodal data from 19 sites across Australia shows that the proposed Graph-Transformer model outperforms the standard Transformer, achieving improvements of up to 10% in the coefficient of determination ( $R^{2}$ ) and 8% in Root Mean Square Error (RMSE) for SSM, and up to 11% and 9% in $R^{2}$ and RMSE, respectively, for RZSM. These findings highlight that integrating graph architecture with temporal models can potentially enhance soil moisture forecasting across diverse geographic regions, benefiting effective drought monitoring and agricultural planning.
- 2 March 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 14, 34011-34029
Open AccessGraph-Transformer for Spatiotemporal Soil Moisture Forecasting Using Multimodal Remote Sensing Data
Soil moisture is a key variable in the hydrological cycle, essential for drought monitoring, water resource management, and agriculture decision-making. However, accurate forecasting of soil moisture remains a challenge due to the nonlinear nature of soil water dynamics and the complex influencing factors. While deep learning models such as Long Short-Term Memory and Transformers have advanced temporal modelling, they struggle with spatial dependencies across diverse geographic locations, as their architecture primarily focuses on temporal dynamics. To address this limitation, we propose a novel hybrid framework that integrates graph neural networks with state-of-the-art time series models. We introduce a Graph-Transformer architecture for improved soil moisture forecasting by jointly modelling spatiotemporal dependencies. Our model forecasts soil moisture at two depths including 0–7 cm, referred to as surface soil moisture (SSM), and 7–28 cm, representing the root-zone soil moisture (RZSM). Evaluation using four years of multimodal data from 19 sites across Australia shows that the proposed Graph-Transformer model outperforms the standard Transformer, achieving improvements of up to 10% in the coefficient of determination ( $R^{2}$ ) and 8% in Root Mean Square Error (RMSE) for SSM, and up to 11% and 9% in $R^{2}$ and RMSE, respectively, for RZSM. These findings highlight that integrating graph architecture with temporal models can potentially enhance soil moisture forecasting across diverse geographic regions, benefiting effective drought monitoring and agricultural planning.
- Open Access
- 9 February 2026
- Published by Association for Computing Machinery (ACM)
- p. 100-108
Q3Vision: A Vision-Based Framework for Game-State Reconstruction in Quake III Arena
- 9 February 2026
- Published by Association for Computing Machinery (ACM)
- p. 100-108
Open AccessQ3Vision: A Vision-Based Framework for Game-State Reconstruction in Quake III Arena
- Open Access
- 20 December 2025
- Published by Elsevier in Computer Physics Communications
- Vol. 321
Benchmarking Monte Carlo codes for the modelling of low-energy neutron production target reactions
- 20 December 2025
- Published by Elsevier in Computer Physics Communications
- Vol. 321
Open AccessBenchmarking Monte Carlo codes for the modelling of low-energy neutron production target reactions
- Top Cited PapersOpen Access
- 16 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 166188-166209
A Data-Driven Review of Remote Sensing-Based Data Fusion in Precision Agriculture From Foundational to Transformer-Based Techniques
This review explores recent advancements in data fusion techniques and Transformer-based remote sensing applications in precision agriculture. Using a systematic, data-driven approach, we analyse research trends from 1994 to 2024, identifying key developments in data fusion, remote sensing, and AI-driven agricultural monitoring. While traditional machine learning and deep learning approaches have demonstrated effectiveness in agricultural decision-making, challenges such as limited scalability, suboptimal feature extraction, and reliance on extensive labelled data persist. This study examines the comparative advantages of Transformer-based fusion methods, particularly their ability to model spatiotemporal dependencies and integrate heterogeneous datasets for applications in soil analysis, crop classification, yield prediction, and disease detection. A comparative analysis of multimodal data fusion approaches is conducted, evaluating data types, fusion techniques, and remote sensing platforms. We demonstrate how Transformers outperform conventional models by enhancing prediction accuracy, mitigating feature redundancy, and optimizing large-scale data integration. Furthermore, we propose a structured roadmap for implementing data fusion in agricultural remote sensing, outlining best practices for ground-truth data selection, platform integration, and fusion model design. By addressing key research gaps and providing a strategic framework, this review offers valuable insights for advancing precision agriculture through AI-driven data fusion techniques.
- 16 September 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 13, 166188-166209
Top Cited PapersOpen AccessA Data-Driven Review of Remote Sensing-Based Data Fusion in Precision Agriculture From Foundational to Transformer-Based Techniques
This review explores recent advancements in data fusion techniques and Transformer-based remote sensing applications in precision agriculture. Using a systematic, data-driven approach, we analyse research trends from 1994 to 2024, identifying key developments in data fusion, remote sensing, and AI-driven agricultural monitoring. While traditional machine learning and deep learning approaches have demonstrated effectiveness in agricultural decision-making, challenges such as limited scalability, suboptimal feature extraction, and reliance on extensive labelled data persist. This study examines the comparative advantages of Transformer-based fusion methods, particularly their ability to model spatiotemporal dependencies and integrate heterogeneous datasets for applications in soil analysis, crop classification, yield prediction, and disease detection. A comparative analysis of multimodal data fusion approaches is conducted, evaluating data types, fusion techniques, and remote sensing platforms. We demonstrate how Transformers outperform conventional models by enhancing prediction accuracy, mitigating feature redundancy, and optimizing large-scale data integration. Furthermore, we propose a structured roadmap for implementing data fusion in agricultural remote sensing, outlining best practices for ground-truth data selection, platform integration, and fusion model design. By addressing key research gaps and providing a strategic framework, this review offers valuable insights for advancing precision agriculture through AI-driven data fusion techniques.
- Open Access
- 25 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. PP, 1
Failures and Resilience in the IP Era: Navigating the Fragility of Modern Telecommunications Networks: The Sovereign Functions
Telecommunications networks have become critical infrastructure, with increasing reliance on their continuous availability driven by expectations of uninterrupted connectivity, real-time communication, and a surge in connected devices across both consumer and industrial domains. Over time, industrial systems and machine-to-machine applications have transitioned from isolated, purpose-built infrastructures to shared, general-purpose IP-based networks. While this evolution has enabled greater flexibility and integration, it has also introduced operational complexity and new classes of failure. Although physical layer redundancy and geographic isolation remain essential components of network resilience, modern networks are heavily dependent on a set of interdependent IP functions. These include routing, addressing & naming services, and time synchronisation—each playing a sovereign role in end-to-end service continuity. Importantly, these functions are increasingly coupled with a range of supporting services—such as authentication & access control, license management, and network configuration & management—which, while not formally specified within the IP protocol suite, are essential to its operation and resilience. This paper presents a failure-centric survey of sovereign and supporting functions in modern telecommunications networks, illustrating how real-world outages often stem from failures in these interdependent layers, which form the organising lens for this study. Through detailed case studies, we illustrate the severe consequences of such failures on network services, along with their broader economic and corporate ramifications. Furthermore, we explore potential mitigation strategies and emphasize the need for continued research to develop more resilient network architectures capable of withstanding inherent vulnerabilities in IP-based systems. This study contributes to enhancing service resilience amid the growing complexity and demands of modern mobile and fixed networks.
- 25 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. PP, 1
Open AccessFailures and Resilience in the IP Era: Navigating the Fragility of Modern Telecommunications Networks: The Sovereign Functions
Telecommunications networks have become critical infrastructure, with increasing reliance on their continuous availability driven by expectations of uninterrupted connectivity, real-time communication, and a surge in connected devices across both consumer and industrial domains. Over time, industrial systems and machine-to-machine applications have transitioned from isolated, purpose-built infrastructures to shared, general-purpose IP-based networks. While this evolution has enabled greater flexibility and integration, it has also introduced operational complexity and new classes of failure. Although physical layer redundancy and geographic isolation remain essential components of network resilience, modern networks are heavily dependent on a set of interdependent IP functions. These include routing, addressing & naming services, and time synchronisation—each playing a sovereign role in end-to-end service continuity. Importantly, these functions are increasingly coupled with a range of supporting services—such as authentication & access control, license management, and network configuration & management—which, while not formally specified within the IP protocol suite, are essential to its operation and resilience. This paper presents a failure-centric survey of sovereign and supporting functions in modern telecommunications networks, illustrating how real-world outages often stem from failures in these interdependent layers, which form the organising lens for this study. Through detailed case studies, we illustrate the severe consequences of such failures on network services, along with their broader economic and corporate ramifications. Furthermore, we explore potential mitigation strategies and emphasize the need for continued research to develop more resilient network architectures capable of withstanding inherent vulnerabilities in IP-based systems. This study contributes to enhancing service resilience amid the growing complexity and demands of modern mobile and fixed networks.
- Open Access
- 5 August 2025
- Published by Springer Nature in Scientific Reports
- Vol. 15 (1) , 1-14
Deep learning based localisation and classification of gamma photon interactions in thick nanocomposite and ceramic monolithic scintillators
Accurate localisation of the first point of interaction (FPoI) of incident gamma photons in monolithic scintillators is crucial for many radiation-based imaging applications - in particular, accurate estimation of the lines of response in positron emission tomography (PET). This is particularly challenging in thick nanocomposite and ceramic scintillator materials, which exhibit high levels of Rayleigh scattering compared to monocrystalline scintillators. In this work, we evaluate deep neural network-based approaches for (1) classifying the mode of photon interaction using an InceptionNet-based classifier and (2) accurately estimating the location of the FPoI based on scintillation photon distributions in several monolithic nanocomposite and ceramic scintillators using both CNN- and InceptionNet-based regression networks. The classifier was able to correctly categorise single-energy deposition events with an accuracy $$\ge$$ 90.1%, two-deposition interactions with an accuracy $$\ge$$ 77.6% and three-plus deposition interactions with an accuracy $$\ge$$ 66.7%. Across the evaluated materials, median total localisation error ranged from 0.58 mm to 2.91 mm with the CNN and 0.59 mm to 2.10 mm with InceptionNet, assuming 50% detector quantum efficiency. Localisation in nanocomposites using the InceptionNet-based regression network improved the most relative to previously-reported results based on classical techniques, in some cases approaching the accuracy achieved with ceramic scintillators.- 5 August 2025
- Published by Springer Nature in Scientific Reports
- Vol. 15 (1) , 1-14
Open AccessDeep learning based localisation and classification of gamma photon interactions in thick nanocomposite and ceramic monolithic scintillators
Accurate localisation of the first point of interaction (FPoI) of incident gamma photons in monolithic scintillators is crucial for many radiation-based imaging applications - in particular, accurate estimation of the lines of response in positron emission tomography (PET). This is particularly challenging in thick nanocomposite and ceramic scintillator materials, which exhibit high levels of Rayleigh scattering compared to monocrystalline scintillators. In this work, we evaluate deep neural network-based approaches for (1) classifying the mode of photon interaction using an InceptionNet-based classifier and (2) accurately estimating the location of the FPoI based on scintillation photon distributions in several monolithic nanocomposite and ceramic scintillators using both CNN- and InceptionNet-based regression networks. The classifier was able to correctly categorise single-energy deposition events with an accuracy $$\ge$$ 90.1%, two-deposition interactions with an accuracy $$\ge$$ 77.6% and three-plus deposition interactions with an accuracy $$\ge$$ 66.7%. Across the evaluated materials, median total localisation error ranged from 0.58 mm to 2.91 mm with the CNN and 0.59 mm to 2.10 mm with InceptionNet, assuming 50% detector quantum efficiency. Localisation in nanocomposites using the InceptionNet-based regression network improved the most relative to previously-reported results based on classical techniques, in some cases approaching the accuracy achieved with ceramic scintillators. - Open Access
- 26 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in TechRxiv
Resilience in the IP Era: Navigating the Fragility of Modern Telecommunications Networks: The Sovereign Functions
Global reliance on telecommunications networks has grown significantly over the past 30 years, driven by expectations of ubiquitous access and demand for real-time communication and streaming services. Concurrently, industrial and machine-to-machine communications have also transitioned from dedicated proprietary networks to commodity IP networks, leading to rapid growth in connected devices across both consumer and enterprise applications. This dependence on complex IP networks calls for a holistic understanding of potential failure points to ensure network resilience. The transition has also exposed the fragility of routing protocols and other distributed IP functions, shaped by the interplay of network complexity, automation, and human factors. This paper examines the shift from traditional redundancy models—based on physical redundancy and geographic isolation of failures—to modern IPcentric networks, where even minor configuration errors can lead to national-scale outages. We identify critical IP functions that are particularly susceptible to triggering cascading failures or present significant challenges in diagnosis and remediation. Through case studies, we illustrate the severe consequences of such failures on network services, along with their broader economic and corporate ramifications. Furthermore, we explore potential mitigation strategies and emphasize the need for continued research to develop more resilient network architectures capable of withstanding inherent vulnerabilities in IP-based systems. This study contributes to enhancing service resilience amid the growing complexity and demands of modern mobile and fixed networks.
- 26 July 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE) in TechRxiv
Open AccessResilience in the IP Era: Navigating the Fragility of Modern Telecommunications Networks: The Sovereign Functions
Global reliance on telecommunications networks has grown significantly over the past 30 years, driven by expectations of ubiquitous access and demand for real-time communication and streaming services. Concurrently, industrial and machine-to-machine communications have also transitioned from dedicated proprietary networks to commodity IP networks, leading to rapid growth in connected devices across both consumer and enterprise applications. This dependence on complex IP networks calls for a holistic understanding of potential failure points to ensure network resilience. The transition has also exposed the fragility of routing protocols and other distributed IP functions, shaped by the interplay of network complexity, automation, and human factors. This paper examines the shift from traditional redundancy models—based on physical redundancy and geographic isolation of failures—to modern IPcentric networks, where even minor configuration errors can lead to national-scale outages. We identify critical IP functions that are particularly susceptible to triggering cascading failures or present significant challenges in diagnosis and remediation. Through case studies, we illustrate the severe consequences of such failures on network services, along with their broader economic and corporate ramifications. Furthermore, we explore potential mitigation strategies and emphasize the need for continued research to develop more resilient network architectures capable of withstanding inherent vulnerabilities in IP-based systems. This study contributes to enhancing service resilience amid the growing complexity and demands of modern mobile and fixed networks.
- 12 December 2024
- Published by Elsevier in Physica Medica
- Vol. 129, 104866
An exploratory study of shielding strategies for boron neutron capture discrimination in 10B Neutron Capture Enhanced Particle Therapy
- 12 December 2024
- Published by Elsevier in Physica Medica
- Vol. 129, 104866
An exploratory study of shielding strategies for boron neutron capture discrimination in 10B Neutron Capture Enhanced Particle Therapy