David Paul Steenson
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
David Paul Steenson has a total of 23 co-authors. Here are the top co-authors by number of shared publications:
- Harith Al-Safi
University of Leeds, UK
2 shared publications - Harith Ibrahim
School of Electronics and Electrical Engineering, University of Leeds, Leeds LS2 9JT, UK
2 shared publications - Ian D. Robertson
School of Electronic and Electrical Engineering, University of Leeds, Leeds, U.K.
2 shared publications - Viktor Doychinov
Faculty of Engineering and Informatics, University of Bradford, Bradford, UK
2 shared publications - Artitsupa Boontan
School of Chemical and Process Engineering, University of Leeds, Leeds, West Yorkshire United Kingdom of Great Britain and Northern Ireland
1 shared publication - Christopher Russell
University of Leeds, School of Electrical and Electronic Engineering, Leeds, West Yorkshire United Kingdom of Great Britain and Northern Ireland
1 shared publication
Latest Publications
- Open Access
Vega: LLM-Driven Intelligent Chatbot Platform for Internet of Things Control and Development
Large language models (LLMs) have revolutionized natural language processing (NLP), yet their potential in Internet of Things (IoT) and embedded systems (ESys) applications remains largely unexplored. Traditional IoT interfaces often require specialized knowledge, creating barriers for non-technical users. We present Vega, a modular system that leverages LLMs to enable intuitive, natural language control and interrogation of IoT devices, specifically, a Raspberry Pi (RPi) connected to various sensors, actuators, and devices. Our solution comprises three key components: a physical circuit with input and output devices used to showcase the LLM’s ability to interact with hardware, an RPi integrating a control server, and a web application integrating LLM logic. Users interact with the system through natural language, which the LLM interprets to remotely call appropriate commands for the RPi. The RPi executes these instructions on the physically connected circuit, with outcomes communicated back to the user via LLM-generated responses. The system’s performance is empirically evaluated using a range of task complexities and user scenarios, demonstrating its ability to handle complex and conditional logic without additional coding on the RPi, reducing the need for extensive programming on IoT devices. We showcase the system’s real-world applicability through physical circuit implementation while providing insights into its limitations and potential scalability. Our findings reveal that LLM-driven IoT control can effectively bridge the gap between complex device functionality and user-friendly interaction, and also opens new avenues for creative and intelligent IoT applications. This research offers insights into the design and implementation of LLM-integrated IoT interfaces.
Open AccessVega: LLM-Driven Intelligent Chatbot Platform for Internet of Things Control and Development
Large language models (LLMs) have revolutionized natural language processing (NLP), yet their potential in Internet of Things (IoT) and embedded systems (ESys) applications remains largely unexplored. Traditional IoT interfaces often require specialized knowledge, creating barriers for non-technical users. We present Vega, a modular system that leverages LLMs to enable intuitive, natural language control and interrogation of IoT devices, specifically, a Raspberry Pi (RPi) connected to various sensors, actuators, and devices. Our solution comprises three key components: a physical circuit with input and output devices used to showcase the LLM’s ability to interact with hardware, an RPi integrating a control server, and a web application integrating LLM logic. Users interact with the system through natural language, which the LLM interprets to remotely call appropriate commands for the RPi. The RPi executes these instructions on the physically connected circuit, with outcomes communicated back to the user via LLM-generated responses. The system’s performance is empirically evaluated using a range of task complexities and user scenarios, demonstrating its ability to handle complex and conditional logic without additional coding on the RPi, reducing the need for extensive programming on IoT devices. We showcase the system’s real-world applicability through physical circuit implementation while providing insights into its limitations and potential scalability. Our findings reveal that LLM-driven IoT control can effectively bridge the gap between complex device functionality and user-friendly interaction, and also opens new avenues for creative and intelligent IoT applications. This research offers insights into the design and implementation of LLM-integrated IoT interfaces.
- Open Access
- 7 May 2025
- Published by MDPI AG in Preprints.org
Vega: LLM-driven Intelligent Chatbot Platform for Internet of Things Control and Development
Large language models (LLMs) have revolutionized natural language processing (NLP), yet their potential in Internet of Things (IoT) and embedded systems (ESys) applications remains largely unexplored. Traditional IoT interfaces often require specialized knowledge, creating barriers for non-technical users. We present Vega a modular system that leverages LLMs to enable intuitive, natural language control and interrogation of IoT devices, specifically a Raspberry Pi (RPi) connected to various sensors, actuators and devices. Our solution comprises three key components: a physical circuit with input and output devices, an RPi integrating a control server, and a web application integrating LLM logic. Users interact with the system through natural language, which the LLM interprets to remotely call appropriate commands for the RPi. The RPi executes these instructions on the physically connected circuit, with outcomes communicated back to the user via LLM-generated responses. The system’s performance is empirically evaluated using a range of task complexities and user scenarios, demonstrating its ability to handle complex and conditional logic without additional coding on the RPi reducing the need for extensive programming on IoT devices. We showcase the system’s real-world applicability through physical circuit implementation, while providing insights into its limitations and potential scalability. Our findings reveal that LLM-driven IoT control can effectively bridge the gap between complex device functionality and user-friendly interaction, and also opens new avenues for creative and intelligent IoT applications. This research offers insights into the design and implementation of LLM-integrated IoT interfaces and is showcased in the following link https://youtu.be/CKV__A8G5Rk.
- 7 May 2025
- Published by MDPI AG in Preprints.org
Open AccessVega: LLM-driven Intelligent Chatbot Platform for Internet of Things Control and Development
Large language models (LLMs) have revolutionized natural language processing (NLP), yet their potential in Internet of Things (IoT) and embedded systems (ESys) applications remains largely unexplored. Traditional IoT interfaces often require specialized knowledge, creating barriers for non-technical users. We present Vega a modular system that leverages LLMs to enable intuitive, natural language control and interrogation of IoT devices, specifically a Raspberry Pi (RPi) connected to various sensors, actuators and devices. Our solution comprises three key components: a physical circuit with input and output devices, an RPi integrating a control server, and a web application integrating LLM logic. Users interact with the system through natural language, which the LLM interprets to remotely call appropriate commands for the RPi. The RPi executes these instructions on the physically connected circuit, with outcomes communicated back to the user via LLM-generated responses. The system’s performance is empirically evaluated using a range of task complexities and user scenarios, demonstrating its ability to handle complex and conditional logic without additional coding on the RPi reducing the need for extensive programming on IoT devices. We showcase the system’s real-world applicability through physical circuit implementation, while providing insights into its limitations and potential scalability. Our findings reveal that LLM-driven IoT control can effectively bridge the gap between complex device functionality and user-friendly interaction, and also opens new avenues for creative and intelligent IoT applications. This research offers insights into the design and implementation of LLM-integrated IoT interfaces and is showcased in the following link https://youtu.be/CKV__A8G5Rk.
- Open Access
- 12 October 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Quantum Electronics
- Vol. 25 (4) , 1-8
Tm3+ Tellurite-Modified-Silica Glass Thin Films Fabricated Using Ultrafast Laser Plasma Doping
Thin glass films have been produced by implanting $\rm Tm^{3+}$ doped and $\rm Tm^{3+}/Er^{3+}$ codoped tellurite glasses into silica substrates using ultrafast laser plasma doping for the first time. The resulting glass films had thicknesses of up to 2 μm, refractive indices of 1.5 - 1.65 and exhibited photoluminscence in the 1.5 - 2.1 μm wavelength region when excited with 808 nm and 976 nm laser diodes. The $\rm OH^-$ content of the silica glass substrate was also found to have an effect on the $\rm Tm^{3+}$ : $^3\rm F_4$ photoluminescence lifetime in the modified thin glass film layer, with the high $\rm OH^-$ containing substrate exhibiting a shorter lifetime. Through optimisation of the femtosecond laser ablation parameters, we have produced crack-free thin films of $\rm Tm^{3+}$ doped tellurite-modified silica glass layers with good thickness uniformities of ±10 nm, and the refractive index of the modified layer is up to 13% higher than the bare substrate material.- 12 October 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Quantum Electronics
- Vol. 25 (4) , 1-8
Open AccessTm3+ Tellurite-Modified-Silica Glass Thin Films Fabricated Using Ultrafast Laser Plasma Doping
Thin glass films have been produced by implanting $\rm Tm^{3+}$ doped and $\rm Tm^{3+}/Er^{3+}$ codoped tellurite glasses into silica substrates using ultrafast laser plasma doping for the first time. The resulting glass films had thicknesses of up to 2 μm, refractive indices of 1.5 - 1.65 and exhibited photoluminscence in the 1.5 - 2.1 μm wavelength region when excited with 808 nm and 976 nm laser diodes. The $\rm OH^-$ content of the silica glass substrate was also found to have an effect on the $\rm Tm^{3+}$ : $^3\rm F_4$ photoluminescence lifetime in the modified thin glass film layer, with the high $\rm OH^-$ containing substrate exhibiting a shorter lifetime. Through optimisation of the femtosecond laser ablation parameters, we have produced crack-free thin films of $\rm Tm^{3+}$ doped tellurite-modified silica glass layers with good thickness uniformities of ±10 nm, and the refractive index of the modified layer is up to 13% higher than the bare substrate material. - 5 June 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Components, Packaging and Manufacturing Technology
- Vol. 8 (9) , 1702-1710
Low-Cost Microfabrication for MEMS Switches and Varactors
This paper presents a low-cost microfabrication technique for manufacturing radio frequency microelectromechanical system (RF MEMS) switches and varactors without intensive clean-room environments. The fabrication process entails only laser microstructuring technique, non-clean-room microlithography, and standard wet-bench and hot-film emboss of SU-8 and ADEX polymers. MEMS movable structures were fabricated out of 14-μm-thick aluminum foils and suspended above coplanar-waveguide transmission lines, which were implemented on top of FR4 substrates via 5-μm-thick SU-8 dielectric anchors. Both MEMS structures and an FR4 substrate were integrated using micropatterned polymers, developed by using dry-film ADEX and SU-8 polymers, for a composite assembly. An average fabrication yield of higher than 60% was achieved, calculated from 10 fabrication attempts. The RF measurement results show that the RF MEMS devices fabricated by using the novel microfabrication process have good figures of merit, at much lower overall fabrication costs, as compared to the devices fabricated by conventional clean-room process, enabling it as a very good microfabrication process for cost-effective rapid prototyping of MEMS.
- 5 June 2018
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Components, Packaging and Manufacturing Technology
- Vol. 8 (9) , 1702-1710
Low-Cost Microfabrication for MEMS Switches and Varactors
This paper presents a low-cost microfabrication technique for manufacturing radio frequency microelectromechanical system (RF MEMS) switches and varactors without intensive clean-room environments. The fabrication process entails only laser microstructuring technique, non-clean-room microlithography, and standard wet-bench and hot-film emboss of SU-8 and ADEX polymers. MEMS movable structures were fabricated out of 14-μm-thick aluminum foils and suspended above coplanar-waveguide transmission lines, which were implemented on top of FR4 substrates via 5-μm-thick SU-8 dielectric anchors. Both MEMS structures and an FR4 substrate were integrated using micropatterned polymers, developed by using dry-film ADEX and SU-8 polymers, for a composite assembly. An average fabrication yield of higher than 60% was achieved, calculated from 10 fabrication attempts. The RF measurement results show that the RF MEMS devices fabricated by using the novel microfabrication process have good figures of merit, at much lower overall fabrication costs, as compared to the devices fabricated by conventional clean-room process, enabling it as a very good microfabrication process for cost-effective rapid prototyping of MEMS.
- Open Access
- 1 December 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-2
Investigation of mm-wave RTD based amplifiers
This work explores the applicability of Resonant Tunnelling Diodes as active elements in two different amplifier configurations in the range 25 GHz-35 GHz, with a view of implementing scaled versions at W-band and beyond, as frontend narrow-band low-noise amplifiers. On-wafer S-parameter measurements are used to represent devices in simulation software for increased fidelity. Initial results are promising, showing close to 10 dB gain at 30 GHz.
- 1 December 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-2
Open AccessInvestigation of mm-wave RTD based amplifiers
This work explores the applicability of Resonant Tunnelling Diodes as active elements in two different amplifier configurations in the range 25 GHz-35 GHz, with a view of implementing scaled versions at W-band and beyond, as frontend narrow-band low-noise amplifiers. On-wafer S-parameter measurements are used to represent devices in simulation software for increased fidelity. Initial results are promising, showing close to 10 dB gain at 30 GHz.
- 13 November 2009
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Microwave Theory and Techniques
- Vol. 57 (12) , 3254-3261
Laser Prototyping of Microwave Circuits in LTCC Technology
In this paper, a process for direct laser structuring of microwave circuits in low-temperature co-fired ceramic (LTCC) technology is reported. An efficient alternative to screen printing is proposed for prototyping circuits by laser patterning the conductors on the unfired tape. A line width and gap of 50 ¿m are achieved with laser machining. A range of samples has been studied using a scanning electron microscope in order to optimize the process parameters. The surface roughness of laser-treated samples is measured with a surface profiler and compared with the untreated samples. A method of creating microvias and trenches in thick LTCC substrate is also demonstrated. For 254 ¿m thick green tape, vias with a diameter and separation of 50 ¿ m are realized along with trenches having a width as small as 30 ¿m. The method of optimizing the laser machining process is described in detail. A band-stop mushroom resonator and a microstrip ring resonator filter are fabricated and their results compared against simulations.
- 13 November 2009
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Microwave Theory and Techniques
- Vol. 57 (12) , 3254-3261
Laser Prototyping of Microwave Circuits in LTCC Technology
In this paper, a process for direct laser structuring of microwave circuits in low-temperature co-fired ceramic (LTCC) technology is reported. An efficient alternative to screen printing is proposed for prototyping circuits by laser patterning the conductors on the unfired tape. A line width and gap of 50 ¿m are achieved with laser machining. A range of samples has been studied using a scanning electron microscope in order to optimize the process parameters. The surface roughness of laser-treated samples is measured with a surface profiler and compared with the untreated samples. A method of creating microvias and trenches in thick LTCC substrate is also demonstrated. For 254 ¿m thick green tape, vias with a diameter and separation of 50 ¿ m are realized along with trenches having a width as small as 30 ¿m. The method of optimizing the laser machining process is described in detail. A band-stop mushroom resonator and a microstrip ring resonator filter are fabricated and their results compared against simulations.
- 10 July 1995
- Published by American Physical Society (APS) in Physical Review Letters
- Vol. 75 (2) , 308-311
Nonequilibrium Acoustic Phonon-Assisted Tunneling in GaAs/(AlGa)As Double Barrier Devices
We report the first observations of nonequilibrium phonon-assisted tunneling in a double barrier resonant tunneling device in GaAs. The change in tunnel current produced by the phonons occurs at a bias voltage, which depends on the phonon energy showing that the device has potential as a phonon spectrometer.
- 10 July 1995
- Published by American Physical Society (APS) in Physical Review Letters
- Vol. 75 (2) , 308-311
Nonequilibrium Acoustic Phonon-Assisted Tunneling in GaAs/(AlGa)As Double Barrier Devices
We report the first observations of nonequilibrium phonon-assisted tunneling in a double barrier resonant tunneling device in GaAs. The change in tunnel current produced by the phonons occurs at a bias voltage, which depends on the phonon energy showing that the device has potential as a phonon spectrometer.