Piotr Wzorek
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Piotr Wzorek has a total of 38 co-authors. Here are the top co-authors by number of shared publications:
- Tomasz Kryjak
AGH University of Krakow
14 shared publications - Kamil Jeziorek
Embedded Vision Systems Group AGH University of Krakow Poland
9 shared publications - Krzysztof Blachut
AGH University of Krakow
8 shared publications - Hiroaki Nishi
Graduate School of Science and Technology, Keio University, Yokohama, Japan
4 shared publications - Hiroshi Nakano
Graduate School of Science and Technology, Keio University, Yokohama, Japan
4 shared publications - Manon Dampfhoffer
CEA-List, Université Grenoble Alpes
4 shared publications
Latest Publications
- Open Access
- 8 September 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Reconfigurable Technology and Systems
- Vol. 19 (3) , 1-34
Hardware-Accelerated Graph Neural Networks: An Alternative Approach for Event-Based Audio Classification and Keyword Spotting on SoC FPGA
As the volume of data recorded by embedded edge sensors increases, particularly from neuromorphic devices producing discrete event streams, there is a need for hardware-aware neural architectures that enable efficient, low-latency and energy-conscious local processing. To address this research gap, we present an FPGA implementation of event-graph neural networks for audio processing. We utilise an artificial cochlea that converts time-series signals into sparse event data, reducing memory and computation costs. Our architecture was implemented on an SoC FPGA and evaluated on two open source datasets. For the classification task, our baseline floating-point model achieves 92.7% accuracy on the SHD dataset—only 2.4% and 2% below the state-of-the-art—while requiring 10 \(\times\) and 67 \(\times\) fewer parameters, respectively. Compared to FPGA-based spiking neural networks, our quantised model reaches 92.3% accuracy, outperforming them by 19.3 pps while reducing resource usage and latency. For the SSC dataset, we report the first hardware-accelerated evaluation, and our models achieve 66.9–71.0% accuracy. Extending our conference work, we further demonstrate the first end-to-end FPGA implementation of the event-audio keyword spotting task, combining graph convolutional layers with recurrent sequence modelling for continuous, streaming operation. The system achieves 95% word-end detection accuracy, with only 10.53 µs latency and 1.18 W power consumption, establishing a strong benchmark for energy-efficient event-driven KWS.- 8 September 2026
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Reconfigurable Technology and Systems
- Vol. 19 (3) , 1-34
Open AccessHardware-Accelerated Graph Neural Networks: An Alternative Approach for Event-Based Audio Classification and Keyword Spotting on SoC FPGA
As the volume of data recorded by embedded edge sensors increases, particularly from neuromorphic devices producing discrete event streams, there is a need for hardware-aware neural architectures that enable efficient, low-latency and energy-conscious local processing. To address this research gap, we present an FPGA implementation of event-graph neural networks for audio processing. We utilise an artificial cochlea that converts time-series signals into sparse event data, reducing memory and computation costs. Our architecture was implemented on an SoC FPGA and evaluated on two open source datasets. For the classification task, our baseline floating-point model achieves 92.7% accuracy on the SHD dataset—only 2.4% and 2% below the state-of-the-art—while requiring 10 \(\times\) and 67 \(\times\) fewer parameters, respectively. Compared to FPGA-based spiking neural networks, our quantised model reaches 92.3% accuracy, outperforming them by 19.3 pps while reducing resource usage and latency. For the SSC dataset, we report the first hardware-accelerated evaluation, and our models achieve 66.9–71.0% accuracy. Extending our conference work, we further demonstrate the first end-to-end FPGA implementation of the event-audio keyword spotting task, combining graph convolutional layers with recurrent sequence modelling for continuous, streaming operation. The system achieves 95% word-end detection accuracy, with only 10.53 µs latency and 1.18 W power consumption, establishing a strong benchmark for energy-efficient event-driven KWS. - 1 September 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 362-363
Efficient FPGA Hardware Acceleration for Event-Based Perception in Mobile Robotics
- 1 September 2026
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 362-363
Efficient FPGA Hardware Acceleration for Event-Based Perception in Mobile Robotics
- 30 June 2026
- Published by Springer Nature
- p. 119-136
End-to-End Keyword Spotting on FPGA Using Graph Neural Networks with a Neuromorphic Auditory Sensor
- 30 June 2026
- Published by Springer Nature
- p. 119-136
End-to-End Keyword Spotting on FPGA Using Graph Neural Networks with a Neuromorphic Auditory Sensor
- Open Access
- 30 May 2026
- Published by Elsevier in Journal of Systems Architecture
- Vol. 177
Embedded graph convolutional networks for real-time event data processing on SoC FPGAs
- 30 May 2026
- Published by Elsevier in Journal of Systems Architecture
- Vol. 177
Open AccessEmbedded graph convolutional networks for real-time event data processing on SoC FPGAs
- Open Access
Hardware-accelerated graph neural networks: an alternative approach for neuromorphic event-based audio classification and keyword spotting on SoC FPGA
As the volume of data recorded by embedded edge sensors increases, particularly from neuromorphic devices producing discrete event streams, there is a growing need for hardware-aware neural architectures that enable efficient, low-latency, and energy-conscious local processing. We present an FPGA implementation of event-graph neural networks for audio processing. We utilise an artificial cochlea that converts time-series signals into sparse event data, reducing memory and computation costs. Our architecture was implemented on a SoC FPGA and evaluated on two open-source datasets. For classification task, our baseline floating-point model achieves 92.7% accuracy on SHD dataset - only 2.4% below the state of the art - while requiring over 10x and 67x fewer parameters. On SSC, our models achieve 66.9-71.0% accuracy. Compared to FPGA-based spiking neural networks, our quantised model reaches 92.3% accuracy, outperforming them by up to 19.3% while reducing resource usage and latency. For SSC, we report the first hardware-accelerated evaluation. We further demonstrate the first end-to-end FPGA implementation of event-audio keyword spotting, combining graph convolutional layers with recurrent sequence modelling. The system achieves up to 95% word-end detection accuracy, with only 10.53 microsecond latency and 1.18 W power consumption, establishing a strong benchmark for energy-efficient event-driven KWS.
Open AccessHardware-accelerated graph neural networks: an alternative approach for neuromorphic event-based audio classification and keyword spotting on SoC FPGA
As the volume of data recorded by embedded edge sensors increases, particularly from neuromorphic devices producing discrete event streams, there is a growing need for hardware-aware neural architectures that enable efficient, low-latency, and energy-conscious local processing. We present an FPGA implementation of event-graph neural networks for audio processing. We utilise an artificial cochlea that converts time-series signals into sparse event data, reducing memory and computation costs. Our architecture was implemented on a SoC FPGA and evaluated on two open-source datasets. For classification task, our baseline floating-point model achieves 92.7% accuracy on SHD dataset - only 2.4% below the state of the art - while requiring over 10x and 67x fewer parameters. On SSC, our models achieve 66.9-71.0% accuracy. Compared to FPGA-based spiking neural networks, our quantised model reaches 92.3% accuracy, outperforming them by up to 19.3% while reducing resource usage and latency. For SSC, we report the first hardware-accelerated evaluation. We further demonstrate the first end-to-end FPGA implementation of event-audio keyword spotting, combining graph convolutional layers with recurrent sequence modelling. The system achieves up to 95% word-end detection accuracy, with only 10.53 microsecond latency and 1.18 W power consumption, establishing a strong benchmark for energy-efficient event-driven KWS.
- 26 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 249-254
Memory-Efficient Hardware Implementation of Time-Ordered Recent Event (TORE) Volumes
There are many different approaches for Dynamic Vision Sensor events representation. Most of them rely on aggregation in a given time window, often discarding previous knowledge about the scene. Recently, a new approach was proposed to use the bio-inspired method named as Time-Ordered Recent Event (TORE) volumes. It contains “local memory” that is compressing the spiking information and can improve state-of-the-art performance in such tasks as event denoising, image reconstruction, classification etc. However, for applications in mobile robotics or automotive systems, not only high accuracy but also low latency and real-time performance are crucial. The solution to these requirements is the use of a computationally and energy-efficient specialized hardware platform. Although the method is presented as easy to implement and memory efficient, hardware acceleration of TORE is not straightforward. In this article we address the modifications to the original method that enables Time-Ordered Recent Event implementation for FPGA reconfigurable logic. The presented approach ensures real-time processing with 2.5 x memory reduction. Additionally, it allows for the use of either integrated or external memory resources, increasing the scalability and applicability of the proposed method.
- 26 August 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 249-254
Memory-Efficient Hardware Implementation of Time-Ordered Recent Event (TORE) Volumes
There are many different approaches for Dynamic Vision Sensor events representation. Most of them rely on aggregation in a given time window, often discarding previous knowledge about the scene. Recently, a new approach was proposed to use the bio-inspired method named as Time-Ordered Recent Event (TORE) volumes. It contains “local memory” that is compressing the spiking information and can improve state-of-the-art performance in such tasks as event denoising, image reconstruction, classification etc. However, for applications in mobile robotics or automotive systems, not only high accuracy but also low latency and real-time performance are crucial. The solution to these requirements is the use of a computationally and energy-efficient specialized hardware platform. Although the method is presented as easy to implement and memory efficient, hardware acceleration of TORE is not straightforward. In this article we address the modifications to the original method that enables Time-Ordered Recent Event implementation for FPGA reconfigurable logic. The presented approach ensures real-time processing with 2.5 x memory reduction. Additionally, it allows for the use of either integrated or external memory resources, increasing the scalability and applicability of the proposed method.
- 4 April 2025
- Published by Springer Nature
- p. 51-68
Hardware-Accelerated Event-Graph Neural Networks for Low-Latency Time-Series Classification on SoC FPGA
- 4 April 2025
- Published by Springer Nature
- p. 51-68
Hardware-Accelerated Event-Graph Neural Networks for Low-Latency Time-Series Classification on SoC FPGA
- Open Access
Hardware-Accelerated Event-Graph Neural Networks for Low-Latency Time-Series Classification on SoC FPGA
As the quantities of data recorded by embedded edge sensors grow, so too does the need for intelligent local processing. Such data often comes in the form of time-series signals, based on which real-time predictions can be made locally using an AI model. However, a hardware-software approach capable of making low-latency predictions with low power consumption is required. In this paper, we present a hardware implementation of an event-graph neural network for time-series classification. We leverage an artificial cochlea model to convert the input time-series signals into a sparse event-data format that allows the event-graph to drastically reduce the number of calculations relative to other AI methods. We implemented the design on a SoC FPGA and applied it to the real-time processing of the Spiking Heidelberg Digits (SHD) dataset to benchmark our approach against competitive solutions. Our method achieves a floating-point accuracy of 92.7% on the SHD dataset for the base model, which is only 2.4% and 2% less than the state-of-the-art models with over 10% and 67% fewer model parameters, respectively. It also outperforms FPGA-based spiking neural network implementations by 19.3% and 4.5%, achieving 92.3% accuracy for the quantised model while using fewer computational resources and reducing latency.
Open AccessHardware-Accelerated Event-Graph Neural Networks for Low-Latency Time-Series Classification on SoC FPGA
As the quantities of data recorded by embedded edge sensors grow, so too does the need for intelligent local processing. Such data often comes in the form of time-series signals, based on which real-time predictions can be made locally using an AI model. However, a hardware-software approach capable of making low-latency predictions with low power consumption is required. In this paper, we present a hardware implementation of an event-graph neural network for time-series classification. We leverage an artificial cochlea model to convert the input time-series signals into a sparse event-data format that allows the event-graph to drastically reduce the number of calculations relative to other AI methods. We implemented the design on a SoC FPGA and applied it to the real-time processing of the Spiking Heidelberg Digits (SHD) dataset to benchmark our approach against competitive solutions. Our method achieves a floating-point accuracy of 92.7% on the SHD dataset for the base model, which is only 2.4% and 2% less than the state-of-the-art models with over 10% and 67% fewer model parameters, respectively. It also outperforms FPGA-based spiking neural network implementations by 19.3% and 4.5%, achieving 92.3% accuracy for the quantised model while using fewer computational resources and reducing latency.
- 22 June 2024
- Published by Springer Nature
- p. 110-122
Optimising Graph Representation for Hardware Implementation of Graph Convolutional Networks for Event-Based Vision
- 22 June 2024
- Published by Springer Nature
- p. 110-122
Optimising Graph Representation for Hardware Implementation of Graph Convolutional Networks for Event-Based Vision