Piotr Łuczak
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Piotr Łuczak has a total of 24 co-authors. Here are the top co-authors by number of shared publications:
- Andrzej Romanowski
Lodz University of Technology, Lodz, Poland
4 shared publications - Krzysztof Ślot
Institute of Applied Computer Science, Lodz University of Technology, 90-924 Lodz, Poland
4 shared publications - Tomasz Jaworski
Lodz University of Technology, Lodz, Poland
3 shared publications - Izabela Perenc
Institute of Applied Computer Science, Lodz University of Technology, Stefanowskiego 18/22, 90-537 Łódź, Poland
2 shared publications - Jacek Kucharski
Institute of Applied Computer Science, Lodz University of Technology, Stefanowskiego 18, 90-537 Lodz, Poland
2 shared publications - Krzysztof Grudzień
Institute of Applied Computer Science, Lodz University of Technology, Łódź, Poland
2 shared publications
Latest Publications
- 22 June 2026
- Published by MIT Press in Neural Computation
- Vol. 38 (8) , 1-21
A Hidden Markov Model–Inspired Sequence Classification Method for Hyperdimensional Computing
This letter introduces a novel method for discrete-sequence classification within the hyperdimensional computing (HDC) paradigm. The method, inspired by the concept of hidden Markov models (HMM), implements mechanisms that effectively address the major challenges arising in analyzing sequences generated by real-world processes, such as variable length, misalignment, symbol repetitions, omissions, or insertions. All algebraic transformations of input data in HMM-based sequence classification are replaced by bitwise operations on appropriately derived hyperdimensional binary vectors (hypervectors). The proposed hypervector transformation pipeline mirrors the algebraic manipulations of the HMM paradigm and involves a procedure that prevents information decay when processing longer sequences. Since only binary bit-wise operations on hypervectors are used in computations, the proposed method is well suited for hardware implementation, especially in the form of custom in-memory computing VLSI devices. The experimental evaluation of the proposed method, conducted on both artificial and real-world data sets, demonstrates its superiority over existing HDC-based sequence analysis approaches, yielding noticeable gains in classification accuracy. We also demonstrate that the proposed approach, like most HDC-based sequence classification methods, is robust against adverse physical, internal, or external factors that induce bit flips in the underlying hardware, which could entirely corrupt the outcomes of classical sequence-analysis methods, such as HMMs.
- 22 June 2026
- Published by MIT Press in Neural Computation
- Vol. 38 (8) , 1-21
A Hidden Markov Model–Inspired Sequence Classification Method for Hyperdimensional Computing
This letter introduces a novel method for discrete-sequence classification within the hyperdimensional computing (HDC) paradigm. The method, inspired by the concept of hidden Markov models (HMM), implements mechanisms that effectively address the major challenges arising in analyzing sequences generated by real-world processes, such as variable length, misalignment, symbol repetitions, omissions, or insertions. All algebraic transformations of input data in HMM-based sequence classification are replaced by bitwise operations on appropriately derived hyperdimensional binary vectors (hypervectors). The proposed hypervector transformation pipeline mirrors the algebraic manipulations of the HMM paradigm and involves a procedure that prevents information decay when processing longer sequences. Since only binary bit-wise operations on hypervectors are used in computations, the proposed method is well suited for hardware implementation, especially in the form of custom in-memory computing VLSI devices. The experimental evaluation of the proposed method, conducted on both artificial and real-world data sets, demonstrates its superiority over existing HDC-based sequence analysis approaches, yielding noticeable gains in classification accuracy. We also demonstrate that the proposed approach, like most HDC-based sequence classification methods, is robust against adverse physical, internal, or external factors that induce bit flips in the underlying hardware, which could entirely corrupt the outcomes of classical sequence-analysis methods, such as HMMs.
- Open Access
Very-Large-Scale Integration-Friendly Method for Vital Activity Detection with Frequency-Modulated Continuous Wave Radars
A simple algorithm for respiratory activity detection in data produced by Frequency-Modulated Continuous-Wave (FMCW) radars is presented in this paper. The proposed computational architecture can be directly mapped onto custom digital–analog VLSI hardware, which is a unique approach in research on intelligent FMCW sensor development, offering a potential energy-efficient data analysis solution for target applications, such as preventing human trafficking or providing life-sign detection under limited visibility. The algorithm comprises two main modules. The first one summarizes radar-produced data into a descriptor reflecting the amount of motion that occurs within appropriately determined time intervals. The second one classifies a sequence of the produced descriptors using a recurrent neural network composed of gated recurrent units. To ensure the algorithm’s implementation feasibility, an analog VLSI circuit comprising its main functional blocks has been designed, manufactured, and tested, providing constraints for neural model derivation. The adverse effects of the primary constraint, the severe restriction on admissible weight resolution, have been handled by introducing a novel training loss component and a simple mechanism for diversifying the effective weight sets of different network neurons. Experimental evaluation of the presented method, performed using the dataset of indoor recordings, indicates that the proposed simple, hardware implementation-friendly algorithm provides over 94% human detection accuracy and similar F1 scores.
Open AccessVery-Large-Scale Integration-Friendly Method for Vital Activity Detection with Frequency-Modulated Continuous Wave Radars
A simple algorithm for respiratory activity detection in data produced by Frequency-Modulated Continuous-Wave (FMCW) radars is presented in this paper. The proposed computational architecture can be directly mapped onto custom digital–analog VLSI hardware, which is a unique approach in research on intelligent FMCW sensor development, offering a potential energy-efficient data analysis solution for target applications, such as preventing human trafficking or providing life-sign detection under limited visibility. The algorithm comprises two main modules. The first one summarizes radar-produced data into a descriptor reflecting the amount of motion that occurs within appropriately determined time intervals. The second one classifies a sequence of the produced descriptors using a recurrent neural network composed of gated recurrent units. To ensure the algorithm’s implementation feasibility, an analog VLSI circuit comprising its main functional blocks has been designed, manufactured, and tested, providing constraints for neural model derivation. The adverse effects of the primary constraint, the severe restriction on admissible weight resolution, have been handled by introducing a novel training loss component and a simple mechanism for diversifying the effective weight sets of different network neurons. Experimental evaluation of the presented method, performed using the dataset of indoor recordings, indicates that the proposed simple, hardware implementation-friendly algorithm provides over 94% human detection accuracy and similar F1 scores.
- Open Access
- 28 June 2024
- Published by Elsevier in Applied Thermal Engineering
- Vol. 254
Fuzzy logic based thermal image processing for temperature monitoring of rotating cylindrical surfaces
- 28 June 2024
- Published by Elsevier in Applied Thermal Engineering
- Vol. 254
Open AccessFuzzy logic based thermal image processing for temperature monitoring of rotating cylindrical surfaces
- Open Access
- 27 December 2022
- Published by Polish Academy of Sciences Chancellery in Bulletin Of The Polish Academy Of Sciences-Technical Sciences
- Vol. 70 (6) , 143552
Neuromorphic approach for breathing rate monitoring using data produced by FMCW radar
The paper introduces a neuromorphic computational approach for breathing rate monitoring of a single person observed using a Frequency-Modulated Continuous Wave radar. The architecture, aimed at implementation in analog hardware to ensure high energy efficiency and to provide system operation longevity, comprises two main functional modules. The first one is a data preprocessing unit aimed at the extraction of information relevant to the analysis objective, whereas the second one is a pre-trained recurrent neural regressor, which analyzes sequences of incoming samples and estimates the breathing rate. To ensure compatibility with neural processing and to achieve simplicity of underlying resources, several solutions were proposed for the data preprocessing module, which provides range-wise space segmentation, selection of a bin of interest (comprising the dominant motion activity), and delivery of data to regressor inputs. To implement these functions, we introduce an appropriate chirp frequency modulation scheme, apply a neuromorphic filtering procedure and use a Winner-Takes-All network for extracting information from the bin of interest. The architecture has been experimentally verified using a dataset of indoor recordings supplied with reference data from a Zephyr BioHarness device. We show that the proposed architecture is capable of making correct breathing rate estimates while being feasible for analog implementation. The mean squared regression error with respect to the Zephyr-produced reference values is approximately 3.3 breaths per minute (with a deviation of ±0:27 in the 95% confidence interval) and the estimates are produced by a recurrent, GRU-based neural regressor, with a total of only 147 parameters.
- 27 December 2022
- Published by Polish Academy of Sciences Chancellery in Bulletin Of The Polish Academy Of Sciences-Technical Sciences
- Vol. 70 (6) , 143552
Open AccessNeuromorphic approach for breathing rate monitoring using data produced by FMCW radar
The paper introduces a neuromorphic computational approach for breathing rate monitoring of a single person observed using a Frequency-Modulated Continuous Wave radar. The architecture, aimed at implementation in analog hardware to ensure high energy efficiency and to provide system operation longevity, comprises two main functional modules. The first one is a data preprocessing unit aimed at the extraction of information relevant to the analysis objective, whereas the second one is a pre-trained recurrent neural regressor, which analyzes sequences of incoming samples and estimates the breathing rate. To ensure compatibility with neural processing and to achieve simplicity of underlying resources, several solutions were proposed for the data preprocessing module, which provides range-wise space segmentation, selection of a bin of interest (comprising the dominant motion activity), and delivery of data to regressor inputs. To implement these functions, we introduce an appropriate chirp frequency modulation scheme, apply a neuromorphic filtering procedure and use a Winner-Takes-All network for extracting information from the bin of interest. The architecture has been experimentally verified using a dataset of indoor recordings supplied with reference data from a Zephyr BioHarness device. We show that the proposed architecture is capable of making correct breathing rate estimates while being feasible for analog implementation. The mean squared regression error with respect to the Zephyr-produced reference values is approximately 3.3 breaths per minute (with a deviation of ±0:27 in the 95% confidence interval) and the estimates are produced by a recurrent, GRU-based neural regressor, with a total of only 147 parameters.
- Open Access
Boosting Intelligent Data Analysis in Smart Sensors by Integrating Knowledge and Machine Learning
The presented paper proposes a hybrid neural architecture that enables intelligent data analysis efficacy to be boosted in smart sensor devices, which are typically resource-constrained and application-specific. The postulated concept integrates prior knowledge with learning from examples, thus allowing sensor devices to be used for the successful execution of machine learning even when the volume of training data is highly limited, using compact underlying hardware. The proposed architecture comprises two interacting functional modules arranged in a homogeneous, multiple-layer architecture. The first module, referred to as the knowledge sub-network, implements knowledge in the Conjunctive Normal Form through a three-layer structure composed of novel types of learnable units, called L-neurons. In contrast, the second module is a fully-connected conventional three-layer, feed-forward neural network, and it is referred to as a conventional neural sub-network. We show that the proposed hybrid structure successfully combines knowledge and learning, providing high recognition performance even for very limited training datasets, while also benefiting from an abundance of data, as it occurs for purely neural structures. In addition, since the proposed L-neurons can learn (through classical backpropagation), we show that the architecture is also capable of repairing its knowledge.
Open AccessBoosting Intelligent Data Analysis in Smart Sensors by Integrating Knowledge and Machine Learning
The presented paper proposes a hybrid neural architecture that enables intelligent data analysis efficacy to be boosted in smart sensor devices, which are typically resource-constrained and application-specific. The postulated concept integrates prior knowledge with learning from examples, thus allowing sensor devices to be used for the successful execution of machine learning even when the volume of training data is highly limited, using compact underlying hardware. The proposed architecture comprises two interacting functional modules arranged in a homogeneous, multiple-layer architecture. The first module, referred to as the knowledge sub-network, implements knowledge in the Conjunctive Normal Form through a three-layer structure composed of novel types of learnable units, called L-neurons. In contrast, the second module is a fully-connected conventional three-layer, feed-forward neural network, and it is referred to as a conventional neural sub-network. We show that the proposed hybrid structure successfully combines knowledge and learning, providing high recognition performance even for very limited training datasets, while also benefiting from an abundance of data, as it occurs for purely neural structures. In addition, since the proposed L-neurons can learn (through classical backpropagation), we show that the architecture is also capable of repairing its knowledge.
- 26 September 2019
- Published by Polish Information Processing Society PTI in Annals of Computer Science and Information Systems
- Vol. 18, 427-431
Towards Big Data Solutions for Industrial Tomography Data Processing
- 26 September 2019
- Published by Polish Information Processing Society PTI in Annals of Computer Science and Information Systems
- Vol. 18, 427-431
Towards Big Data Solutions for Industrial Tomography Data Processing
- Open Access
- 9 September 2019
- Published by Association for Computing Machinery (ACM)
- p. 230-233
SpiderHand
- 9 September 2019
- Published by Association for Computing Machinery (ACM)
- p. 230-233
Open AccessSpiderHand
- Open Access
X-ray Imaging Analysis of Silo Flow Parameters Based on Trace Particles Using Targeted Crowdsourcing
This paper presents a novel method for tomographic measurement and data analysis based on crowdsourcing. X-ray radiography imaging was initially applied to determine silo flow parameters. We used traced particles immersed in the bulk to investigate gravitational silo flow. The reconstructed images were not perfect, due to inhomogeneous silo filling and nonlinear attenuation of the X-rays on the way to the detector. Automatic processing of such data is not feasible. Therefore, we used crowdsourcing for human-driven annotation of the trace particles. As we aimed to extract meaningful flow parameters, we developed a modified crowdsourcing annotation method, focusing on selected important areas of the silo pictures only. We call this method “targeted crowdsourcing”, and it enables more efficient crowd work, as it is focused on the most important areas of the image that allow determination of the flow parameters. The results show that it is possible to analyze volumetric material structure movement based on 2D radiography data showing the location and movement of tiny metal trace particles. A quantitative description of the flow obtained from the horizontal and vertical velocity components was derived for different parts of the model silo volume. Targeting the attention of crowd workers towards either a specific zone or a particular particle speeds up the pre-processing stage while preserving the same quality of the output, quantified by important flow parameters.
Open AccessX-ray Imaging Analysis of Silo Flow Parameters Based on Trace Particles Using Targeted Crowdsourcing
This paper presents a novel method for tomographic measurement and data analysis based on crowdsourcing. X-ray radiography imaging was initially applied to determine silo flow parameters. We used traced particles immersed in the bulk to investigate gravitational silo flow. The reconstructed images were not perfect, due to inhomogeneous silo filling and nonlinear attenuation of the X-rays on the way to the detector. Automatic processing of such data is not feasible. Therefore, we used crowdsourcing for human-driven annotation of the trace particles. As we aimed to extract meaningful flow parameters, we developed a modified crowdsourcing annotation method, focusing on selected important areas of the silo pictures only. We call this method “targeted crowdsourcing”, and it enables more efficient crowd work, as it is focused on the most important areas of the image that allow determination of the flow parameters. The results show that it is possible to analyze volumetric material structure movement based on 2D radiography data showing the location and movement of tiny metal trace particles. A quantitative description of the flow obtained from the horizontal and vertical velocity components was derived for different parts of the model silo volume. Targeting the attention of crowd workers towards either a specific zone or a particular particle speeds up the pre-processing stage while preserving the same quality of the output, quantified by important flow parameters.
- 2 October 2016
- Published by Polish Information Processing Society PTI
- Vol. 8, 1627-1630
APEOW: A Personal Persuasive Avatar for Encouraging Breaks in Office Work
- 2 October 2016
- Published by Polish Information Processing Society PTI
- Vol. 8, 1627-1630
APEOW: A Personal Persuasive Avatar for Encouraging Breaks in Office Work