Applied sciences

Bulletin of the Polish Academy of Sciences Technical Sciences

Description

The Bulletin of the Polish Academy of Sciences Technical Sciences has been published bimonthly by the Division IV Engineering Sciences of the Polish Academy of Sciences since the establishment of PAS in 1952. The journal is peer-reviewed and issued in electronic format. It aims to publish original, high-quality papers from multidisciplinary engineering sciences, with preferred topics including:

Artificial and Computational Intelligence,
Biomedical Engineering and Biotechnology,
Civil Engineering,
Control, Informatics and Robotics,

Electronics, Telecommunication and Optoelectronics,
Mechanical and Aeronautical Engineering, Thermodynamics,
Material Science and Nanotechnology,
Power Systems and Power Electronics.

Submit your article

Journal Metrics:

JCR Impact Factor 2024:	1.1
5 Year Impact Factor 2023:	1.0
CiteScore 2024:	2.7
SCImago Journal Rank (SJR) 2023:	0.271
Source Normalized Impact per Paper (SNIP) 2023:	0.517
Ministry of Education and Science:	100 points

Abbreviated title: Bull. Pol. Acad. Sci. Tech. Sci.

ISSN

ISSN 2300-1917

Editorial Board 2023-2025

Editor-in-Chief:

A. Rogalski, Military University of Technology

Honorary (Past) Editor-in Chief:

T. Kaczorek, Warsaw University of Technology

M.P. Kaźmierkowski, Warsaw University of Technology

Deputy Editor-in-Chief:

B. Błachowski, Institute of Fundamental Technological Research PAN

M. Mrozowski, Gdansk University of Technology

Board of Topical Co-editors:

Artificial and Computational Intelligence

B. Sawicki and S. Osowski, Warsaw University of Technology

Biomedical Engineering and Biotechnology

P. Ładyżyński, Institute of Biocybernetics and Biomedical Engineering PAN

Civil Engineering

L. Czarnecki, Building Research Institute, ITB, Warsaw

Ł. Sadowski, Wroclaw University of Science and Technology

Control, Robotics and Informatics

J. Klamka and A. Babiarz, Silesian Technical University

J. Stefanowski, Poznan University of Technology

Electronics, Telecommunication and Optoelectronics

M. Mrozowski, Gdansk University of Technology

P. Kryszkiewicz, Poznan University of Technology

Mechanical and Aeronautical Engineering, Thermodynamics

B. Błachowski, Institute of Fundamental Technological Research PAN

G. Zboiński, Institute of Fluid-Flow Machinery PAN and University of Warmia and Mazury in Olsztyn

Materials Science and Nanotechnology

P. Zięba and P. Czaja, Institute of Metallurgy and Materials Science PAN

Power Systems and Power Electronics

J. Rąbkowski and M. Jasiński, Warsaw University of Technology

International Editorial Advisory Board

R. Asthana, University of Wisconsin-Stout, Menomonie, USA

Xu Binshi, China Association of Plant Engineering, Beijing, P.R. China

F. Blaabjerg, Aalborg University, Denmark

C. Cecati, University of L’Aquila, Italy

A. Cichocki, RIKEN Institute, Tokyo, Japan

M. David, National Polytechnique de Toulouse, France

R. Ebner, Materials Centre Leoben, Leoben, Austria

E. Fornasini, University of Padova, Padova, Italy

L.G. Franquelo, University of Sevilla, Spain

M. Gad-el-Hak, Virginia Commonwealth University, Richmond, USA

M. Giersig, Free University of Berlin, Germany

D. van Gemert, Catholic University Leuven, KU Leuven, Belgium

L. Keviczky, Hungarian Academy of Sciences, Budapest, Hungary

V. Kučera, Czech Technical University in Prague, Prague, Czech Republic

R. Kennel, Technical University Munich, Germany

T.A. Kowalewski, Institute of Fundamental Technological Research PAN

E. Levi, Liverpool John Moore University, UK

G. Maier, Technical University of Milan, Milan, Italy

K.F. Man, City University of Hong Kong,

R. Maniewski, Institute of Biocybernetics and Biomedical Engineering PAN

H.A. Mang, Austrian Academy of Sciences, Vienna, Austria

H. Mihashi, Tohoku University, Aoba-ku, Sendai, Japan

S. Mindess, University of British Columbia, Vancouver, Canada

D.A. Mlynski, University of Karlsruhe, Karlsruhe, Germany

A.S. Nowak, University of Michigan, Ann Arbor, USA

K. Ohnishi, Keio University, Yokohama, Japan

A. Öberg, Linköping University, Linköping, Sweden

W. Pedrycz, University of Alberta, Canada

M. Razeghi, Northwestern University, Evanston, USA

J. Rodriguez, University of Andres Bello, Santiago, Chile

J.V. Sloten, Catholic University Leuven, Leuven, Belgium

B.M. Wilamowski, University of Auburn, Alabama, USA

A.L. Yarin, University of Illinois at Chicago, USA

Du Xiangwan, Chinese Academy of Engineering, China

J. Żurada, Department of Computer Engineering, University of Louisville, USA

Editorial Office:

Pałac Kultury i Nauki

Wydział IV Nauk Technicznych PAN

Pl. Defilad 1

PL 00-901 Warszawa

Managing Editor:

Renata Podraza, e-mail: Renata.Podraza@pan.pl

Finance:

Katarzyna Łasak, e-mail: Katarzyna.Lasak@pan.pl

The Bulletin of the Polish Academy of Sciences Technical Sciences is an open access journal with all content available with no charge in full text version.

The journal content is available under the licencse CC BY 4.0 https://creativecommons.org/licenses/by/4.0/.

Volumes
Instructions for authors
Additional info

Select number

2026
- Early Access
- 74
  - No. 4 (in progress)
  - No. 3
  - No. 2
  - No. 1
2025
2024
2023
2022
2021
2020
2019
2018
2017
2016
2015
2014
2013
2012
2011
2010
2009
2008
2007
2006
2005
2004

Content

Bulletin of the Polish Academy of Sciences Technical Sciences | 2026 | 74 | 4

1 DouRD: enhancing DouDizhu AI with role-differentiated modeling

Yuezhonyi Sun , Shouzhen Zhang

Bulletin of the Polish Academy of Sciences Technical Sciences | 2026 | 74 | 4 | e158770 | DOI: 10.24425/bpasts.2026.158770

Keywords: attention mechanism deep Monte Carlo DouDizhou imperfect information game

Download PDF Download RIS Download Bibtex

Abstract

Imperfect information games impose greater demands on AI decision-making than perfect information settings, requiring models to infer hidden information, reason about opponent strategies, and dynamically optimize policies under uncertainty. In this study, we proposed a novel role-differentiated modeling approach within the deep Monte Carlo framework to enhance DouDizhu AI, the challenging three-player asymmetric imperfect information game. Our method incorporated attention mechanisms with role-specific adaptations to investigate their differential impacts on the landlord and peasant roles. Key findings demonstrate that: (1) the landlord and peasant roles require fundamentally distinct model architectures: experiments confirmed their functional independence; (2) attention mechanisms exhibit role-dependent effectiveness: CBAM significantly improved Peasant strategy execution, whereas SE and ECA offered moderate gains, while Self-Attention showed no enhancement; (3) surprisingly, applying attention mechanisms to the landlord role led to performance degradation, reinforcing the superiority of LSTM for this role. These results highlight the importance of role-aware architecture design in the imperfect information game setting, and challenge the universal applicability of attention mechanisms.

Go to article

Authors and Affiliations

Yuezhonyi Sun

Shouzhen Zhang

e-mail:

ORCID:

School of Computer Science and Technology, Harbin University of Science and Technology, Harbin, China

2 Model goodness of fit evaluation based on a fuzzy inference system in virtual commissioning

Łukasz Glodek , Anna Glodek , Witold Nocoń , Szymon Bysko

Bulletin of the Polish Academy of Sciences Technical Sciences | 2026 | 74 | 4 | e158306 | DOI: 10.24425/bpasts.2026.158306

Keywords: virtual commissioning model goodness of fit fuzzy logic industrial automation systems

Download PDF Download RIS Download Bibtex

Abstract

Modern industrial plants are becoming increasingly complex, resulting in the need for rapid testing and validation of industrial automation systems. To meet the requirements mentioned above, new simulation techniques, like virtual commissioning (VC), can be employed, as they allow for identifying process bottlenecks at the very beginning of the commissioning process. Moreover, it has also been used for maintenance operator training. The essential stage of VC is verification of the model of a commissioned plant quality – model goodness of fit. A plethora of measures are used for model goodness of fit evaluation, but each is characterized by a different range of values and interpretations. Thus, the best idea is to use the hybrid approach for model goodness of fit evaluation, combining the information from different measures. In order to create a flexible system for decision-making, if a model quality is good and sufficient to be used in VC, the Virtual-Commissioning-Model Fuzzy Coefficient (VCMF) is introduced based on the Takagi-Sugeno-Kang fuzzy-inference system. It considers knowledge of virtual commissioning of industrial automation systems and information carried by different methods of goodness of fit evaluation (NRMSE, ME, MAE, and MIA). VCMF was based on data from the belt conveyor, which was thoroughly analyzed. Current, velocity, and torque time series underwent the data pre-processing and analysis methods, which resulted in obtaining a model. VCMF allows for differentiating models into those that can be used in VC and those that cannot. The threshold value was defined by Gaussian Mixture Modeling and Bayesian Information Criterion.

Go to article

Authors and Affiliations

Łukasz Glodek

e-mail:

ORCID:

Anna Glodek

Witold Nocoń

e-mail:

ORCID:

Szymon Bysko

e-mail:

ORCID:

PROPOINT S.A., Gliwice, Poland
Faculty of Automatic Control, Electronics and Computer Science, Silesian University of Technology, Gliwice, Poland

3 Advanced CNN architectures and explainable AI for complex emotion recognition from facial images: experimental validation in human-robot interaction

Eryka Probierz , Kamil Skowroński , Adam Gałuszka , Anita Gałuszka

Bulletin of the Polish Academy of Sciences Technical Sciences | 2026 | 74 | 4 | e158776

Keywords: complex emotion recognition facial expression analysis convolutional neural networks explainable AI SHAP LIME OhBot human-robot interaction image-based affective computing AMAL attention layer

Download PDF Download RIS Download Bibtex

Abstract

This study investigates the recognition of complex emotional states from facial images using advanced convolutional neural network architectures and explainable artificial intelligence techniques. Unlike prior work focused on basic categorical emotions, we target subtle affective states such as frustration, confusion, or skepticism, which are critical for nuanced human-robot interactions. We compare a conventional deep learning model (ResNet50), an advanced EfficientNet-Transformer architecture, and our proposed CNN model enhanced with the Attention Map Alignment Layer (AMAL), designed to improve interpretability and focus on semantically relevant facial regions. Experimental evaluation on benchmark datasets (AffectNet, EMOTIC) and in a real-time simulation involving the OhBot social robot demonstrates that the proposed model achieves higher recognition accuracy for complex emotions and provides more consistent feature attribution using SHAP and LIME frameworks. The results highlight the potential of integrating explainable computer vision systems into interactive robotics, improving transparency and emotional understanding in artificial agents.

Go to article

Authors and Affiliations

Eryka Probierz

e-mail:

ORCID:

Kamil Skowroński

e-mail:

ORCID:

Adam Gałuszka

e-mail:

ORCID:

Anita Gałuszka

e-mail:

ORCID:

Helena Chodkowska University of Technology and Economics, Faculty of Engineering, Jagiellonska 82F, 03-301 Warsaw, Poland
Department of Automatic Control and Robotics, Silesian University of Technology, Akademicka 16, 44-100 Gliwice, Poland
Katowice Business University, Management Faculty, Harcerzy Wrzesnia 1939 3, 40-659 Katowice, Poland

4 The influence of compaction technology on the internal structure of the asphalt mixture

Marek Iwański , Małgorzata Durlej

Bulletin of the Polish Academy of Sciences Technical Sciences | 2026 | 74 | 4 | e158778

Keywords: asphalt mixture computed x-Ray tomography resistance to water and frost internal structure

Download PDF Download RIS Download Bibtex

Abstract

A fundamental property of asphalt mixtures is the void content. It significantly influences their resistance to water and frost. Currently, this is traditionally determined using the hydrostatic method. This method may not be effective for environmentally friendly mixtures produced using Warm Mix Asphalt technology. They are produced and compacted at a lower temperature than traditional methods. Therefore, they may be characterized by abnormal void content in the internal structure. Microtomographic analysis can now be used to thoroughly examine the internal structure of asphalt mixtures in terms of pore size distribution, interconnection patterns, and their arrangement. This is particularly important in identifying changes occurring within the asphalt mixture as a result of the destructive effects of water and frost. Studies were conducted on the effect of vibratory and Marshall impact compaction on the internal structure of the asphalt mixture. Mixture samples were analyzed before and after conditioning according to AASHTO T283 and WT-2 2014 standards. It was found that the compaction method affects the distribution and interconnection of pores. Samples compacted using the vibratory method are more uniform in terms of the distribution of large and interconnected pores within the asphalt mixture structure. Smaller pores with a volume of 0 to 0.5 mm3 occur between the mini-pores, increasing the resistance of the asphalt mixture to water and frost. It was found that, in addition to extremely small pores, interconnected pores have the greatest impact on the mixture resistance to water and frost.

Go to article

Authors and Affiliations

Marek Iwański

e-mail:

ORCID:

Małgorzata Durlej

e-mail:

ORCID:

Kielce University of Technology, Faculty of Civil Engineering and Architecture, Al. Tysi ˛aclecia P.P. 7, 25-314 Kielce, Poland

5 A methodological framework for evaluating ADAS training for older drivers: Feasibility and user perception

Małgorzata Pelka , Aleksandra Rodak

Bulletin of the Polish Academy of Sciences Technical Sciences | 2026 | 74 | 4 | e158971

Keywords: driver training ADAS simulation sickness older drivers trust calibration

Download PDF Download RIS Download Bibtex

Abstract

The rapid introduction of Advanced Driver Assistance Systems (ADAS) poses a unique challenge for older drivers, who often face barriers in adopting these technologies. This study evaluates the effectiveness of a practical, simulator-based training concept designed specifically for drivers aged 50+. The empirical analysis of a research group of 25 people focused on verifying four research hypotheses regarding the suitability of the simulator, trust calibration, user awareness, and training utility. The results confirmed that the high-fidelity simulator is an appropriate training environment for this demographic; analysis of the Revised Simulator Sickness Questionnaire (RSSQ) revealed a statistically significant reduction in symptoms during the adaptation process, validating the physical feasibility of the training (H1). The intervention led to a measurable increase in trust towards ADAS, with a strong effect size, confirming positive behavioral adaptation (H2). Furthermore, participants demonstrated raised awareness of system benefits, primarily identifying enhanced safety and speed control (H3). The proposed training model achieved high internal consistency and received positive subjective usability ratings (H4). These findings support the deployment of simulatorbased practical training as an effective tool for preventing digital exclusion among older drivers. Key words: driver training; ADAS; simulation sickness; older drivers; trust calibration.

Go to article

Authors and Affiliations

Małgorzata Pelka

e-mail:

ORCID:

Aleksandra Rodak

e-mail:

ORCID:

Motor Transport Institute, Poland

Instructions for authors

Guide for Authors

https://www.editorialsystem.com/bpasts/journal/for_authors/

Fees for open access publications in Bulletin of the Polish Academy of Sciences Technical Sciences:

2000 PLN (approx. 500 EUR) - up to 8 pages of the journal format and mandatory over-length charges of 250 PLN (approx. 60 EUR) per page (see the above link with instructions for Authors for details)

Guide for Reviewers

https://www.editorialsystem.com/bpasts/journal/for_reviewers/

Call for Papers

https://www.editorialsystem.com/bpasts/journal/call_for_papers/

Guide for Guest Editors

https://www.editorialsystem.com/editor/bpasts/journal/page1/

Additional info

NEW PUBLICATION FEES
Articles submitted by December 31st, 2024: existing fee: 1500 PLN (and mandatory over-length charges of 230 PLN per page)
Articles submitted from January 1st, 2025: new fee: 2000 PLN (approx. 500 EUR- depending on the exchange rate) - a flat fee per paper up to 8 pages of the journal format (each additional page will be charged an additional 250 PLN).