Publikace Fakulty elektrotechniky a informatiky / Publications of Faculty of Electrical Engineering and Computer Science (FEI)

Permanent URI for this collectionhttp://hdl.handle.net/10084/151874

Browse

Now showing 1 - 8 out of 8 results

Phase transition driven Zn-Ion battery with laser-processed V2C/V2O5 electrodes for wearable temperature monitoring
(Wiley, 2025) Deshmukh, Sujit; Vaghasiya, Jayraj V.; Michalička, Jan; Langer, Rostislav; Otyepka, Michal; Pumera, Martin
Flexible power supply devices present significant potential for wearable bioelectronics within the Internet of Things. Aqueous zinc-ion batteries have emerged as a viable and safe alternative for power supply in flexible electronics. Nevertheless, typical battery behaviors are generally detrimental with unfavorable phase transition of electrodes, which invariably lead to rapid performance degradation. Here, extraordinary capacity enhancement of 150% is presented, sustained over 60 000 cycles, attained using vanadium carbide MXene (V2C)/vanadium pentoxide (V2O5) heterostructure as cathode. The unique cathode material is created through the rational engineering of MAX (V2AlC), employing a single-step laser writing process. The ultrastable Zn ion battery stands in stark contrast to all previously reported counterparts, which typically exhibit capacity degradation within a few hundred/thousand cycles. The primary mechanisms driving this enhancement include the delamination of V2C MXene and an unexpected favorable phase transition during cycling. Additionally, a wearable power supply is constructed using a series configuration and is integrated with a commercial temperature sensor for wireless, real-time body temperature monitoring. This study highlights the critical role of electrode design for advanced wearable bioelectronics.
A novel diagnostic framework for breast cancer: combining deep learning with mammogram-DBT feature fusion
(Elsevier, 2025) Gupta, Nishu; Kubíček, Jan; Penhaker, Marek; Derawi, Mohammad
Background and motivation: Breast cancer detection remains a critical challenge in medical imaging due to the complexity of tumor features and variability in breast tissue. Conventional mammography struggles with dense tissues, leading to missed diagnoses. Digital Breast Tomosynthesis (DBT) offers improved 3D imaging but brings significant computational burdens. This study proposes a novel framework using the Fully Elman Neural Network (FENN) with feature fusion to enhance the accuracy and reliability of breast cancer diagnosis. Materials and methods: Mammogram images from the CBIS-DDSM dataset and DBT images from the BreastCancer-Screening-DBT dataset were used. The preprocessing step involved Extended-Tuned Adaptive Frost Filtering (Ext-AFF) to enhance image quality by reducing noise. Feature extraction was performed using Disentangled Variational Autoencoder (D-VAE), capturing critical texture features. These features were fused using Deep Generalized Canonical Correlation Analysis (Dg-CCA) to maximize feature correlation across modalities. Finally, a Fully Elman Neural Network was employed for classification, distinguishing between benign, malignant, biopsy-proven cancer, and normal tissues. Results: The proposed FENN-based framework achieved superior classification performance compared to existing methods. Key metrics such as accuracy, sensitivity, specificity, and Matthew's correlation coefficient (MCC) demonstrated significant improvements. The fusion of mammogram and DBT images led to enhanced discriminative power, reducing false positives and negatives across various breast cancer classes. Discussion and conclusion: The integration of mammogram and DBT image data with advanced machine learning techniques, such as D-VAE and FENN, enhances diagnostic precision. The proposed framework shows promise for improving clinical decision-making in breast cancer screening by overcoming the limitations of traditional imaging methods. The system's ability to handle complex interdependencies in imaging data offers substantial potential for earlier and more accurate diagnosis. Future directions: Future research will focus on real-time clinical deployment of the framework, incorporating real-time image acquisition and analysis for faster diagnoses. Additionally, scaling the system for large datasets with varying image quality will further validate its robustness and applicability in diverse clinical environments.
V-shaped and S-shaped binary artificial protozoa optimizer (APO) algorithm for wrapper feature selection on biological data
(Springer Nature, 2025) Seyyedabbasi, Amir; Hu, Gang; Shehadeh, Hisham A.; Wang, Xiaopeng; Canatalay, Peren Jerfi
This study addresses the limitation of feature selection (FS) problems in high-dimensional biomedical datasets. The high dimensional datasets contain attributes that are deemed irrelevant, redundant, and noisy. Thus, the process of feature selection is a valuable initial step aimed at improving the performance of classification models through the identification and selection of a constrained set of significant and impactful features. Due to the NP-hard nature of feature selection, it is crucial to recognize that addressing these challenges requires the utilization of metaheuristic algorithms. However, since the feature selection problem is a discrete problem, the binary version of metaheuristic algorithms should be used. To overcome these challenges, this paper proposes a novel bAPO algorithm that leverages adaptive population dynamics for more efficient exploration and exploitation of the solution space. The proposed bAPO algorithm uses V-shaped and S shaped transfer functions to obtain wrapper feature selection in biological data. There are eight different versions of the bAPO algorithm in this study that were evaluated with 14 well-known biological datasets. The obtained results have been analyzed with the fitness value, the number of selected features, k-nearest neighbors (KNN) accuracy, support vector machine (SVM) accuracy, and random forest (RF). Statistical validation using p-value analysis demonstrates the robustness and reliability of the results. The obtained findings suggest that the proposed bAPO algorithm provides a powerful method for tackling optimization problems, particularly in high-dimensional datasets. In fitness performance, the bAPO-V1 and bAPO-V2 (27.70%) demonstrate superior performance, and in terms of reduced features, the bAPO-V2 (36.36%) algorithm achieved good performance.
Active microrobots for dual removal of biofilms via chemical and physical mechanisms
(American Chemical Society, 2025) Peng, Xia; Oral, Cagatay M.; Urso, Mario; Ussia, Martina; Pumera, Martin
Bacterial biofilms are complex multicellular communities that adhere firmly to solid surfaces. They are widely recognized as major threats to human health, contributing to issues such as persistent infections on medical implants and severe contamination in drinking water systems. As a potential treatment for biofilms, this work proposes two strategies: (i) light-driven ZnFe2O4 (ZFO)/Pt microrobots for photodegradation of biofilms and (ii) magnetically driven ZFO microrobots for mechanical removal of biofilms from surfaces. Magnetically driven ZFO microrobots were realized by synthesizing ZFO microspheres through a low-cost and large-scale hydrothermal synthesis, followed by a calcination process. Then, a Pt layer was deposited on the surface of the ZFO microspheres to break their symmetry, resulting in self-propelled light-driven Janus ZFO/Pt microrobots. Light-driven ZFO/Pt microrobots exhibited active locomotion under UV light irradiation and controllable motion in terms of “stop and go” features. Magnetically driven ZFO microrobots were capable of maneuvering precisely when subjected to an external rotating magnetic field. These microrobots could eliminate Gram-negative Escherichia coli (E. coli) biofilms through photogenerated reactive oxygen species (ROS)-related antibacterial properties in combination with their light-powered active locomotion, accelerating the mass transfer to remove biofilms more effectively in water. Moreover, the actuation of magnetically driven ZFO microrobots allowed for the physical disruption of biofilms, which represents a reliable alternative to photocatalysis for the removal of strongly anchored biofilms in confined spaces. With their versatile characteristics, the envisioned microrobots highlight a significant potential for biofilm removal with high efficacy in both open and confined spaces, such as the pipelines of industrial plants.
Setkání vysokoškolských pracovišť v rámci konference Trendy v biomedicínském inženýrství 2025 a řešitelů projektu LERCO
(Vysoká škola báňská - Technická univerzita Ostrava, 2025) kolektiv autorů; Penhaker, Marek; Augustynek, Martin
Konference je zaměřena na diskuzi aktuálních trendů ve vývoji vědy, výzkumu a výuky v oblasti biomedicínského inženýrství v České a Slovenské republice. Navazuje na dlouhodobou tradici pravidelných setkávání, která se konají ve dvouletém cyklu a představují jedinečnou příležitost pro sdílení zkušeností a poznatků mezi pedagogickými i vědeckými pracovníky oboru. Hlavním cílem letošního ročníku je propojit řešitelské týmy s potenciálními uživateli výsledků projektu LERCO a vytvořit platformu pro odbornou diskuzi mezi výzkumnými institucemi a aplikační sférou. Konference tak podporuje nejen výměnu vědeckých informací, ale i vznik nových spoluprací, které mohou přispět k rychlejšímu přenosu poznatků do praxe a k rozvoji biomedicínského inženýrství v širším kontextu.
WOFEX 2021 : 19th annual workshop, Ostrava, 1th September 2021 : proceedings of papers
(Vysoká škola báňská - Technická univerzita Ostrava, 2021) Krátký, Michal; Dvorský, Jiří; Moravec, Pavel
The workshop WOFEX 2021 (PhD workshop of Faculty of Electrical Engineer-ing and Computer Science) was held on September 1st September 2021 at the VSB – Technical University of Ostrava. The workshop offers an opportunity for students to meet and share their research experiences, to discover commonalities in research and studentship, and to foster a collaborative environment for joint problem solving. PhD students are encouraged to attend in order to ensure a broad, unconfined discussion. In that view, this workshop is intended for students and researchers of this faculty offering opportunities to meet new colleagues.
WOFEX 2020 : 18th annual workshop, Ostrava, 8th September 2020 : proceedings of papers
(Vysoká škola báňská - Technická univerzita Ostrava, 2020) Krátký, Michal; Dvorský, Jiří; Moravec, Pavel
Magnetická smyčková anténa : pokaždé trochu jinak
(EDUCA TV o.p.s., 2015) Burger, Oldřich; Dvorský, Marek
Kniha shrnuje teoretický návrh elektricky malé smyčkové antény (Magnetic Loop Antenna - MLA). V druhé (praktické) části popisuje několik variant a variací této antény. Další kapitola je věnována zpětné vazbě uživatelů tohoto typu antény.

Browse

Recent Submissions