KLKrzysztof Lorenz

Krzysztof Lorenz

*This is an algorithmically generated author record based on publicly available information.

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


Krzysztof Lorenz has a total of 11 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Digital innovation in the United States: Spatial determinants of transformation as exemplified by Kickstarter campaigns

    by Krzysztof Lorenz, Piotr Gutowski, Ewelina Gutowska, Anna Drab-Kurowska

    Digital transformation is reshaping innovation processes and capital allocation models, fostering the emergence of alternative financing mechanisms such as crowdfunding platforms. This study investigates the spatial determinants of digital innovation development using Kickstarter campaigns in the United States as a case study. Empirical data were preprocessed and classified into digital and traditional categories. Advanced AI methods, including Deep Autoencoders and Self-Organizing Maps (SOM), revealed spatial clusters of digital innovation in crowdfunding. Cluster visualizations exposed geographic concentration patterns and links to local infrastructure. AI uncovered latent ties between campaign structure and regional context, underscoring the role of AI and crowdfunding in decentralized, localized digital transformation.

  • Open Access

    Ekonomiczne aspekty selekcji cech wykorzystujące paradygmat algorytmu genetycznego w interfejsach mózg–komputer

    by Krzysztof Michał Lorenz

    Economic aspects of feature selection method based on the genetic algorithm paradigm adapted to the specific characteristics of Brain–Computer Interfaces This monograph is based on the doctoral dissertation entitled Feature selection method based on the genetic algorithm paradigm adapted to the specific characteristics of Brain–Computer Interfaces, which was submitted and successfully defended in 2024 at the Faculty of Computer Science at the West Pomeranian University of Technology in Szczecin. Developing a new algorithm proved to be a significant research challenge due to the specific nature of brain waves observed in individual users of the brain–computer interface (BCI). Extracting a large number of redundant features becomes necessary as each user exhibits unique brain wave patterns. From this vast set of features, only those exhibiting the highest discriminatory ability for a given user are selected. Consequently, the number of features extracted from the EEG signal during the estimation of the core classifier parameters in the BCI system can reach hundreds or even thousands. However, on the other hand, in order for the interface to operate in real-time-like mode, it is crucial to limit the number of features to be extracted from the signal for each subsequent control instruction generation. Another challenge arises from the high specificity of brain waves, necessitating separate calibration sessions with each user to estimate classifier parameters based on the data collected. This limitation results in relatively small calibration datasets, typically ranging from 100 to 200 records, which is significantly small compared to the thousands of possible features that can be extracted from the EEG signal. Therefore, the selection of a few essential features with the highest discriminatory abilities becomes an extremely important and challenging stage in constructing a motor imagery-based interface. From an economic perspective, the development of brain–computer interfaces (BCIs) constitutes a significant driver of growth in the advanced technology sector. This technology stimulates innovation, fosters the emergence of start-ups, and increases demand for highly skilled professionals in areas such as artificial intelligence, biomedical engineering, and computer science. The steadily growing value of the global BCI market makes it an attractive domain for investment and a source of competitive advantage in the digital economy. In this context, the optimization of feature selection plays a crucial role by reducing computational costs and shortening data processing time, thereby enhancing the efficiency of BCI system implementation. Reducing the number of input features decreases the demand for IT resources, energy, and technical personnel, which translates into lower operational costs and improved scalability. The GAAMmf algorithm developed in this study, based on the genetic algorithm paradigm, enables effective feature set reduction while maintaining high predictive quality, measured by the accuracy of brain activity pattern classification. The proposed approach has applications not only in BCI systems but also across other data-driven and AI-based sectors of the economy, such as finance, logistics, e-commerce, and risk management. In these domains, precise feature selection supports faster decision-making, reduces prediction costs, and improves resource allocation efficiency. As such, feature selection emerges as a tool of strategic economic importance, fostering the development of data analytics, the automation of decision-making processes, and the digital transformation of organizations. The monograph is an extension of a doctoral dissertation aimed at developing a feature selection method based on genetic algorithms, adapted to the specific characteristics of brain–computer interfaces. These characteristics include the need to preserve information about the original feature location and limit the feature space to only a few to several relevant features. The proposed feature selection method enabled the selection of a set of features with higher or comparable discriminative abilities, as measured by the accuracy of brain activity pattern classification, and with a smaller number of features than reference methods.

  • Open Access

    Viewer Engagement in Response to Mixed and Uniform Emotional Content in Marketing Videos—An Electroencephalographic Study

    by Izabela Rejer, Jarosław Jankowski, Justyna Dreger, Krzysztof Lorenz

    This study presents the results of an experiment designed to investigate whether marketing videos containing mixed emotional content can sustain consumers interest longer compared to videos conveying a consistent emotional message. During the experiment, thirteen participants, wearing EEG (electroencephalographic) caps, were exposed to eight marketing videos with diverse emotional tones. Participant engagement was measured with an engagement index, a metric derived from the power of brain activity recorded over the frontal and parietal cortex and computed within three distinct frequency bands: theta (4–8 Hz), alpha (8–13 Hz), and beta (13–30 Hz). The outcomes indicated a statistically significant influence of emotional content type (mixed vs. consistent) on the duration of user engagement. Videos containing a mixed emotional message were notably more effective in sustaining user engagement, whereas the engagement level for videos with a consistent emotional message declined over time. The principal inference drawn from the study is that advertising materials conveying a consistent emotional message should be notably briefer than those featuring a mixed emotional message to achieve an equivalent level of message effectiveness, measured through engagement duration.


  • Open Access

    GAAMmf: genetic algorithm with aggressive mutation and decreasing feature set for feature selection

    by Rejer Izabela, Lorenz Krzysztof

    This paper introduces a modified version of a genetic algorithm with aggressive mutation (GAAM), one of the genetic algorithms (GAs) used for feature selection. The modification proposed in this study expands the original GAAM’s capabilities by allowing not only feature selection but also feature reduction. To obtain this effect, we applied the concept of ranks used in the non-dominated sorting genetic algorithm (NSGA) and the concept of penalty term used in the Holland genetic algorithm. With those two concepts, we managed to balance the importance of two competing criteria in the GAAM fitness function: classification accuracy and the feature subset’s size. To assess the algorithm’s effectiveness, we evaluated it on eleven datasets with different characteristics and compared the results with eight reference methods: GAAM, Melting GAAM, Holland GA with a penalty term, NSGA-II, Correlation-based Feature Selection, Lasso, Sequential Forward Selection, and IniPG (an algorithm for particle swarm optimisation). The main conclusion drawn from this study is that the genetic algorithm with aggressive mutation and decreasing feature set (GAAMmf) introduced in this paper returned feature sets with a significantly smaller number of features than almost all reference methods. Furthermore, GAAMmf outperformed most of the methods in terms of classification accuracy (except the original GAAM). In contrast to Holland GA and NSGA-II, GAAMmf was able to perform the feature reduction task for all datasets, regardless of the initial number of features.


  • Open Access

    Sustainable Transport of Goods in the Odra River Region in the Context of the Green Economy

    by Agnieszka Budziewicz-Guźlecka, Piotr Gutowski, Ewelina Gutowska, Krzysztof Lorenz, Agnieszka Łopatka, Svitlana Bilan, Andrzej Gawlik

    The article addresses the issues related to sustainable inland waterway transport in the context of stimulating transformations towards a green economy. The considerations focused on the second-largest river in Poland – the Oder. The clear economic needs and benefits arising from the river’s regulation and the restoration of its transport capabilities were juxtaposed with the results of a study regarding the perception of these changes by the public opinion. To clarify, these were the residents of the Oder River Basin, thus people in the immediate impact area of the river.