Wyniki wyszukiwania - BazTech

1

From knowledge to entrepreneurship: the concept of the utility factors model in economics and finance

Siemiatowski Fabian, Szulczewska-Remi Aleksandra

Zeszyty Naukowe. Organizacja i Zarządzanie / Politechnika Śląska

|

2025

|

z. 221

503--527

EN

Purpose: This study aims to develop the Utility Factors Model (UFM) to assess the utility of academic research and improve knowledge transfer by identifying factors that motivate entrepreneurs to engage with university knowledge and analyzing their attitudes toward economic and financial knowledge transfer. Additionally, it explores how research spillovers foster entrepreneurship and economic development, drawing on the Knowledge Spillover Theory of Entrepreneurship (KSTE). Design/methodology/approach: A qualitative research approach was employed, incorporating multiple case studies and semi-structured interviews with 44 Polish companies. The study followed a narrative literature review to contextualize knowledge transfer theories. The qualitative data from interviews were analyzed to identify barriers in research utilization, which directly informed the development of UFM. Findings: The findings reveal several key aspects. Identified barriers include a misalignment between academic research outputs and business needs, limited practical application of theoretical models, and ineffective knowledge transfer mechanisms. The practical application of UFM demonstrates that the model provides structured indicators for assessing the utility of economics and finance research, enabling entrepreneurs to evaluate feasibility, financial institutions to assess economic impact, and policymakers to design informed regulations. Additionally, knowledge transfer mechanisms are enhanced through the integration of theories such as Triple Helix, absorptive capacity, and KSTE, ensuring that research remains accessible and fosters entrepreneurship by structuring knowledge spillovers. Research limitations/implications: Future research on the empirical validation of UFM in various economics and finance contexts is necessary to refine its adaptability across different industries and policy environments. Practical implications: The practical contribution provides entrepreneurs, policymakers, university authorities, and financial professionals with a clear framework to integrate academic insights into business strategy, the innovation process, and regulatory decisions. UFM extends knowledge transfer theories by adapting them to the field of economics and finance, showing how research spillovers drive entrepreneurship and innovation. Originality/value: Unlike traditional knowledge transfer models, UFM incorporates KSTE, emphasizing structured spillovers as a source of entrepreneurial opportunities. It bridges the gap between theory and practice, offering a structured, transparent approach to making academic research actionable. The study contributes a novel methodology for assessing research impact beyond academic citations and journal rankings, emphasizing real-world usability.

2

Organizational learning: an interpretive approach from the administrative field

Jácome-Lara Ibett M., Tinajero-Jiménez Marlon R., Pérez-Salas Francisco P., Guerrero-Arrieta Katherine G.

Polish Journal of Management Studies

|

2025

|

Vol. 31, No. 1

139--157

EN

The study of organizational learning in the administrative area within the university context provides an integrative perspective, offering an applicable framework to transform academic environments where knowledge management and overcoming structural barriers are balanced. This evidence can be transferred to other universities in similar contexts. This research adopted a qualitative approach based on the interpretative paradigm. Semi-structured interviews were conducted with departmental directors from public universities in Zone 3 of Ecuador. The data collected were analyzed using the qualitative software MAXQDA. The findings indicate that organizational learning functions as an intangible asset that enhances innovation and responsiveness to change. Knowledge transfer was identified as a critical component facilitated by effective leadership. Furthermore, positive mental models promote a collaborative environment, though resistance to change can limit learning. The study revealed that organizational learning in public universities is essential for adaptation and competitiveness. It underscores the importance of knowledge transfer, positive mental models, and collaborative culture to enhance academic and administrative performance.

PL

Badanie uczenia się organizacyjnego w obszarze administracyjnym w kontekście uniwersyteckim zapewnia integracyjną perspektywę, oferując praktyczne ramy do transformacji środowisk akademickich, w których zarządzanie wiedzą i pokonywanie barier strukturalnych są zrównoważone. Wyniki tych badań można przenieść na inne uniwersytety w podobnych kontekstach. W niniejszym badaniu przyjęto podejście jakościowe oparte na paradygmacie interpretacyjnym. Przeprowadzono częściowo ustrukturyzowane wywiady z dyrektorami wydziałów publicznych uniwersytetów w strefie 3 Ekwadoru. Zebrane dane analizowano za pomocą oprogramowania jakościowego MAXQDA. Wyniki wskazują, że uczenie się organizacyjne funkcjonuje jako niematerialny zasób, który zwiększa innowacyjność i zdolność reagowania na zmiany. Transfer wiedzy został zidentyfikowany jako kluczowy element ułatwiany przez skuteczne przywództwo. Ponadto pozytywne modele mentalne sprzyjają tworzeniu środowiska sprzyjającego współpracy, chociaż opór przed zmianami może ograniczać uczenie się. Badanie wykazało, że uczenie się organizacyjne na uniwersytetach publicznych ma zasadnicze znaczenie dla adaptacji i konkurencyjności. Podkreśla ono znaczenie transferu wiedzy, pozytywnych modeli mentalnych i kultury współpracy dla poprawy wyników akademickich i administracyjnych.

3

Business process effectiveness - a puzzle of many pieces. The role of knowledge transfer and integration, business process efficiency and business process modelling

Malewska Kamila, Mierzejewska Katarzyna, Roszyk-Kowalska Gabriela, Chomicki Michał

Management

|

2025

|

Vol. 29, no. 1

425--446

EN

Efficient management of business processes is crucial for operational excellence and customer satisfaction. Organizations employ Business Process Management techniques to design, monitor, optimize and automate these processes effectively. This paper explores the elements that ensure the smooth functioning of business operations and drive organizational success, and is focused on the determinants of business process effectiveness. Based on a literature review, this study aims to examine the role of knowledge transfer and integration, business process efficiency and business process modelling in shaping business process effectiveness. Data collected from Polish 300 managers and specialists using the CAWI method was analysed using structural equation modelling.

4

The role of managerial competencies in interorganizational knowledge transfer: a hybrid literature review

Domaradzka Aurelia, Sulich Adam

Zeszyty Naukowe. Organizacja i Zarządzanie / Politechnika Śląska

|

2024

|

z. 201

91--103

EN

Purpose: This article aims to illustrate the role of managerial competencies in inter- organizational knowledge transfer. Design/methodology/approach: To achieve this objective, a hybrid literature review methodology in human resources management is adopted. This research combines a traditional narrative literature review with a systematic, bibliometric analysis. The traditional review justifies scientific discourse through subjectively selected publications, while the systematic review involves repeatable, objective searches of the Scopus database, analyzed using VOSviewer software. Findings: The findings highlight the critical role of managerial competencies in facilitating knowledge transfer between organizations. The evolving competencies of managerial staff within international organizations significantly influence the effectiveness of inter- organizational knowledge transfer. Research limitations/implications: Future research could expand on this study by exploring other databases and using additional bibliometric tools. Limitations include the focus on the Scopus database and potential biases in publication selection. Practical implications: This research offers insights for international enterprises on the importance of developing managerial competencies to enhance knowledge transfer. Organizations can leverage these findings to improve training programs and managerial practices, thereby fostering more effective knowledge sharing. Social implications: Enhanced managerial competencies in knowledge transfer can lead to more efficient organizational practices, potentially benefiting society by improving corporate social responsibility and influencing public and industry policies towards better knowledge management practices. Originality/value: This paper provides a novel hybrid approach to literature review, combining traditional and systematic methods, and underscores the essential role of managerial competencies in inter-organizational knowledge transfer. It is valuable for researchers, HR professionals, and international business managers.

5

The impact of workforce age diversity on non-financial organizational outcomes considering the role of knowledge transfer

Waligóra Łucja

Zeszyty Naukowe. Organizacja i Zarządzanie / Politechnika Śląska

|

2024

|

z. 199

633--645

EN

Purpose: The purpose of this research is to investigate the impact of workforce age diversity on non-financial organizational outcomes, with a specific focus on the role of knowledge transfer. It aims to understand the implications of age diversity for organizational success, considering both positive and negative effects, and to provide actionable insights for management practices. Design/methodology/approach: This study employs a quantitative approach involving surveys conducted among medium to large enterprises in Poland. Data collection utilized structured questionnaires administered to HR managers, HR directors, and rank-and-file employees. The study measures workforce age diversity using estimated data and calculates diversity indices (Blau and Teachman) to quantify diversity levels. Knowledge transfer is assessed using a validated scale, and non-financial organizational outcomes are measured through scales assessing innovation, risk-taking, and flexibility. Findings: The empirical analysis reveals that age diversity among employees does not directly correlate with organizational outcomes such as innovation and risk-taking. However, knowledge transfer significantly enhances these outcomes. Contrary to initial hypotheses, age diversity does not directly influence knowledge transfer within organizations, indicating a complex relationship that requires nuanced management strategies. Research limitations/implications: Limitations include the use of estimated age diversity data and the specific focus on Polish organizations, limiting generalizability. Future research should explore additional mediating and moderating variables, such as organizational culture and leadership styles, to better understand the dynamics between age diversity, knowledge transfer, and organizational outcomes. Practical implications: Practically, this research underscores the importance of fostering effective knowledge transfer practices within diverse age groups to enhance organizational innovation and flexibility. It recommends that organizations invest in training and development programs aimed at facilitating intergenerational knowledge exchange, thereby optimizing workforce potential and adapting to demographic shifts. Originality/value: This paper contributes to the literature by providing empirical insights into the complex interplay between age diversity, knowledge transfer, and organizational outcomes. It highlights the critical role of knowledge transfer in leveraging age diversity as a strategic asset for organizational competitiveness and sustainability.

6

Knowledge transfer across peer and multigenerational teams of employees

Czainska Katarzyna

Zeszyty Naukowe. Organizacja i Zarządzanie / Politechnika Śląska

|

2024

|

z. 201

79--89

EN

Purpose: identification of differences in methods, forms and IT channels of knowledge transfer used in employee peer and multigenerational groups. Design/methodology/approach: preferences for knowledge transfer in peer groups were assumed on the basis of a benchmark survey conducted by researchers at Jagiellonian University in 2020. On the other hand, preferences for knowledge transfer in multigenerational groups were identified on the basis of original studies conducted in April and May 2023. Findings: it was noted that there are differences in the preferred ways, forms and channels of knowledge transfer in the studied employee groups. Research limitations/implications: The comparative study was carried out in two specific social groups (academic and military), therefore further research should be conducted in other sectors, especially economic ones. Practical implications: a positive phenomenon for businesses is the willingness of younger employees to acquire knowledge through direct contact with older employees with higher seniority. Social implications: a positive phenomenon for businesses is the willingness of younger employees to acquire knowledge through direct contact with older employees with higher seniority. This attitude is conducive to building intergenerational knowledge networks and shaping a knowledge management strategy based on trust, while contradicting the thesis that young employees do not engage in the process of intergenerational knowledge transfer. Originality/value: The basic value of the conducted research is to refute the stereotype according to which young employees prefer functioning in the virtual world and do not appreciate direct relationships; The above stereotype combined with the lack of trust confirmed in the literature resulted in a tendency to separate peer groups, which made it difficult, among others, knowledge transfer. The willingness of young employees to acquire knowledge from older mentors, indicated in this research, should be the foundation for building a knowledge transfer strategy based on intergenerational employee integration and motivational tools (financial and non-financial) encouraging employees to share knowledge.

7

Dzielenie się wiedzą i transfer wiedzy we współczesnej organizacji

Skrzypek Elżbieta, Sagan Sylwia

Problemy Jakości

|

2024

|

R. 56, nr 3

2--11

PL

Cel: Celem artykułu jest wskazanie rangi oraz znaczenia transferu i dzielenia się wiedzą w organizacji, a także pokazanie wynikających z tego korzyści i barier występujących w tych procesach. Wskazanie uwarunkowań, motywów, barier, korzyści, efektów i czynników wspierających oraz stymulujących zachowania związane z dzieleniem się wiedzą. Ponadto wskazanie na wybrane badania, które podkreślają stan i znaczenie szeroko rozumianego procesu dzielenia się wiedzą w organizacjach oraz pokazanie związków, jakie zachodzą między dzieleniem się wiedzą i transferem wiedzy. Projekt badania/metodyka badawcza/koncepcja: Projekt zakłada wskazanie różnic w podejściu do subprocesów zarządzania wiedzą. Badanie obejmuje krytyczną analizę dostępnej literatury oraz analizę wyników opublikowanych badań oraz wnioskowanie. Wyniki/wnioski: Ukazanie istoty, różnorodności w podejściu do definiowania transferu i dzielenia się wiedzą, wskazanie związków, jakie zachodzą między transferem i dzieleniem się wiedzą, ukazanie potrzeby podniesienia rangi tych subprocesów w zarządzaniu wiedzą we współczesnej organizacji, wskazanie na potrzebę kontynuacji badań nad problemami związanymi z transferem i dzieleniem się wiedzą. Ograniczenia: Zarządzanie wiedzą w polskich przedsiębiorstwach wzbudza coraz większe zainteresowanie. Jednocześnie dzielenie się wiedzą i transfer wiedzy jako subprocesy zarządzania wiedzą napotykają na szereg barier. Potwierdzają to liczne badania prowadzone w tym zakresie. Zastosowanie praktyczne: Wskazanie zależności pomiędzy dzieleniem się wiedzą i transferem wiedzy oraz pokazanie korzyści, jakie mogą osiągnąć organizacje realizujące te subprocesy w ramach procesu zarządzania wiedzą. Oryginalność/wartość poznawcza: Pokazanie znaczenia dzielenia się wiedzą jako najważniejszego aspektu zarządzania wiedzą w celu zachęcenia organizacji do szerszego zainteresowania się zarówno problematyką zarządzania wiedzą, jak i jego subprocesami, jakimi są transfer i dzielenie się wiedzą. Przedstawione wyniki badań ukazują wybrane elementy zarządzania wiedzą związane z oddziaływaniem subprocesów transfer i dzielenie się wiedzą na organizację i pracownika.

EN

Purpose: The purpose of this article is to indicate the purpose of knowledge sharing and transfer in a contemporary organisation. It aims to show the benefits and barriers occurring in these processes. To achieve the above, we needed to find the determinants, motives, barriers, benefits, effects and factors supporting and stimulating knowledge sharing behaviour. In addition, the authors selected some major works that highlight the status and importance of the broadly understood knowledge sharing process in organisations and strived to show the relationships that occur between knowledge sharing and knowledge transfer. Design/methodology/approach: This work aims to identify differences in approaches to knowledge management sub-processes. The study includes a critical analysis of the available literature and an analysis of the results of published research and logical inference and reasoning. Findings/conclusions: To show the essence, the diversity of approaches to defining knowledge transfer and sharing, to indicate the relationships that occur between knowledge transfer and sharing, to show the need to raise the profile of these sub-processes in knowledge management in a contemporary organisation, to indicate the need to continue research on problems related to knowledge transfer and sharing. Research limitations: Knowledge management in Polish enterprises is of growing interest. At the same time, knowledge sharing and knowledge transfer as sub-processes of knowledge management face a number of barriers. This is confirmed by numerous studies conducted in this area. Practical implications: To indicate the relationship between knowledge sharing and knowledge transfer and to show the benefits that can be achieved by organisations implementing these sub-processes as part of the knowledge management process Originality/value: To show the importance of knowledge sharing as the most important aspect of knowledge management in order to encourage organisations to take a broader interest in both knowledge management and its sub-processes of knowledge transfer and knowledge sharing. The results of the study distil crucial elements of knowledge management related to the impact of the knowledge sharing and transfer sub-processes on the organisation and the employees.

8

Knowledge transfer in interim management projects

Skowron-Mielnik Beata, Sobiecki Grzegorz

Engineering Management in Production and Services

|

2024

|

Vol. 16, no. 1

48--64

EN

This study aims to define the role of knowledge in a triad of factors determining effectiveness in Interim Management (IM) projects. The discussion is based on the authors’ research concept, which, in addition to knowledge, also explores the categories of trust and power. A longitudinal study using the empirical-inductive approach was conducted in Poland between 2019 and 2021. It included ten enterprises that implemented IM projects in the studied period. The results presented in this article confirm the importance of the empirically adopted study factors, including the transfer of knowledge between the Interim Manager and the client’s (organisation’s) project team. A significant relationship between the level of knowledge and the levels of trust and power emerges as particularly evident. Research can be continued to verify the authors’ initial findings and include the proposed research tools and entities representing different sectors, management cultures and geographical regions in search of additional variables and their correlations with trust, power and knowledge. The research conclusions may prove applicable to both Interim Managers (IMs) and their clients (organisations). They can be used not only for pre-project planning but also during the IM projects.

9

Knowledge transfer as a feature of small and medium-sized enterprises’ resilience to challenging economic conditions: evidence from peripheral countries

Zygmunt Aleksandra, Zygmunt Justyna

Economics and Environment

|

2024

|

No. 4

art. no. 1068

EN

The aim of this paper is to examine whether and how peripheral countries differ in terms of knowledge transfer as a feature of small and medium-sized enterprises (SMEs) resilience to challenging economic conditions (economic shocks). The study focuses on the Visegrad Group countries, which are peripheral within the European Union, offering a unique research context due to their similar cultural backgrounds and transition from centrally planned to market economies. The research covers the period 2016−2023, a period characterised by inflationary pressures and the COVID-19 pandemic. The study uses a comparative analysis and zero unitarization method to test the hypothesis. The results demonstrate that while there were significant differences in the level of knowledge transfer in the peripheral countries studied, all Visegrad Group countries showed a consistent upward tendency in knowledge transfer over the analysis period. The study contributes to the growing body of research on firms’ resilience by suggesting that knowledge transfer in the periphery serves as a mechanism to increase SMEs’ resilience to market or environmental disturbances and, more broadly, to the sustainable development of countries.

PL

Celem artykułu jest zbadanie, czy i w jaki sposób kraje peryferyjne różnią się pod względem transferu wiedzy jako cechy odporności małych i średnich przedsiębiorstw na trudne warunki gospodarcze. Badanie koncentruje się na krajach Grupy Wyszehradzkiej, które są należą do krajów peryferyjnych Unii Europejskiej, oferując unikalny kontekst badawczy ze względu na ich podobne tło kulturowe i rozpoczęcie transformacji gospodarki centralnie planowanej do rynkowej w tym samym czasie. Badanie obejmuje lata 2016−2023, które cechowało występowanie presji inflacyjnej oraz pandemii covid. Do przetestowania hipotezy wykorzystano analizę porównawczą i metodę unitaryzacji zerowanej. Wyniki pokazują, że chociaż istniały znaczne różnice w poziomie transferu wiedzy w badanych krajach peryferyjnych, wszystkie kraje Grupy Wyszehradzkiej wykazały stałą tendencję wzrostową w zakresie transferu wiedzy w analizowanym okresie. Otrzymane rezultaty stanowią wkład do rosnącej liczby badań nad odpornością firm na trudne warunki gospodarcze sugerując, że transfer wiedzy w regionach peryferyjnych służy jako mechanizm zwiększający odporność firm na zakłócenia rynkowe lub środowiskowe, a w szerszym kontekście wpływa na zrównoważony rozwój krajów.

10

STN-CDRS: Sentiment Transfer Network for Cross-Domain Recommendation Systems

Taneja Nikita, Thakur Hardeo Kumar

Computer Assisted Methods in Engineering and Science

|

2024

|

Vol. 31, no. 3

389--415

EN

In enterprise environments, the products may come from a variety of categories or do-mains. Users may engage with entities in one domain, but not in the others when theyare presented with multiple domains. Such users are referred to as “cold-starters” in otherdomains. The primary difficulty in cross-domain recommendation systems is to efficientlytransfer user’s latent information based on their engagements in one domain into theother domains. The advancements in recommendation systems have inspired us to de-velop review-driven recommendation models that utilize cross-domain knowledge transferand deep learning models. This work proposes a sentiment transfer network specificallydesigned for providing recommendation in cross-domain (STN-CDRS). The novelty of thework lies in the user rating enrichment mechanism, which is done by extracting latentinformation from user review data to fill sparse rating matrix. This enrichment uses pre-viously developed RNN-Core method for efficiently learning user reviews. The reviewsprovided by the users are used to enrich sparse data across domains. This enrichmentallows two things: alleviates the cold start problem and allows more intersecting usersacross domains to bridge the gap while learning. This work empirically demonstrates itsefficiency by iteratively updating over the baseline recommendation models in terms ofMAE (mean absolute error), RMSD (root mean squared deviation), precision and recallmeasures with other state-of-the-art-review-aided cross-domain recommendation systems.

11

Sustainable university – Knowledge and technology transfer channels to enterprises

Kobylińska Urszula, Irimia-Dieguez Ana Isabel

Economics and Environment

|

2023

|

No. 3

527--555

EN

The main aim of the article is an empirical verification of the channels through which the transfer of knowledge and technology from technical universities to enterprises takes place. The specific objective is to indicate the forms in which scientists can transfer knowledge and technology to enterprises in the field of sustainable solutions. In order to identify the features of the hidden dimensions of the university-enterprise relationship, the exploratory factor analysis (EFA) was used. The factor analysis showed that there are 3 channels through which scientists from technical universities establish relations with enterprises: the consulting and educational channel, the scientific and information channel, and the research and commercialization channel. In each of these channels, forms of knowledge and technology transfer have been identified that may relate to environmental topics for enterprises.

PL

Głównym celem artykułu jest empiryczna weryfikacja kanałów, którymi odbywa się transfer wiedzy i technologii z uczelni technicznych do przedsiębiorstw. Celem szczegółowym jest wskazanie form, w jakich naukowcy mogą transferować wiedzę i technologię do przedsiębiorstw, m.in. w zakresie rozwiązań środowiskowych. W celu identyfikacji cech ukrytych wymiarów relacji uczelnia--przedsiębiorstwo posłużono się eksploracyjną analizą czynnikową (EFA). Analiza czynnikowa wykazała, że istnieją 3 kanały, poprzez które naukowcy z uczelni technicznych nawiązują relacje z przedsiębiorstwami: konsultacyjno-edukacyjny, naukowo-informacyjny oraz badawczo-komercjalizacyjny. W każdym z tych kanałów zidentyfikowano formy transferu wiedzy i technologii, które mogą odnosić się do zagadnień środowiskowych ważnych dla przedsiębiorstw.

12

Supervised denoising of diffusion-weighted magnetic resonance images using a convolutional neural network and transfer learning

Jurek Jakub, Materka Andrzej, Ludwisiak Kamil, Majos Agata, Gorczewski Kamil, Cepuch Kamil, Zawadzka Agata

Biocybernetics and Biomedical Engineering

|

2023

|

Vol. 43, no. 1

206--232

EN

In this paper, we propose a method for reducing thermal noise in diffusion-weighted magnetic resonance images (DWI MRI) of the brain using a convolutional neural network (CNN) trained on realistic, synthetic MR data. Two reference methods are considered: a) averaging of repeated scans, a widespread method used in clinics to improve signal-to-noise ratio of MR images and b) the blockwise Non-Local Means (NLM) filter, one of the post-processing methods frequently used in DWI denoising. To obtain training data for transfer learning, the effects of echo-planar imaging (EPI) – Nyquist ghosting and ramp sampling – are modelled in a data-driven fashion. These effects are introduced to the digital phantom of brain anatomy (BrainWeb). Real noise maps are obtained from the MRI scanner with a brainDWI-designed protocol and later combined with simulated, noise-free EPI images. The Point Spread Function is measured in a DW image of an AJR-approved geometrical phantom. Inter-scan patient movement is captured from a brain scan of a healthy volunteer using image registration. The denoising methods are applied to the simulated EPI brain images and in real EPI DWI of the brain. The quality of denoised images is evaluated at several signal-to-noise ratios. The characteristics of noise residuals are studied thoroughly. A diffusion phantom is used to investigate the influence of denoising on ADC measurements. The method is also evaluated on a GRAPPA dataset. We show that our method outperforms NLM and image averaging and allows for a significant reduction in scan time by lowering the number of repeated scans. We also analyse the trained CNN denoisers and point out the challenges accompanying this denoising method.

13

PCG signal classification using a hybrid multi round transfer learning classifier

Ismail Shahid, Ismail Basit

Biocybernetics and Biomedical Engineering

|

2023

|

Vol. 43, no. 1

313--334

EN

Diagnosis of cardiovascular diseases using Phonocardiography(PCG) is a challenging task as signal itself is cyclo-stationary. It has spectral contents which are overlapped by multiple sources having similar spectral contents but acting as noise. Moreover, length variation in the signals and sampling using different equipment also make analysis of these signal a testing task. In this research, authors have introduced a hybrid technique to counter the variations just mentioned. Our technique is composed of high resolution spectrum generation, conversion of spectral contents to Spectrogram and multi round training. Use of fixed length spectral contents makes system independent of signal length. By using Spectrogram, the deep features can be extracted from spectrum which are used as an input to Pre-trained networks (PTNs). Finally, transfer learning is applied with multiple rounds of training. The introduced methodology is validated using multiple datasets having different PCG signals, sampling frequency, signals length and signal quality. From the reported results, it is evident that Chirplet Z transform (CZT) based Spectrogram can be utilized for mutlticlass classification. If CZT based Spectrograms are passed through multi rounds of training, then accuracy can be further increased. The reported results are accurate to 99% in the case of testing for best case scenarios and even in worst case, the results dont fall below 85%. However, an important observation is that they are consistent across the experimental protocols. The computational cost associated with the introduced technique is low which makes it suitable for hardware implementation.

14

Transfer learning techniques for medical image analysis: A review

Kora Padmavathi, Ooi Chui Ping, Faust Oliver, Raghavendra U., Gudigar Anjan, Chan Wai Yee, Meenakshi K., Swaraja K., Plawiak Pawel, Acharya U. Rajendra

Biocybernetics and Biomedical Engineering

|

2022

|

Vol. 42, no. 1

79--107

EN

Medical imaging is a useful tool for disease detection and diagnostic imaging technology has enabled early diagnosis of medical conditions. Manual image analysis methods are labor-intense and they are susceptible to intra as well as inter-observer variability. Automated medical image analysis techniques can overcome these limitations. In this review, we investigated Transfer Learning (TL) architectures for automated medical image analysis. We discovered that TL has been applied to a wide range of medical imaging tasks, such as segmentation, object identification, disease categorization, severity grading, to name a few. We could establish that TL provides high quality decision support and requires less training data when compared to traditional deep learning methods. These advantageous properties arise from the fact that TL models have already been trained on large generic datasets and a task specific dataset is only used to customize the model. This eliminates the need to train the models from scratch. Our review shows that AlexNet, ResNet, VGGNet, and GoogleNet are the most widely used TL models for medical image analysis. We found that these models can understand medical images, and the customization refines the ability, making these TL models useful tools for medical image analysis.

15

Knowledge and technology transfer as driving force for social innovations

Šimelytė Agnė, Tvaronavičienė Manuela, Holmen Rasmus Bøgh, Burinskas Arūnas, Razminienė Kristina

Polish Journal of Management Studies

|

2021

|

Vol. 23, No. 2

512--536

EN

Knowledge and technology transfer are defined as driving force for new business models, innovations and economic development. The aim of the paper is to carry out detailed literature analysis in order to create new framework of technology and knowledge transfer that contributes to social innovation. To explore the level of investigation and latest trends of the topic, the article provides bibliometric analysis on knowledge and technology transfer. The information is obtained from Web of Science for the period of 1990 to 2021. VOSviewer has been used for citation analysis, co-authorship and bibliographic de-coupling. More than 5,000 articles have been found with the keywords technology transfer and knowledge transfer in the database WoS indexed at six well-established citation indexes. For the bibliometric analysis, 308 articles in the fields of economics and business management have been used. Results of this review integrates concept of social innovation into theory of knowledge-based of firms. Furthermore, it composes the model of new knowledge and technology transfer that leads to social innovations. Thereby, our article contributes to theory of knowledge-based of firms and the concept of social innovation.

PL

Transfer wiedzy i technologii definiowany jest jako siła napędowa nowych modeli biznesowych, innowacji i rozwoju gospodarczego. Celem artykułu jest przeprowadzenie szczegółowej analizy literatury w celu stworzenia nowych ram transferu technologii i wiedzy przyczyniających się do innowacji społecznych. Aby zbadać poziom badań i najnowsze trendy w tym temacie, artykuł zawiera analizę bibliometryczną dotyczącą transferu wiedzy i technologii. Informacje pochodzą z Web of Science za okres 1990-2021. VOSviewer został wykorzystany do analizy cytowań, współautorstwa i rozprzęgania bibliograficznego. W bazie danych WoS odnaleziono ponad 5000 artykułów ze słowami kluczowymi transfer technologii i transfer wiedzy, zindeksowanych według sześciu uznanych indeksów cytowań. Do analizy bibliometrycznej wykorzystano 308 artykułów z dziedziny ekonomii i zarządzania przedsiębiorstwem. Wyniki tego przeglądu integrują koncepcję innowacji społecznych z teorią firm opartych na wiedzy. Ponadto tworzy model transferu nowej wiedzy i technologii, który prowadzi do innowacji społecznych. Tym samym nasz artykuł wpisuje się w teorię firm opartych na wiedzy oraz koncepcję innowacji społecznych.

16

Prediction of drug response in major depressive disorder using ensemble of transfer learning with convolutional neural network based on EEG

Sadat Shahabi Mohsen, Shalbaf Ahmad, Maghsoudi Arash

Biocybernetics and Biomedical Engineering

|

2021

|

Vol. 41, no. 3

946--959

EN

Major Depressive Disorder (MDD) is one of the leading causes of disability worldwide. Prediction of response to Selective Serotonin Reuptake Inhibitors (SSRIs) antidepressants in patients with MDD is necessary for preventing side effects of mistreatment. In this study, a deep Transfer Learning (TL) strategy based on powerful pre-trained convolutional neural networks (CNNs) in the big data datasets is developed for classification of Responders and Non-Responders (R/NR) to SSRI antidepressants, using 19-channel Electroencephalography (EEG) signal acquired from 30 MDD patients in the resting state. Multiple time-frequency images are obtained from each EEG channel using Continuous Wavelet Transform (CWT) for feeding into pre-trained CNN models that are VGG16, Xception, DenseNet121, MobileNetV2 and InceptionResNetV2. Our plan is to adapt and fine-tune the weights of networks to the target task with the small-sized dataset. Finally, to improve the recognition performance, an ensemble method based on majority voting of outputs of five mentioned deep TL architectures has been developed. Results indicate that the best performance among basic models achieved by DenseNet121 with accuracy, sensitivity and specificity of 95.74%, 95.56% and 95.64%, respectively. An Ensemble of these basic models created to surpass the accuracy obtained by each individual basic model. Our experiments show that ensemble model can gain accuracy, sensitivity and specificity of 96.55%, 96.01% and 96.95%, respectively. Therefore, proposed ensemble of TL strategy of pre-trained CNN models based on WT images obtained from EEG signal can be used for antidepressants treatment outcome prediction with a high accuracy.

17

Automatic detection of coronavirus disease (COVID-19) in X-ray and CT images: A machine learning based approach

Kassani Sara Hosseinzadeh, Kassani Peyman Hosseinzadeh, Wesolowski Michal J., Schneider Kevin A., Deters Ralph

Biocybernetics and Biomedical Engineering

|

2021

|

Vol. 41, no. 3

867--879

EN

The newly identified Coronavirus pneumonia, subsequently termed COVID-19, is highly transmittable and pathogenic with no clinically approved antiviral drug or vaccine available for treatment. The most common symptoms of COVID-19 are dry cough, sore throat, and fever. Symptoms can progress to a severe form of pneumonia with critical complications, including septic shock, pulmonary edema, acute respiratory distress syndrome and multi-organ failure. While medical imaging is not currently recommended in Canada for primary diagnosis of COVID-19, computer-aided diagnosis systems could assist in the early detection of COVID-19 abnormalities and help to monitor the progression of the disease, potentially reduce mortality rates. In this study, we compare popular deep learningbased feature extraction frameworks for automatic COVID-19 classification. To obtain the most accurate feature, which is an essential component of learning, MobileNet, DenseNet, Xception, ResNet, InceptionV3, InceptionResNetV2, VGGNet, NASNet were chosen amongst a pool of deep convolutional neural networks. The extracted features were then fed into several machine learning classifiers to classify subjects as either a case of COVID-19 or a control. This approach avoided task-specific data pre-processing methods to support a better generalization ability for unseen data. The performance of the proposed method was validated on a publicly available COVID-19 dataset of chest X-ray and CT images. The DenseNet121 feature extractor with Bagging tree classifier achieved the best performance with 99% classification accuracy. The second-best learner was a hybrid of the a ResNet50 feature extractor trained by LightGBM with an accuracy of 98%.

18

Automated detection of COVID-19 from CT scan using convolutional neural network

Mishra Narendra Kumar, Singh Pushpendra, Joshi Shiv Dutt

Biocybernetics and Biomedical Engineering

|

2021

|

Vol. 41, no. 2

572--588

EN

Under the prevailing circumstances of the global pandemic of COVID-19, early diagnosis and accurate detection of COVID-19 through tests/screening and, subsequently, isolation of the infected people would be a proactive measure. Artificial intelligence (AI) based solutions, using Convolutional Neural Network (CNN) and exploiting the Deep Learning model’s diagnostic capabilities, have been studied in this paper. Transfer Learning approach, based on VGG16 and ResNet50 architectures, has been used to develop an algorithm to detect COVID-19 from CT scan images consisting of Healthy (Normal), COVID-19, and Pneumonia categories. This paper adopts data augmentation and fine-tuning techniques to improve and optimize the VGG16 and ResNet50 model. Further, stratified 5-fold cross-validation has been conducted to test the robustness and effectiveness of the model. The proposed model performs exceptionally well in case of binary classification (COVID-19 vs. Normal) with an average classification accuracy of more than 99% in both VGG16 and ResNet50 based models. In multiclass classification (COVID-19 vs. Normal vs. Pneumonia), the proposed model achieves an average classification accuracy of 86.74% and 88.52% using VGG16 and ResNet50 architectures as baseline, respectively. Experimental results show that the proposed model achieves superior performance and can be used for automated detection of COVID-19 from CT scans.

19

A deep learning based approach for classification of abdominal organs using ultrasound images

Santhosh Reddy D., Rajalakshmi P., Mateen M. A.

Biocybernetics and Biomedical Engineering

|

2021

|

Vol. 41, no. 2

779--791

EN

Ultrasound imaging is one of the primary modalities used for diagnosing a multitude of medical conditions affecting organs and soft tissues the body. Unlike X-rays, which use ionizing radiation, ultrasound imaging utilizes non-hazardous acoustic waves and is widely preferred by doctors. However, ultrasound imaging sometimes requires substantial manual effort in the identification of organs during real-time scanning. Also, it is a challenging task if the scanning performed by an unskilled clinician does not comprise adequate information about the organ, leading to an incorrect diagnosis and thereby fatal consequences. Hence, the automated organ classification in such scenarios can offer potential benefits. In this paper, We propose a convolutional neural network-based architecture (CNNs), precisely, a transfer learning approach using ResNet, VGG, GoogleNet, and Inception models for accurate classification of abdominal organs namely kidney, liver, pancreas, spleen, and urinary bladder. The performance of the proposed framework is analyzed using in-house developed dataset comprising of 1906 ultrasound images. Performance analysis shows that the proposed framework achieves a classification accuracy and F1 score of 98.77% and 98.55%, respectively, on an average. Also, we provide the performance of the proposed architecture in comparison with the state-of-the-art studies.

20

Opracowanie koncepcji i implementacja modelu rozpoznawania obrazu z wykorzystaniem elementów sztucznej inteligencji

Sierżantowicz Anna, Ptasznik Andrzej

Zeszyty Naukowe Warszawskiej Wyższej Szkoły Informatyki

|

2020

|

nr 23

7--26

PL

W niniejszym artykule przedstawiono koncepcję i implementację modelu do rozpoznawania ras psów na podstawie zdjęcia. Do realizacji zadania wykorzystano model głębokiej sieci neuronowej bazujący na strukturze InceptionV3. Sieć została wytrenowana i przetestowana na zbiorze przypadków uczących liczącym ponad 20 tys. zdjęć 120 ras psów z zastosowaniem transferu wiedzy. Zbadano również wpływ jakości zdjęć na wyniki klasyfikacji. Sieć uzyskała bardzo dobre rezultaty zarówno w przypadku analizy typowych, jak i nietypowych zdjęć.

EN

This article presents the concept and implementation of a model for recognizing dog breeds based on an input image. The task was performed with the use of a deep neural network model based on the InceptionV3 structure. The neural network has been trained and tested on a dataset counting more than 20,000 images of 120 dog breeds using transfer learning technique. The impact of image quality on classification results was also examined. The model obtained very good results in the analysis of both typical and unusual input images.