Nina Evans

Digital Transformation (DT) has become a major focus with the rapid advancement of digital technologies. However, achieving successful digital business transformation (DBT) goes beyond simply implementing new technologies; it requires a strong emphasis on the organisational dynamics and the behaviours of leaders and staff. This paper shares findings from a focus group of nine experts who work as the Enterprise Transformation (ET) team within various organisations. The aim was to explore their lived experien ces regarding organisational behaviour and workplace politics exhibited during DBT, as well as the challenges these behaviours pose to managers. Participants highlighted that disruptive transformations often lead to negative organisational behaviours to sa botage the efforts of the ET team, noting the paradox that high-performing employees are often the most resistant to change. They also observed that the organisation fails to recognise and celebrate the success of the transformation. The experts suggested alternative strategies for successful transformation, arguing that traditional change management approaches — designed to reduce disruption —are not suited to DBT. Furthermore, they recommended starting the transformation with a small, isolated team or depart ment and gradually expanding once success is achieved. A key insight was that executive leaders must be fully committed to the change and adopt a ‘chaos management’ approach, which differs from conventional change management practices. Key propositions are suggested, emphasising that successful digital transformation hinges on addressing aspects of organisational dynamics - leadership, culture, communication, and processes - to navigate the complexities of disruptive digital transformation.

Jelena Duras Gled, Ljerka Luic

Generation X musicians represent a transitional generation from the pre -digital to the digital era, having experience developing their musical identity and reputation in both. In the process of development, they use digital platforms to communicate directly with their audience and utilize digital technologies for music production, promotion, and distribution. They face the challenge of reconciling traditional approaches they used in the pre -digital era with the demands of the digital ecosystem. The research explores how Generation X musicians perceive the transition process in developing their musical identity using traditional and digital approach and what strategies they have adopted to keep relevance in the digital age. The results show that Generation X musicians use a combination of traditional and digital tools, with this integrated approach proving to be the best strategy for them as they feel nostalgic and question the quality and relevance of online visibility. Although they have digital skills, they still need to take full advantage of the digital ecosystem in building their digital identity, leaving room for further research in this area. Continuing previous autoethnographic research identifying the information and communication challenges musicians face when developing their digital identity, this study gives deeper insight on those challenges from the perspective of Generation X musicians and the difficulties they face when reconciling traditional musical practices with new digital opportunities. T he input of this study is to contribute to the existing knowledge of the strategies musicians from various generations use to build digital identity, in particularly Generation X musicians, and to contribute to a better understanding of musician digital identity overall since there is a lack of research in this field.

Christopher Pandolfi, Xavier Massé, Ana Rita Morais, Yefri Ventura, Marko Cigljarev, Angela Jerath

The design of healthcare systems has unintentionally contributed to a rise in medical errors, partly due to the integration of new technologi es into outdated systems. By a pplying user-centred design, we can gain valuable insights from diverse pe rspectives, helping to develop and refine products and services that improve the healthcare process and enhance safety for all stakeholders. This paper explores the application of design thinking to analyse healthcare systems, with a specif ic focus on the pre-surgical process. It highlights three key design t ools—ecosystem mapping, partici patory workshops, and data visualizations—that were instrumental in identifying issues, proposing interventions, and communicating findings. User-centred design proves to be an effective approach for creating solutions that align with the needs of all users involved in the healthcare process.

Lisa Graichen, Matthias Graichen

Together with new hardware solutions, such as virtual reality (VR) headsets, the use of innovative interaction modes, such as mid -air gestures, is increasing in various areas of research, industry, and everyday life. As such setups are complex and not as well established as traditional haptic or touch-based interfaces, there is a higher risk of users experiencing errors, failures, or technical malfunctions. As for why gesture recognition rates may not be as high as desired, it is not yet clear why this is the case. We conducted a study in a VR context, using an HTC Vive headset and the Leap Motion gesture recognition device. Participants performed basic tasks with a “blocks” application using a pre-defined set of gestures. Afterwards they were asked to rate their levels on tr ust, acceptance and subjective feeling of immersion . We also measured basic hand parameters. We examined the correlation between hand size and observed detection errors of the gesture recognition device. Moreover, we analyzed the influence of perceived errors on the subjective feeling of immersion. We found no significant correlation between hand measurements and error rates. However, there is some evidence that hand length has some effect, which means smaller hands seem to slightly increase the errors rate in interactions using the gesture recognition device . Perceived errors had a negative impact on the feeling of immersion.

Aleksandra Vatian, Natalia Gusarova, Ivan Tomilov, Pavel Brunko, Alexey Zubanenko

Rapid and reliable diagnosis of cerebral stroke is a vital necessity, and among them, ischemic stroke is the most difficult to recognize on MRI images. Increasing the efficiency of stroke diagnosis is associated with the transition to incre asingly “heavy” AI tools working in 3D mode, processing MRI images not pixel-by-pixel, but voxel-by-voxel and using complex multifactor information processing algorithms. The implementation of such products requires large computing resources, which are often unavailable outside large medical centers. In addition, existing explainable AI tools identify the affected area very roughly and generally, which reduces the doctor’s confidence in the diagnostic result. On the other hand, one can use AI models operat ing in 2D mode - weaker, but faster and less demanding on computing resources. The article uses a Siamese neural network as a base model. To improve classification efficiency, a model pretrain on “light” synthetic data based on Perlin noise is proposed. To objectify the choice of mode, the article uses the apparatus of topological data analysis, namely, changes in persistent entropy and Renyi entropy of data embeddings on fully connected layers of a neural network. It is experimentally confirmed that using a 2D model, when trained on slices with maximum lesion visibility, produces ROC-AUC values no worse than using a full-scale 3D SOTA models, while allowing the clinician to selectively evaluate the individual slices he or she selects. It is experimentally c onfirmed that simple model that contains only locally useful features can support neural network training to a level comparable to much more complex and resource-intensive generative model.

Gridaphat Sriharee

Stock prediction using machine learning is an interesting topic for investors. However, the performance of the prediction depends on different techniques and the data itself. In this p aper, a feature selection methodology has been proposed. It co nsists of filter method and wrapper method . A feature selection experiment was conducted on 50 stocks ( SET50) from the Stock Exchange of Thailand (SET). The calculation of feature importance for feature selection was discussed. The feature importance shows how the cohort indicators behave in each wrapping level. Preliminary experiment was conducted to investigate some technical indicators that could be affected by SET50 . The basic machine learning models both regression models and classification models were examined to evaluate the performance of the models based on these features. The proposed f eature selection methodology was flexible and practical as each stock can be influenced by different features. Based on the measured feature importance, the features can be selected in different ways which can efficiently increase the performance of the machine learning model.

Diogo Araújo, Rita Gomes, Ivan Gomes, Luís Romero, Pedro Miguel Faria

This study focuses on the implementation and evaluation of generative models for the generation of textile designs using Generative Adversar ial Networks (GANs). The appro ach involved developing both unconditional and conditional vers ions of Wasserstein GANs (WGA Ns) and Wasserstein GANs with Gradient Penalty (WGAN-GP), as we ll as adaptations for higher r esolution outputs. A diverse dataset of 13,000 textile patterns was compiled, and the models were trained on this data, with architectures designed to optimize image generation in terms of both resolution and fe ature learning. The training process was analyzed using loss stability assessments, visual evaluation, a nd accuracy metrics. Results showed that WGAN-GP models demonstrated great er loss stabilization but lowe r overall accuracy since the discriminator learned faster, while conditional models showed i mprovement in image fidelity but with some divergence issues during training. Additionally, efforts to upscale output resolution to 256x256 pixels were largely unsuccessful, with significant loss oscillations and poor constructed generated samples. This study concludes with recommendations for further refinement of the model architectures and training strategies to improve the generation of high-quality, high-resolution textile designs.

Cláudio Keiji Iwata, Napoleão Verardi Galegale, Márcia Ito, Marília Macorin de Azevedo, Marcelo Duduchi Feitosa, Carlos Hideo Arima

The evolution of information technology combined with artificia l intelligence, IoT (Internet of Things) and robotics has made processes integrated and intelligent. The increased use of technology and the need for evidence-based decisions have contributed to the rapid expa nsion of a large volume of data in recent years. The quality of data generated mainly by humans must be given special attention, as errors can occur more frequently, making the pre-processing phase, such as data cleaning, a determining factor for better results in data analysis. The aim of this article is therefore to analyze data cleaning methods applied in Big Data environments by conducting a systematic review. The review method was based on the Kitchenham protocol, and the search databases were Scopus, Web of Science and CAPES. After searching and selecting the articles according to the protocol, 69 articles were analyz ed, revealing the use of a wide variety of techniques, such as machine learning, data mining, natural lang uage processing and others. The review also emphasized the various publication formats and the wide dissemination and discussion of research on data cleaning in Big Data in the academic community. Finally, t his study provides the state of the art of data cleansing techniques that have been used in a Big Data con text, offering insights and directions for future research.

Pedro Isaías

Editorial preface for Volume 19, Issue 2 of the IADIS International Journal on Computer Science and Information Systems (IJCSIS). This issue brings together peer-reviewed original research contributions covering the wide spectrum of Information Systems, Artificial Intelligence, Software Engineering, and Digital Transformation.