Abstract
This study examines the social factors influencing the acceptance of autonomous buses, with a focus on per-ceived benefits, safety, and comfort. It also explores whether these factors differ among residents of cities with varying sizes and urban mobility solutions. A survey was conducted in three Polish cities, collecting data from 1,160 respondents. Structural Equation Modelling (SEM) was used to analyse relationships between perceived benefits, safety, comfort, and future intentions to use autonomous buses. Results indicate that safety and comfort positively influence future intentions to use autonomous buses. However, the effect of perceived benefits varies across cities, suggesting that urban mobility conditions shape public acceptance. The study focuses on Polish cities, which may limit generalizability. Future research should examine other geo-graphical contexts. Findings provide insights for policymakers and manufacturers on enhancing public trust and promoting autonomous bus adoption. Improving public awareness and addressing safety concerns may increase societal acceptance of autonomous mobility. The study uniquely assesses how city characteristics influence social acceptance of autonomous buses.

Abstract
The increasing global burden of lung diseases necessitates the development of improved diagnostic tools. According to the WHO, hundreds of millions of individuals worldwide are currently affected by various forms of lung disease. The rapid advancement of artificial neural networks has revolutionized lung disease diagnosis, enabling the development of highly effective detection and classification systems. This article presents dual channel neural networks in image feature extraction based on classical CNN and vision transformers for multi-label lung disease diagnosis. Two separate subnetworks are employed to capture both global and local feature representations, thereby facilitating the extraction of more informative and discriminative image features. The global network analyzes all-organ regions, while the local network simultaneously focuses on multiple single-organ regions. We then apply a novel feature fusion operation, leveraging a multi-head attention mechanism to weight global features according to the significance of localized features. Through this multi-channel approach, the framework is designed to identify complicated and subtle features within images, which often go unnoticed by the human eye. Evaluation on the ChestX-ray14 benchmark dataset demonstrates that our hybrid model consistently outperforms established state-of-the-art architectures, including ResNet-50, DenseNet-121, and CheXNet, by achieving significantly higher AUC scores across multiple thoracic disease classification tasks. By incorporating test-time augmentation, the model achieved an average accuracy of 95.7% and a specificity of 99%. The experimental findings indicated that our model attained an average testing AUC of 87%. In addition, our method tackles a more practical clinical problem, and preliminary results suggest its feasibility and effectiveness. It could assist clinicians in making timely decisions about lung diseases.

Abstract

Abstract

Abstract
Building on the work carried out in the context of both the master's thesis and the EUGLOH Tromso Idea Camp 2024, this paper proposes to explore somatic relationships that could help to develop a grammar of practical applicability that specifies which properties pertain to each the three dimensions of Emotional Design presented by Donald Norman. Thus, a proto-ontology affecting some of these factors is presented. The validity of this proposal was methodologically tested mainly through the use of Cultural Probes, along with other methodological tools, which were used to collect emotionally relevant artifacts owned by the participants. This data was submitted through both Content Analysis and Artifact Analysis in order to determine which properties of the artifacts made them meaningful to the users. Different preliminary data related to the three dimensions of Emotional Design emerged: in the first visceral dimension, elements of a perceptual-sensory nature; in the behavioral dimension, some preliminary factors relating to the prevalence of both feedback and image schemas stood out; lastly, the reflective aspect proved to be the one where the most properties were determined, mainly related to symbolic properties.

Abstract
This research aims to leverage digital drawing as a non-verbal language to transcend the communication barriers faced by individuals with partial to complete locked-in syndrome (LIS). It will explore the possibility of using the human body as an interface, through assistive technology, in accordance with its limitation in functionality, to facilitate social reconnection and emotional expression through drawing. This approach is grounded in the understanding that creative expression and communication are fundamental human needs and can significantly impact the well-being and quality of life of individuals with severe motor impairments. This paper will focus on the development of the drawing activities. These activities will run under a mixed reality set that can be tailored by caregivers or therapists to the end-user's needs and preferences, ensuring functionality and user satisfaction through an accessible, enriching, and emotionally rewarding experience. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.