Search Results (61)

This paper presents a novel digital identity ecosystem built upon a hierarchical structure of Blockchain tokens, where both government-certified and uncertified tokens can coexist to represent various attributes of an individual’s identity. At the core of this system is the government, which functions as a trusted authority capable of creating entities and issuing a unique, non-replicable digital identity token for each one. Entities are the exclusive owners of their identity tokens and can attach additional tokens—such as those issued by the government, educational institutions, or financial entities—to form a verifiable, token-based digital identity tree. This model accommodates a flexible identity framework that enables decentralized yet accountable identity construction. Our contributions include the design of a digital identity system (supported by smart contracts) that enforces uniqueness through state-issued identity tokens while supporting user-driven identity formation. The model differentiates between user types and certifies tokens according to their source, enabling a scalable and extensible structure. We also analyze the economic, technical, and social feasibility of deploying this system, including a breakdown of transaction costs for key stakeholders such as governments, end-users, and institutions like universities. Considering the benefits of blockchain, implementing a digital identity ecosystem in this technology is economically viable for all involved stakeholders. Full article

As climate change concerns, urban congestion, and environmental degradation intensify, cities prioritise cycling as a sustainable transport option to reduce CO₂ emissions and improve quality of life. However, rampant bicycle theft and poor security infrastructure often deter daily commuters and tourists from cycling. This study explores how advanced security measures can bolster sustainable urban mobility and tourism by addressing these challenges. A mixed-methods approach is utilised, incorporating primary survey data from Slovenia and secondary data on bicycle sales, imports and thefts from 2015 to 2024. Findings indicate that access to secure parking substantially enhances users’ sense of safety when commuting by bike. Regression analysis shows that for every 1000 additional bicycles sold, approximately 280 more thefts occur—equivalent to a 0.28 rise in reported thefts—highlighting a systemic vulnerability associated with sustainability-oriented behaviour. To bridge this gap, the study advocates for an innovative security framework that combines blockchain technology and Non-Fungible Tokens (NFTs) with encrypted Quick Response (QR) codes. Each bicycle would receive a tamper-proof QR code connected to a blockchain-verified NFT documenting ownership and usage data. This system facilitates real-time authentication, enhances traceability, deters theft, and builds trust in cycling as a dependable transport alternative. The proposed solution merges sustainable transport, digital identity, and urban security, presenting a scalable model for individual users and shared mobility systems. Full article

Text-based person search (TPS), a critical technology for security and surveillance, aims to retrieve target individuals from image galleries using textual descriptions. The existing methods face two challenges: (1) ambiguous attribute–noun association (AANA), where syntactic ambiguities lead to incorrect associations between attributes and the intended nouns; and (2) textual noise and relevance imbalance (TNRI), where irrelevant or non-discriminative tokens (e.g., ‘wearing’) reduce the saliency of critical visual attributes in the textual description. To address these aspects, we propose the dependency-aware entity–attribute alignment network (DEAAN), a novel framework that explicitly tackles AANA through dependency-guided attention and TNRI via adaptive token filtering. The DEAAN introduces two modules: (1) dependency-assisted implicit reasoning (DAIR) to resolve AANA through syntactic parsing, and (2) relevance-adaptive token selection (RATS) to suppress TNRI by learning token saliency. Experiments on CUHK-PEDES, ICFG-PEDES, and RSTPReid demonstrate state-of-the-art performance, with the DEAAN achieving a Rank-1 accuracy of 76.71% and an mAP of 69.07% on CUHK-PEDES, surpassing RDE by 0.77% in Rank-1 and 1.51% in mAP. Ablation studies reveal that DAIR and RATS individually improve Rank-1 by 2.54% and 3.42%, while their combination elevates the performance by 6.35%, validating their synergy. This work bridges structured linguistic analysis with adaptive feature selection, demonstrating practical robustness in surveillance-oriented TPS scenarios. Full article

Background/Objectives: Sleep disorders are prevalent among aging populations and are often linked to cognitive decline, chronic conditions, and reduced quality of life. Traditional diagnostic methods, such as polysomnography, are resource-intensive and limited in accessibility. Meanwhile, individuals frequently describe their sleep experiences through unstructured narratives in clinical notes, online forums, and telehealth platforms. This study proposes a machine learning pipeline (sleepCare) that classifies sleep-related narratives into clinically meaningful categories, including stress-related, neurodegenerative, and breathing-related disorders. The proposed framework employs natural language processing (NLP) and machine learning techniques to support remote applications and real-time patient monitoring, offering a scalable solution for the early identification of sleep disturbances. Methods: The sleepCare consists of a three-tiered classification pipeline to analyze narrative sleep reports. First, a baseline model used a Multinomial Naïve Bayes classifier with n-gram features from a Bag-of-Words representation. Next, a Support Vector Machine (SVM) was trained on GloVe-based word embeddings to capture semantic context. Finally, a transformer-based model (BERT) was fine-tuned to extract contextual embeddings, using the [CLS] token as input for SVM classification. Each model was evaluated using stratified train-test splits and 10-fold cross-validation. Hyperparameter tuning via GridSearchCV optimized performance. The dataset contained 475 labeled sleep narratives, classified into five etiological categories relevant for clinical interpretation. Results: The transformer-based model utilizing BERT embeddings and an optimized Support Vector Machine classifier achieved an overall accuracy of 81% on the test set. Class-wise F1-scores ranged from 0.72 to 0.91, with the highest performance observed in classifying normal or improved sleep (F1 = 0.91). The macro average F1-score was 0.78, indicating balanced performance across all categories. GridSearchCV identified the optimal SVM parameters (C = 4, kernel = ‘rbf’, gamma = 0.01, degree = 2, class_weight = ‘balanced’). The confusion matrix revealed robust classification with limited misclassifications, particularly between overlapping symptom categories such as stress-related and neurodegenerative sleep disturbances. Conclusions: Unlike generic large language model applications, our approach emphasizes the personalized identification of sleep symptomatology through targeted classification of the narrative input. By integrating structured learning with contextual embeddings, the framework offers a clinically meaningful, scalable solution for early detection and differentiation of sleep disorders in diverse, real-world, and remote settings. Full article

Current research on intelligent question answering mainly focuses on high-resource languages such as Chinese and English, with limited studies on question understanding and reasoning in low-resource languages. In addition, during the joint modeling of question understanding tasks, the interdependence among subtasks can lead to error accumulation during the interaction phase, thereby affecting the prediction performance of the individual subtasks. To address the issue of error propagation caused by sentence-level intent encoding in the joint modeling of intent recognition and slot filling, this paper proposes a Cross-lingual Token-level Bi-Interactive Model (Bi-XTM). The model introduces a novel subtask interaction method that leverages the token-level intent output distribution as additional information for slot vector representation, effectively reducing error propagation and enhancing the information exchange between intent and slot vectors. Meanwhile, to address the scarcity of Kazakh (Arabic alphabet) language corpora, this paper constructs a cross-lingual joint question understanding dataset for the Xinjiang tourism domain, named JISD, which includes 16,548 Chinese samples and 1399 Kazakh samples. This dataset provides a new resource for cross-lingual intent recognition and slot filling joint tasks. Experimental results on the publicly available multi-lingual question understanding dataset MTOD and the newly constructed dataset demonstrate that the proposed Bi-XTM achieves state-of-the-art performance in both monolingual and cross-lingual settings. Full article

As globalization and rapid economic development drive a surge in air transportation demand, the need for enhanced efficiency and safety in flight operations has become increasingly critical. However, the exponential growth in flight numbers has exacerbated airspace congestion, creating a stark contrast with the limited availability of airspace resources. This imbalance poses significant challenges to flight punctuality and operational efficiency. To mitigate these issues, existing models often rely solely on individual flight data, which restricts the breadth and depth of feature learning. In this study, we propose an innovative Inverted Transformer framework for aviation trajectory prediction enhanced by multi-flight mode fusion. This framework leverages multi-flight inputs and inverted data processing to enrich feature representation and optimize the modeling of multi-variate time series. By treating the entire time series of each variable as an independent token, our model effectively captures global temporal dependencies and enhances correlation analysis among multiple variables. Extensive experiments on real-world aviation trajectory datasets demonstrate the superiority of our proposed framework. The results show significant improvements in prediction accuracy. Moreover, the integration of multi-flight data enables the model to learn more comprehensive flight patterns, leading to robust performance across varying flight conditions. This research provides a novel perspective and methodology for aviation trajectory prediction, contributing to the efficient and safe development of air transportation systems. Full article

Introduction: Widespread adoption of AI for medical decision-making is still hindered due to ethical and safety-related concerns. For AI-based decision support systems in healthcare settings, it is paramount to be reliable and trustworthy. Common deep learning approaches, however, have the tendency towards overconfidence when faced with unfamiliar or changing conditions. Inappropriate extrapolation beyond well-supported scenarios may have dire consequences highlighting the importance of the reliable estimation of local knowledge uncertainty and its communication to the end user. Materials and Methods: While neural network ensembles (ENNs) have been heralded as a potential solution to these issues for many years, deep learning methods, specifically modeling the amount of knowledge, promise more principled and reliable behavior. This study compares their reliability in clinical applications. We centered our analysis on experiments with low-dimensional toy datasets and the exemplary case study of mortality prediction for intensive care unit hospitalizations using Electronic Health Records (EHRs) from the MIMIC3 study. For predictions on the EHR time series, Encoder-Only Transformer models were employed. Knowledge uncertainty estimation is achieved with both ensemble and Spectral Normalized Neural Gaussian Process (SNGP) variants of the common Transformer model. We designed two datasets to test their reliability in detecting token level and more subtle discrepancies both for toy datasets and an EHR dataset. Results: While both SNGP and ENN model variants achieve similar prediction performance (AUROC: $\approx 0.85$, AUPRC: $\approx 0.52$ for in-hospital mortality prediction from a selected MIMIC3 benchmark), the former demonstrates improved capabilities to quantify knowledge uncertainty for individual samples/patients. Discussion/Conclusions: Methods including a knowledge model, such as SNGP, offer superior uncertainty estimation compared to traditional stochastic deep learning, leading to more trustworthy and safe clinical decision support. Full article

The popularity of cryptocurrency exchanges has surged in recent years, accompanied by the proliferation of new digital platforms and tokens. However, the issue of credit risk and the reliability of crypto exchanges remain critical, highlighting the need for indicators to assess the safety of investing through these platforms. This study examines a unique, hand-collected dataset of 228 cryptocurrency exchanges operating between April 2011 and May 2024. Using various machine learning algorithms, we identify the key factors contributing to exchange shutdowns, with trading volume, exchange lifespan, and cybersecurity scores emerging as the most significant predictors. Since individual machine learning models often capture distinct data characteristics and exhibit varying error patterns, we employ a forecast combination approach by aggregating multiple predictive distributions. Specifically, we evaluate several specifications of the generalized linear pool (GLP), beta-transformed linear pool (BLP), and beta-mixture combination (BMC). Our findings reveal that the beta-transformed linear pool and the beta-mixture combination achieve the best performances, improving forecast accuracy by approximately 4.1% based on a robust H-measure, which effectively addresses the challenges of misclassification in imbalanced datasets. Full article

Efficient cattle healthcare management is vital for ensuring productivity and welfare in dairy production, yet traditional record-keeping methods often lack transparency, security, and efficiency, leading to challenges in livestock product quality and healthcare. This study introduces a novel framework leveraging Zero Knowledge (ZK)-Rollups-enhanced Layer 2 blockchain and Non-Fungible Tokens (NFTs) to address these issues. NFTs serve as secure digital certificates for individual cattle health records, ensuring transparency and traceability. ZK-Rollups on the Layer 2 blockchain enhance scalability, privacy, and cost-efficiency, while smart contracts automate key processes such as veterinary scheduling, medication delivery, and insurance claims, minimizing administrative overhead. Performance evaluations reveal significant advancements, with transaction delays of 4.1 ms, throughput of 249.8 TPS, gas costs reduced to 26,499.76 Gwei, and a time-to-finality of 1.1 ms, achieved through ZK-SNARKs (ZK-Succinct Non-Interactive Arguments of Knowledge) integration. These results demonstrate the system’s potential to revolutionize cattle healthcare management by combining transparency, security, and operational efficiency. Full article

Recycling plays a crucial role in impacting national GDP and environmental sustainability. Given the complexities inherent in recycling processes, technology serves as a driving force for advancing and optimizing these practices. In the Kingdom of Saudi Arabia, substantial initiatives are underway to foster a green environment and promote a circular economy. However, at the time of writing this paper, existing regulations mandate recycling primarily for business sectors, with no corresponding requirements for household waste collection or segregation. As a result, a significant portion of recyclable waste remains unprocessed. This paper expands upon earlier studies carried out in Jeddah, analyzing the obstacles and variables impacting sustainable recycling solutions, along with the essential conditions to boost household involvement in recycling. This study explores the potential of blockchain technology to improve household engagement by developing a blockchain-based loyalty program. The proposed system leverages the decentralized, immutable, and transparent features of blockchain technology to reward individuals with tokens for the recycling waste they produce, thereby facilitating token tracking across the recycling value chain and enhancing transparency in the circular economy. This article delves into the technical architecture of the loyalty program, aligning its domain model elements with blockchain design heuristics and integrating it with a mobile application that aims to boost recycling engagement by applying social economy principles. This innovative approach promises to overcome the current regulatory and motivational barriers, as well as promote sustainable recycling habits at the household level. Full article

Small and medium-scale enterprises (SMEs) need a platform that actively enables collaboration with research institutions and consultants as SMEs lack the financial resources to conduct independent research. Such a platform will require a verifiable manipulation-free system to enable, execute, and record collaboration activities and to track reputations among the organizations and individuals that use the platform. Blockchain provides an opportunity to build such a collaborative platform by enabling the verifiable recording of the results of the collaborations, aggregating the resulting reputation of the collaborating parties, and offering tokenized incentives to reward positive contributions to the platform. Cryptocurrencies from which blockchain tokens are derived are volatile, thereby reducing business organizations’ interest in blockchain applications. Hence, there is a need to design a self-sustaining valuable token model that incentivizes user behaviours that positively contribute to the platform. This paper explores the application of game theory in analyzing token-based economic interactions between various groups of users in an implemented blockchain-based collaboration platform to design and simulate a token distribution system that provides a fair reward mechanism for users while also providing a dynamic pricing model for the utility value provided by platform tokens. To achieve this objective, we adopted the design science research method, a running case of a blockchain collaboration platform that enables research collaboration, and extensive form games in game theory, first to analyze and simulate token outcomes of users of the collaboration platform. Secondly, the research used a logarithmic model to show the dynamic utility pricing property of the developed token model where the self-sustainability of the token is backed by the availability of an internal resource within the platform. Thirdly, we applied a qualitative approach to analyze potential risks in the designed token model and proposed risk mitigation strategies. Thus, the resulting models and their simulations, such as token distribution models and a dynamic token utility model, as well as the identified token risks and their mitigation strategies, represent the main contributions of this work. Full article

This study sets out to analyze the negative effects of tokenism among a group of Portuguese female firefighters alongside the strategies they adopt to integrate into a male majority professional context and inherently associated with masculinity. Individual semi-structured interviews were carried out with nine men and nine women before their content was subject to thematic analysis. The results confirm how, in the context of the work performed by firefighters, there is a clear differentiation between the genders, with women both being more visible and leading to conformity to depicting stereotypical femininity. In order to fit in, female firefighters attempt to replicate the attitudes of their male colleagues, demonstrate high standards of performance, and tone down any expression of perceivably feminine characteristics. Full article

The Unmanned Aerial Vehicle (UAV) tracking tasks find extensive utility across various applications. However, current Transformer-based trackers are generally tailored for diverse scenarios and lack specific designs for UAV applications. Moreover, due to the complexity of training in tracking tasks, existing models strive to improve tracking performance within limited scales, making it challenging to directly apply lightweight designs. To address these challenges, we introduce an efficient attention mechanism known as Macaron Attention, which we integrate into the existing UAV tracking framework to enhance the model’s discriminative ability within these constraints. Specifically, our attention mechanism comprises three components, fixed window attention (FWA), local squeezing global attention (LSGA), and conventional global attention (CGA), collectively forming a Macaron-style attention implementation. Firstly, the FWA module addresses the multi-scale issue in UAVs by cropping tokens within a fixed window scale in the spatial domain. Secondly, in LSGA, to adapt to the scale variation, we employ an adaptive clustering-based token aggregation strategy and design a “window-to-window” fusion attention model to integrate global attention with local attention. Finally, the CGA module is applied to prevent matrix rank collapse and improve tracking performance. By using the FWA, LSGA, and CGA modules, we propose a brand-new tracking model named MATrack. The UAV123 benchmark is the major evaluation dataset of MATrack with 0.710 and 0.911 on success and precision, individually. Full article

Pest damage is a major factor in reducing crop yield and has negative impacts on the economy. However, the complex background, diversity of pests, and individual differences pose challenges for classification algorithms. In this study, we propose a patch-based neural network (PMLPNet) for multi-class pest classification. PMLPNet leverages spatial and channel contextual semantic features through meticulously designed token- and channel-mixing MLPs, respectively. This innovative structure enhances the model’s ability to accurately classify complex multi-class pests by providing high-quality local and global pixel semantic features for the fully connected layer and activation function. We constructed a database of 4510 images spanning 40 types of plant pests across 4 crops. Experimental results demonstrate that PMLPNet outperforms existing CNN models, achieving an accuracy of 92.73%. Additionally, heat maps reveal distinctions among different pest images, while patch probability-based visualizations highlight heterogeneity within pest images. Validation on external datasets (IP102 and PlantDoc) confirms the robust generalization performance of PMLPNet. In summary, our research advances intelligent pest classification techniques, effectively identifying various pest types in diverse crop images. Full article

Achieving a high participation rate is a common challenge in healthcare research based on web-based surveys. A study on local anesthetic systemic toxicity awareness and usage among medical practitioners at two Swiss university hospitals encountered resistance in obtaining personal email addresses from Heads of Departments. Participants were therefore divided into two groups: those who were directly invited via email (personal invitation group) and those who received a generic link through intermediaries (generic link group). The latter group was eventually excluded from survey data analysis. To determine whether one method of survey administration was more effective than another, we carried out a retrospective analysis of response rates and the proportion of new questionnaires completed after initial invitation and subsequent reminders. The results showed significantly higher response rates in the personal invitation group (40.2%, 313/779) compared to the generic link group (25.3%, 22/87), emphasizing the effectiveness of personal invitations on response rate (+14.9%, p = 0.007). The personal invitation group consistently yielded a higher number of completed questionnaires following the initial invitation and each reminder. The method of survey administration can greatly influence response rates and should be acknowledged as a quality criterion when conducting web-based surveys. Full article