Search Results (210)

Background/Objectives: Conventional workflows, peripheral blood smears, and bone marrow assessment supplemented by LDI-PCR, molecular cytogenetics, and array-CGH, are expert-driven in the face of biological and imaging variability. Methods: We propose an AI pipeline that integrates convolutional neural networks (CNNs) and transfer learning-based models with two explainable AI (XAI) approaches, LIME and Grad-Cam, to deliver both high diagnostic accuracy and transparent rationale. Seven public sources were curated into a unified benchmark (66,550 images) covering ALL, AML, CLL, CML, and healthy controls; images were standardized, ROI-cropped, and split with stratification (80/10/10). We fine-tuned multiple backbones (DenseNet-121, MobileNetV2, VGG16, InceptionV3, ResNet50, Xception, and a custom CNN) and evaluated the accuracy and F1-score, benchmarking against the recent literature. Results: On the five-class task (ALL/AML/CLL/CML/Healthy), MobileNetV2 achieved 97.9% accuracy/F1, with DenseNet-121 reaching 97.66% F1. On ALL subtypes (Benign, Early, Pre, Pro) and across tasks, DenseNet121 and MobileNetV2 were the most reliable, achieving state-of-the-art accuracy with the strongest, nucleus-centric explanations. Conclusions: XAI analyses (LIME, Grad-CAM) consistently localized leukemic nuclei and other cell-intrinsic morphology, aligning saliency with clinical cues and model performance. Compared with baselines, our approach matched or exceeded accuracy while providing stronger, corroborated interpretability on a substantially larger and more diverse dataset. Full article

AI-based audio generation has advanced rapidly, enabling deepfake audio to reach levels of naturalness that closely resemble real recordings and complicate the distinction between authentic and synthetic signals. While numerous CNN- and Transformer-based detection approaches have been proposed, most adopt a model-centric perspective in which the spectral representation remains fixed. Parallel data-centric efforts have explored alternative representations such as scalograms and CQT, yet the field still lacks a unified framework that jointly evaluates the influence of model architecture, its hyperparameters (e.g., learning rate, number of epochs), and the spectral representation along with its own parameters (e.g., representation type, window size). Moreover, there is no standardized approach for benchmarking custom architectures against established baselines under consistent experimental conditions. FakeVoiceFinder addresses this gap by providing a systematic framework that enables direct comparison of model-centric, data-centric, and hybrid evaluation strategies. It supports controlled experimentation, flexible configuration of models and representations, and comprehensive performance reporting tailored to the detection task. This framework enhances reproducibility and helps clarify how architectural and representational choices interact in synthetic audio detection. Full article

Driven by technological innovation, service diversification, and the evolution and defects of current networks, the 6th-generation (6G) network architecture is lacking in research. One of the challenges in this research is that the architectural design should take into account multiple factors: customers, operators, and vendors. For service-oriented and network-oriented design requirements, this article proposes a data-driven distributed autonomous architecture (DDAA) for 6G with a three-layer four-plane logical hierarchy. The architecture is simplified as four network function units (NFUs), the interaction among which is carried via dual-bus interfaces, i.e., the service-based interface (SBI) and data transmission interface (DTI). In addition, it is user data-centric and rendered as distributed autonomous domains (ADs) with different scales to better adapt to customized services. Different transition stages from the 5th generation (5G) to 6G are discussed. Network simplification evaluation is further provided by going through several signaling procedures of the 3rd-generation partnership project (3GPP), inspiring advanced research and subsequent standardization of the 6G network architecture. Full article

The apparel industry plays a critical role in the global economy but continues to face persistent challenges related to fit accuracy, overproduction, inefficiencies, and limited digital integration. These issues are particularly evident in made-to-measure (MtM) manufacturing, where manual processes, fragmented digital tools, and weak data continuity hinder scalability and sustainability. This study aims to identify the key barriers to MtM 4.0 adoption and propose a digitally integrated workflow capable of supporting efficient, sustainable, and customer-centric apparel production. A systematic review of Industry 4.0 technologies and MtM practices is conducted to structure the problem and derive the requirements for a next-generation workflow. Based on these insights, a three-stage MtM 4.0 workflow (connecting design, product development, and production) is developed and operationalized in a functional prototype, MtM Lusitano 4.0. The prototype integrates a web configurator, a rule-based pattern engine, and ERP/MES connectivity, enabling full digital continuity from customer input to shop-floor execution. Results from industrial deployment confirm functional improvements, including increased measurement accuracy, reduced manual interventions, and stable production release flows. The study concludes that the proposed MtM 4.0 workflow strengthens operational efficiency, supports sustainability goals, and provides a structured pathway for digital transformation in the apparel sector. Full article

Background: Telepharmacy consultations (TPCs) became a routine element of pharmacy operations. However, there is limited data available on local pharmacy customer feedback related to TPC. Methods: A customer survey was developed seeking feedback on TPC. The pharmacy customers were invited to complete the survey in two local pharmacies in Germany. The survey and corresponding informed consent form were approved by the Ethics Committee. Results: In total, 178 pharmacy customers were enrolled (median age 41–50 years). From those, 37% agreed when asked whether they were generally interested in TPC. A total of 37% had the nearest pharmacy 5–15 min from their home. A total of 42% visited their pharmacy quarterly. A total of 36% used technical devices in median 1–2 h per days. A total of 33% classified their own digital skills at least as sufficient. A total of 59% would use their smartphone as a potential device for TPC. A total of 83% rated it as (slightly) important that the pharmacist providing TPC can be heard clearly. A total of 76% each (strongly) agreed that an argument for TPC would include limited mobility or pandemic/quarantine. A total of 33% (strongly) agreed that a key argument against TPC were technical requirements. A total of 75% considered situations of immobility to be the most important future perspective for TPC. Conclusions: Many pharmacy customers see TPC as an opportunity, e.g., in cases of limited mobility or during pandemic or quarantine. However, the use of appropriate technology can be a limiting factor. Full article

District heating is critical for low-carbon urban energy systems, yet most networks remain centralized in both heat generation and data ownership, fossil-dependent, and poorly integrated with digital, customer-centric, and market-responsive solutions. While artificial intelligence (AI), the Internet of Things (IoT), and automation offer transformative opportunities, their adoption raises complex challenges related to business models, regulation, and consumer trust. This paper addresses the absence of a comprehensive synthesis linking technological innovation, business-model evolution, and institutional adaptation in the digital transformation of district heating. Using the PRISMA-ScR methodology, this review systematically analyzed 69 peer-reviewed studies published between 2006 and 2024 across four thematic domains: digital technologies and automation, business-model innovation, customer engagement and value creation, and challenges and implementation barriers. The results reveal that research overwhelmingly emphasizes technical optimization, such as AI-driven forecasting and IoT-based fault detection, whereas economic scalability, regulatory readiness, and user participation remain underexplored. Studies on business-model innovation highlight emerging approaches such as dynamic pricing, co-ownership, and sector coupling, yet few evaluate financial or policy feasibility. Evidence on customer engagement shows increasing attention to real-time data platforms and prosumer participation, but also persistent barriers related to privacy, digital literacy, and equity. The review develops a schematic conceptual framework illustrating the interactions among technology, business, and governance layers, demonstrating that successful digitalization depends on alignment between innovation capacity, market design, and institutional flexibility. Full article

Online customer reviews contain rich signals about product value but are difficult to convert into strategy-ready evidence. This study proposes an end-to-end framework that maps review text to the Value Proposition Canvas (VPC) and quantifies alignment between user needs and product performance. Using customer reviews for three Samsung Galaxy Watch generations, an LLM extracts six dimensions (Customer Jobs, Pains, Gains, Feature Gaps, Emotions, Usage Context). Extracted phrases are embedded with a transformer model, clustered via K-means with data-driven k selection, and labeled by an LLM to form an interpretable taxonomy. Subsequently, the analysis derives frequency profiles, a gap density indicator, a context–gap matrix, and a composite Product–Market Fit (PMF) score that balances gain rate, gap rate, and coverage with sensitivity analysis to alternative weights. The findings show predominantly positive affect, with unmet needs concentrated in battery endurance and interaction stability. Productivity- and interaction-centric jobs attain the highest PMF score, while several monitoring-centric jobs are comparatively weaker. Significant cross-generation differences in job composition indicate evolving usage priorities across successive releases. The framework provides a scalable, reproducible path from unstructured VOC to decision support, enabling data-driven prioritization for product and UX management while advancing theory-grounded analysis of customer value. Full article

Background: This study deploys the Lean Six Sigma DMAIC framework to achieve systemic optimization of the school subscription process in Tunisia’s public transport service, a critical administrative operation affecting efficiency and customer satisfaction across the urban mobility network. Methods: Beyond conventional applications, the research integrates advanced analytical and process engineering tools, including capability indices, measurement system analysis (MSA), variance decomposition, and root-cause prioritization through Pareto–ANOVA integration, supported by a structured control plan aligned with ISO 9001:2015 and ISO 31000:2018 risk-management standards. Results: Quantitative diagnosis revealed severe process instability and nonconformities in information flow, workload balancing, and suboptimal resource allocation that constrained effective capacity utilization. Corrective interventions were modeled and validated through statistical control and real-time performance dashboards to institutionalize improvements and sustain process stability. The implemented actions led to a 37.5% reduction in cycle time, an 80% decrease in process errors, a 38.5% increase in customer satisfaction, and a 38.9% improvement in throughput. Conclusions: This study contributes theoretically by positioning Lean Six Sigma as a data-centric governance framework for stochastic capacity optimization and process redesign in public service systems, and practically by providing a replicable, evidence-based roadmap for operational excellence in governmental organizations within developing economies. Full article

Artificial intelligence (AI) has emerged as a transformative force across various sectors, providing innovative solutions and enhancing operational processes. In the e-commerce domain, AI has significantly contributed to customer-centric approaches and strategic decision-making, fostering superior customer experiences. This study investigates the role and impact of AI in the Saudi e-commerce sector, focusing on the perspectives of female customers and retailers. Grounded in sociotechnical theory, the research employs a mixed-methods approach, combining quantitative surveys and semi-structured interviews. The quantitative findings demonstrate that AI-enabled e-commerce positively influences customer experience, customer satisfaction, and operational efficiency. Key AI capabilities, such as task automation, personalized recommendations, and predictive analytics, enhance online retail systems’ performance. The qualitative analysis highlights both the opportunities and challenges associated with AI adoption, emphasizing the need for specialized infrastructure and skilled professionals. Participants recommend addressing the skill gap and adopting phased implementation strategies to optimize AI integration. This study provides actionable insights and strategic recommendations for policymakers and stakeholders in the Saudi e-commerce sector. Full article

Recent research has increasingly emphasized the synergies between Supply Chain Management Practices (SCMPs) and Quality Management Principles (QMPs), particularly through the emerging concept of Supply Chain Quality Management (SCQM). Despite this recognition, empirical evidence on how these practices interact to influence performance remains very limited, especially in the context of developing countries. This study addresses the gap by interviewing 70 Tunisian agri-food companies to investigate the relationships between five dimensions of SCMP, strategic supplier partnerships, customer relationship, information sharing, information quality and postponement, and the seven principles of ISO9001 QMP: leadership, engagement of people, improvement, customer focus, process approach, evidence-based decision making, and relationship management. Using factor analysis and structural equation modelling, the study explores the mediating role of competitive advantage (CA): price/cost, product quality, product innovation, delivery dependability and time-to-market—on operational performance. The findings indicate that analyzing SCMP, QMP, and CA as aggregated blocks does not produce significant explanatory correlations. Instead, judiciously reorganizing their sub-constructs into five integrated groups provides a more effective model: (1) information and decision capacity, (2) customer-centric innovation, (3) process management and agility, (4) supplier and network management, and (5) leadership and workforce engagement. This integrated classification offers managers a coherent framework for implementing SCMP and QMP to enhance competitiveness results. Full article

In the digitally saturated hospitality environment, research on digital transformation remains dominated by macro-level adoption trends and user-generated content, while the potential of micro-level web-behavioural data remains largely untapped. Recent systematic reviews highlight a fragmented body of literature and note that hospitality studies seldom address first-party behavioural data or big-data analytics capabilities. To address this gap, we collected clickstream, navigation and booking-funnel data from five luxury hotels in the Mediterranean and employed big-data analytics integrated with simulation modelling—specifically fuzzy cognitive mapping (FCM)—to model causal relationships among digital touchpoints, managerial actions and customer outcomes. FCM is a robust simulation tool that captures stakeholder knowledge and causal influences across complex systems. Using a case-study methodology, we show that first-party behavioural data enable real-time insights, support knowledge-based decision-making and drive digital service innovation. Across a 12-month panel, visitor volume was strongly associated with search traffic and social traffic, with the total-visitors model explaining 99.8% of variance. Our findings extend digital-transformation models by embedding micro-level behavioural data flows and simulation modelling. Practically, this study offers a replicable framework that helps managers integrate web-analytics into decision-making and customer-centric innovation. Overall, embedding micro-level web-behavioural analytics within an FCM framework yields a decision-ready, replicable pipeline that translates behavioural evidence into high-leverage managerial interventions. Full article

Smart grid operators face escalating cyber threats and tight resource constraints, demanding the transparent, defensible prioritization of security controls. This paper asks how to select cybersecurity controls for smart grids while retaining picture fuzzy evidence throughout and supporting policy-sensitive “what-if” analyses. We propose a hybrid Picture Fuzzy Stepwise Weight Assessment Ratio Analysis (SWARA) and Combinative Distance-based Assessment (CODAS) framework that carries picture fuzzy evidence end-to-end over a domain-specific cost/benefit criteria system and a relative-assessment matrix, complemented by multi-scenario sensitivity analysis. Applied to ten prominent solutions across twenty-nine sub-criteria in four dimensions, the model highlights Performance as the most influential main criterion; at the sub-criterion level, the decisive factors are updating against new threats, threat-detection capability, and policy-customization flexibility; and Zero Trust Architecture emerges as the best overall alternative, with rankings stable under varied weighting scenarios. A managerial takeaway is that foundation controls (e.g., OT-integrated monitoring and ICS-aware detection) consistently remain near the top, while purely deceptive or access-centric options rank lower in this context. The framework contributes an end-to-end picture fuzzy risk-assessment model for smart grid cybersecurity and suggests future work on larger expert panels, cross-utility datasets, and dynamic, periodically refreshed assessments. Full article

Modern custom machine construction and automation projects face pressure to shorten innovation cycles, reduce durations, and manage growing system complexity. Traditional methods like Waterfall and V-Model have limits where end-to-end data traceability is vital throughout the product life cycle. This study introduces the implementation of a web application that incorporates a model-based design approach to assess its applicability and effectiveness in conceptual design scenarios. At the heart of this approach is the Case-Based Axiomatic Design Assistant (CADA), which utilizes Axiomatic Design principles to break down complex tasks into structured, analyzable sub-concepts. It also incorporates Case-Based Reasoning (CBR) to systematically store and reuse design knowledge. The effectiveness of the visual assistant was evaluated through expert-led assessments across different fields. The results revealed a significant reduction in design effort when utilising prior knowledge, thus validating both the efficiency of CADA as a model and the effectiveness of its implementation within a user-centric application, highlighting its collaborative features. The findings support this approach as a scalable solution for enhancing conceptual design quality, facilitating knowledge reuse, and promoting agile development. Full article

In retail enterprises, employee well-being is recognized as a key factor influencing service quality and operational sustainability. While prior research has extensively investigated enterprise-centric approaches to improving employee well-being, little scholarly attention has been devoted to understanding the effects of customer participation and service scene innovation on employee well-being. Employing a case study methodology, this research investigates a Chinese exemplary retail enterprise “Pang Donglai”, exploring how retail enterprises can leverage service scene innovation to improve employee well-being from the perspective of scene innovation. The findings reveal that service scene innovation in retail enterprises can be categorized into three types: empowerment-oriented scene innovation, autonomy-oriented shopping scene innovation, and thematic display scene innovation. These innovations facilitate empathetic interactions between employees and customers, effectively enhancing employee well-being and creating a virtuous cycle of value co-creation among the enterprise, employees, and customers. Therefore, retail enterprises can continuously improve the working situation of employees, the display of products, and the shopping environment of customers, in order to enhance employee well-being and thus improve their voluntary behaviour and its sustainability. This study provides empirical insights into how retail enterprises can enhance employee well-being through service scene innovation, thereby contributing to the improvement of business performance. Full article

New trends in industry emphasize green and sustainable production on the one hand and personalized or individualized production on the other hand. Introducing new manufacturing technologies and materials to integrate the customer’s specific requirements into the product, while keeping the focus on environmental footprint, becomes a serious challenge. As a result, new production paradigms are developed to keep up with new trends. The most known Industry 4.0 paradigm is oriented towards new technologies and digitalization. Recently, Industry 5.0 appeared as a supplement to the existing Industry 4.0 paradigm, oriented to sustainability and the worker. A multidisciplinary approach is necessary to address these challenges. The Industry 5.0 paradigm’s main pillars—human centricity, resilience, and sustainability—are also pillars of the multidisciplinary approach used in this research. A human-centric approach includes workforce reskilling and acquiring new technologies to ensure that technology serves to enhance human work, while creating a supportive and inclusive work environment and prioritizing employee engagement and wellbeing. Resilience as a second pillar is related to the ability of manufacturing systems and processes to adapt to changing conditions to remain robust and flexible, and sustainability is an important and long-term requirement of this multidisciplinary approach. Based on the research part of the Erasmus+ ExCurS project, particularly research focused on application and training related to digital twins, an advanced concept of organizational sustainability is presented in this paper. The concept of organizational sustainability is realized through the usage of key digital twin technologies aligned with human-centric approaches. A new prototype of a digital twin that optimizes an assembly system based on a developed algorithm and humanoid decision-making is provided as a proof of concept. The human-centric digital twin for industrial application is presented through a case study of personalized products. Full article