Search Results (267)

Healthcare data rapidly increases, and patients seek customized, effective healthcare services. Big data and machine learning (ML) enabled smart healthcare systems hold revolutionary potential. Unlike previous reviews that separately address AI or big data, this work synthesizes their convergence through real-world case studies, cross-domain ML applications, and a critical discussion on ethical integration in smart diagnostics. The review focuses on the role of big data analysis and ML towards better diagnosis, improved efficiency of operations, and individualized care for patients. It explores the principal challenges of data heterogeneity, privacy, computational complexity, and advanced methods such as federated learning (FL) and edge computing. Applications in real-world settings, such as disease prediction, medical imaging, drug discovery, and remote monitoring, illustrate how ML methods, such as deep learning (DL) and natural language processing (NLP), enhance clinical decision-making. A comparison of ML models highlights their value in dealing with large and heterogeneous healthcare datasets. In addition, the use of nascent technologies such as wearables and Internet of Medical Things (IoMT) is examined for their role in supporting real-time data-driven delivery of healthcare. The paper emphasizes the pragmatic application of intelligent systems by highlighting case studies that reflect up to 95% diagnostic accuracy and cost savings. The review ends with future directions that seek to develop scalable, ethical, and interpretable AI-powered healthcare systems. It bridges the gap between ML algorithms and smart diagnostics, offering critical perspectives for clinicians, data scientists, and policymakers. Full article

Customer churn prediction has become crucial for businesses, yet it poses significant challenges regarding privacy preservation and prediction accuracy. In this paper, we address two fundamental questions: (1) How can customer churn be effectively predicted while ensuring robust privacy protection of sensitive data? (2) How can large language models enhance churn prediction accuracy while maintaining data privacy? To address these questions, we propose FairRAG, a robust architecture that combines differential privacy, retrieval-augmented generation, and LLMs. Our approach leverages OPT-125M as the core language model along with a sentence transformer for semantic similarity matching while incorporating differential privacy mechanisms to generate synthetic training data. We evaluate FairRAG on two diverse datasets: Bank Churn and Telco Churn. The results demonstrate significant improvements over both traditional machine learning approaches and standalone LLMs, achieving accuracy improvements of up to 11% on the Bank Churn dataset and 12% on the Telco Churn dataset. These improvements were maintained when using differentially private synthetic data, thus indicating robust privacy and accuracy trade-offs. Full article

Design and use of wearable technology have grown exponentially, particularly in consumer products and service sectors, e.g., healthcare. However, there is a lack of a comprehensive understanding of wearable technology in consumer acceptance. This systematic review utilized a PRISMA on peer-reviewed articles published between 2014 and 2024 and collected on WoS, Scopus, and ScienceDirect. A total of 38 full-text articles were systematically reviewed and analyzed using bibliometric, thematic, and descriptive analysis to understand the technical functions of digital wearable products (DWPs) in consumer acceptance. The findings revealed four key functions: (i) wearable technology, (ii) appearance and design, (iii) biomimetic innovation, and (iv) security and privacy, found in eight types of DWPs, among them smartwatches, medical robotics, fitness devices, and wearable fashions, significantly predicted the customers’ acceptance moderated by the behavioral factors. The review also identified five key outcomes: health and fitness, enjoyment, social value, biomimicry, and market growth. The review proposed a comprehensive acceptance model that combines biomimetic principles and AI-driven features into the technical functions of the technical function model (TAM) while addressing security and privacy concerns. This approach contributes to the extended definition of TAM in wearable technology, offering new pathways for biomimetic research in smart devices and robotics. Full article

Tiny Machine Learning (TinyML) extends edge AI capabilities to resource-constrained devices, offering a promising solution for real-time, low-power intelligence in smart cities. This review systematically analyzes 66 peer-reviewed studies from 2019 to 2024, covering applications across urban mobility, environmental monitoring, public safety, waste management, and infrastructure health. We examine hardware platforms and machine learning models, with particular attention to power-efficient deployment and data privacy. We review the approaches employed in published studies for deploying machine learning models on resource-constrained hardware, emphasizing the most commonly used communication technologies—while noting the limited uptake of low-power options such as Low Power Wide Area Networks (LPWANs). We also discuss hardware–software co-design strategies that enable sustainable operation. Furthermore, we evaluate the alignment of these deployments with the United Nations Sustainable Development Goals (SDGs), highlighting both their contributions and existing gaps in current practices. This review identifies recurring technical patterns, methodological challenges, and underexplored opportunities, particularly in the areas of hardware provisioning, usage of inherent privacy benefits in relevant applications, communication technologies, and dataset practices, offering a roadmap for future TinyML research and deployment in smart urban systems. Among the 66 studies examined, 29 focused on mobility and transportation, 17 on public safety, 10 on environmental sensing, 6 on waste management, and 4 on infrastructure monitoring. TinyML was deployed on constrained microcontrollers in 32 studies, while 36 used optimized models for resource-limited environments. Energy harvesting, primarily solar, was featured in 6 studies, and low-power communication networks were used in 5. Public datasets were used in 27 studies, custom datasets in 24, and the remainder relied on hybrid or simulated data. Only one study explicitly referenced SDGs, and 13 studies considered privacy in their system design. Full article

Skin cancer is one of the most prevalent forms of cancer worldwide, and early and accurate diagnosis critically impacts patient outcomes. Given the sensitive nature of medical data and its fragmented distribution across institutions (data silos), privacy-preserving collaborative learning is essential to enable knowledge-sharing without compromising patient confidentiality. While federated learning (FL) offers a promising solution, existing methods struggle with heterogeneous and missing modalities across institutions, which reduce the diagnostic accuracy. To address these challenges, we propose an effective and flexible Personalized Multimodal Federated Learning framework (PMM-FL), which enables efficient cross-client knowledge transfer while maintaining personalized performance under heterogeneous and incomplete modality conditions. Our study contains three key contributions: (1) A hierarchical aggregation strategy that decouples multi-module aggregation from local deployment via global modular-separated aggregation and local client fine-tuning. Unlike conventional FL (which synchronizes all parameters in each round), our method adopts a frequency-adaptive synchronization mechanism, updating parameters based on their stability and functional roles. (2) A multimodal fusion approach based on multitask learning, integrating learnable modality imputation and attention-based feature fusion to handle missing modalities. (3) A custom dataset combining multi-year International Skin Imaging Collaboration(ISIC) challenge data (2018–2024) to ensure comprehensive coverage of diverse skin cancer types. We evaluate PMM-FL through diverse experiment settings, demonstrating its effectiveness in heterogeneous and incomplete modality federated learning settings, achieving 92.32% diagnostic accuracy with only a 2% drop in accuracy under 30% modality missingness, with a 32.9% communication overhead decline compared with baseline FL methods. Full article

Large language models (LLMs) show promise in enhancing medical research through domain-specific question answering. However, their clinical application is limited by hallucination risk, limited domain specialization, and privacy concerns. Public LLMs like GPT-4-Consensus pose challenges for use with institutional data, due to the inability to ensure patient data protection. In this work, we present a secure, custom-designed retrieval-augmented generation (RAG) LLM system deployed entirely within our institution and tailored for radiology research. Radiology researchers at our institution evaluated the system against GPT-4-Consensus through a blinded survey assessing factual accuracy (FA), citation relevance (CR), and perceived performance (PP) using 5-point Likert scales. Our system achieved mean ± SD scores of 4.15 ± 0.99 for FA, 3.70 ± 1.17 for CR, and 3.55 ± 1.39 for PP. In comparison, GPT-4-Consensus obtained 4.25 ± 0.72, 3.85 ± 1.23, and 3.90 ± 1.12 for the same metrics, respectively. No statistically significant differences were observed (p = 0.97, 0.65, 0.42), and 50% of participants preferred our system’s output. These results validate that secure, local RAG-based LLMs can match state-of-the-art performance while preserving privacy and adaptability, offering a scalable tool for medical research environments. Full article

Insider threats pose significant challenges to organizations, seriously endangering information security and privacy protection. These threats arise when employees with legitimate access to systems and databases misuse their privileges. Such individuals may alter, delete, or insert data into datasets, sell customer or client email addresses, leak strategic company plans, or transfer industrial and intellectual property information. These actions can severely damage a company’s reputation, result in revenue losses and loss of competitive advantage, and, in extreme cases, lead to bankruptcy. This study presents a novel solution that examines how organizational factors such as job satisfaction and security, organizational support, attachment, commitment, involvement in information security, and organizational norms influence employees’ attitudes and intentions, thereby mitigating insider threats. A key strength of this research is its integration of two foundational theories: the Social Bond Theory (SBT) and the Theory of Planned Behavior (TPB). The results reveal that job satisfaction and security, affective and normative commitment, information security training, and personal norms all contribute to reducing insider threats. Furthermore, the findings indicate that employees’ attitudes, perceived behavioral control, and subjective norms significantly influence their intentions to mitigate insider threats. However, organizational support and continuance commitment were not found to have a significant impact. Full article

This study proposes a federated learning-based real-time surface roughness prediction framework for WEDM to address issues of empirical parameter tuning and data privacy. By sharing only the model parameters, cross-machine training was enabled without exposing raw data. A custom data acquisition system collected discharge current and spindle current signals, which were solely used as input features to train the deep learning model. Data balancing techniques improved prediction accuracy, achieving performance comparable to centralized models. After optimizing the training dataset through balancing and augmentation, the federated model achieved a Root Mean Square Error (RMSE) of 0.076, which closely approaches the 0.074 RMSE obtained by the centralized model. The results show that federated learning enhances both data security and model generalization, offering an effective solution for smart manufacturing. Full article

The widespread deployment of service robots in industries such as hospitality has significantly transformed service delivery, influencing not only customers but also employees. This study examines the multi-dimensional impact of service robots on hotel employees, focusing on their attitudes, emotional responses, and willingness to collaborate, as shaped by perceived benefits (service reliability, process efficiency, and job crafting) and risks (inefficiency, insufficient intelligence, and privacy concerns). Data were collected from 471 hotel employees in South Korea with experience working alongside service robots, and Hayes’ Process Macro Model 4 was employed for hypothesis testing. The findings reveal that perceived benefits positively influence employees’ attitudes, emotions, and willingness to collaborate, while perceived risks exert a negative impact. Furthermore, attitudes and emotional responses mediate these relationships. These findings provide theoretical and practical insights for managers, policymakers, and service robot manufacturers to address employee concerns, improve human–robot collaboration, and promote sustainable technological integration within the service industry. Full article

Online marketing environments are rapidly being transformed by Artificial Intelligence (AI). This represents the implementation of Machine Learning (ML) that has significant potential in content personalization, enhanced usability, and hyper-targeted marketing, and it will reconfigure how businesses reach and serve customers. This systematic examination of machine learning in the Digital Marketing (DM) industry is also closely examined, focusing on its effect on human–computer interaction (HCI). This research methodically elucidates how machine learning can be applied to the automation of strategies for user engagement that increase user experience (UX) and customer retention, and how to optimize recommendations from consumer behavior. The objective of the present study is to critically analyze the functional and ethical considerations of ML integration in DM and to evaluate its implications on data-driven personalization. Through selected case studies, the investigation also provides empirical evidence of the implications of ML applications on UX/customer loyalty as well as associated ethical aspects. These include algorithmic bias, concerns about the privacy of the data, and the need for greater transparency of ML-based decision-making processes. This research also contributes to the field by delivering actionable, data-driven strategies for marketing professionals and offering them frameworks to deal with the evolving responsibilities and tasks that accompany the introduction of ML technologies into DM. Full article

The deployment of emotion-recognition technologies expands across healthcare education and gaming sectors to improve human–computer interaction. These systems examine facial expressions together with vocal tone and physiological signals, which include pupil size and electroencephalogram (EEG), to detect emotional states and deliver customized responses. The technology provides benefits through accessibility, responsiveness, and adaptability but generates multiple complex ethical issues. The combination of emotional profiling with biased algorithmic interpretations of culturally diverse expressions and affective data collection without meaningful consent presents major ethical concerns. The increased presence of these systems in classrooms, therapy sessions, and personal devices makes the potential for misuse or misinterpretation more critical. The paper integrates findings from literature review and initial emotion-recognition studies to create a conceptual framework that prioritizes data dignity, algorithmic accountability, and user agency and presents a conceptual framework that addresses these risks and includes safeguards for participants’ emotional well-being. The framework introduces structural safeguards which include data minimization, adaptive consent mechanisms, and transparent model logic as a more complete solution than privacy or fairness approaches. The authors present functional recommendations that guide developers to create ethically robust systems that match user principles and regulatory requirements. The development of real-time feedback loops for user awareness should be combined with clear disclosures about data use and participatory design practices. The successful oversight of these systems requires interdisciplinary work between researchers, policymakers, designers, and ethicists. The paper provides practical ethical recommendations for developing affective computing systems that advance the field while maintaining responsible deployment and governance in academic research and industry settings. The findings hold particular importance for high-stakes applications including healthcare, education, and workplace monitoring systems that use emotion-recognition technology. Full article

Product engagement detection in retail environments is critical for understanding customer preferences through nonverbal cues such as gaze and hand movements. This study presents a system leveraging a 360-degree top-view fisheye camera combined with two perspective cameras, the only sensors required for deployment, effectively capturing subtle interactions even under occlusion or distant camera setups. Unlike conventional image-based gaze estimation methods that are sensitive to background variations and require capturing a person’s full appearance, raising privacy concerns, our approach utilizes a novel Transformer-based encoder operating directly on 3D skeletal keypoints. This innovation significantly reduces privacy risks by avoiding personal appearance data and benefits from ongoing advancements in accurate skeleton estimation techniques. Experimental evaluation in a simulated retail environment demonstrates that our method effectively identifies critical gaze-object and hand-object interactions, reliably detecting customer engagement prior to product selection. Despite yielding slightly higher mean angular errors in gaze estimation compared to a recent image-based method, the Transformer-based model achieves comparable performance in gaze-object detection. Its robustness, generalizability, and inherent privacy preservation make it particularly suitable for deployment in practical retail scenarios such as convenience stores, supermarkets, and shopping malls, highlighting its superiority in real-world applicability. Full article

(1) Live streaming commerce has refined online consumer engagement by fostering a real-time, socially enriched shopping environment. Despite its growing prominence, the role of social scene characteristics in consumer purchase decisions in live streaming remains insufficiently examined. (2) This study uses the Cognition-Affection-Conation (C-A-C) framework to examine how these social characteristics influence purchase intention through the mediating roles of emotional and cognitive trust, with privacy concerns as a moderator factor. The research employs Structural Equation Modeling (SEM) to test the hypothesis using data from 504 valid responses. (3) The results demonstrate that the characteristics of social scenes proposed in this study enhance consumer trust and positively impact purchase intention. Moreover, privacy concerns weaken the effect of interactivity atmosphere and scene immersion on emotion trust, though they do not weaken the effect of social identity on emotion trust. (4) These findings contribute to the theoretical understanding of live commerce by identifying the psychological mechanisms linking the social service scene to purchasing behavior. They also offer practical implications for platforms and merchants seeking to improve consumer engagement and trust in competitive digital marketplaces. This research highlights the importance of integrating social scenes and privacy management into the strategic design of live streaming commerce services. Full article

Artificial Intelligence (AI) is rapidly transforming orthodontic care by providing personalized treatment plans that enhance precision and efficiency. This narrative review explores the current applications of AI in orthodontics, particularly its role in predicting tooth movement, fabricating custom aligners, optimizing treatment times, and offering real-time patient monitoring. AI’s ability to analyze large datasets of dental records, X-rays, and 3D scans allows for highly individualized treatment plans, improving both clinical outcomes and patient satisfaction. AI-driven aligners and braces are designed to apply optimal forces to teeth, reducing treatment time and discomfort. Additionally, AI-powered remote monitoring tools enable patients to check their progress from home, decreasing the need for in-person visits and making orthodontic care more accessible. The review also highlights future prospects, such as the integration of AI with robotics for performing orthodontic procedures, predictive orthodontics for early intervention, and the use of 3D printing technologies to fabricate orthodontic devices in real-time. While AI offers tremendous potential, challenges remain in areas such as data privacy, algorithmic bias, and the cost of adopting AI technologies. However, as AI continues to evolve, its capacity to revolutionize orthodontic care will likely lead to more streamlined, patient-centered, and effective treatments. This review underscores the transformative role of AI in modern orthodontics and its promising future in advancing dental care. Full article

Background: Advancements in pharmacogenomics, artificial intelligence (AI), and CRISPR gene-editing technology are revolutionizing precision medicine by enabling highly individualized therapeutic strategies. Artificial intelligence-driven computational techniques improve biomarker discovery and drug optimization while pharmacogenomics helps to identify genetic polymorphisms affecting medicine metabolism, efficacy, and toxicity. Genetically editing based on CRISPR presents a precise method for changing gene expression and repairing damaging mutations. This review explores the convergence of these three fields to enhance improved precision medicine. Method: A methodical study of the current literature was performed on the effects of pharmacogenomics on drug response variability, artificial intelligence, and CRISPR in predictive modeling and gene-editing applications. Results: Driven by artificial intelligence, pharmacogenomics allows clinicians to classify patients and select the appropriate medications depending on their DNA profiles. This reduces the side effect risk and increases the therapeutic efficacy. Precision genetic modifications made feasible by CRISPR technology improve therapy outcomes in oncology, metabolic illnesses, neurological diseases, and other fields. The integration of artificial intelligence streamlines genome-editing applications, lowers off-target effects, and increases CRISPR specificity. Notwithstanding these advances, issues including computational biases, moral dilemmas, and legal constraints still arise. Conclusions: The synergy of artificial intelligence, pharmacogenomics, and CRISPR alters precision medicine by letting customized therapeutic interventions. Clinically translating, however, hinges on resolving data privacy concerns, assuring equitable access, and strengthening legal systems. Future research should focus on refining CRISPR gene-editing technologies, enhancing AI-driven pharmacogenomics, and developing moral guidelines for applying these tools in individualized medicine going forward. Full article