Search Results (712)

In the realm of Industry 5.0, the incorporation of Artificial Intelligence (AI) in overseeing workers, machinery, and industrial systems is essential for fostering a human-centric, sustainable, and resilient industry. Despite technological advancements, the construction industry remains largely labor intensive, with site management and interventions predominantly reliant on manual judgments, leading to inefficiencies and various challenges. This research emphasizes identifying unsafe behaviors and risks within construction environments by employing AI. Given the continuous emergence of unsafe behaviors that requires certain caution, it is imperative to adapt to these novel categories while retaining the knowledge of existing ones. Although deep convolutional neural networks have shown excellent performance in behavior recognition, they traditionally function as predefined multi-way classifiers, which exhibit limited flexibility in accommodating emerging unsafe behavior classes. Addressing this issue, this study proposes a versatile and efficient recognition model capable of expanding the range of unsafe behaviors while maintaining the recognition of both new and existing categories. Adhering to the continual learning paradigm, this method integrates two types of complementary prompts into the pre-trained model: task-invariant prompts that encode knowledge shared across tasks, and task-specific prompts that adapt the model to individual tasks. These prompts are injected into specific layers of the frozen backbone to guide learning without requiring a rehearsal buffer, enabling effective recognition of both new and previously learned unsafe behaviors. Additionally, this paper introduces a benchmark dataset, Split-UBR, specifically constructed for continual unsafe behavior recognition on construction sites. To rigorously evaluate the proposed model, we conducted comparative experiments using average accuracy and forgetting as metrics, and benchmarked against state-of-the-art continual learning baselines. Results on the Split-UBR dataset demonstrate that our method achieves superior performance in terms of both accuracy and reduced forgetting across all tasks, highlighting its effectiveness in dynamic industrial environments. Full article

Pollution-intensive industries (PIIs) generate substantial economic benefits while posing serious environmental challenges, making the optimization of their spatial distribution a critical issue for sustainable development. Understanding the spatiotemporal dynamics behind PII location patterns is essential for effective land-use planning and industrial policy. This study investigates the location patterns of newly established PIIs in the Beijing–Tianjin–Hebei urban agglomeration of China between 2007 and 2019. By integrating principal component analysis with a geographically and temporally weighted regression model, the research explores how key drivers influence PII distribution across both spatial and temporal dimensions. The results indicate that government intervention has historically been the most significant factor shaping PII distribution, although its influence has gradually declined due to increasing marketization and technological progress. PIIs are more likely to cluster in areas with moderate levels of economic development, as both very high and very low development levels tend to discourage agglomeration. Over time, improvements in infrastructure, transportation and market conditions have enabled PIIs to overcome geographical constraints. Moreover, industrial parks have emerged as a critical factor by offering cost-efficiency and resource optimization, thereby attracting new PII investment. These findings underscore the importance of accounting for spatiotemporal heterogeneity when analyzing industrial distribution. The study provides policy-relevant insights into industrial land-use planning, highlighting the need for differentiated land supply strategies and the strategic development of industrial parks. It also offers useful references for other developing countries facing similar challenges amid the ongoing restructuring of global manufacturing. Full article

People with intellectual disability and visual impairment often have difficulties in accessing leisure events, engaging in cognitive activities, and performing physical exercise. The present study assessed a program aimed at helping six adults with moderate or moderate-to-mild intellectual disability and blindness in each of the aforementioned areas. The program relied on the use of a technology system involving a smartphone, which was supplied with Internet connection and fitted with the Live Transcribe and MacroDroid applications. These applications were set up to (a) enable the participants to use verbal utterances to successfully access preferred songs and comic sketches (leisure events) and answer series of verbal questions (cognitive activity) automatically presented to them, and (b) enable the smartphone to verbally guide the participants’ performance of series of body movements (physical exercise). The program was introduced according to a nonconcurrent multiple baseline design across participants. The intervention was divided into two phases, which included 17–33 and 39–48 sessions, respectively. The results showed that the participants’ baseline performance (without the support of the system) was generally poor. During the intervention with the system, all participants succeeded in accessing the music or comic events available, satisfactorily answering series of questions, and performing series of body movements. The Percentage of Nonoverlapping Data and the Tau (novlap) methods used to compare baseline and intervention performance produced indices of 1 for all participants (confirming the strong impact of the intervention). These results, which need replication to establish their generality, suggest that the technology system might represent a useful tool for helping people like the participants of this study. Full article

Venture capital (VC) is vital for innovation and economic growth, providing capital and networks to early-stage firms. While research shows a generally positive impact, challenges and failures are often overlooked, potentially creating a skewed perception of success. A review of 72 articles reveals that VC investment is concentrated in developed nations and a few emerging economies, highlighting uneven growth and the need for government interventions to promote a more balanced landscape. The review emphasises the critical importance of examining contextual factors, such as institutional frameworks and technological infrastructure, in assessing the effectiveness of venture capital in various emerging economies. This systematic review offers several key contributions with practical implications for policymakers, private investors, and the business community. First, it provides evidence-based insights into the effectiveness of VC in fostering innovation and economic growth, informing the design of targeted policies to support SME development. Second, it offers a nuanced understanding of the factors that influence the success of VC-backed SMEs in emerging economies, enabling more informed investment decisions. Third, building upon existing research, this study asserts its contribution by providing valuable, practical guidance for entrepreneurs. It offers a deeper understanding of the VC landscape, outlining both its potential benefits and inherent challenges. This enables entrepreneurs to develop more informed strategies for engaging with VC funding and maximising its impact on their businesses. The study also acknowledges limitations related to database restrictions, language bias, and limitations in search terms, suggesting avenues for future research to contribute to shaping venture capital investments and overall economic growth. Full article

Heart failure (HF) remains a leading cause of recurrent hospitalisations worldwide, largely driven by acute episodes of decompensation. Early identification of impending decompensation could enable timely intervention and potentially prevent costly admissions. Non-invasive wearable devices have emerged as promising tools for continuously monitoring physiological parameters and detecting early signs of deterioration. This review summarises recent advances in wearable technologies designed to predict HF decompensation and appraises their ability to generate clinically useful alerts. It will examine various modalities designed to monitor different aspects of cardiorespiratory physiology that have the potential to detect abnormalities preceding heart failure decompensation. Broadly, these devices either monitor physical activity capacity and cardiac function or monitor changes in pulmonary fluid congestion. We will also cover evidence exploring whether these devices can generate timely alerts for interventions to improve patient outcomes and reduce hospitalisations. However, despite advances in these technologies, challenges remain regarding their accuracy and usability for remote monitoring, as well as concerns with data storage, processing, patient adherence, and integration into existing healthcare workflows. While current limitations exist, previous results warrant further research into this area, with a focus on larger randomised trials, exploring both single- and multi-sensor systems, using artificial intelligence and cost-effectiveness analysis. Overall, non-invasive wearables represent an opportunity to create a more proactive approach to HF management, with the potential to shift the paradigm from reactive treatment to anticipatory care. Full article

Atypical parkinsonian disorders—progressive supranuclear palsy (PSP), corticobasal degeneration (CBD), and multiple system atrophy (MSA)—are rare, rapidly progressive neurodegenerative syndromes characterized by distinct molecular pathologies, heterogeneous clinical phenotypes, and limited therapeutic options. Accurate diagnosis remains a major clinical challenge, especially during early and prodromal phases, due to overlap with Parkinson’s disease (PD), phenotypic evolution, and the absence of reliable stand-alone biomarkers. Misclassification delays prognosis, impairs patient care, and hinders clinical trial design. This review synthesizes advances from 2015 to 2025 in clinical, imaging, and biomarker-based diagnosis of PSP, CBD, and MSA. We examine their phenotypic spectra, neuropathological substrates, and epidemiological trends, and critically evaluate the diagnostic performance and translational potential of emerging tools—including quantitative MRI morphometry, second-generation tau and α-synuclein PET ligands, neurophysiological markers such as video-oculography and autonomic testing, and fluid biomarkers such as neurofilament light chain. Persistent diagnostic barriers are identified, from phenotypic mimicry and pathological pleomorphism to the limited specificity of molecular assays and inequitable access to advanced technologies. We propose tiered, multimodal diagnostic algorithms that integrate structured clinical phenotyping with quantitative imaging, molecular diagnostics, systemic risk profiling, and autopsy-linked validation. Such biology-anchored approaches could enable diagnosis years before classical features emerge, improve patient stratification for disease-modifying trials, and lay the foundation for precision medicine in atypical parkinsonian disorders. A paradigm shift from descriptive nosology to mechanistically grounded frameworks is essential to accelerate early intervention and transform the clinical management of these devastating diseases. Full article

Wearable devices (WDs) are increasingly integrated into clinical workflows to enable continuous, non-invasive vital signs monitoring. Combined with Artificial Intelligence (AI), these systems can shift clinical monitoring from being reactive to predictive, allowing for earlier detection of deterioration and more personalized interventions. The value of these technologies lies not in absolute measurements, but in detecting physiological parameters trends relative to each patient’s baseline. Such a trend-based approach enables real-time prediction of deterioration, enhancing patient safety and continuity of care. However, despite their shared multiparametric capabilities, WDs are not interchangeable. This narrative review analyzes nine clinically validated devices, Radius VSM^® (Masimo Corporation, Irvine, CA, USA), BioButton^® (BioIntelliSense Inc., Redwood City, CA, USA. Distributed by Medtronic), Portrait Mobile^® (GE HealthCare, Chicago, IL, USA), VitalPatch^® (VitalConnect Inc., San Jose, CA, USA), CardioWatch 287-2^® (Corsano Health B.V., The Hague, The Netherlands. Distributed by Medtronic), Cosinuss C-Med Alpha^® (Cosinuss Gmb, Munich, Germany), SensiumVitals^® (Sensium Healthcare Limited, Abingdon, Oxfordshire, UK), Isansys Lifetouch^® (Isansys Lifecare Ltd., Abingdon, Oxfordshire, UK), and CheckPoint Cardio^® (CheckPoint R&D LTD., Kazanlak, Bulgaria), highlighting how differences in sensor configurations, battery life, connectivity, and validation contexts influence their suitability across various clinical environments. Rather than establishing a hierarchy of technical superiority, this review emphasizes the importance of context-driven selection, considering care setting, patient profile, infrastructure requirements, and interoperability. Each device demonstrates strengths and limitations depending on patient population and operational demands, ranging from perioperative, post-operative, emergency, or post-Intensive Care Unit (ICU) settings. The findings support a tailored approach to WD implementation, where matching device capabilities to clinical needs is key to maximizing utility, safety, and efficiency. Full article

The rapid evolution of healthcare technology is being driven by advancements in Micro-Electro-Mechanical Systems (MEMS), BioMEMS (Biological MEMS), and the expanding concept of the Internet of Bodies (IoB). This review explores the convergence of these three domains and their transformative impact on personalized medicine (PM), with a focus on smart, connected biomedical devices. Starting from the historical development of MEMS for medical sensing and diagnostics, the review traces the emergence of BioMEMS as biocompatible, minimally invasive solutions for continuous monitoring and real-time intervention. The integration of such devices within the IoB ecosystem enables data-driven, remote, and predictive healthcare, offering tailored diagnostics and treatment for chronic and acute conditions alike. The paper classifies IoB-associated technologies into non-invasive, invasive, and incorporated devices, reviewing wearable systems such as smart bracelets, e-tattoos, and smart footwear, as well as internal devices including implantable and ingestible. Alongside these opportunities, significant challenges persist, particularly in device biocompatibility, data interoperability, cybersecurity, and ethical regulation. By synthesizing recent advances and critical perspectives, this review aims to provide a comprehensive understanding of the current landscape, clinical potential, and future directions of MEMS, BioMEMS, and IoB-enabled personalized healthcare. Full article

This study explores a conceptual framework for integrating Artificial Intelligence (AI) into Enterprise Resource Planning (ERP) systems, emphasising its transformative potential in highly automated industrial environments, often referred to as ‘dark factories’, where operations are carried out with minimal human intervention using robotics, AI, and IoT. These lights-out manufacturing environments demand intelligent, autonomous systems that go beyond traditional ERP functionalities to deliver sustainable enterprise operations and supply chain management. Drawing from secondary data and a comprehensive review of existing literature, the study identifies significant gaps in current AI-ERP research and practice, namely, the absence of a unified adoption framework, limited focus on AI-specific implementation challenges, and a lack of structured post-adoption evaluation metrics. In response, this paper proposes a novel integrated conceptual framework that combines the Technology–Organisation–Environment (TOE) framework, the Technology Acceptance Model (TAM), and the Information Systems (IS) Success Model. The model incorporates industry-specific dark factors, such as AI autonomy, human–machine collaboration, operational agility, and sustainability, by optimising resource efficiency, enabling predictive maintenance, enhancing supply chain resilience, and supporting circular economy practices. The primary research aim of the current study is to provide a theoretical foundation for further empirical research on the input of AI-ERP systems into autonomous industry settings. The framework provides a robust theoretical foundation and actionable guidance for researchers, technology leaders, and policy-makers navigating the integration of AI and ERP in sustainable enterprise operations and supply chain management. Full article

Vascular surgery has evolved from durable yet invasive open reconstructions to less traumatic endovascular techniques. While endovascular repair reduces perioperative morbidity, it introduces durability challenges and the need for lifelong surveillance. Laparoscopic surgery bridged some gaps but was hindered by steep learning curves and technical limitations. Robotic-assisted surgery represents a “third revolution”, combining the durability of open repair with the recovery and ergonomic benefits of minimally invasive approaches through enhanced 3D visualization, wristed instrumentation, and tremor filtration. This review synthesizes current evidence on robotic applications in vascular surgery, including aortic, visceral, venous, and endovascular interventions. Feasibility of robotic vascular surgery has been demonstrated in over 1500 patients across aortic, visceral, venous, and decompression procedures. Reported outcomes include pooled conversion rates of ~5%, 30-day mortality of 1–3%, and long-term patency rates exceeding 90% in aortoiliac occlusive disease. Similarly favorable outcomes have been observed in AAA repair, visceral artery aneurysm repair, IVC reconstructions, renal vein transpositions, and minimally invasive decompression procedures such as median arcuate ligament and thoracic outlet syndromes. Endovascular robotics enhances catheter navigation precision and reduces operator radiation exposure by 85–95%, with multiple series demonstrating consistent benefit compared to manual techniques. Despite these advantages, adoption is limited by high costs, lack of dedicated vascular instruments, absent haptic feedback on most platforms, and the need for standardized training. Most available evidence is observational and from high-volume centers, highlighting the need for multicenter randomized trials. Future directions include AI-enabled planning and augmented-reality navigation, which are the most feasible near-term technologies since they rely largely on software integration with existing systems. Other advances such as microsurgical robotics, soft-robotic platforms, and telesurgery remain longer-term developments requiring new hardware and regulatory pathways. Overcoming barriers through collaborative innovation, structured training, and robust evidence generation is essential for robotics to become a new standard in vascular care. Full article

Cell-based therapeutics are redefining interventions for vision loss by enabling tissue replacement, regeneration, and neuroprotection. This review surveys contemporary cellular strategies in ophthalmology through the lenses of therapeutic effectiveness, translational readiness, and governance. We profile principal sources—embryonic and induced pluripotent stem cells, mesenchymal stromal cells, retinal pigment epithelium, retinal progenitor and limbal stem cells—and enabling platforms including extracellular vesicles, encapsulated cell technology and biomaterial scaffolds. We synthesize clinical evidence across age-related macular degeneration, inherited retinal dystrophies, and corneal injury/limbal stem-cell deficiency, and highlight emerging applications for glaucoma and diabetic retinopathy. Delivery routes (subretinal, intravitreal, anterior segment) and graft formats (single cells, sheets/patches, organoids) are compared using standardized structural and functional endpoints. Persistent barriers include GMP-compliant derivation and release testing; differentiation fidelity, maturation, and potency; genomic stability and tumorigenicity risk; graft survival, synaptic integration, and immune rejection despite ocular immune privilege; the scarcity of validated biomarkers and harmonized outcome measures and ethical, regulatory, and health-economic constraints. Promising trajectories span off-the-shelf allogeneic products, patient-specific iPSC-derived grafts, organoid and 3D-bioprinted tissues, gene-plus-cell combinations, and cell-free extracellular-vesicle therapeutics. Overall, cell-based therapies remain investigational. With adequately powered trials, methodological harmonization, long-term surveillance, scalable xeno-free manufacturing, and equitable access frameworks, they may eventually become standards of care; at present, approvals are limited to specific products/indications and regions, and no cell therapy is the standard of care for retinal disease. Full article

Artificial intelligence (AI), as an emerging interdisciplinary field dedicated to simulating and extending human intelligence, is increasingly integrating into the domain of infectious disease medicine with unprecedented depth and breadth. This narrative review is based on a systematic literature search in databases such as PubMed and Web of Science for relevant studies published between 2018 and 2025, with the aim of synthesizing the current landscape. It demonstrates transformative potential, particularly in the realm of diagnostic assistance. Confronting global challenges such as pandemic control, emerging infectious diseases, and antimicrobial resistance, AI technologies offer innovative solutions to these pressing issues. Leveraging its robust capabilities in data mining, pattern recognition, and predictive analytics, AI enhances diagnostic efficiency and accuracy, enables real-time monitoring, and facilitates the early detection and intervention of outbreaks. This narrative review systematically examines the application scenarios of AI within infectious disease diagnostics, based on an analysis of recent literature. It highlights significant technological advances and demonstrated practical outcomes related to high-throughput sequencing (HTS) for pathogen surveillance, AI-driven analysis of digital and radiological images, and AI-enhanced point-of-care testing (POCT). Simultaneously, the review critically analyzes the key challenges and limitations hindering the clinical translation of current AI-based diagnostic technologies. These obstacles include data scarcity and quality constraints, limitations in model generalizability, economic and administrative burdens, as well as regulatory and integration barriers. By synthesizing existing research findings and cataloging essential data resources, this review aims to establish a valuable reference framework to guide future in-depth research, from model development and data sourcing to clinical validation and standardization of AI-assisted infectious disease diagnostics. Full article

This study proposes the Sustainability-Aligned Digital Integration Model for Geotechnical-Related Engineering Disciplines in Türkiye (SDIM–Geo–TR) as a roadmap for sustainable digital transformation. Built on a four-stage methodology—global technology mapping, national contextualization, criteria definition, and phased integration—the model synthesizes emerging technologies such as GIS, BIM, UAV, IoT and Digital Twin into a maturity framework. It illustrates how digital adoption in Türkiye has evolved from early GIS use to more integrated multi-technology ecosystems but remains hampered by interoperability gaps, skill shortages and cost constraints. SDIM–Geo–TR organizes this evolution into four maturity stages and assesses progress using sustainability impact, technical feasibility, data compatibility, cost effectiveness and adoption level. The findings highlight that achieving fully integrated digital geotechnical practice requires coordinated policy interventions, standardization efforts and capacity building. By aligning international best practices with Türkiye-specific drivers, the model offers a practical roadmap for guiding sustainable and digitally enabled geotechnical engineering. Full article

The built environment plays a crucial role in shaping residents’ quality of life and emotional well-being. In the context of growing efforts to promote livable and walkable cities, a key question emerges: how can emerging technologies—particularly virtual reality (VR)—be leveraged to evaluate and enhance urban environments through the lens of pedestrian emotional perception? This study systematically reviewed the literature published between 2015 and 2024 in the China National Knowledge Infrastructure (CNKI) and Web of Science (WOS) databases, ultimately identifying 37 Chinese-language and 113 English-language journal articles. Using bibliometric analysis and CiteSpace, the research mapped publication trends, research hotspots, and disciplinary networks across linguistic contexts. Results reveal that Chinese-language studies often emphasize embodied cognition and electroencephalogram (EEG) monitoring, while English-language studies focus more on VR application in stress recovery and health assessment. Based on this synthesis, this study proposes a “sensory–cognitive–affective” framework and a set of spatial intervention strategies, offering a novel perspective for emotion-driven urban design. The findings highlight a paradigm shift from engineering-oriented planning to human-centered approaches, with VR technologies serving as a critical enabling tool. This review contributes both conceptual and methodological foundations for future research at the intersection of immersive technologies, built environment studies, and urban emotional well-being. Full article

Accidental opioid overdose and Sudden Unexpected Death in Epilepsy (SUDEP) represent major forms of preventable mortality, often involving sudden-onset catastrophic events that could be survivable with rapid detection and intervention. The current physiological monitoring technologies are potentially applicable, but face challenges, including complex setups, poor patient compliance, high costs, and uncertainty about community-based use. Paradoxically, simple clinical observation in supervised injection facilities has proven highly effective, suggesting observable changes in central body motion may be sufficient to detect life-threatening events. We describe a novel wearable biosensor for continuous central body motion monitoring, offering a potential early warning system for life-threatening events. The biosensor incorporates a low-power, triaxial MEMS accelerometer within a discreet, chest-worn device, enabling long-term monitoring with minimal user burden. Two system architectures are described: stored data for retrospective analysis/research, and an in-development system for real-time overdose detection and response. Early user research highlights the importance of accuracy, discretion, and trust for adoption among people who use opioids. The initial clinical data collection, including the OD-SEEN study, demonstrates feasibility for capturing motion data during real-world opioid use. This technology represents a promising advancement in non-invasive monitoring, with potential to improve the outcomes for at-risk populations with multiple health conditions. Full article