Search Results (211)

Efficient detection of road surface defects is vital for timely maintenance and traffic safety. This study introduces a novel AI-powered web framework, TriRoad AI, that integrates multiple versions of the You Only Look Once (YOLO) object detection algorithms—specifically YOLOv8 and YOLOv11—for automated detection of potholes and cracks. A user-friendly browser interface was developed to enable real-time image analysis, confidence-based prediction filtering, and severity-based geolocation mapping using OpenStreetMap. Experimental evaluation was conducted using two datasets: one from online sources and another from field-collected images in Ankara, Turkey. YOLOv8 achieved a mean accuracy of 88.43% on internet-sourced images, while YOLOv11-B demonstrated higher robustness in challenging field environments with a detection accuracy of 46.15%, and YOLOv8 followed closely with 44.92% on mixed field images. The Gemini AI model, although highly effective in controlled environments (97.64% detection accuracy), exhibited a significant performance drop of up to 80% in complex field scenarios, with its accuracy falling to 18.50%. The proposed platform’s uniqueness lies in its fully integrated, browser-based design, requiring no device-specific installation, and its incorporation of severity classification with interactive geospatial visualization. These contributions address current gaps in generalization, accessibility, and practical deployment, offering a scalable solution for smart infrastructure monitoring and preventive maintenance planning in urban environments. Full article

Indigenous students remain significantly underrepresented in medical education, contributing to persistent health inequities in their communities. Systemic barriers, including cultural isolation, inadequate resources, and biased curricula, hinder their success. But what if generative artificial intelligence (GAI) could be the game-changer? This scoping review explores the potential of generative artificial intelligence (GAI) in making medical education more inclusive and supportive for Indigenous students through a comprehensive analysis of existing literature. From AI-powered engagement platforms to personalised learning systems and immersive simulations, GAI can be harnessed to bridge the gap. While GAI holds promise, challenges like biased datasets and limited access to technology must be addressed. To unlock GAI’s potential, we recommend faculty development, expansion of digital infrastructure, and Indigenous-led AI design. By carefully harnessing GAI, medical schools can take a crucial step towards creating a more diverse and equitable healthcare workforce, ultimately improving health outcomes for Indigenous communities. Full article

AI-powered health assistants offer promising opportunities to enhance health management among older adults. However, real-world uptake remains limited, not only due to individual hesitation, but also because of complex interactions among users, platforms, and public policies. This study investigates the dynamic behavioral mechanisms behind adoption in aging populations using a tripartite evolutionary game model. Based on replicator dynamics, the model simulates the strategic behaviors of older adults, platforms, and government. It identifies evolutionarily stable strategies, examines convergence patterns, and evaluates parameter sensitivity through a Jacobian matrix analysis. Results show that when adoption costs are high, platform trust is low, and government support is limited, the system tends to converge to a low-adoption equilibrium with poor service quality. In contrast, sufficient policy incentives, platform investment, and user trust can shift the system toward a high-adoption state. Trust coefficients and incentive intensity are especially influential in shaping system dynamics. This study proposes a novel framework for understanding the co-evolution of trust, service optimization, and institutional support. It emphasizes the importance of coordinated trust-building strategies and layered policy incentives to promote sustainable engagement with AI health technologies in aging societies. 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

The rapid expansion of IoT devices poses new challenges for AI-driven services, particularly in terms of energy consumption. Although cloud-based AI processing has been the dominant approach, its high energy consumption calls for more energy-efficient alternatives. Edge computing offers an approach for reducing both latency and energy consumption. In this paper, we propose a methodology for estimating the power consumption of AI accelerators on an embedded edge device. Through experimental evaluations involving GPU- and Edge TPU-based platforms, the proposed method demonstrated estimation errors below 8%. The estimation errors were partly due to unaccounted power consumption from main memory and storage access. The proposed approach provides a foundation for more reliable energy management in AI-powered edge computing systems. Full article

The amount of protein and fat in raw milk determines its quality, value in the marketplace, and related payment to suppliers. Technicians use expensive specialized laboratory equipment to measure milk quality in specialized laboratories. The continuous quality monitoring of the milk supply in the supplier’s tanks enables the production of higher quality products, better milk supply chain optimization, and reduced milk waste. This paper presents an inexpensive AI-powered IoT sensor that continuously measures the protein and fat in the raw milk in the tanks of dairy farms, pickup trucks, and intermediate storage depots across any milk supply chain. The proposed sensor consists of an in-tank IoT device and related software components that run on any IoT platform. The in-tank IoT device quality incorporates a low-cost spectrometer and a microcontroller that can send milk supply measurements to any IoT platform via NB-IoT. The in-tank IoT device of the milk quality sensor is housed in a food-safe polypropylene container that allows its deployment in any milk tank. The IoT software component of the milk quality sensors uses a specialized machine learning (ML) algorithm to translate the spectrometry measurements into milk fat and protein measurements. The paper presents the design of an in-tank IoT sensor and the corresponding IoT software translation of the spectrometry measurements to protein and fat measurements. Moreover, it includes an experimental milk quality sensor evaluation that shows that sensor accuracy is ±0.14% for fat and ±0.07% for protein. Full article

Accurate short-term forecasting of photovoltaic power generation is vital for the operational stability of isolated energy systems, especially in regions with increasing renewable energy penetration. This study presents a novel AI-based forecasting framework applied to the island of Cyprus. Using machine learning methods, particularly regression trees, the proposed approach evaluates the impact of key environmental variables on PV performance, with an emphasis on atmospheric dust transport and air composition variability. A distinguishing feature of this work is the integration of cross-continental dust events and diverse atmospheric parameters into a structured forecasting model. A new clustering methodology is introduced to classify these inputs and analyze their correlation with PV output, enabling improved feature selection for model training. Importantly, all input parameters are sourced from publicly accessible, internet-based platforms, facilitating wide reproducibility and operational application. The obtained results demonstrate that incorporating dust deposition and air composition features significantly enhances forecasting accuracy, particularly during severe dust episodes. This research not only fills a notable gap in the PV forecasting literature but also provides a scalable model for other dust-prone regions transitioning to high levels of solar energy integration. Full article

As electric vehicles (EVs) continue to advance toward widespread adoption, innovations in power electronics are playing a pivotal role in improving efficiency, performance, and sustainability. This review presents recent progress in bidirectional converters and regenerative braking systems (RBSs), highlighting their contributions to energy recovery, battery longevity, and vehicle-to-grid integration. Bidirectional converters support two-way energy flow, enabling efficient regenerative braking and advanced charging capabilities. The integration of wide-bandgap semiconductors, such as silicon carbide and gallium nitride, further enhances power density and thermal performance. The paper evaluates various converter topologies, including single-stage and multi-stage architectures, and assesses their suitability for high-voltage EV platforms. Intelligent control strategies, including fuzzy logic, neural networks, and sliding mode control, are discussed for optimizing braking force and maximizing energy recuperation. In addition, the paper explores the influence of regenerative braking on battery degradation and presents hybrid energy storage systems and AI-based methods as mitigation strategies. Special emphasis is placed on the integration of RBSs in advanced electric vehicle platforms, including autonomous systems. The review concludes by identifying current challenges, emerging trends, and key design considerations to inform future research and practical implementation in electric vehicle energy systems. Full article

As streaming platforms adopt artificial intelligence (AI)-powered subtitle systems to satisfy global demand for instant localization, the cognitive impact of these automated translations on viewers remains largely unexplored. This study used a web-based eye-tracking protocol to compare the cognitive load that GPT-4o-generated Arabic subtitles impose with that of professional human translations among 82 native Arabic speakers who viewed a 10 min episode (“Syria”) from the BBC comedy drama series State of the Union. Participants were randomly assigned to view the same episode with either professionally produced Arabic subtitles (Amazon Prime’s human translations) or machine-generated GPT-4o Arabic subtitles. In a between-subjects design, with English proficiency entered as a moderator, we collected fixation count, mean fixation duration, gaze distribution, and attention concentration (K-coefficient) as indices of cognitive processing. GPT-4o subtitles raised cognitive load on every metric; viewers produced 48% more fixations in the subtitle area, recorded 56% longer fixation durations, and spent 81.5% more time reading the automated subtitles than the professional subtitles. The subtitle area K-coefficient tripled (0.10 to 0.30), a shift from ambient scanning to focal processing. Viewers with advanced English proficiency showed the largest disruptions, which indicates that higher linguistic competence increases sensitivity to subtle translation shortcomings. These results challenge claims that large language models (LLMs) lighten viewer burden; despite fluent surface quality, GPT-4o subtitles demand far more cognitive resources than expert human subtitles and therefore reinforce the need for human oversight in audiovisual translation (AVT) and media accessibility. Full article

With the rise of live-streaming services on e-commerce platforms, AI-powered virtual idols have demonstrated tremendous application potential and thus possess high commercial value. From the perspective of psychological distance, this study adopts the Stimulus–Organism–Response (S–O–R) theoretical framework to construct a research model of “AI-powered virtual idols–psychological distance–impulsive buying intention”. The model aims to explore how AI-powered virtual idols promote digital natives’ impulsive buying intention in the context of e-commerce live streaming. Furthermore, this study examines the moderating effect of technology readiness on the relationship between AI-powered virtual idols and psychological distance. The findings reveal that the level of intelligence of AI-powered virtual idols—including interactivity, anthropomorphism, homogeneity, and reputation—enhances digital natives’ impulsive buying intention by reducing psychological distance. For digital natives with lower technology readiness, the effect of AI-powered virtual idols in narrowing psychological distance is more pronounced. These findings enrich AI-driven consumer behavior models from a theoretical perspective and offer theoretical support and practical insights for developing AI-empowered digital marketing strategies tailored to the psychological traits and technological adaptability of digital natives. Full article

The rapid growth of the Internet of Things (IoT) and smart devices has led to an increasing demand for real-time data processing at the edge of networks closer to the source of data generation. This review paper introduces how artificial intelligence (AI) can be integrated with edge computing to enable efficient and scalable object recognition applications. It covers the key considerations of employing deep learning on edge computing devices, such as selecting edge devices, deep learning frameworks, lightweight deep learning models, hardware optimization, and performance metrics. An example of an application is also presented in this article, which is about real-time power transmission line detection using edge computing devices. The evaluation results show the significance of implementing lightweight models and model compression techniques such as quantized Tiny YOLOv7. It also shows the hardware performance on some edge devices, such as Raspberry Pi and Jetson platforms. Through practical examples, readers will gain insights into designing and implementing AI-powered edge solutions for various object recognition use cases, including smart surveillance, autonomous vehicles, and industrial automation. The review concludes by addressing emerging trends, such as federated learning and hardware accelerators, which are set to shape the future of AI on edge computing for object recognition. Full article

Continuous-time Recurrent Neural Networks (CTRNNs) are well-suited for modeling temporal dynamics in low-power neuromorphic and analog computing systems, making them promising candidates for edge-based human activity recognition (HAR) in healthcare. However, training CTRNNs remains challenging due to their continuous-time nature and the need to respect physical hardware constraints. In this work, we propose G-CTRNN, a novel gradient-based training framework for analog-friendly CTRNNs designed for embedded healthcare applications. Our method extends Backpropagation Through Time (BPTT) to continuous domains using TensorFlow’s automatic differentiation, while enforcing constraints on time constants and synaptic weights to ensure hardware compatibility. We validate G-CTRNN on the WISDM human activity dataset, which simulates realistic wearable sensor data for healthcare monitoring. Compared to conventional RNNs, G-CTRNN achieves superior classification accuracy with fewer parameters and greater stability—enabling continuous, real-time HAR on low-power platforms such as MEMS computing networks. The proposed framework provides a pathway toward on-device AI for remote patient monitoring, elderly care, and personalized healthcare in resource-constrained environments. Full article

Monitoring parturient cattle during calving is crucial for reducing cow and calf mortality, enhancing reproductive and production performance, and minimizing labor costs. Traditional monitoring methods include direct animal inspection or the use of specialized sensors. These methods can be effective, but impractical in large-scale ranching operations due to time, cost, and logistical constraints. To address this challenge, a network of low-power and long-range IoT sensors combining the Global Navigation Satellite System (GNSS) and tri-axial accelerometers was deployed to monitor in real-time 15 parturient Brangus cows on a 700-hectare pasture at the Chihuahuan Desert Rangeland Research Center (CDRRC). A two-stage machine learning approach was tested. In the first stage, a fully connected autoencoder with time encoding was used for unsupervised detection of anomalous behavior. In the second stage, a Random Forest classifier was applied to distinguish calving events from other detected anomalies. A 5-fold cross-validation, using 12 cows for training and 3 cows for testing, was applied at each iteration. While 100% of the calving events were successfully detected by the autoencoder, the Random Forest model failed to classify the calving events of two cows and misidentified the onset of calving for a third cow by 46 h. The proposed framework demonstrates the value of combining unsupervised and supervised machine learning techniques for detecting calving events in rangeland cattle under extensive management conditions. The real-time application of the proposed AI-driven monitoring system has the potential to enhance animal welfare and productivity, improve operational efficiency, and reduce labor demands in large-scale ranching. Future advancements in multi-sensor platforms and model refinements could further boost detection accuracy, making this approach increasingly adaptable across diverse management systems, herd structures, and environmental conditions. Full article

This paper presents a systematic, narrative review of 62 academic publications (2015–2025) that explore the integration of spatial data infrastructures (SDIs) with emerging smart city technologies to improve local governance. SDIs provide a structured framework for managing geospatial data and, in combination with IoT sensors, geospatial and 3D platforms, cloud computing and AI-powered analytics, enable real-time data-driven decision-making. The review identifies four key technology areas: IoT and sensor technologies, geospatial and 3D mapping platforms, cloud-based data infrastructures, and AI analytics that uniquely contribute to smart governance through improved monitoring, prediction, visualization, and automation. Opportunities include improved urban resilience, public service delivery, environmental monitoring and citizen engagement. However, challenges remain in terms of interoperability, data protection, institutional barriers and unequal access to technologies. To fully realize the potential of integrated SDIs in smart government, the report highlights the need for open standards, ethical frameworks, cross-sector collaboration and citizen-centric design. Ultimately, this synthesis provides a comprehensive basis for promoting inclusive, adaptive and accountable local governance systems through spatially enabled smart technologies. Full article

Climate change presents serious challenges for infrastructure, regional planning, and public awareness. However, effectively understanding and analyzing large-scale climate discussions remains difficult. Traditional methods often struggle to extract meaningful insights from unstructured data sources, such as social media discourse, making it harder to track climate-related concerns and emerging trends. To address this gap, this study applies Natural Language Processing (NLP) techniques to analyze large volumes of climate-related data. By employing supervised and weak supervision methods, climate data are efficiently labeled to enable targeted analysis of regional- and infrastructure-specific climate impacts. Furthermore, BERT-based Named Entity Recognition (NER) is utilized to identify key climate-related terms, while sentiment analysis of platforms like Twitter provides valuable insights into trends in public opinion. AI-driven visualization tools, including predictive modeling and interactive mapping, are also integrated to enhance the accessibility and usability of the analyzed data. The research findings reveal significant patterns in climate-related discussions, supporting policymakers and planners in making more informed decisions. By combining AI-powered analytics with advanced visualization, the study enhances climate impact assessment and promotes the development of sustainable, resilient infrastructure. Overall, the results demonstrate the strong potential of AI-driven climate analysis to inform policy strategies and raise public awareness. Full article