Search Results (851)

The escalating impacts and occurrence of wildfires threaten the public, economies, and global ecosystems. Physiologically declining or dead trees are a great portion of the fires because these trees are prone to higher ignition and have lower moisture content. To prevent wildfires, hazardous vegetation needs to be removed, and the vegetation should be identified early on. This work proposes a real-time fire risk tree detection framework using UAV images, which is based on lightweight object detection. The model uses the MobileNetV3-Small spine, which is optimized for edge deployment, combined with an SSD head. This configuration results in a highly optimized and fast UAV-based inference pipeline. The dataset used in this study comprises over 3000 annotated RGB UAV images of trees in healthy, partially dead, and fully dead conditions, collected from mixed real-world forest scenes and public drone imagery repositories. Thorough evaluation shows that the proposed model outperforms conventional SSD and recent YOLOs on Precision (94.1%), Recall (93.7%), mAP (90.7%), F1 (91.0%) while being light-weight (8.7 MB) and fast (62.5 FPS on Jetson Xavier NX). These findings strongly support the model’s effectiveness for large-scale continuous forest monitoring to detect health degradations and mitigate wildfire risks proactively. The framework UAV-based environmental monitoring systems differentiates itself by incorporating a balance between detection accuracy, speed, and resource efficiency as fundamental principles. Full article

Eco-migration (EM) constitutes a specialized form of migration aimed at enhancing living environments and alleviating ecological pressure. Nevertheless, large-scale external migration has intensified habitat fragmentation (HF) in resettlement areas. This paper takes the Shule River Resettlement Project (SRRP) as a case, based on the China Land Cover Dataset (CLCD) data of the resettlement area from 1996 to 2020, using the Landscape Pattern Index (LPI) and the land use transfer matrix (LTM) to clearly define the stages of migration and the types of resettlement areas and to quantitative explore how EM affects HF. The results show that (1) EM accelerates the transformation of natural habitats (NHs) to artificial habitats (AHs) and shows the characteristics of sudden changes in the initial stage (1996–2002), with stability in the middle stage (2002–2006) and late stage (2007–2010) and dramatic changes in the post-migration stage (2011–2020). In IS, MS, LS, and PS, AH increased by 26.145 km², 21.573 km², 22.656 km², and 16.983 km², respectively, while NH changed by 73.116 km², −21.575 km², −22.655 km², −121.82 km², and −213.454 km², respectively. The more dispersed the resettlement areas are the more obvious the expansion of AH will be, indicating that the resettlement methods for migrants have a significant effect on habitat changes. (2) During the resettlement process, the total number of plaques (NP), edge density (ED), diversity (SHDI), and dominance index (SHEI) all continued to increase, while the contagion index (C) and aggregation index (AI) continued to decline, indicating that the habitat is transforming towards fragmentation, diversification, and complexity. Compared with large-scale migration bases (LMBs), both small-scale migration bases (SMBs), and scattered migration settlement points (SMSPs) exhibit a higher degree of HF, which reflects how the scale of migration influences the extent of habitat fragmentation. While NHs are experiencing increasing fragmentation, AHs tend to show a decreasing trend in fragmentation. Ecological migrants play a dual role: they contribute to the alteration and fragmentation of natural habitat patterns, while simultaneously promoting the formation and continuity of artificial habitat structures. This study offers valuable practical insights and cautionary lessons for the resettlement of ecological migrants. Full article

The rapid advancement of artificial intelligence (AI) and machine learning has revolutionised how systems process information, make decisions, and adapt to dynamic environments. AI-driven approaches have significantly enhanced efficiency and problem-solving capabilities across various domains, from automated decision-making to knowledge representation and predictive modelling. These developments have led to the emergence of increasingly sophisticated models capable of learning patterns, reasoning over complex data structures, and generalising across tasks. As AI systems become more deeply integrated into networked infrastructures and the Internet of Things (IoT), their ability to process and interpret data in real-time is essential for optimising intelligent communication networks, distributed decision making, and autonomous IoT systems. However, despite these achievements, the internal mechanisms that drive LLMs’ reasoning and generalisation capabilities remain largely unexplored. This lack of transparency, compounded by challenges such as hallucinations, adversarial perturbations, and misaligned human expectations, raises concerns about their safe and beneficial deployment. Understanding the underlying principles governing AI models is crucial for their integration into intelligent network systems, automated decision-making processes, and secure digital infrastructures. This paper provides a comprehensive analysis of explainability approaches aimed at uncovering the fundamental mechanisms of LLMs. We investigate the strategic components contributing to their generalisation abilities, focusing on methods to quantify acquired knowledge and assess its representation within model parameters. Specifically, we examine mechanistic interpretability, probing techniques, and representation engineering as tools to decipher how knowledge is structured, encoded, and retrieved in AI systems. Furthermore, by adopting a mechanistic perspective, we analyse emergent phenomena within training dynamics, particularly memorisation and generalisation, which also play a crucial role in broader AI-driven systems, including adaptive network intelligence, edge computing, and real-time decision-making architectures. Understanding these principles is crucial for bridging the gap between black-box AI models and practical, explainable AI applications, thereby ensuring trust, robustness, and efficiency in language-based and general AI systems. Full article

Artificial intelligence (AI) has emerged as a powerful tool for advancing the interpretation of ground penetrating radar (GPR) data, offering solutions to long-standing challenges in manual analysis, such as subjectivity, inefficiency, and limited scalability. This review investigates recent developments in AI-driven techniques for GPR interpretation, with a focus on machine learning, deep learning, and hybrid approaches that incorporate physical modeling or multimodal data fusion. We systematically analyze the application of these techniques across various domains, including utility detection, infrastructure monitoring, archeology, and environmental studies. Key findings highlight the success of convolutional neural networks in hyperbola detection, the use of segmentation models for stratigraphic analysis, and the integration of AI with robotic and real-time systems. However, challenges remain with generalization, data scarcity, model interpretability, and operational deployment. We identify promising directions, such as domain adaptation, explainable AI, and edge-compatible solutions for practical implementation. By synthesizing current progress and limitations, this review aims to bridge the gap between theoretical advancements in AI and the practical needs of GPR practitioners, guiding future research towards more reliable, transparent, and field-ready systems. Full article

The widespread and persistent occurrence of micropollutants—such as pesticides, pharmaceuticals, heavy metals, personal care products, microplastics, and per- and polyfluoroalkyl substances (PFAS)—has emerged as a critical environmental and public health concern, necessitating the development of highly sensitive, selective, and field-deployable detection technologies. Microfluidic sensors, including biosensors, have gained prominence as versatile and transformative tools for real-time environmental monitoring, enabling precise and rapid detection of trace-level contaminants in complex environmental matrices. Their miniaturized design, low reagent consumption, and compatibility with portable and smartphone-assisted platforms make them particularly suited for on-site applications. Recent breakthroughs in nanomaterials, synthetic recognition elements (e.g., aptamers and molecularly imprinted polymers), and enzyme-free detection strategies have significantly enhanced the performance of these biosensors in terms of sensitivity, specificity, and multiplexing capabilities. Moreover, the integration of artificial intelligence (AI) and machine learning algorithms into microfluidic platforms has opened new frontiers in data analysis, enabling automated signal processing, anomaly detection, and adaptive calibration for improved diagnostic accuracy and reliability. This review presents a comprehensive overview of cutting-edge microfluidic sensor technologies for micropollutant detection, emphasizing fabrication strategies, sensing mechanisms, and their application across diverse pollutant categories. We also address current challenges, such as device robustness, scalability, and potential signal interference, while highlighting emerging solutions including biodegradable substrates, modular integration, and AI-driven interpretive frameworks. Collectively, these innovations underscore the potential of microfluidic sensors to redefine environmental diagnostics and advance sustainable pollution monitoring and management strategies. Full article

Cruciferous vegetables are popular in Asian dishes. However, striped flea beetles prefer to feed on leaves, which can damage the appearance of crops and reduce their economic value. Due to the lack of pest monitoring, the occurrence of pests is often irregular and unpredictable. Regular and quantitative spraying of pesticides for pest control is an alternative method. Nevertheless, this requires manual execution and is inefficient. This paper presents a system powered by solar energy, utilizing batteries and supercapacitors for energy storage to support the implementation of edge AI devices in outdoor environments. Raspberry Pi is utilized for artificial intelligence image recognition and the Internet of Things (IoT). YOLOv5 is implemented on the edge device, Raspberry Pi, for detecting striped flea beetles, and StyleGAN3 is also utilized for data augmentation in the proposed system. The recognition accuracy reaches 85.4%, and the results are transmitted to the server through a 4G network. The experimental results indicate that the system can operate effectively for an extended period. This system enhances sustainability and reliability and greatly improves the practicality of deploying smart pest detection technology in remote or resource-limited agricultural areas. In subsequent applications, drones can plan routes for pesticide spraying based on the distribution of pests. Full article

Rice lodging severely affects crop growth, yield, and mechanized harvesting efficiency. The accurate detection and quantification of lodging areas are crucial for precision agriculture and timely field management. However, Unmanned Aerial Vehicle (UAV)-based lodging detection faces challenges such as complex backgrounds, variable lighting, and irregular lodging patterns. To address these issues, this study proposes SWRD–YOLO, a lightweight instance segmentation model that enhances feature extraction and fusion using advanced convolution and attention mechanisms. The model employs an optimized loss function to improve localization accuracy, achieving precise lodging area segmentation. Additionally, a grid-based lodging ratio estimation method is introduced, dividing images into fixed-size grids to calculate local lodging proportions and aggregate them for robust overall severity assessment. Evaluated on a self-built rice lodging dataset, the model achieves 94.8% precision, 88.2% recall, 93.3% mAP@0.5, and 91.4% F1 score, with real-time inference at 16.15 FPS on an embedded NVIDIA Jetson Orin NX device. Compared to the baseline YOLOv8n-seg, precision, recall, mAP@0.5, and F1 score improved by 8.2%, 16.5%, 12.8%, and 12.8%, respectively. These results confirm the model’s effectiveness and potential for deployment in intelligent crop monitoring and sustainable agriculture. Full article

Mammography is the main method for early detection of breast cancer, which is still a major global health concern. However, inter-reader variability and the inherent difficulty of interpreting subtle radiographic features frequently limit the accuracy of diagnosis. A thorough assessment of deep convolutional neural networks (CNNs) for automated mammogram classification is presented in this work, along with the introduction of two innovative multi-view integration techniques: Dual-Branch Ensemble (DBE) and Merged Dual-View (MDV). By setting aside two datasets for out-of-sample testing, we evaluate the generalizability of the model using six different mammography datasets that represent various populations and imaging systems. We compare a number of cutting-edge architectures on both individual and combined datasets, including ResNet, DenseNet, EfficientNet, MobileNet, Vision Transformers, and VGG19. Both MDV and DBE strategies improve classification performance, according to experimental results. VGG19 and DenseNet both obtained high ROC AUC scores of 0.9051 and 0.7960 under the MDV approach. DenseNet demonstrated strong performance in the DBE setting, achieving a ROC AUC of 0.8033, while ResNet50 recorded a ROC AUC of 0.8042. These enhancements demonstrate how beneficial multi-view fusion is for boosting model robustness. The impact of domain shift is further highlighted by generalization tests, which emphasize the need for diverse datasets in training. These results offer practical advice for improving CNN architectures and integration tactics, which will aid in the creation of trustworthy, broadly applicable AI-assisted breast cancer screening tools. Full article

This study presents the design and validation of an integrated fire safety system that leverages edge AI, hybrid sensing, and precision suppression to overcome the latency and collateral limitations of conventional smoke detection and sprinkler systems. The proposed platform features a dual-mode sensor array for early fire recognition, motorized ventilation units for rapid smoke extraction, and a 360° directional nozzle for targeted agent discharge using a residue-free clean extinguishing agent. Experimental trials demonstrated an average fire detection time of 5.8 s and complete flame suppression within 13.2 s, with 90% smoke clearance achieved in under 95 s. No false positives were recorded during non-fire simulations, and the system remained fully functional under simulated cloud communication failure, confirming its edge-resilient architecture. A probabilistic risk analysis based on ISO 31000 and NFPA 551 frameworks showed risk reductions of 75.6% in life safety, 58.0% in property damage, and 67.1% in business disruption. The system achieved a composite risk reduction of approximately 73%, shifting the operational risk level into the ALARP region. These findings demonstrate the system’s capacity to provide proactive, energy-efficient, and spatially targeted fire response suitable for high-value infrastructure. The modular design and SmartThings Edge integration further support scalable deployment and real-time system intelligence, establishing a strong foundation for future adaptive fire protection frameworks. Full article

The exponential growth of video data across domains such as surveillance, transportation, and healthcare has raised critical challenges in scalability, real-time processing, and privacy preservation. While existing studies have addressed individual aspects of Video Big Data Analytics (VBDA), an integrated, up-to-date perspective remains limited. This paper presents a comprehensive survey of system architectures and enabling technologies in VBDA. It categorizes system architectures into four primary types as follows: centralized, cloud-based infrastructures, edge computing, and hybrid cloud–edge. It also analyzes key enabling technologies, including real-time streaming, scalable distributed processing, intelligent AI models, and advanced storage for managing large-scale multimodal video data. In addition, the study provides a functional taxonomy of core video processing tasks, including object detection, anomaly recognition, and semantic retrieval, and maps these tasks to real-world applications. Based on the survey findings, the paper proposes ViMindXAI, a hybrid AI-driven platform that combines edge and cloud orchestration, adaptive storage, and privacy-aware learning to support scalable and trustworthy video analytics. Our analysis in this survey highlights emerging trends such as the shift toward hybrid cloud–edge architectures, the growing importance of explainable AI and federated learning, and the urgent need for secure and efficient video data management. These findings highlight key directions for designing next-generation VBDA platforms that enhance real-time, data-driven decision-making in domains such as public safety, transportation, and healthcare. These platforms facilitate timely insights, rapid response, and regulatory alignment through scalable and explainable analytics. This work provides a robust conceptual foundation for future research on adaptive and efficient decision-support systems in video-intensive environments. Full article

With the rapid proliferation of artificial intelligence (AI) applications, an increasing number of edge devices—such as smartphones, cameras, and embedded controllers—are being tasked with performing AI-based inference. Due to constraints in storage capacity, computational power, and network connectivity, these devices are often categorized as operating in resource-constrained environments. In such scenarios, deploying powerful Transformer-based models like ChatGPT and Vision Transformers is highly impractical because of their large parameter sizes and intensive computational requirements. While lightweight Transformer models, such as MobileViT, offer a promising solution to meet storage and computational limitations, their robustness remains insufficient. This poses a significant security risk for AI applications, particularly in critical edge environments. To address this challenge, our research focuses on enhancing the robustness of lightweight Transformer models under resource-constrained conditions. First, we propose a comprehensive robustness evaluation framework tailored for lightweight Transformer inference. This framework assesses model robustness across three key dimensions: noise robustness, distributional robustness, and adversarial robustness. It further investigates how model size and hardware limitations affect robustness, thereby providing valuable insights for robustness-aware model design. Second, we introduce a novel adversarial robustness enhancement strategy that integrates lightweight modeling techniques. This approach leverages methods such as gradient clipping and layer-wise unfreezing, as well as decision boundary optimization techniques like TRADES and SMART. Together, these strategies effectively address challenges related to training instability and decision boundary smoothness, significantly improving model robustness. Finally, we deploy the robust lightweight Transformer models in real-world resource-constrained environments and empirically validate their inference robustness. The results confirm the effectiveness of our proposed methods in enhancing the robustness and reliability of lightweight Transformers for edge AI applications. 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

Ischemic stroke ranks among the top global causes of disability and mortality, with a highly dynamic pathological process. Post-stroke neuroinflammation, mediated by microglia, demonstrates a dual role in both injury and repair. The CX3CR1/CX3CL1 signaling axis, highly expressed in microglia, acts as a key regulator. This review examines the spatiotemporal dynamics of the axis across the stroke process and its involvement in neural repair. Crucially, this signaling pathway demonstrates stage-dependent functional duality: its cellular sources, receptor expression profiles, and functional consequences undergo temporally orchestrated shifts, manifesting coexisting or interconverting protective and damaging properties. Ignoring this dynamism compromises the therapeutic efficacy of targeted interventions. Thus, we propose a triple precision strategy of “stroke phase—biomarker—targeted intervention”. It uses specific biomarkers for precise staging and designs interventions based on each phase’s signaling characteristics. Despite challenges like biomarker validation, mechanistic exploration, and cross-species differences, integrating cutting-edge technologies such as spatial metabolomics and AI-driven dynamic modeling promises to shift stroke therapy toward personalized spatiotemporal programming. Temporally targeting CX3CR1 signaling may offer a key basis for developing next-generation precision neural repair strategies for stroke. Full article

Oscillatory neural networks have so far been successfully applied to a number of computing problems, such as associative memories, or to handle computationally hard tasks. In this paper, we show how to use oscillators to process time-dependent waveforms with minimal or no preprocessing. Since preprocessing and first-layer processing are often the most power-hungry steps in neural networks, our findings may open new doors to simple and power-efficient edge-AI devices. Full article