Search Results (226)

With the increasing urgency for digital transformation in large-scale caged layer farms, traditional methods for monitoring the environment and chicken health, which often rely on human experience, face challenges related to low efficiency and poor real-time performance. In this study, we focused on caged layer chickens and proposed an improved abnormal beak detection model based on the You Only Look Once v8 (YOLOv8) framework. Data collection was conducted using an inspection robot, enhancing automation and consistency. To address the interference caused by chicken cages, an Efficient Multi-Scale Attention (EMA) mechanism was integrated into the Spatial Pyramid Pooling-Fast (SPPF) module within the backbone network, significantly improving the model’s ability to capture fine-grained beak features. Additionally, the standard convolutional blocks in the neck of the original model were replaced with Grouped Shuffle Convolution (GSConv) modules, effectively reducing information loss during feature extraction. The model was deployed on edge computing devices for the real-time detection of abnormal beak features in layer chickens. Beyond local detection, a digital twin remote monitoring system was developed, combining three-dimensional (3D) modeling, the Internet of Things (IoT), and cloud-edge collaboration to create a dynamic, real-time mapping of physical layer farms to their virtual counterparts. This innovative approach not only improves the extraction of subtle features but also addresses occlusion challenges commonly encountered in small target detection. Experimental results demonstrate that the improved model achieved a detection accuracy of 92.7%. In terms of the comprehensive evaluation metric (mAP), it surpassed the baseline model and YOLOv5 by 2.4% and 3.2%, respectively. The digital twin system also proved stable in real-world scenarios, effectively mapping physical conditions to virtual environments. Overall, this study integrates deep learning and digital twin technology into a smart farming system, presenting a novel solution for the digital transformation of poultry farming. Full article

Pollen allergy has emerged as a critical global health challenge. Proactive pollen monitoring is imperative for safeguarding susceptible populations through timely preventive interventions. Current manual detection methods suffer from inherent limitations: notably, suboptimal accuracy and delayed response times, which hinder effective allergy management. Therefore, we present an automated pollen concentration detection system integrated with a novel GGD-YOLOv8n model (Ghost-generalized-FPN-DualConv-YOLOv8), which was specifically designed for allergenic pollen species identification. The methodological advancements comprise three components: (1) combining the C2f convolution in Backbone with the G-Ghost module, this module generates features through half-convolution operations and half-symmetric linear operations, enhancing the extraction and expression capabilities of detailed feature information. (2) The conventional neck network is replaced with a GFPN architecture, facilitating cross-scale feature aggregation and refinement. (3) Standard convolutional layers are substituted with DualConv, thereby reducing model complexity by 22.6% (parameters) and 22% GFLOPs (computational load) while maintaining competitive detection accuracy. This systematic optimization enables efficient deployment on edge computing platforms with stringent resource constraints. The experimental validation substantiates that the proposed methodology outperforms the baseline YOLOv8n model, attaining a 5.4% increase in classification accuracy accompanied by a 4.7% enhancement in mAP@50 metrics. When implemented on Jetson Nano embedded platforms, the system demonstrates computational efficiency with an inference latency of 364.9 ms per image frame, equating to a 22.5% reduction in processing time compared to conventional implementations. The empirical results conclusively validate the dual superiority in detecting precision and operational efficacy when executing microscopic pollen image analysis on resource-constrained edge computing devices; they establish a feasible algorithm framework for automated pollen concentration monitoring systems. Full article

This work presents a current-controlled CMOS ring oscillator (CCRO) optimized for ultra-low-voltage applications in next-generation energy-constrained systems. Leveraging bulk voltage tuning in 22 nm FDSOI differential inverter stages, the topology enables frequency adjustment while operating MOSFETs in the subthreshold region—critical for minimizing power in sub-1 V environments. Simulations at 0.4 V supply demonstrate robust performance: a three-stage oscillator achieves a 537–800 MHz tuning range with bias current (I_BIAS) modulation from 30–130 nA, while a four-stage configuration spans 388–587 MHz. At 70 nA I_BIAS, the three-stage design delivers a nominal frequency of 666.8 MHz with just 10.23 µW power dissipation, underscoring its suitability for ultra-low-power IoT and biomedical applications. The oscillator’s linear frequency sensitivity (2.63 MHz/nA) allows precise, dynamic control over performance–power tradeoffs. To address diverse application needs, the design integrates three tunability mechanisms: programmable capacitor arrays for coarse frequency adjustments, configurable stage counts (three- or four-stage topologies), and supply voltage scaling. This multi-modal approach extends the operational range to 1 MHz–1 GHz, ensuring compatibility with low-speed sensor interfaces and high-speed edge-computing tasks. The CCRO’s subthreshold operation at 0.4 V—coupled with nanoampere-level current consumption—makes it uniquely suited for battery-less systems, wearable health monitors, and implantable medical devices where energy efficiency and adaptive clocking are paramount. By eliminating traditional voltage-controlled oscillators’ complexity, this topology offers a compact, scalable solution for emerging ultra-low-power technologies. Full article

In modern intensive pig farming, accurately monitoring piglet behavior is crucial for health management and improving production efficiency. However, the complexity of existing models demands high computational resources, limiting the application of piglet behavior recognition in farming environments. In this study, the piglet multi-behavior-recognition approach is divided into three stages. In the first stage, the LAMP pruning algorithm is used to prune and optimize redundant channels, resulting in the lightweight YOLOv8-Prune. In the second stage, based on YOLOv8, the AIFI module and the Gather–Distribute mechanism are incorporated, resulting in YOLOv8-GDA. In the third stage, using YOLOv8-GDA as the teacher model and YOLOv8-Prune as the student model, knowledge distillation is employed to further enhance detection accuracy, thus obtaining the YOLOv8-Piglet model, which strikes a balance between the detection accuracy and speed. Compared to the baseline model, YOLOv8-Piglet significantly reduces model complexity while improving detection performance, with a 6.3% increase in precision, 11.2% increase in recall, and an mAP@0.5 of 91.8%. The model was deployed on the NVIDIA Jetson Orin NX edge computing platform for the evaluation. The average inference time was reduced from 353.9 ms to 163.2 ms, resulting in a 53.8% reduction in the processing time. This study achieves a balance between model compression and recognition accuracy through the collaborative optimization of pruning and knowledge extraction. Full article

Forest fires pose an escalating global threat, severely impacting ecosystems, public health, and economies. Timely detection, especially during early stages, is critical for effective intervention. In this study, we propose a novel deep learning-based framework that augments the YOLOv4 object detection architecture with a modified EfficientNetV2 backbone and Efficient Channel Attention (ECA) modules. The backbone substitution leverages compound scaling and Fused-MBConv/MBConv blocks to improve representational efficiency, while the lightweight ECA blocks enhance inter-channel dependency modeling without incurring significant computational overhead. Additionally, we introduce a domain-specific preprocessing pipeline employing Canny edge detection, CLAHE + Jet transformation, and pseudo-NDVI mapping to enhance fire-specific visual cues in complex natural environments. Experimental evaluation on a hybrid dataset of forest fire images and video frames demonstrates substantial performance gains over baseline YOLOv4 and contemporary YOLO variants (YOLOv5–YOLOv9), with the proposed model achieving 97.01% precision, 95.14% recall, 93.13% mAP, and 92.78% F1-score. Furthermore, our model outperforms fourteen state-of-the-art approaches across standard metrics, confirming its efficacy, generalizability, and suitability for real-time deployment in UAV-based and edge computing platforms. These findings highlight the synergy between architectural optimization and domain-aware preprocessing for high-accuracy, low-latency wildfire detection systems. Full article

The rise of wearable devices has enabled real-time processing of sensor data for critical health monitoring applications, such as human activity recognition (HAR) and cardiac disorder classification (CDC). However, the limited computational and memory resources of wearables necessitate lightweight yet accurate classification models. While deep neural networks (DNNs), including convolutional neural networks (CNNs) and long short-term memory networks, have shown high accuracy for HAR and CDC, their large parameter sizes hinder deployment on edge devices. On the other hand, various DNN compression techniques have been proposed, but exploiting the combination of various compression techniques with the aim of achieving memory efficient DNN models for HAR and CDC tasks remains under-investigated. This work studies the impact of CNN architecture parameters, focusing on the convolutional and dense layers, to identify configurations that balance accuracy and efficiency. We derive two versions of each model—lean and fat—based on their memory characteristics. Subsequently, we apply three complementary compression techniques: filter-based pruning, low-rank factorization, and dynamic range quantization. Experiments across three diverse DNNs demonstrate that this multi-faceted compression approach can significantly reduce memory and computational requirements while maintaining validation accuracy, leading to DNN models suitable for intelligent health monitoring on resource-constrained wearable devices. Full article

The advancement of precision agriculture increasingly depends on innovative technological solutions that optimize resource utilization and minimize environmental impact. This paper introduces a novel heterogeneous federated learning architecture specifically designed for intelligent agricultural systems, with a focus on combine tractors equipped with advanced nutrient and crop health sensors. Unlike conventional FL applications, our architecture uniquely addresses the challenges of communication efficiency, dynamic network conditions, and resource allocation in rural farming environments. By adopting a decentralized approach, we ensure that sensitive data remain localized, thereby enhancing security while facilitating effective collaboration among devices. The architecture promotes the formation of adaptive clusters based on operational capabilities and geographical proximity, optimizing communication between edge devices and a global server. Furthermore, we implement a robust checkpointing mechanism and a dynamic data transmission strategy, ensuring efficient model updates in the face of fluctuating network conditions. Through a comprehensive assessment of computational power, energy efficiency, and latency, our system intelligently classifies devices, significantly enhancing the overall efficiency of federated learning processes. This paper details the architecture, operational procedures, and evaluation methodologies, demonstrating how our approach has the potential to transform agricultural practices through data-driven decision-making and promote sustainable farming practices tailored to the unique challenges of the agricultural sector. Full article

This paper presents COGNIFOG, an innovative framework under development that is designed to leverage decentralized decision-making, machine learning, and distributed computing to enable autonomous operation, adaptability, and scalability across the IoT–edge–cloud continuum. The work emphasizes Continuous Integration/Continuous Deployment (CI/CD) practices, development, and versatile integration infrastructures. The described methodology ensures efficient, reliable, and seamless integration of the framework, offering valuable insights into integration design, data flow, and the incorporation of cutting-edge technologies. Through three real-world trials in smart cities, e-health, and smart manufacturing and the development of a comprehensive QuickStart Guide for deployment, this work highlights the efficiency and adaptability of the COGNIFOG platform, presenting a robust solution for addressing the complexities of next-generation computing environments. Full article

This study proposes a cyber–physical framework for the integration of a heterogeneous swarm of robots, sensors, microrobots, and AR for structural health monitoring and confined space inspection based on the application’s unique challenges. The structural issues investigated are cracks in the walls, deformation of the structures, and damage to the culverts and devices commonly used in buildings. The PC and augmented reality interfaces are incorporated for human–robot collaboration to provide the necessary information to the human user while teleoperating the robots. The proposed interfaces use edge computing and machine learning to enhance operator interactions and to improve damage detection in confined spaces and challenging environments. The proposed swarm inspection framework is called HeSARIC. Full article

Artificial intelligence (AI) plays a crucial role in modern healthcare by enhancing disease modeling and outbreak prediction. In this study, we develop an epidemiological model for the Marburg virus, integrating vaccination and treatment strategies while considering vaccine efficacy and treatment failure. The model exhibits mathematical symmetry in its equilibrium analysis, ensuring a balanced assessment of disease dynamics across human and bat reservoir populations. We compute the Marburg-free and endemic equilibrium points, derive the secondary infection threshold, and conduct sensitivity analysis using the PRCC method to identify key disease transmission parameters that are important for disease control. To validate the theory, we optimized a deep neural network (DNN) via grid search and employed it for dynamic analysis, which also validates the cutting-edge application of AI in healthcare. We also compare AI-based predictions with traditional numerical solutions for reproduction number for humans $R_{0h}>1$ and $R_{0h}<1$ for validation and efficacy of the AI approach. The results demonstrate the model’s stability, efficacy, and predictive power, emphasizing the synergy between AI and mathematical epidemiology. This study provides valuable insights for public health interventions and effective disease control strategies by leveraging AI-driven simulations, highlighting AI’s potential to revolutionize and enhance early detection and tailor treatment strategies. Full article

The Monit4Healthy system is an IoT-enabled health monitoring solution designed to address critical challenges in real-time biomedical signal processing, energy efficiency, and data transmission. The system’s modular design merges wireless communication components alongside a number of physiological sensors, including galvanic skin response, electromyography, photoplethysmography, and EKG, to allow for the remote gathering and evaluation of health information. In order to decrease network load and enable the quick identification of abnormalities, edge computing is used for real-time signal filtering and feature extraction. Flexible data transmission based on context and available bandwidth is provided through a hybrid communication approach that includes Bluetooth Low Energy and Wi-Fi. Under typical monitoring scenarios, laboratory testing shows reliable wireless connectivity and ongoing battery-powered operation. The Monit4Healthy system is appropriate for scalable deployment in connected health ecosystems and portable health monitoring due to its responsive power management approaches and structured data transmission, which improve the resiliency of the system. The system ensures the reliability of signals whilst lowering latency and data volume in comparison to conventional cloud-only systems. Limitations include the requirement for energy profiling, distinctive hardware miniaturizing, and sustained real-world validation. By integrating context-aware processing, flexible design, and effective communication, the Monit4Healthy system complements existing IoT health solutions and promotes better integration in clinical and smart city healthcare environments. Full article

Our modern lives are increasingly shaped by the Internet of Things (IoT), as IoT devices monitor and manage everything from our homes to our workplaces, becoming an essential part of health systems and daily infrastructure. However, this rapid growth in IoT has introduced significant security challenges, leading to increased vulnerability to cyber attacks. To address these challenges, machine learning-based intrusion detection systems (IDSs)—traditionally considered a primary line of defense—have been deployed to monitor and detect malicious activities in IoT networks. Despite this, these IDS solutions often struggle with the inherent resource constraints of IoT devices, including limited computational power and memory. To overcome these limitations, we propose an approach to enhance intrusion detection efficiency. First, we introduce a recursive clustering method for data condensation, integrating compactness and entropy-driven sampling to select a highly representative subset from the larger dataset. Second, we adopt a Monte Carlo Cross-Entropy approach combined with a stability metric of features to consistently select the most stable and relevant features, resulting in a lightweight, efficient, and high-accuracy IoT-based IDS. Evaluation of our proposed approach on three IoT datasets from real devices (N-BaIoT, Edge-IIoTset, CICIoT2023) demonstrates comparable classification accuracy while significantly reducing training and testing times by 45× and 15×, respectively, and lowering memory usage by 18×, compared to competitor approaches. Full article

Personal protective equipment (PPE) is crucial for infection prevention and is effective only when worn correctly and consistently. Health organizations often use education or inspections to mitigate non-compliance, but these are costly and have limited success. This study developed a novel on-device, AI-based computer vision system to monitor healthcare worker PPE adherence in real time. Using a custom-built image dataset of 7142 images of 11 participants wearing various combinations of PPE (mask, gloves, gown), we trained a series of binary classifiers for each PPE item. By utilizing a lightweight MobileNetV3 model, we optimized the system for edge computing on a Raspberry Pi 5 single-board computer, enabling rapid image processing without the need for external servers. Our models achieved high accuracy in identifying individual PPE items (93–97%), with an overall accuracy of 85.58 ± 0.82% when all items were correctly classified. Real-time evaluation with 11 unseen medical staff in a cardiac intensive care unit demonstrated the practical viability of our system, maintaining a high per-item accuracy of 87–89%. This study highlights the potential for AI-driven solutions to significantly improve PPE compliance in healthcare settings, offering a cost-effective, efficient, and reliable tool for enhancing patient safety and mitigating infection risks. Full article

The convergence of the Internet of Physical–Virtual Things (IoPVT) and the Metaverse presents a transformative opportunity for safety and health monitoring in outdoor environments. This concept paper explores how integrating human activity recognition (HAR) with the IoPVT within the Metaverse can revolutionize public health and safety, particularly in urban settings with challenging climates and architectures. By seamlessly blending physical sensor networks with immersive virtual environments, the paper highlights a future where real-time data collection, digital twin modeling, advanced analytics, and predictive planning proactively enhance safety and well-being. Specifically, three dimensions of humans, technology, and the environment interact toward measuring safety, health, and climate. Three outdoor cultural scenarios showcase the opportunity to utilize HAR–IoPVT sensors for urban external staircases, rural health, climate, and coastal infrastructure. Advanced HAR–IoPVT algorithms and predictive analytics would identify potential hazards, enabling timely interventions and reducing accidents. The paper also explores the societal benefits, such as proactive health monitoring, enhanced emergency response, and contributions to smart city initiatives. Additionally, we address the challenges and research directions necessary to realize this future, emphasizing AI technical scalability, ethical considerations, and the importance of interdisciplinary collaboration for designs and policies. By articulating an AI-driven HAR vision along with required advancements in edge-based sensor data fusion, city responsiveness with fog computing, and social planning through cloud analytics, we aim to inspire the academic community, industry stakeholders, and policymakers to collaborate in shaping a future where technology profoundly improves outdoor health monitoring, enhances public safety, and enriches the quality of urban life. Full article

The rapid development of flexible sensor technology has made flexible sensor arrays a key research area in various applications due to their exceptional flexibility, wearability, and large-area-sensing capabilities. These arrays can precisely monitor physical parameters like pressure and strain in complex environments, making them highly beneficial for sectors such as smart wearables, robotic tactile sensing, health monitoring, and flexible electronics. This paper reviews the fabrication processes, operational principles, and common materials used in flexible sensors, explores the application of different materials, and outlines two conventional preparation methods. It also presents real-world examples of large-area pressure and strain sensor arrays. Fabrication techniques include 3D printing, screen printing, laser etching, magnetron sputtering, and molding, each influencing sensor performance in different ways. Flexible sensors typically operate based on resistive and capacitive mechanisms, with their structural designs (e.g., sandwich and fork-finger) affecting integration, recovery, and processing complexity. The careful selection of materials—especially substrates, electrodes, and sensing materials—is crucial for sensor efficacy. Despite significant progress in design and application, challenges remain, particularly in mass production, wireless integration, real-time data processing, and long-term stability. To improve mass production feasibility, optimizing fabrication processes, reducing material costs, and incorporating automated production lines are essential for scalability and defect reduction. For wireless integration, enhancing energy efficiency through low-power communication protocols and addressing signal interference and stability are critical for seamless operation. Real-time data processing requires innovative solutions such as edge computing and machine learning algorithms, ensuring low-latency, high-accuracy data interpretation while preserving the flexibility of sensor arrays. Finally, ensuring long-term stability and environmental adaptability demands new materials and protective coatings to withstand harsh conditions. Ongoing research and development are crucial to overcoming these challenges, ensuring that flexible sensor arrays meet the needs of diverse applications while remaining cost-effective and reliable. Full article