Search Results (2,796)

Background/Objectives: Lyme disease diagnosis remains challenging due to the limitations of current methods. While PCR-based assays are widely used, their sensitivity can be affected by sample type and the inhibition of host DNA. This study aimed to evaluate the feasibility and sensitivity of a CRISPR/Cas12-based detection system for Borrelia burgdorferi sensu lato, comparing its performance with real-time PCR. Methods: DNA from three Borrelia genospecies (B. burgdorferi, B. garinii, and B. afzelii) was amplified targeting the OspA gene. Detection was performed using a Cas12/crRNA system with a fluorescent ssDNA reporter. Sensitivity assays were conducted on serial dilutions of Borrelia DNA, with and without human genomic DNA, and results were compared with qPCR. Results: Direct detection of Borrelia DNA without amplification was not feasible. However, when combined with PCR, the Cas12/crRNA system reliably detected as few as 5 genome copies per reaction. End-point PCR extended to 60 cycles improved detection robustness for B. garinii and B. afzelii, although sensitivity decreased in the presence of human genomic DNA. Conclusions: The Cas12/crRNA-based system offers a sensitive and accessible alternative to qPCR, especially in settings lacking real-time PCR instrumentation. Future developments may include integration with isothermal amplification and microfluidic platforms to enhance direct detection capabilities. Full article

Drones offer a promising solution for automating distribution tower inspection, but real-time defect detection remains challenging due to limited computational resources and the small size of critical defects. This paper proposes TDD-YOLO, an optimized model based on YOLOv11n, which enhances small defect detection through four key improvements: (1) SPD-Conv preserves fine-grained details, (2) CBAM amplifies defect salience, (3) BiFPN enables efficient multi-scale fusion, and (4) a dedicated high-resolution detection head improves localization precision. Evaluated on a custom dataset, TDD-YOLO achieves an mAP@0.5 of 0.873, outperforming the baseline by 3.9%. When deployed on a Jetson Orin Nano at 640 × 640 resolution, the system achieves an average frame rate of 28 FPS, demonstrating its practical viability for real-time autonomous inspection. Full article

Children with intoeing gait are at increased risk of tripping and consequent injury, reduced mobility, and psychological issues. Quantification of tripping is needed outside the gait lab during daily life for improved clinical assessment and treatment evaluation and to enrich the database for artificial intelligence (AI) learning. This paper presents the development of a low-cost, wearable tripping monitor to log a child’s Tripping Hazard Events (THEs) and steps taken during two weeks of everyday activity. A combination of sensors results in a high probability of THE detection, even during rapid gait, while guarding against false positives and minimizing power and therefore monitor size. A THE is logged when the feet come closer than a predefined threshold during the intoeing foot swing phase. Foot proximity is determined by a Radio Frequency Identification (RFID) reader in “sniffer” mode on the intoeing foot and a target of passive Near-Field Communication (NFC) tags on the contralateral foot. A Force Sensitive Resistor (FSR) in the intoeing shoe sets a time window for sniffing during gait and enables step counting. Data are stored in 15 min epochs. Laboratory testing and an IRB-approved human participant study validated system performance and identified the need for improved mechanical robustness, prompting a redesign of the monitor. A custom Python (version 3.10.13)-based Graphical User Interface (GUI) lets clinicians initiate recording sessions and view time records of THEs and steps. The monitor’s flexible design supports broader applications to real-world activity detection. Full article

After rough planing, defects such as wormholes and small patches of green bark residue and decay are often overlooked and misclassified. Strip-like defects, including splinters and chipped edges, are easily confused with the natural bamboo grain, and a single elongated defect is frequently fragmented into multiple detection boxes. This study proposes a modified TASNet-YOLO model, an improved detector built on YOLO11n. Unlike prior YOLO-based bamboo defect detectors, TASNet-YOLO is a mechanism-guided redesign that jointly targets two persistent failure modes—limited visibility of small, low-contrast defects and fragmentation of elongated defects—while remaining feasible for real-time production settings. In the backbone, a newly designed TriMAD_Conv module is introduced as the core unit, enhancing the detection of wormholes as well as small-area defects such as green bark residue and decay. The additive-gated C3k2_AddCGLU is further integrated at selected C3k2 stages. The combination of additive interaction and CGLU improves channel selection and detail retention, highlighting differences between splinters and chipped edges and bamboo grain strips, thereby reducing false positives and improving precision. In the neck, the neck replaces nearest-neighbor upsampling and CBS with SNI-GSNeck to improve cross-scale alignment and fusion. Under an acceptable real-time budget, predictions for splinters and chipped edges become more contiguous and better aligned to edges, while wormholes predictions are more circular and less noisy. Experiments on our in-house dataset (8445 bamboo-strip defect images) show that, compared with YOLO11n, the proposed model improves detection accuracy by 5.1%, achieves 106.4 FPS, and reduces computational costs by 0.4 GFLOPs per forward pass. These properties meet the throughput demand of 2 m/s conveyor lines, and the compact model size and compute footprint make edge deployment straightforward for fast online screening and preliminary quality grading in industrial production. Full article

With the development of infrared imaging technology and the integration of intelligent algorithms, the realization of non-contact, dynamic and real-time detection of SF6 gas leakage based on infrared video has been a significant research direction. However, the existing real-time detection algorithms exhibit low accuracy in detecting SF6 leakage and are susceptible to noise, which makes it difficult to meet the actual needs of engineering. To address this problem, this paper proposes a real-time SF6 leakage detection method, VGEC-Net, based on multi-channel fusion and spatiotemporal feature extraction. The proposed method first employs the ViBe-GMM algorithm to extract foreground masks, which are then fused with infrared images to construct a dual-channel input. In the backbone network, a CE-Net structure—integrating CBAM and ECA-Net—is combined with the P3D network to achieve efficient spatiotemporal feature extraction. A Feature Pyramid Network (FPN) and a temporal Transformer module are further integrated to enhance multi-scale feature representation and temporal modeling, thereby significantly improving the detection performance for small-scale targets. Experimental results demonstrate that VGEC-Net achieves a mean average precision (mAP) of 61.7% on the dataset used in this study, with a mAP@50 of 87.3%, which represents a significant improvement over existing methods. These results validate the effectiveness and advancement of the proposed method for infrared video-based gas leakage detection. Furthermore, the model achieves 78.2 frames per second (FPS) during inference, demonstrating good real-time processing capability while maintaining high detection accuracy, exhibiting strong application potential. Full article

Escalating Human–Wildlife Conflict (HWC), particularly involving protected large carnivores such as the wolf, poses a significant challenge in Europe. This problem, exacerbated by ecological pressure, necessitates the development of innovative, non-lethal, and effective prevention methods that overcome the limitations of current passive solutions, such as habituation. This article presents the design and implementation of a prototype for an autonomous, multi-sensory preventive system. Its three-layer architecture is based on a decentralized network of sensory-deterrent nodes that utilize Edge AI for real-time species detection and adaptive selection of deterrent stimuli. During field validation, the prototype’s biological efficacy as a proof-of-concept was confirmed in a crop protection scenario against the European roe deer (Capreolus capreolus). The system’s deployment led to a near-total elimination of damages. The paper also presents key technical performance metrics (e.g., response time, energy consumption) and the accuracy of the implemented AI detection model, verified using both field and historical data. The positive test results demonstrate that the developed platform provides an effective and flexible foundation for preventive systems. Its successful validation on a common herbivore species represents a crucial, measurable step toward the target implementation and further research on the system’s effectiveness in providing protection against large carnivores. Full article

Pediatric thrombosis (PT) represents a rare condition that can manifest from neonatal life to adolescence, encompassing life-threatening complications. Its pathogenesis is attributed to immature hemostasis in conjunction with environmental and genetic factors, predominantly including those resulting in increased levels of plasminogen activator inhibitor 1 (PAI-1), the principal inhibitor of fibrinolysis, which is subject to upstream regulation by angiotensin-converting enzyme (ACE). Although the implication of microRNAs (miRNAs), epigenetic modulators of gene expression, has been demonstrated in adult thrombosis, evidence is lacking in the pediatric setting. Here, we investigated the involvement of two miRNA regulators of PAI-1 (SERPINE1 gene) in PT, in relation to clinical and genetic parameters that induce PAI-1 fluctuations. Following bioinformatic target-prediction, miRNA expression was assessed by quantitative real-time PCR in serum-samples of 19 pediatric patients with thrombosis (1–18 months post-incident), and 19 healthy controls. Patients were genotyped for the SERPINE1-4G/5G and ACE-I/D polymorphisms by PCR-based assays. Genotypic and thrombosis-related clinical data were analyzed in relation to miRNA-expression. Two miRNAs (miR-145-5p, miR-34a-5p) were identified to target SERPINE1 mRNA, with miR-34a additionally targeting the mRNA of ACE. The expression of miR-34a was significantly decreased in patients compared to controls (p = 0.029), while no difference was observed in miR-145 expression. Within patients, miR-34a expression demonstrated a peak 1–3 months post-thrombosis and was diminished upon treatment completion (p = 0.031), followed by a slight long-term increase. MiR-34a levels differed significantly by thrombosis site (p = 0.019), while a significant synergistic interaction between site and onset type (provoked/unprovoked) was detected (p = 0.016). Finally, an epistatic modification was observed in cerebral cases, since double homozygosity (4G/4G + D/D) led to a miR-34 decrease, with D/D carriership reversing the 4G/4G-induced upregulation of miR-34a (p = 0.006). Our findings suggest that in pediatric thrombosis, downregulation of miR-34a is indicative of impaired fibrinolytic capacity, attributed to deficient regulation of the inhibitory ACE/PAI-1 axis. Full article

The global food crises and growing population necessitate efficient agricultural land use. Weeds cause up to 40% yield loss in major crops, resulting in over USD 100 billion in annual economic losses. Camera-equipped UAVs offer a solution for automatic weed detection, but the high computational and energy demands of deep learning models limit their use to expensive, high-end UAVs. In this paper, we present a low-cost UAV system built from off-the-shelf components, featuring a custom-designed on-board computing system based on the NVIDIA Jetson Nano. This system efficiently manages real-time image acquisition and inference using the energy-efficient Squeeze U-Net neural network for weed detection. Our approach ensures the pipeline operates in real time without affecting the drone’s flight autonomy. We also introduce the AgriAdapt dataset, a novel collection of 643 high-resolution aerial images of salad crops with weeds, which fills a key gap by providing realistic UAV data for benchmarking segmentation models under field conditions. Several deep learning models are trained and validated on the newly introduced AgriAdapt dataset, demonstrating its suitability for effective weed segmentation in UAV imagery. Quantitative results show that the dataset supports a range of architectures, from larger models such as DeepLabV3 to smaller, lightweight networks like Squeeze U-Net (with only 2.5 M parameters), achieving high accuracy (around 90%) across the board. These contributions distinguish our work from earlier UAV-based weed detection systems by combining a novel dataset with a comprehensive evaluation of accuracy, latency, and energy efficiency, thus directly targeting deep learning applications for real-time UAV deployment. Our results demonstrate the feasibility of deploying a low-cost, energy-efficient UAV system for real-time weed detection, making advanced agricultural technology more accessible and practical for widespread use. Full article

Aflatoxins, which are potentially genotoxic and carcinogenic substances, are mainly produced by the Aspergillus section Flavi, including Aspergillus flavus and A. parasiticus. Current Aspergillus spp. detection is often based on molecular methods, such as real-time PCR and loop-mediated isothermal amplification (LAMP), targeting genes of the aflatoxin biosynthetic cluster. In this study, we developed a Lab-on-a-Chip (LoC) method based on real-time PCR and on LAMP for the specific detection of aflatoxigenic strains of A. flavus and A. parasiticus from infected hazelnuts. LoC-LAMP and LoC-real-time PCR assays were tested in terms of specificity, sensitivity, speed, and repeatability. The microfluidic chip allowed quick, specific, sensitive, simple, automatized, cheap, and user-friendly detection of aflatoxigenic strains of A. flavus and A. parasiticus. The LoC-LAMP showed a limit of detection (LOD) of 10 fg of DNA, while the LoC-real-time PCR showed a LOD of 10 pg of DNA. Achieving comparable sensitivity to that of LAMP and real-time PCR techniques, both LoC methods developed in this work offer the advantages of automation, minimal sample requirements, reagent requirements, and cost-effectiveness. Overall, the developed methods open the perspective for alternative monitoring of aflatoxigenic fungi in the agri-food industry. Full article

Securing Industrial Control Systems (ICSs) is critical, but it is made challenging by the constant evolution of cyber threats and the scarcity of labeled attack data in these specialized environments. Standard intrusion detection systems (IDSs) often fail to adapt when transferred to new networks with limited data. To address this, this paper introduces an adaptive intrusion detection framework that combines a hybrid Convolutional Neural Network and Long Short-Term Memory (CNN-LSTM) model with a novel transfer learning strategy. We employ a Reinforcement Learning (RL) agent to intelligently guide the fine-tuning process, which allows the IDS to dynamically adjust its parameters such as layer freezing and learning rates in real-time based on performance feedback. We evaluated our system in a realistic data-scarce scenario using only 50 labeled training samples. Our RL-Guided model achieved a final F1-score of 0.9825, significantly outperforming a standard neural fine-tuning model (0.861) and a target baseline model (0.759). Analysis of the RL agent’s behavior confirmed that it learned a balanced and effective policy for adapting the model to the target domain. We conclude that the proposed RL-guided approach creates a highly accurate and adaptive IDS that overcomes the limitations of static transfer learning methods. This dynamic fine-tuning strategy is a powerful and promising direction for building resilient cybersecurity defenses for critical infrastructure. Full article

This paper introduces an autonomous vision-based tracking system for a quadrotor unmanned aerial vehicle (UAV) equipped with an onboard camera, designed to track a maneuvering target without external localization sensors or GPS. Accurate capture of dynamic aerial targets is essential to ensure real-time tracking and effective management. The system employs a robust and computationally efficient visual tracking method that combines HSV filter detection with a shape detection algorithm. Target states are estimated using an enhanced extended Kalman filter (EKF), providing precise state predictions. Furthermore, a closed-loop Proportional-Integral-Derivative (PID) controller, based on the estimated states, is implemented to enable the UAV to autonomously follow the moving target. Extensive simulation and experimental results validate the system’s ability to efficiently and reliably track a dynamic target, demonstrating robustness against noise, light reflections, or illumination interference, and ensure stable and rapid tracking using low-cost components. Full article

Real-time operating systems (RTOSs) are widely used in embedded systems to ensure deterministic task execution, predictable responses, and concurrent operations, which are crucial for time-sensitive applications. However, the growing complexity of embedded systems, increased network connectivity, and dynamic software updates significantly expand the attack surface, exposing RTOSs to a variety of security threats, including memory corruption, privilege escalation, and side-channel attacks. Traditional security mechanisms often impose additional overhead that can compromise real-time guarantees. In this work, we present a Risk-aware Permission Adjustment (RPA) framework, implemented on CHERIoT RTOS, which is a CHERI-based operating system. RPA aims to detect anomalous behavior in real time, quantify security risks, and dynamically adjust permissions to mitigate potential threats. RPA maintains system continuity, enforces fine-grained access control, and progressively contains the impact of violations without interrupting critical operations. The framework was evaluated through targeted fault injection experiments, including 20 real-world CVEs and 15 abstract vulnerability classes, demonstrating its ability to mitigate both known and generalized attacks. Performance measurements indicate minimal runtime overhead while significantly reducing system downtime compared to conventional CHERIoT and FreeRTOS implementations. Full article

Background and Objectives: Acute kidney injury (AKI) is a common complication in patients with trauma and is associated with increased morbidity and mortality rates. Early identification of patients at risk of AKI may enable timely intervention and improved outcomes. Biomarkers such as urinary mitochondrial DNA copy number (mtDNAcn) may play a role in predicting AKI. However, its role as a predictor of AKI has rarely been studied in patients with trauma. Therefore, the aim of this study was to evaluate the utility of mtDNA for early detection of AKI in this patient population. Materials and Methods: This single-center prospective observational study included patients with trauma admitted to a regional trauma center between July 2022 and July 2023. Serum and urine samples were collected at baseline and at 24, 48, and 72 h to measure mtDNAcn using real-time polymerase chain reaction test. Clinical variables, including hemoglobin (Hb) levels, were also recorded. Results: Among 65 enrolled patients, 25 (38.5%) developed AKI. Patients with AKI showed significantly lower Hb levels and higher urinary mtDNAcn at admission. Multivariate logistic regression analysis identified low Hb and elevated urinary mtDNAcn as independent predictors of AKI. The optimal cutoff value was 10.95 g/dL for Hb and 738.0 copies/μL for urinary mtDNAcn. However, no significant temporal differences in serum mtDNAcn were observed between the AKI and no-AKI groups. Conclusions: Both Hb and urinary mtDNAcn may serve as independent biomarkers for early identification of AKI in patients with trauma. Future studies are warranted to determine optimal targets and validate these findings in larger multicenter cohorts. Full article

Background: Cryptosporidium spp. cause opportunistic infections in immunosuppressed individuals, such as people living with HIV (PLWH). However, the association between giardiasis and HIV infection remains uncertain. This study assessed co-infections in Ghanaian PLWH and HIV-negative individuals, analyzing socio-economic, clinical, and immunological implications, including the Giardia duodenalis assemblage and Cryptosporidium spp. sub-family levels. Methods: Stool samples from Ghanaian PLWH were tested using several real-time PCR assays targeting G. duodenalis at the species level and assemblages A and B to optimize diagnostic accuracy. GD60 gene-based Sanger sequencing was used for Cryptosporidium spp. subtyping. Results were correlated with anonymized patient data to evaluate interactions with HIV infection. Results: In PLWH, C. hominis Ib, C. hominis Ie, and C. parvum IIc were detected at similar frequencies, followed by C. hominis Ia, C. hominis Id, and C. parvum IIe in decreasing order. Only C. parvum IIc was repeatedly observed in individuals with CD4+ T cell counts above 200/µL, while other sub-families occurred preferentially in those with lower counts. C. hominis Ia and Ib were associated with PLWH not receiving antiretroviral therapy; C. hominis Ia was linked to recently diagnosed HIV infections. No relevant associations between G. duodenalis assemblages and HIV infection were found. Conclusions: Sub-families Ia and Ib of C. hominis preferentially occur in individuals with severe immunosuppression, while C. parvum IIc is also detectable in individuals with better immune function. The prevalence of giardiasis in Ghana appears to be influenced by factors other than HIV-induced immunosuppression. Full article

Generative artificial intelligence (AI) and persistent empirical gaps are reshaping the cyber threat landscape faster than Zero-Trust Architecture (ZTA) research can respond. We reviewed 10 recent ZTA surveys and 136 primary studies (2022–2024) and found that 98% provided only partial or no real-world validation, leaving several core controls largely untested. Our critique, therefore, proceeds on two axes: first, mainstream ZTA research is empirically under-powered and operationally unproven; second, generative-AI attacks exploit these very weaknesses, accelerating policy bypass and detection failure. To expose this compounding risk, we contribute the Cyber Fraud Kill Chain (CFKC), a seven-stage attacker model (target identification, preparation, engagement, deception, execution, monetization, and cover-up) that maps specific generative techniques to NIST SP 800-207 components they erode. The CFKC highlights how synthetic identities, context manipulation and adversarial telemetry drive up false-negative rates, extend dwell time, and sidestep audit trails, thereby undermining the Zero-Trust principles of verify explicitly and assume breach. Existing guidance offers no systematic countermeasures for AI-scaled attacks, and that compliance regimes struggle to audit content that AI can mutate on demand. Finally, we outline research directions for adaptive, evidence-driven ZTA, and we argue that incremental extensions of current ZTA that are insufficient; only a generative-AI-aware redesign will sustain defensive parity in the coming threat cycle. Full article