Search Results (7,795)

Background and Objectives: To clinically validate a semi-automatic measurement of Tear Meniscus Central Area (TMCA) to differentiate between Non-Aqueous Deficient Dry Eye (Non-ADDE) and Aqueous Deficient Dry Eye (ADDE) patients. Materials and Methods: 120 volunteer participants were included in the study. Following TFOS DEWS II diagnostic criteria, a battery of tests was conducted for dry eye diagnosis: Ocular Surface Disease Index questionnaire, tear film osmolarity, tear film break-up time, and corneal staining. Additionally, lower tear meniscus videos were captured with Tearscope illumination and, separately, with fluorescein using slit-lamp blue light and a yellow filter. Tear meniscus height was measured from Tearscope videos to differentiate Non-ADDE from ADDE participants, while TMCA was obtained from fluorescein videos. Both parameters were analyzed using the open-source software NIH ImageJ. Results: Receiver Operating Characteristics analysis showed that semi-automatic TMCA evaluation had significant diagnostic capability to differentiate between Non-ADDE and ADDE participants, with an optimal cut-off value to differentiate between the two groups of 54.62 mm² (Area Under the Curve = 0.714 ± 0.051, p < 0.001; specificity: 71.7%; sensitivity: 68.9%). Conclusions: The semi-automatic TMCA evaluation showed preliminary valuable results as a diagnostic tool for distinguishing between ADDE and Non-ADDE individuals. Full article

Street networks provide an invaluable source of information about the different temporal and spatial patterns emerging in our cities. These streets are often represented as graphs where intersections are modeled as nodes and streets as edges between them. Previous work has shown that raster representations of the original data can be created through a learning algorithm on low-dimensional representations of the street networks. In contrast, models that capture high-level urban network metrics can be trained through convolutional neural networks. However, the detailed topological data is lost through the rasterization of the street network, and the models cannot recover this information from the image alone, failing to capture complex street network features. This paper proposes a model capable of inferring good representations directly from the street network. Specifically, we use a variational autoencoder with graph convolutional layers and a decoder that generates a probabilistic, fully connected graph to learn latent representations that encode both local network structure and the spatial distribution of nodes. We train the model on thousands of street network segments and use the learned representations to generate synthetic street configurations. Finally, we proposed a possible application to classify the urban morphology of different network segments, investigating their common characteristics in the learned space. Full article

Hundreds of Japanese features of war (field positions, tunnels, and fortifications) were constructed in Hong Kong during World War II. However, most of them were poorly documented and were left unknown but still in relatively good condition because of their durable design, workmanship, and remoteness. These features of war form parts of Hong Kong’s brutal history. Conservation, at least in digital form, is worth considering. With the authors coming from multidisciplinary and varied backgrounds, this paper aims to explore these features using a scientific workflow. First, we reviewed the surviving archival sources of the Imperial Japanese Army and Navy. Second, airborne LiDAR data were used to form territory digital terrain models (DTM) based on the Red Relief Image Map (RRIM) for identifying suspected locations. Third, field expeditions of searching for features of war were conducted through guidance of Global Navigation Satellite System—Real-Time Kinetics (GNSS-RTK). Fourth, the found features were 3D-laser scanned to generate mesh models as a digital archive and validate the findings of DTM-RRIM. This study represents a reverse-engineering effort to reconstruct the planned Japanese defense tactics of guerilla fight and Kamikaze grottos that were never used in Hong Kong. Full article

Mid-infrared passive spectroscopic imaging is a novel non-invasive and remote sensing method based on Planck’s law. It enables the acquisition of component-specific information from the human body by measuring naturally emitted thermal radiation in the mid-infrared region. Unlike active methods that require an external light source, our passive approach harnesses the body’s own emission, thereby enabling safe, long-term monitoring. In this study, we successfully demonstrated the simultaneous, non-invasive measurements of blood glucose and lactate levels of the human body using this method. The measurements, conducted over approximately 80 min, provided emittance data derived from mid-infrared passive spectroscopy that showed a temporal correlation with values obtained using conventional blood collection sensors. Furthermore, to evaluate localized metabolic changes, we performed k-means clustering analysis of the spectral data obtained from the upper arm. This enabled visualization of time-dependent lactate responses with spatial resolution. These results demonstrate the feasibility of multi-component monitoring without physical contact or biological sampling. The proposed technique holds promise for translation to medical diagnostics, continuous health monitoring, and sports medicine, in addition to facilitating the development of next-generation healthcare technologies. Full article

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

Chemometrics has emerged as a powerful approach for deciphering complex environmental systems, enabling the identification of pollution sources through the integration of faunal community structures with physicochemical parameters and in situ analytical data. Leveraging advanced technologies—including satellite imaging, drone surveillance, sensor networks, and Internet of Things platforms—chemometric methods facilitate real-time and longitudinal monitoring of both pristine and anthropogenically influenced ecosystems. This review provides a critical and comprehensive overview of the foundational principles underpinning chemometric applications in environmental science. Emphasis is placed on identifying pollution sources, their ecological distribution, and potential impacts on human health. Furthermore, the study highlights the role of chemometrics in interpreting multidimensional datasets, thereby enhancing the accuracy and efficiency of modern environmental monitoring systems across diverse geographic and industrial contexts. A comparative analysis of analytical techniques, target analytes, application domains, and the strengths and limitations of selected in situ and remote sensing-based chemometric approaches is also presented. Full article

In remote sensing building detection tasks, data acquisition remains a critical bottleneck that limits both model performance and large-scale deployment. Due to the high cost of manual annotation, limited geographic coverage, and constraints of image acquisition conditions, obtaining large-scale, high-quality labeled datasets remains a significant challenge. To address this issue, this study proposes an automatic semantic labeling framework for remote sensing imagery. The framework leverages geospatial vector data provided by OpenStreetMap, precisely aligns it with high-resolution satellite imagery from Bing Maps through projection transformation, and incorporates a quality-aware sample filtering strategy to automatically generate accurate annotations for building detection. The resulting dataset comprises 36,647 samples, covering buildings in both urban and suburban areas across multiple cities. To evaluate its effectiveness, we selected three publicly available datasets—WHU, INRIA, and DZU—and conducted three types of experiments using the following four representative object detection models: SSD, Faster R-CNN, DETR, and YOLOv11s. The experiments include benchmark performance evaluation, input perturbation robustness testing, and cross-dataset generalization analysis. Results show that our dataset achieved a mAP at 0.5 intersection over union of up to 93.2%, with a precision of 89.4% and a recall of 90.6%, outperforming the open-source benchmarks across all four models. Furthermore, when simulating real-world noise in satellite image acquisition—such as motion blur and brightness variation—our dataset maintained a mean average precision of 90.4% under the most severe perturbation, indicating strong robustness. In addition, it demonstrated superior cross-dataset stability compared to the benchmarks. Finally, comparative experiments conducted on public test areas further validated the effectiveness and reliability of the proposed annotation framework. Full article

Background: MRI-based radiomics has emerged as a promising approach to enhance the non-invasive, presurgical assessment of lymph node staging in rectal cancer (RC). However, its clinical implementation remains limited due to methodological variability in published studies. We conducted a systematic review and meta-analysis to synthesize the diagnostic performance of MRI-based radiomics models for predicting pathological nodal status (pN) in RC. Methods: A systematic literature search was conducted in PubMed, Web of Science, and Scopus for studies published until 31 December 2024. Eligible studies applied MRI-based radiomics for pN prediction in RC patients. We excluded other imaging sources and models combining radiomics and other data (e.g., clinical). All models with available outcome metrics were included in data analysis. Data extraction and quality assessment (QUADAS-2) were performed independently by two reviewers. Random-effects meta-analyses including hierarchical summary receiver operating characteristic (HSROC) and restricted maximum likelihood estimator (REML) analyses were conducted to pool sensitivity, specificity, area under the curve (AUC), and diagnostic odds ratios (DORs). Sensitivity analyses and publication bias evaluation were also performed. Results: Sixteen studies (n = 3157 patients) were included. The HSROC showed pooled sensitivity, specificity, and AUC values of 0.68 (95% CI, 0.63–0.72), 0.73 (95% CI, 0.68–0.78), and 0.70 (95% CI, 0.65–0.75), respectively. The mean pooled AUC and DOR obtained by REML were 0.78 (95% CI, 0.75–0.80) and 6.03 (95% CI, 4.65–7.82). Funnel plot asymmetry and Egger’s test (p = 0.025) indicated potential publication bias. Conclusions: Overall, MRI-based radiomics models demonstrated moderate accuracy in predicting pN status in RC, with some studies reporting outstanding results. However, heterogeneity in relevant methodological approaches such as the source of MRI sequences or machine learning methods applied along with possible publication bias call for further standardization and preclude their translation to clinical practice. Full article

Automated waste classification is an essential step toward efficient recycling and waste management. Traditional deep learning models, such as convolutional neural networks, rely on extensive labeled datasets to achieve high accuracy. However, the annotation process is labor-intensive and time-consuming, limiting the scalability of these approaches in real-world applications. Zero-shot learning is a machine learning paradigm that enables a model to recognize and classify objects it has never seen during training by leveraging semantic relationships and external knowledge sources. In this study, we investigate the potential of zero-shot learning for waste classification using two vision-language models: OWL-ViT and OpenCLIP. These models can classify waste without direct exposure to labeled examples by leveraging textual prompts. We apply this approach to the TrashNet dataset, which consists of images of municipal solid waste organized into six distinct categories: cardboard, glass, metal, paper, plastic, and trash. Our experimental results yield an average classification accuracy of 76.30% with Open Clip ViT-L/14-336 model, demonstrating the feasibility of zero-shot learning for waste classification while highlighting challenges in prompt sensitivity and class imbalance. Despite lower accuracy than CNN- and ViT-based classification models, zero-shot learning offers scalability and adaptability by enabling the classification of novel waste categories without retraining. This study underscores the potential of zero-shot learning in automated recycling systems, paving the way for more efficient, scalable, and annotation-free waste classification methodologies. Full article

Ocular diseases can significantly affect vision and overall quality of life, with diagnosis often being time-consuming and dependent on expert interpretation. While previous computer-aided diagnostic systems have focused primarily on medical imaging, this paper proposes VisionTrack, a multi-modal AI system for predicting multiple retinal diseases, including Diabetic Retinopathy (DR), Age-related Macular Degeneration (AMD), Diabetic Macular Edema (DME), drusen, Central Serous Retinopathy (CSR), and Macular Hole (MH), as well as normal cases. The proposed framework integrates a Convolutional Neural Network (CNN) for image-based feature extraction, a Graph Neural Network (GNN) to model complex relationships among clinical risk factors, and a Large Language Model (LLM) to process patient medical reports. By leveraging diverse data sources, VisionTrack improves prediction accuracy and offers a more comprehensive assessment of retinal health. Experimental results demonstrate the effectiveness of this hybrid system, highlighting its potential for early detection, risk assessment, and personalized ophthalmic care. Experiments were conducted using two publicly available datasets, RetinalOCT and RFMID, which provide diverse retinal imaging modalities: OCT images and fundus images, respectively. The proposed multi-modal AI system demonstrated strong performance in multi-label disease prediction. On the RetinalOCT dataset, the model achieved an accuracy of 0.980, F1-score of 0.979, recall of 0.978, and precision of 0.979. Similarly, on the RFMID dataset, it reached an accuracy of 0.989, F1-score of 0.881, recall of 0.866, and precision of 0.897. These results confirm the robustness, reliability, and generalization capability of the proposed approach across different imaging modalities. Full article

This article examines the theological trajectories of Watchman Nee (1903–1972) and Witness Lee (1905–1997) on sanctification, union with Christ, and deification, situating their contributions within recent reappraisals of the doctrine of theosis in the academy. Though deification was universally affirmed by the early church and retained in various forms in medieval and early Protestant theology, post-Reformation Western Christianity marginalized this theme in favor of juridical and forensic soteriological categories. Against this backdrop, Nee and Lee offer a theologically rich, biblically grounded, and experientially oriented articulation of deification that warrants greater scholarly attention. Drawing from the Keswick Holiness tradition, patristic sources, and Christian mysticism, Nee developed a soteriology that integrates justification, sanctification, and glorification within an organic model of progressive union with God. Though he does not explicitly use the term “deification”, the language he employs regarding union and participation closely mirrors classical expressions of Christian theosis. For Nee, sanctification is not merely moral improvement but the transformative increase of the divine life, culminating in conformity to Christ’s image. Lee builds upon and expands Nee’s participatory soteriology into a comprehensive theology of deification, explicitly referring to it as “the high peak of the divine revelation” in the Holy Scriptures. For Lee, humans become God “in life and nature but not in the Godhead”. By employing the phrase “not in the Godhead”, Lee upholds the Creator–creature distinction—i.e., humans never participate in the ontological Trinity or God’s incommunicable attributes. Yet, in the first portion of his description, he affirms that human beings undergo an organic, transformative process by which they become God in deeply significant ways. His framework structures sanctification as a seven-stage process, culminating in the believer’s transformation and incorporation into the Body of Christ to become a constituent of a corporate God-man. This corporate dimension—often overlooked in Western accounts—lies at the heart of Lee’s ecclesiology, which he sees as being consummated in the eschatological New Jerusalem. Ultimately, this study argues that Nee and Lee provide a coherent, non-speculative model of deification that integrates biblical exegesis, theological tradition, and practical spirituality, and thus, present a compelling alternative to individualistic and forensic soteriologies while also highlighting the need for deeper engagement across global theological discourse on sanctification, union with Christ, and the Triune God. Full article

Background: Biomechanical and neuromuscular differences between falls and recoveries have been well-studied; however, the cortical correlations remain unclear. Using mobile brain imaging via electroencephalography (EEG), we examined differences in sensorimotor beta frequencies between falls and recoveries during an unpredicted slip in walking. Methods: We recruited 22 young adults (15 female; 18–35 years) who experienced a slip (65 cm) during walking. Raw EEG signals were band-pass filtered, and independent component analysis was performed to remove non-neural sources, eventually three participants were excluded due to excessive artifacts. Peak beta power was extracted from three time-bins: 400 milliseconds pre-, 0–150 milliseconds post and 150–300 milliseconds post-perturbation from the midline (Cz) electrode. A 2 × 3 Analysis of Covariance assessed the interaction between time-bins and group on beta power, followed by Independent and Paired t-tests for between and within-group post hoc comparisons. Results: All participants (n = 19) experienced a balance loss, seven experienced a fall. There was a time × group interaction on beta power (p < 0.05). With no group differences pre-perturbation, participants who experienced a fall exhibited higher beta power during 0–150 milliseconds post-perturbation than those who recovered (p < 0.001). However, there were no group differences in beta power during 150–300 milliseconds post-perturbation. Conclusions: Young adults exhibiting a greater increase in beta power during the early post-perturbation period experienced a fall, suggesting a higher cortical error detection due to a larger mismatch in the expected and ongoing postural state and greater cortical dependence for sensorimotor processing. Our study results provide an overview of the possible cortical governance to modulate slip-fall/recovery outcomes. Full article

With the increase in the penetration rate of distributed sources and loads, the sensor monitoring data is increasing dramatically. Power grid maintenance services require a rapid response in power quality data analysis. To achieve a rapid response and highly accurate classification of power quality disturbances (PQDs), this paper proposes an efficient classification algorithm for PQDs based on Lissajous trajectory (LT) and a lightweight DenseNet, which utilizes the concept of Lissajous curves to construct an ideal reference signal and combines it with the original PQD signal to synthesize a feature trajectory with a distinctive shape. Meanwhile, to enhance the ability and efficiency of capturing trajectory features, a lightweight L-DenseNet skeleton model is designed, and its feature extraction capability is further improved by integrating an attention mechanism with L-DenseNet. Finally, the LT image is input into the fusion model for training, and PQD classification is achieved using the optimally trained model. The experimental results demonstrate that, compared with current mainstream PQD classification methods, the proposed algorithm not only achieves superior disturbance classification accuracy and noise robustness but also significantly improves response speed in PQD classification tasks through its concise visualization conversion process and lightweight model design. Full article

This study investigates a lithium-ion battery failure in heating insoles that ignited during normal walking while powered off. Through comprehensive material characterization, electrical testing, thermal analysis, and mechanical gait simulation, we systematically excluded electrical or thermal abuse as failure causes. X-ray/CT imaging localized the ignition source to the lateral heel edge of the pouch cell, correlating precisely with peak mechanical stress identified through gait analysis. Remarkably, the cyclic load was less than 10% of the single crush load threshold specified in safety standards. Key findings reveal multiple contributing factors as follows: the uncoated polyethylene separator’s inability to prevent stress-induced internal short circuits, the circuit design’s lack of battery health monitoring functionality that permitted undetected degradation, and the hazardous placement inside clothing that exacerbated burn injuries. These findings necessitate a multi-level safety framework for lithium-ion battery products, encompassing enhanced cell design to prevent internal short circuit, improved circuit protection with health monitoring capabilities, optimized product integration to mitigate mechanical and environmental impact, and effective post-failure containment measures. This case study exposes a critical need for product-specific safety standards that address the unique demands of wearable lithium-ion batteries, where existing certification requirements fail to prevent real-use failure scenarios. Full article

Duck egg quality classification is critical in farms, hatcheries, and salted egg processing plants, where cracked eggs must be identified before further processing or distribution. However, duck eggs present a unique challenge due to their white eggshells, which make cracks difficult to detect visually. In current practice, human inspectors use standard white light for crack detection, and many researchers have focused primarily on improving detection algorithms without addressing lighting limitations. Therefore, this paper presents duck egg crack detection using an adaptive convolutional neural network (CNN) model ensemble with multi-light channels. We began by developing a portable crack detection system capable of controlling various light sources to determine the optimal lighting conditions for crack visibility. A total of 23,904 images were collected and evenly distributed across four lighting channels (red, green, blue, and white), with 1494 images per channel. The dataset was then split into 836 images for training, 209 images for validation, and 449 images for testing per lighting condition. To enhance image quality prior to model training, several image pre-processing techniques were applied, including normalization, histogram equalization (HE), and contrast-limited adaptive histogram equalization (CLAHE). The Adaptive MobileNetV2 was employed to evaluate the performance of crack detection under different lighting and pre-processing conditions. The results indicated that, under red lighting, the model achieved 100.00% accuracy, precision, recall, and F1-score across almost all pre-processing methods. Under green lighting, the highest accuracy of 99.80% was achieved using the image normalization method. For blue lighting, the model reached 100.00% accuracy with the HE method. Under white lighting, the highest accuracy of 99.83% was achieved using both the original and HE methods. Full article