Search Results (188)

This paper presents a significant evolution of the Identification of Active Anomalies (IAA) system, moving beyond previous descriptive frameworks by integrating an advanced machine learning pipeline for automated, real-time Structural Health Monitoring (SHM). Utilizing acoustic emission (AE), the upgraded IAA framework combines signal clustering, image recognition, and machine learning to monitor the structural condition of a highway overpass located near a major urban agglomeration. The monitoring results provide a reliable foundation for assessing structural health and implementing automated traffic control, which is essential to ensure safe operations. Unlike baseline implementations, this intelligent system extracts multi-parametric features using Principal Component Analysis (PCA) and transforms temporal wave streams into Continuous Wavelet Transform (CWT) scalograms. These visual representations are processed by a custom 14-layer Deep Convolutional Neural Network (CNN) combined with an unsupervised Self-Organizing Map (SOM) to eliminate operational noise and classify internal failures. AE signals recorded under service loads undergo multi-parametric analysis using pattern recognition techniques and are assigned to specific classes corresponding to active anomalies within the material or structure. Each class is linked to a distinct structural hazard level, ranging from safe operation to a critical loss of structural safety. Corresponding traffic control measures, including vehicle speed and weight restrictions, are dynamically introduced to maintain operational safety. To validate the scalability of the framework, this study synthesizes statistical data across a comprehensive fleet of 180 monitored bridge structures, backed by a predictive ARIMA time-series model that forecasts residual service life. The proposed methodology was experimentally validated on an A2 highway overpass, a vital component of the Łódź transport hub that facilitates north–south and east–west transit in Poland. The IAA system functions as a proactive diagnostic tool for infrastructure management agencies, preventing sudden, unforeseen structural failures. Ultimately, it enables the efficient and safe operation of a Smart City while ensuring that maintenance funds are rationally and optimally allocated. Full article

Automated vehicular traffic management in Latin American cities requires solutions capable of capturing, processing, and visualizing events through measurable operational update intervals. Conventional automatic number plate recognition (ANPR) pipelines can return plate text while leaving the visual adequacy of the associated crop unassessed and disconnected from downstream cloud persistence, alerts, and monitoring. Because this separation can propagate visually unreliable evidence into operational records, a unified workflow is needed to evaluate plate-crop legibility before the event is exposed to operators. This work presents a three-phase methodology, applied to the SAVH system (Sistema de Aforo Vehicular, Vehicle Counting System), which integrates a Dahua ANPR camera (Zhejiang Dahua Vision Technology Co., Ltd., Hangzhou, China) with a cloud architecture on Amazon Web Services (AWS). The camera captures the vehicle and performs textual reading of the license plate, sending vehicle notifications directly to the FastAPI service deployed on Amazon EC2. This service extracts the visual evidence and runs the YOLOv8n classification variant (YOLOv8n–CLS), which classifies the legibility of the plate crop into two classes: legible plate and non-legible plate. Structured events and visual evidence are persisted in managed storage services, and a serverless function serves the web dashboard queries through an application programming interface (API) managed by Amazon API Gateway. The model was trained on a relabeled dataset derived from the public LPLCv2 collection, split into training, validation, and test subsets. Evaluation on 720 independent images from the test set achieved 97.78% overall accuracy, with 97.75% macro precision, 97.82% macro recall, 97.78% macro F1-score, and an AUC of 0.9981. External validation on 2000 real Guayaquil images achieved 86.10% accuracy, 85.84% macro F1-score, and an AUC of 0.9742. The external results show a performance gap consistent with domain shift and motivate cautious interpretation of deployment results. The contribution is the integration and evaluation methodology rather than a new neural architecture: YOLOv8n–CLS, FastAPI, and the AWS services are existing components assembled into a documented operational workflow. Full article

Cultural ecosystem services (CES) are widely measured but rarely attributed to the specific landscape elements that generate them. We coupled element-level image recognition with service-level text analysis across 20,447 reviews and 18,997 photographs from three social media platforms covering 15 national-, provincial-, and municipal-level forest parks in Guangzhou, China (2020–2024). A 2660-term dictionary quantified nine CES; a fine-tuned deep learning classifier identified 28 landscape elements; multiple correspondence analysis described the element-service structure and ridge regression tested associations within four case parks. Natural elements aligned with ecological, aesthetic, and inspirational services and built elements with cultural, social, and wellness services, but two results qualify that division. First, individual elements were associated with different services in opposite directions: seasonal forest with higher aesthetic appreciation but lower recreation, water features with higher aesthetic value but lower inspiration. Second, the mapping differed across the four case parks rather than holding constant; in the municipal case park, only built facilities positively predicted social interaction. These four parks are illustrative exemplars rather than representative samples of their tiers. Dynamic biological elements (birds 0.43%, insects 0.12%, fish 0.08%) ranked lowest of all 28 elements. These are descriptive associations awaiting mechanistic explanation; on that reading, planning for CES would be better organized around intended services than element inventories, calibrated to the individual park. Full article

As a road repair material, emulsified asphalt offers advantages such as convenient construction, good fluidity, and environmental safety. However, its relatively low strength limits its application range, making performance enhancement a key research focus. In this study, waterborne epoxy resin (WER) was used to modify emulsified asphalt, and the preparation process and performance were systematically investigated. Three types of waterborne epoxy systems were selected, and through compatibility, film-forming performance, and bonding strength tests, the JT waterborne epoxy system was identified as having the best overall performance, with an optimal epoxy-to-curing-agent ratio of 1:0.6. Modified emulsified asphalts with different proportions of WER and styrene–butadiene rubber were prepared. Using fluorescence microscopy, image recognition techniques, and multiple experimental evaluations, the distribution of epoxy resin in the emulsified asphalt was quantitatively analyzed. The results show that the addition of WER significantly improves the bonding strength of emulsified asphalt, with the fastest rate of increase observed in the 5−10% range. However, a comprehensive evaluation considering microstructure uniformity, rheological performance, and water resistance indicates that the optimal overall performance is achieved in the 10−12% range, and the WER content should strictly be controlled below 15% to avoid severe local agglomeration. Meanwhile, the modified water-boiling test reveals that the adhesion between WERAE and aggregates is significantly enhanced, implying a potentially improved resistance to moisture-induced damage under practical service conditions. The standard deviation of area results indicate that when the WER content exceeds 15%, local agglomeration occurs, which is unfavorable for strength development of the modified system; the distribution uniformity results further show that when the WER content is greater than 12%, it negatively affects the uniform dispersion of WER within the emulsified asphalt. Full article

Tourism has become a critical pathway for town construction, everyday-life improvement, and cultural revitalization. Yet, the mechanisms through which destination image is associated with town attraction remain insufficiently understood, particularly at the fine-grained town scale. Drawing on social media photographs and check-in records from 26 characteristic towns in Tianjin, China, this study deconstructs tourist destination image into image genes and examines their associations with town gravity. A VGG19-based image-recognition model was used to identify and aggregate 68 scene types into nine image-gene categories, while check-in data from Weibo and Little Red Book were used to measure destination gravity. The results show that uniqueness image, cultural custom genes, public space genes, sidewalk density, and POI mix are significantly and positively associated with town gravity, whereas animal genes exhibit a significant negative association. These findings provide an empirical basis for policymakers and planners to strengthen distinctive cultural representation, optimize public-space systems and service diversity, and promote the sustainable attractiveness of town destinations. Full article

Recently, the Internet of Things (IoT) has evolved into the Artificial Intelligence of Things (AIoT) through its combination with artificial intelligence (AI) technology and has become capable of providing intelligent services in all industrial sectors. Globally, energy consumption within buildings is continuously increasing alongside the advancement of IT and AI technologies. Since this increase is attributed to various causes—ranging from large-scale climate change to small-scale indoor environmental factors (air quality) and health factors—research aimed at reducing indoor energy consumption is actively underway. In particular, in the home environment where people spend a significant portion of their day, maintaining indoor air quality (IAQ) is critical for health, and energy conservation in heating, ventilation, and air conditioning (HVAC) systems is essential. In Korea, the number of single-person households is increasing and was expected to reach 36.1% of all households by 2024, leading people to live in increasingly smaller homes. This study aimed to verify residents using contactless facial recognition to prevent pandemics such as COVID-19 and to provide comfortable indoor air quality. Resident facial recognition was performed by identifying residents’ faces in images captured by the Pi camera using OpenCV’s Haar feature-based cascade classifier. Indoor air quality measurements were conducted in four indoor locations, measuring various environmental factors (PM_2.5, CO₂, etc.) based on environmental sensors and the IoT. Furthermore, to manage indoor air quality, AI was utilized based on the measurement data to classify the four spaces, with a success rate of 96%. Additionally, considering the indoor area of the experimental environment (97 m²), it was confirmed that operating a 70 W air purifier only when the resident is indoors can reduce power consumption by approximately 33–75% compared to running it 24 h a day. Full article

Federated learning provides a feasible way to support collaborative vehicle part recognition without sharing raw data across distributed vehicle service nodes. However, real vehicle scenarios exhibit spatiotemporal heterogeneity, where client distributions vary and new vehicle models, parts, and viewpoints emerge over time. Such heterogeneity causes catastrophic forgetting and degrades knowledge retention in federated continual learning. To address this problem, this paper proposes FedACA (Federated Continual Learning with Adaptive Class Anchors), a class-anchor-based federated continual learning method for vehicle part image classification. The method uses a frozen Vision Transformer backbone and introduces scene-aware prompt adaptation, adaptive class anchors, non-parametric global prototype selection, and class-aware prompt fusion. These modules stabilize class semantics, reduce feature drift, and improve cross-client knowledge alignment in a data-local federated setting with raw-data non-sharing; however, FedACA does not provide formal privacy guarantees. Experiments on a self-constructed 67-class multi-view vehicle-part dataset and CIFAR-100 show that, under the task-aware class-masking protocol, FedACA achieves final-stage average accuracies of 97.34% ± 0.72% and 95.71% ± 0.63%, respectively, over three independent random seeds, outperforming the evaluated federated continual learning baselines. These results demonstrate that FedACA improves recognition performance and historical knowledge retention under spatiotemporally heterogeneous federated continual learning settings. Full article

Quality inspection of imported saw-ginned cotton mainly involves the determination of color grade and impurity grade. Traditional manual grading and High Volume Instrument (HVI) testing are limited by subjectivity, insufficient accuracy, single-indicator measurement, and long inspection cycles. To address these limitations, this study developed a machine vision-based intelligent identification system for saw-ginned cotton quality grading. The system integrates a portable image acquisition box, a cloud-based intelligent recognition service, and a HarmonyOS-based mobile application. A total of 6363 saw-ginned cotton images were collected using the self-developed image acquisition device for model training and testing. Based on U-Net background segmentation, a dual-branch parallel recognition framework was established for cotton color grading and impurity grading. The CA-ResNet50 model, integrating ResNet50, the Efficient Channel Attention (ECA) mechanism, and the AdamW optimization strategy, was constructed for cotton color grade recognition. The AD-UNet model, incorporating Atrous Spatial Pyramid Pooling (ASPP)-based multi-scale contextual modeling and the DySample adaptive upsampling mechanism, was developed for impurity segmentation. In addition, the HarmonyOS-based mobile application supports information query, image acquisition, intelligent recognition, and data traceability. Experimental results showed that the CA-ResNet50 color grading model achieved an F₁-Score of 94.8%. Based on the AD-UNet impurity segmentation results and the calculated impurity area ratio, the accuracy of impurity grade determination reached 97.3%. The average cloud-based inference time for a single image was approximately 0.8 s, and the complete workflow, including sample flattening, image acquisition, and recognition, required approximately 10 min. The proposed system improves the accuracy, efficiency, objectivity, and traceability of saw-ginned cotton quality identification, providing technical support for rapid inspection and quality supervision of imported cotton. Full article

Ancient timber structures are important carriers of valuable cultural heritage, and their structural safety directly determines whether historic buildings can remain in safe service over time. Cracks represent one of the most widespread and important forms of damage in ancient timber structures. They can directly lead to cross-sectional weakening of structural members, degradation of load-bearing capacity, and the gradual development of overall structural safety risks. To address the limitations of existing crack assessment methods, such as strong subjectivity in weight determination, insufficient accuracy in grade boundary discrimination, and inadequate coupling with mechanical performance, this study proposes a crack safety assessment method for ancient timber structures based on an improved entropy–fuzzy matter-element model. A multi-dimensional evaluation index system is established, incorporating crack geometric characteristics, structural load-bearing capacity, and service time effects. A mechanically driven load-carrying capacity degradation index is introduced to quantitatively characterize the influence mechanism of crack propagation on structural performance deterioration. The entropy weight method is employed to objectively determine the weights of each indicator, and an asymmetric closeness degree is introduced to improve the traditional fuzzy matter-element model, thereby enhancing the stability and accuracy of safety grade classification. A case study of the Bawang Academy, Shenyang Jianzhu University, is conducted. Crack parameters are obtained using image recognition and three-dimensional laser scanning techniques, and a comprehensive structural safety assessment is performed. The results indicate that the proposed method can accurately reflect the actual damage distribution and deterioration level of the structure, providing a reliable theoretical basis and technical support for crack safety evaluation and preventive conservation of ancient timber structures. Full article

Lithium-ion batteries experience structural degradation during operation and storage, which can negatively impact performance, safety, and service life. Early identification of these degradation-induced structural changes is important for battery health assessment and reliability monitoring. This study proposes a deep learning-based framework for classifying the structural condition of 18650 lithium-ion batteries using X-ray micro-computed tomography (µCT) images. The proposed approach combines centroid-based core cropping, image normalization, three-slice stacking, and transfer learning using a fine-tuned InceptionResNet-V2 architecture. Three adjacent µCT slices are stacked into an RGB-like representation to preserve local three-dimensional structural information while maintaining compatibility with a two-dimensional convolutional neural network. The original classification head of InceptionResNet-V2 was replaced with a custom classification block consisting of dropout layers, fully connected layers, and a SoftMax classifier optimized for battery condition recognition. The framework was evaluated using four battery structural conditions: pristine, cycle-aged, calendar-aged, and thermally cycled cells. Experimental results demonstrated an overall classification accuracy of 96.62%, with a precision of 95.62%, sensitivity of 96.94%, specificity of 98.92%, and F1-score of 96.20%. Comparative analysis with previously reported battery imaging studies demonstrated that the proposed framework achieves competitive performance while addressing the challenging task of structural condition classification from µCT imagery. The results demonstrate the potential of combining advanced X-ray imaging and transfer learning for automated lithium-ion battery structural health assessment and degradation monitoring. Full article

Background and Clinical Significance: Cerebral amyloid angiopathy (CAA) is a neurovascular disorder characterized by the deposition of amyloid beta (Aβ) peptides within the walls of small-to-medium-sized cerebral vessels, leading to vascular fragility and an increased risk of lobar intracerebral hemorrhage (ICH), cognitive decline, and recurrent stroke. CAA is an important cause of spontaneous ICH in elderly patients and may be underrecognized, particularly when presenting with acute neurologic symptoms that mimic ischemic stroke. Early identification has significant implications for management, prognosis, and secondary prevention. Case Presentation: An 80-year-old male presented to the emergency department with incoherent speech, rambling, and severe headache concerning for acute stroke. His medical history was notable for a prior cerebrovascular accident, hypertension, diabetes mellitus, benign prostatic hyperplasia, and recent evaluation for dementia-like symptoms. Initial neuroimaging revealed a 3.2 cm intraparenchymal hemorrhage in the left occipital lobe with surrounding edema. Subsequent MRI demonstrated a lobar hemorrhage pattern suggestive of CAA based on imaging findings and clinical context. The patient was admitted to the intensive care unit (ICU) for close neurologic monitoring. He remained hemodynamically stable with no new motor or sensory deficits. Over a three-day hospital course, his speech and visual deficits improved. Blood pressure was carefully controlled, and repeat imaging demonstrated stable hemorrhage without progression. He was diagnosed with probable CAA and discharged home with supportive services. Conclusions: This case highlights the importance of considering cerebral amyloid angiopathy in elderly patients presenting with spontaneous lobar intracerebral hemorrhage and cognitive symptoms. Prompt recognition and appropriate neuroimaging are critical for diagnosis, risk stratification, and guiding management. Full article

We present FLIC, a real-world annotated dataset designed for the visual estimation of food leftovers in canteens and other collective catering environments using standard 2D RGB imagery. Collected over 22 days in an operational university canteen, the dataset includes 401 paired image acquisitions of full and leftover trays, each associated with pixel-precise semantic segmentation masks and physically measured food mass. The goal is to support research on the estimation of leftover food mass from tray images, a task that has received limited attention compared to pre-consumption food recognition, despite its relevance for sustainability and operational decision making in food services. Unlike existing food datasets, FLIC jointly provides paired before–after visual observations and reliable mass ground truth, enabling quantitative analysis of food leftovers under realistic conditions without relying on depth or multi-view information. To demonstrate the dataset’s applicability, we rely on the concept of digital density, relating pixel area to food mass, and implement a lightweight, interpretable baseline mass estimation pipeline. This includes an automatic food/no-food segmentation stage, evaluated across multiple deep learning models (U-Net, DABNet, DINOv2+FeatUp, and SAM), followed by an assisted food recognition stage that leverages the fixed daily menu to map broad user input (e.g., “first course” vs. “second course”) to a specific food class. Experimental results highlight both the potential and the intrinsic challenges of visual food leftover estimation. Full article

Metal pipelines may have various defects due to long-term service, corrosion, external strikes, etc. Traditional closed-circuit television (CCTV) inspection techniques are capable of detecting these defects. However, substantial human resources are required and the detection results are subjected to human subjectivity. Thus, this study develops a deep learning-based intelligent defect detection model for metal pipeline images. CNNs (convolutional neural networks) are utilized to automatically extract defects, which may mitigate the interference of subjective factors and enhance the recognition capability of the defects in pipelines. The proposed model builds upon the original YOLOv8n model by incorporating the SCSA (Spatial and Channel Synergistic Attention) mechanism, LskBlock, and SlideLoss function, respectively. These enhancements improve the ability to detect small targets, increase recognition accuracy, and facilitate global optimization, respectively. The developed YOLO-LSS (YOLOv8n-LskBlock-SlideLoss-SCSA) model is compared with other deep learning models characterized by the following metrics: mAP50, mAP50:95, precision, recall rate, and F1-score, respectively. It is found that mAP50 achieves 79.05% (+2.86%), mAP50:95 53.7% (+7.19%), precision 81.6% (+5.30%), recall rate 75.5% (+2.90%), and F1-score 78.4 (+4.01), indicating that the proposed model effectively enhances the capability of detecting internal defects in pipelines. Full article

Pachydermodactyly (PDD) is a benign, non-inflammatory, non-erosive digital fibromatosis characterized by progressive, asymptomatic, periarticular soft tissue thickening predominantly affecting the proximal interphalangeal (PIP) joints. Additional localizations, including the palm and the distal interphalangeal (DIP) or metacarpophalangeal (MCP) joints, have also been reported. The etiology of PDD is multifactorial, encompassing idiopathic, trauma-induced, genetic, and behavioral factors. Objective: The aim of this report is to describe the clinical, imaging, and laboratory features of pachydermodactyly in two male adolescents initially referred to a pediatric rheumatology service for suspected juvenile idiopathic arthritis (JIA), highlighting the diagnostic pitfalls and differentiation criteria from inflammatory arthritis. In addition, a narrative review of cases published from 1975 to 2025 is presented to contextualize our findings within the broader literature. Results: Two male adolescents (aged 13 years and 5 months and 16 years) presented with progressive, painless periarticular soft tissue swelling of the PIP joints, initially raising suspicion for JIA. Comprehensive evaluation identified characteristic features of PDD in both patients, with complete absence of inflammatory markers, synovitis, or osseous changes. Case 1 was classified as mono-PDD and Case 2 as classic, trauma-associated PDD with atypical perilesional hypopigmentation, requiring MRI for definitive exclusion of infiltrative pathology. A narrative review of 15 representative published cases from 2014 to 2025 is presented, demonstrating persistent underdiagnosis and consistent misclassification as JIA across multiple clinical settings and geographic regions. Conclusions: PDD should be considered in the differential diagnosis of any adolescent presenting with painless digital swelling. Its recognition as a benign, non-inflammatory entity is essential to prevent unnecessary diagnostic procedures and immunosuppressive therapy. Clinical awareness and multidisciplinary assessment remain the cornerstones of accurate diagnosis and appropriate management. Full article

This paper proposes an intelligent stress detection method based on convolutional neural networks and the DeepFace framework, addressing the challenges of increasingly prominent global mental health issues and the limitations of traditional psychological services in terms of early warning latency and coverage. A three-level cascaded strategy combining RetinaFace, MTCNN, and OpenCV is first employed for face detection and localization, and facial expression features are extracted via the DeepFace framework. By integrating Russell’s valence–arousal model with Lazarus’s cognitive appraisal theory, an emotion–stress mapping rule is constructed to convert seven-category emotion probability distributions into 1–5 scale stress values. The method employs a cloud–edge collaborative flow, with feature extraction performed at the edge and original images promptly destroyed to mitigate privacy risks. Experiments on public expression datasets indicate that the method achieves above 99% face detection accuracy, 84.99% emotion recognition accuracy, and 86.09% stress assessment consistency grounded in the emotion–stress mapping rule, with an average response time per frame of approximately 200 ms. Based on 233 multi-scenario surveys, some respondents show limited stress self-awareness, suggesting traditional self-reporting may have blind spots, and thus this method serves as a useful supplement. Full article