RESUMEN

As condições fitossanitárias de plantas arbóreas podem ser utilizadas para caracterizar comunidades vegetais, indicando condições de qualidade estrutural do componente vegetal. Assim, ambientes alterados antropicamente podem representar uma ameaça à fitossanidade. O objetivo deste estudo foi averiguar as características fitossanitárias do componente arbóreo em um trecho de 400 metros de extensão ao longo da linha férrea localizada no município de Três Barras, estado de Santa Catarina, Brasil. Foram registradas 33 espécies arbóreas, 29 gêneros e 19 famílias. Os índices ecológicos avaliados foram a abundância, densidade, riqueza e equabilidade. Foram avaliados 190 indivíduos em relação a qualidade da copa, grau de infestação de cipós e sanidade da árvore. Embora a qualidade da copa e a sanidade sejam majoritariamente boas, houve um relativo alto número de infestação de cipós. Tal ocorrência pode ser devido à condição de borda em que as plantas se encontram. Os bons índices ecológicos aliados ao baixo número de espécies arbóreas exóticas também indicam boas condições ecológicas e de fitossanidade local. Contudo, são necessários mais estudos (p. ex. florísticos e fitossociológicos) na área. A arborização urbana das proximidades aliada à formação de corredores ecológicos que liguem os fragmentos à Floresta Nacional de Três Barras pode ser uma medida de conservação e regeneração a ser explorada.

Phytosanitary conditions of tree plants can be used to characterize plant communities, indicating structural quality conditions of the plant component. Thus, anthropically altered environments may pose a threat to plant health. The objective of this study was to investigate the phytosanitary and ecological condition of the tree component in a stretch of 400 meters along the railway line located in the municipality of Três Barras, Santa Catarina state, Brazil. Thirty-three tree species were recorded, in addition to 54 taxonomically unidentified individuals. The ecological indices evaluated were abundance, density, richness and evenness. 190 individuals were evaluated in terms of crown quality, Abstract degree of liana infestation and tree health. Although canopy quality and health are mostly good, there was a relatively high number of vine infestations. Such an occurrence may be due to the edge condition in which the plants are located. The good ecological indices combined with the low number of exotic tree species also indicate good ecological conditions and local plant health. However, more studies are needed in the area. Urban afforestation, combined with the formation of ecological corridors that connect the fragments to the Três Barras National Forest, can be a conservation and regeneration measure to be explored.

RESUMEN

Dragonflies are some of the most stable and maneuverable flying organisms. To explore the mechanism of how dragonfly leading edges enhance flight lift, this article conducts a detailed study on the leading edge veins and the microstructures on them of dragonfly wings. Observations have discovered the special leading edge vein and the regularly distributed microstructures on the leading edge vein. A biomimetic model has been established, and computational fluid dynamics (CFD) simulation analysis has been conducted on the biomimetic model. The analysis explores the effects of microstructure characteristics, distribution patterns, and positions on the aerodynamic characteristics of dragonfly gliding. The analysis shows that the leading edge structure influences the incoming flow, simultaneously promotes the formation of the leading edge vortex (LEV), and increases the lift-to-drag ratio by up to 4%. A wing prototype featuring biomimetic microstructures is subsequently fabricated and tested in wind tunnel experiments. Compared with a control group without leading edge structures, the airflow passing through the biomimetic structures is influenced by the shape and arrangement of these structures. The smoother transition of the leading edge vein's shape facilitates the flow of air. The microstructures primarily filter and accelerate the airflow. The spacing of the microstructures affects the stability of the airflow, thereby influencing aerodynamic performance. Additionally, the middle-row arrangement of microstructures is more beneficial for gliding conditions, while the upper-row arrangement is more advantageous for flapping conditions. These findings enhance our understanding of insect wings and advance micro aerial vehicle applications. RESEARCH HIGHLIGHTS: This study observed the leading-edge veins and microstructures of dragonfly wings in detail. Using a biomimetic model and computational fluid dynamics (CFD) simulations, it was found that these leading-edge structures promote the formation of leading-edge vortices (LEV), increasing the lift-to-drag ratio by up to 4%. Wind tunnel experiments demonstrated that wings with biomimetic microstructures significantly improved airflow smoothness and lift compared with control wings. Additionally, the arrangement of microstructures greatly affects airflow stability and aerodynamic performance, with middle-row arrangements being more beneficial for gliding and upper-row arrangements for flapping conditions. These findings enhance our understanding of insect wings and provide innovative guidance for designing efficient micro aerial vehicles.

RESUMEN

BACKGROUND: TRILUMINATE Pivotal is a prospective, randomized, controlled study of patients with severe tricuspid regurgitation (TR). Venous congestion due to TR may lead to end-organ dysfunction and failure. The potential to reverse or stop further deterioration in end-organ function is an important goal of treatment. OBJECTIVES: Examine changes in end-organ function after tricuspid transcatheter edge-to-edge repair (TEER) and assess the association of baseline end-organ function with heart failure (HF) hospitalizations and mortality. METHODS: Subjects were randomized 1:1 to either the TEER group (TriClip™ System + medical therapy) or Control group (medical therapy alone). Laboratory assessments and TR grading were performed at baseline and at all follow-up visits (discharge, 30 days, 6 months, and 12 months). An independent echocardiography core laboratory assessed TR severity and an independent clinical events committee adjudicated adverse events. RESULTS: 572 subjects were enrolled and randomized (285 TEER, 287 Control). Patients with moderate to severe end-organ impairment (eGFR <45 ml/min/1.73m2 or MELD-XI >15) at baseline had increased incidence of HF hospitalization and death through 12 months, regardless of treatment. There were no statistically significant differences between TEER and Control in eGFR or MELD-XI at 12 months. In subgroup analyses examining only successful TEER patients (moderate or less TR at discharge) compared to control patients, as well as when censoring patients with normal baseline values, both eGFR (+3.55 ± 1.04 vs 0.07 ± 1.10 , p=0.022) and MELD-XI (-0.52 ± 0.18 vs 0.34 ± 0.18, p=0.0007) improved. CONCLUSIONS: Baseline end-organ function were associated with HF hospitalization and death in patients with severe TR. At 12 months, eGFR and MELD-XI scores were not statistically significantly different between the overall TEER and Control groups. In patients who had successful TEER, statistically significant, yet small, favorable changes occurred for both eGFR and MELD-XI. Further investigation is needed to assess whether these changes in end-organ function after successful TEER are clinically meaningful and reduce HF hospitalization or death.

RESUMEN

Background: Transoesophageal echocardiography is rarely reported as a possible cause of aortic dissection during the transcatheter edge-to-edge repair procedure. Herein, we present a case of type B aortic dissection following the transcatheter mitral valve edge-to-edge repair procedure, most likely related to the transoesophageal echocardiography probe. Case summary: A 68-year-old Chinese man complained of exertional dyspnoea lasting over 2 years and had been diagnosed with severe mitral regurgitation. He was admitted to our hospital for the treatment of severe mitral regurgitation with transcatheter edge-to-edge repair. One MitraClip XTR (Abbott Vascular) was successfully implanted under the guidance of active transoesophageal echocardiography, and the mitral regurgitation became trace. However, the patient complained of persistent back pain after the treatment, and computed tomography angiography revealed a type B aortic dissection in the descending aorta. After 2 weeks of unsuccessful conservative treatment, he successfully underwent endovascular stenting and was discharged from the hospital. The patient recovered well and remained event free during the 6-month follow-up. Discussion: Herein, we presented a rare complication following transcatheter mitral valve edge-to-edge repair that was most likely related to the transoesophageal echocardiography probe-type B aortic dissection. We postulated that repetitive flexion of the transoesophageal echocardiography probe led to compression-induced injury to the descending aorta wall at the mid-oesophageal level, which was the most probable aetiology of type B aortic dissection. Although this complication is rare, it is potentially fatal and therefore needs attention.

RESUMEN

Aims: Tricuspid regurgitation (TR) is associated with heart failure (HF) and reduced survival. Within a short-time period, transcatheter tricuspid valve repair or replacement (TTVR/TTVr) for TR has evolved from innovation to clinical reality. The present study's aim is to provide 1-year results between TR patients treated with TTVR and TTVr compared with untreated patients, in terms of cardiac survival, rehospitalization, right-side HF symptom development, and New York Heart Association (NYHA) improvement. Methods and results: Seventy-seven patients (pts) have been prospectively inserted into a dedicated database from January 2020 till January 2023. Twenty-six patients (33.8%) have been treated with TTVR/r [treated group (TG)], and 51 pts (66.2%) have been left untreated with medical therapy optimization [untreated group (UNTG)]. Analysing the cardiac death between the two groups, there was a significant statistical difference since TG has less incidence of exitus in the general population (P = 0.05). Concerning HF hospitalization, TG has a lower incidence with a P = 0.005. In TG, there was a significant improvement in NYHA class at follow-up (FUP) (P = 0.001) as well as an improvement in right-side HF symptoms (P = 0.001). Conclusion: This study shows that treatment in the case of TR with right-side HF has a positive impact on cardiac death and HF hospitalization at 1 year. And there is a significant improvement in clinical and echocardiographic status at FUP in the TG.

RESUMEN

Objective.The objective of this study is to explore the capabilities of photon-counting computed tomography (PCCT) in simultaneously imaging and differentiating materials with close atomic numbers, specifically barium (Z= 56) and iodine (Z= 53), which is challenging for conventional computed tomography (CT).Approach.Experiments were conducted using a bench-top PCCT system equipped with a cadmium zinc telluride detector. Various phantom setups and contrast agent concentrations (1%-5%) were employed, along with a biological sample. Energy thresholds were tuned to the K-edge absorption energies of barium (37.4 keV) and iodine (33.2 keV) to capture multi-energy CT images. K-edge decomposition was performed using K-edge subtraction and principal component analysis (PCA) techniques to differentiate and quantify the contrast agents.Main results.The PCCT system successfully differentiated and accurately quantified barium and iodine in both phantom combinations and a biological sample, achieving high correlations (R2≈1) between true and reconstructed concentrations. PCA outperformed K-edge subtraction, particularly in the presence of calcium, by providing superior differentiation between barium and iodine.Significance.This study demonstrates the potential of PCCT for reliable, detailed imaging in both clinical and research settings, particularly for contrast agents with similar atomic numbers. The results suggest that PCCT could offer significant improvements in imaging quality over conventional CT, especially in applications requiring precise material differentiation.

Asunto(s)

RESUMEN

A gastrogastric fistula is a delayed complication of the endoscopic ultrasound-directed transgastric endoscopic retrograde cholangiopancreatography. Endoscopic closure of these fistulae poses a significant challenge, and surgical intervention may be required in some patients. In this study, we discuss the case of a 69-year-old woman with persistent fistula following the endoscopic ultrasound-directed transgastric endoscopic retrograde cholangiopancreatography procedure. Despite the failure of conventional advanced endoscopic fistula closure methods, successful closure of the fistula was achieved using a postinfarct ventricular septal defect occluder.

RESUMEN

Organic cocrystals, representing one type of new functional materials, have gathered significant interest in various engineering areas. Owing to their diverse stacking modes, rich intermolecular interactions and abundant functional components, the physicochemical properties of organic cocrystals can be tailored to meet different requirements and exhibit novel characteristics. The past few years have witnessed the rapid development of organic cocrystals in both fundamental characteristics and various applications. Beyond the typical properties like ambipolarity, emission tuning ability, ferroelectricity, etc. that are previously well demonstrated, many novel impressive and cutting-edge properties and applications of cocrystals also emerge and advance recently. Especially during the nearest five years, photothermal conversion, room-temperature phosphorescence, thermally activated delay fluorescence, circularly polarized luminescence, organic solid-state lasers, near-infrared sensing, photocatalysis, batteries, and stimuli responses have been reported. In this minireview, these new properties are carefully summarized. Besides, some neoteric architecture and methodologies, such as host-guest structures and machine learning-based screening, are introduced. Finally, the potential future developments and expectations for organic cocrystals are discussed for further investigation on multiple functions and applications.

RESUMEN

Soil conservation adheres to various United Nations Sustainable Development Goals while in Brazil is a constitutional obligation. To attain the goals and fulfil the obligation, laws, policies, governance and science must be imbricated to deliver suitable conservation solutions for the long term, namely appropriate to positively influence other downstream chains such as the food chain. However, in Brazil, a major world producer and exporter of food, weaknesses were recently diagnosed by judicial authorities concerning soil governance and coordinated land use policies. Integrated scientific assessments on soil conservation and mitigation of degraded soil are also lacking in this country. This was enough motivation and the purpose to present here a holistic view over the soil conservation agenda and promoting policies in Brazil, based on a literature review that followed the guidelines and criteria of PRISMA approach. We termed this analysis a review hinged on "edge-to-edge" science contributions for two reasons. Firstly, the intent of retrieving from the recently published literature solely papers centered on a relevant soil conservation topic (e.g., soil characterization, here called an "edge") but with complementary analyses over boundary topics (frontier "edges", such as soil degradation). Secondly, the intent of underlining the urgency to assist decision-makers with scientific evidence in all dimensions of the soil conservation agenda ("edge-to-edge" science), namely soil characterization (e.g., quality reference values), soil degradation assessment (e.g., anthropogenic-related soil erosion or contamination), soil degradation consequences focused on the carbon cycle (e.g., net CO2 emissions and climate warming), sustainable management practices and production systems (e.g., no-tillage agriculture and integrated crop-livestock-forestry systems), and scientific evaluation of existing laws as well as of governance and policy programs with potential implications on soil quality (e.g., the Forest Code). Thus, this literature review addressed all these topics following a multidisciplinary discourse, which produced an extensive but comprehensive document about soil conservation in Brazil.

RESUMEN

In recent years, decentralized machine learning has emerged as a significant advancement in biomedical applications, offering robust solutions for data privacy, security, and collaboration across diverse healthcare environments. In this review, we examine various decentralized learning methodologies, including federated learning, split learning, swarm learning, gossip learning, edge learning, and some of their applications in the biomedical field. We delve into the underlying principles, network topologies, and communication strategies of each approach, highlighting their advantages and limitations. Ultimately, the selection of a suitable method should be based on specific needs, infrastructures, and computational capabilities.

RESUMEN

The discovery of the quantum Hall effect has established the foundation of the field of topological condensed matter physics. An amazingly accurate quantization of the Hall conductance, now enshrined in quantum metrology, is stable against any reasonable perturbation due to its topological protection. Conversely, the latter implies a form of censorship by concealing any local information from the observer. The spatial distribution of the current in a quantum Hall system is such a piece of information, which, thanks to spectacular recent advances, has now become accessible to experimental probes. It is an old question whether the original and intuitively compelling theoretical picture of the current, flowing in a narrow channel along the sample edge, is the physically correct one. Motivated by recent experiments locally imaging quantized current in a Chern insulator (Bi, Sb)[Formula: see text]Te[Formula: see text] heterostructure [Rosen et al., Phys. Rev. Lett. 129, 246602 (2022); Ferguson et al., Nat. Mater. 22, 1100-1105 (2023)], we theoretically demonstrate the possibility of a broad "edge state" generically meandering away from the sample boundary deep into the bulk. Further, we show that by varying experimental parameters one can continuously tune between the regimes with narrow edge states and meandering channels, all the way to the charge transport occurring primarily within the bulk. This accounts for various features observed in, and differing between, experiments. Overall, our findings underscore the robustness of topological condensed matter physics, but also unveil the phenomenological richness, hidden until recently by the topological censorship-most of which, we believe, remains to be discovered.

RESUMEN

The primary objective of this study was to develop a custom algorithm to assess three-dimensional (3D) acetabular coverage of the femoral head based on surface models generated from computed tomography (CT) imaging. The secondary objective was to apply this algorithm to asymptomatic young adult hip joints to assess the regional 3D acetabular coverage variability and understand how these novel 3D metrics relate to traditional two-dimensional (2D) radiographic measurements of coverage. The algorithm developed automatically identifies the lateral- and medial-most edges of the acetabular lunate at one-degree intervals around the acetabular rim based on local radius of curvature. The acetabular edges and the center of a best-fit sphere to the femoral head are then used to compute the mean 3D subchondral arc angles and hip joint coverage angles in five acetabular octants. This algorithm was applied to hip models generated from pelvis/hip CT imaging or abdomen/pelvis CT angiograms of 50 patients between 17 and 25 years of age who had no history of congenital or developmental hip pathology, neuromuscular conditions, or bilateral pelvic and/or femoral fractures. Corresponding 2D acetabular coverage measures of lateral center edge angle (LCEA) and acetabular arc angle (AAA) were assessed on the patients' clinical or digitally reconstructed radiographs. The 3D subchondral arc angle in the superior region (58.0 [54.6-64.8] degrees) was significantly higher (p < 0.001) than all other acetabular subregions. The 3D hip joint coverage angle in the superior region (26.2 [20.7-28.5] degrees) was also significantly higher (p < 0.001) than all other acetabular subregions. 3D superior hip joint coverage angle demonstrated the strongest correlation with 2D LCEA (r = 0.649, p < 0.001), while 3D superior-anterior subchondral arc angle demonstrated the strongest correlation with 2D AAA (r = 0.718, p < 0.001). The 3D coverage metrics in the remaining acetabular regions did not strongly correlate with typical 2D radiographic measures. The discrepancy between standard 2D measures of radiographic acetabular coverage and actual 3D coverage identified on advanced imaging indicates potential discord between anatomic coverage and the standard clinical measures of coverage on 2D imaging. As 2D measurement of acetabular coverage is increasingly used to guide surgical decision-making to address acetabular deformities, this work would suggest that 3D measures of acetabular coverage may be important to help discriminate local coverage deficiencies, avoid inconsistencies resulting from differences in radiographic measurement techniques, and provide a better understanding of acetabular coverage in the hip joint, potentially altering surgical planning and guiding surgical technique.

RESUMEN

Skin cancer poses a significant global health concern necessitating innovative treatment approaches. This review explores the potential of vesicle nanoformulation incorporating EA (edge activators) to overcome barriers in skin cancer management. The skin's inherent protective mechanisms, specifically the outermost layer called the stratum corneum and the network of blood arteries, impede the permeation of drugs. Phospholipid-enriched EA based nanoformulation offer a promising solution by enhancing drug penetration through skin barriers. EAs like Span 80, Span 20, Tween 20, and sodium cholate etc., enhance vesicles deformability, influencing drug permeation. This review discusses topical application of drugs treat skin cancer, highlighting challenges connected with the conventional liposome and the significance of using EA-based nanoformulation in overcoming these challenges. Furthermore, it provides insights into various EA characteristics, critical insights, clinical trials, and patents. The review also offers a concise overview of composition, preparation techniques, and the application of EA-based nanoformulation such as transfersomes, transliposomes, transethosomes, and transniosomes for delivering drugs to treat skin cancer. Overall, this review intends to accelerate the development of formulations that incorporate EA, which would further improve topical drug delivery and enhance therapeutic outcomes in skin cancer treatment.

RESUMEN

INTRODUCTION: Vehicles play an important role in pedestrian injury risk in crashes. This study examined the association between vehicle front-end geometry and the risk of fatal pedestrian injuries in motor vehicle crashes. METHOD: A total of 17,897 police-reported crashes involving a single passenger vehicle and a single pedestrian in seven states were used in the analysis. Front-end profile parameters of vehicles (2,958 vehicle makes, series, and model years) involved in these crashes were measured from vehicle profile photos, including hood leading edge height, bumper lead angle, hood length, hood angle, and windshield angle. We defined a front-end-shape indicator based on the hood leading edge height and bumper lead angle. Logistic regression analysis evaluated the effects of these parameters on the risk that a pedestrian was fatally injured in a single-vehicle crash. RESULTS: Vehicles with tall and blunt, tall and sloped, and medium-height and blunt front ends were associated with significant increases of 43.6%, 45.4%, and 25.6% in pedestrian fatality risk, respectively, when compared with low and sloped front ends. There was a significant 25.1% increase in the risk if a hood was relatively flat as defined in this study. A relatively long hood and a relatively large windshield angle were associated with 5.9% and 10.7% increases in the risk, respectively, but the increases were not significant. CONCLUSIONS: Vehicle front-end profiles that were significantly associated with increased pedestrian fatal injury risk were identified. PRACTICAL APPLICATIONS: Automakers can make vehicles more pedestrian friendly by designing vehicle front ends that are lower and more sloped. The National Highway Traffic Safety Administration (NHTSA) can consider evaluations that account for the growing hood heights and blunt front ends of the vehicle fleet in the New Car Assessment Program or regulation.

Asunto(s)

RESUMEN

Insole blanking production technology plays a vital role in contemporary machining and manufacturing industries. Existing insole blanking production models have limitations because most robots are required to accurately position the workpiece to a predetermined location, and special auxiliary equipment is usually required to ensure the precise positioning of the robot. In this paper, we present an adaptive blanking robotic system for different lighting environments, which consists of an industrial robot arm, an RGB-D camera configuration, and a customized insole blanking table and mold. We introduce an innovative edge detection framework that utilizes color features and morphological parameters optimized through particle swarm optimization (PSO) techniques to Adaptive recognition of insole edge contours. A path planning framework based on FSPS-BIT* is also introduced, which integrates the BIT* algorithm with the FSPS algorithm for efficient path planning of the robotic arm.

RESUMEN

Recent improvements in artificial intelligence and computer vision make it possible to automatically detect abnormalities in medical images. Skin lesions are one broad class of them. There are types of lesions that cause skin cancer, again with several types. Melanoma is one of the deadliest types of skin cancer. Its early diagnosis is at utmost importance. The treatments are greatly aided with artificial intelligence by the quick and precise diagnosis of these conditions. The identification and delineation of boundaries inside skin lesions have shown promise when using the basic image processing approaches for edge detection. Further enhancements regarding edge detections are possible. In this paper, the use of fractional differentiation for improved edge detection is explored on the application of skin lesion detection. A framework based on fractional differential filters for edge detection in skin lesion images is proposed that can improve automatic detection rate of malignant melanoma. The derived images are used to enhance the input images. Obtained images then undergo a classification process based on deep learning. A well-studied dataset of HAM10000 is used in the experiments. The system achieves 81.04% accuracy with EfficientNet model using the proposed fractional derivative based enhancements whereas accuracies are around 77.94% when using original images. In almost all the experiments, the enhanced images improved the accuracy. The results show that the proposed method improves the recognition performance.

Asunto(s)

RESUMEN

To address the issues of low survivability and communication efficiency in wireless sensor networks caused by frequent node movement or damage in highly dynamic and high-mobility battlefield environments, we propose a dynamic topology optimization method based on a virtual backbone network. This method involves two phases: topology reconstruction and topology maintenance, determined by a network coverage threshold. When the coverage falls below the threshold, a virtual backbone network is established using a connected dominating set (CDS) and non-backbone node optimization strategies to reconstruct the network topology, quickly restore network connectivity, effectively improve network coverage, and optimize the network structure. When the coverage is above the threshold, a multi-CDS scheduling algorithm and slight position adjustments of non-backbone nodes are employed to maintain the network topology, further enhancing network coverage with minimal node movement. Simulations demonstrate that this method can improve coverage and optimize network structure under different scales of network failures. Under three large-scale failure operational scenarios where the network coverage threshold was set to 80%, the coverage was enhanced by 26.12%, 15.88%, and 13.36%, and in small-scale failures, the coverage was enhanced by 7.55%, 4.90% and 7.84%.

RESUMEN

Mobile Edge Computing (MEC) is crucial for reducing latency by bringing computational resources closer to the network edge, thereby enhancing the quality of services (QoS). However, the broad deployment of cloudlets poses challenges in efficient network slicing, particularly when traffic distribution is uneven. Therefore, these challenges include managing diverse resource requirements across widely distributed cloudlets, minimizing resource conflicts and delays, and maintaining service quality amid fluctuating request rates. Addressing this requires intelligent strategies to predict request types (common or urgent), assess resource needs, and allocate resources efficiently. Emerging technologies like edge computing and 5G with network slicing can handle delay-sensitive IoT requests rapidly, but a robust mechanism for real-time resource and utility optimization remains necessary. To address these challenges, we designed an end-to-end network slicing approach that predicts common and urgent user requests through T distribution. We formulated our problem as a multi-agent Markov decision process (MDP) and introduced a multi-agent soft actor-critic (MAgSAC) algorithm. This algorithm prevents the wastage of scarce resources by intelligently activating and deactivating virtual network function (VNF) instances, thereby balancing the allocation process. Our approach aims to optimize overall utility, balancing trade-offs between revenue, energy consumption costs, and latency. We evaluated our method, MAgSAC, through simulations, comparing it with the following six benchmark schemes: MAA3C, SACT, DDPG, S2Vec, Random, and Greedy. The results demonstrate that our approach, MAgSAC, optimizes utility by 30%, minimizes energy consumption costs by 12.4%, and reduces execution time by 21.7% compared to the closest related multi-agent approach named MAA3C.

RESUMEN

Of the 100,000 railroad bridges in the United States, 50% are over 100 years old. Many of these bridges do not meet the minimum vertical clearance standards, making them susceptible to impact from over-height vehicles. The impact can cause structural damage and unwanted disruption to railroad bridge services; rapid notification of the railroad authorities is crucial to ensure that the bridges are safe for continued use and to affect timely repairs. Therefore, researchers have developed approaches to identify these impacts on railroad bridges. Some recent approaches use machine learning to more effectively identify impacts from the sensor data. Typically, the collected sensor data are transmitted to a central location for processing. However, the challenge with this centralized approach is that the transfer of data to a central location can take considerable time, which is undesirable for time-sensitive events, like impact detection, that require a rapid assessment and response to potential damage. To address the challenges posed by the centralized approach, this study develops a framework for edge implementation of machine-learning predictions on wireless smart sensors. Wireless sensors are used because of their ease of installation and lower costs compared to their wired counterparts. The framework is implemented on the Xnode wireless smart sensor platform, thus bringing artificial intelligence models directly to the sensor nodes and eliminating the need to transfer data to a central location for processing. This framework is demonstrated using data obtained from events on a railroad bridge near Chicago; results illustrate the efficacy of the proposed edge computing framework for such time-sensitive structural health monitoring applications.