Structural basis of a transcription pre-initiation complex on a divergent promoter.

Most eukaryotic promoter regions are divergently transcribed. As the RNA polymerase II pre-initiation complex (PIC) is intrinsically asymmetric and responsible for transcription in a single direction, it is unknown how divergent transcription arises. Here, the Saccharomyces cerevisiae Mediator complexed with a PIC (Med-PIC) was assembled on a divergent promoter and analyzed by cryoelectron microscopy. The structure reveals two distinct Med-PICs forming a dimer through the Mediator tail module, induced by a homodimeric activator protein localized near the dimerization interface. The tail dimer is associated with ∼80-bp upstream DNA, such that two flanking core promoter regions are positioned and oriented in a suitable form for PIC assembly in opposite directions. Also, cryoelectron tomography visualized the progress of the PIC assembly on the two core promoter regions, providing direct evidence for the role of the Med-PIC dimer in divergent transcription.

Ectopic expression in commonly used transgenic Drosophila GAL4 driver lines.

Transgenic tools such as the GAL4/UAS system in Drosophila have been used extensively to induce spatiotemporally controlled changes in gene expression and tissue-specific expression of a range of transgenes. We previously discovered unexpected expression of the commonly used dilp2-GAL4 line in tracheal tissue which significantly impacted growth phenotypes. We realized that few GAL4 lines have been thoroughly characterized, particularly when considering transient activity that may have significant impact on phenotypic readouts. Here, we characterized a further subset of 12 reportedly tissue-specific GAL4 lines commonly used in genetic studies of development, growth, endocrine regulation, and metabolism. Ten out of 12 GAL4 lines exhibited ectopic activity in other larval tissues, with seven being active in the larval trachea. Since this ectopic activity may result in phenotypes that do not depend on the manipulation in the intended target tissue, it is recommended to carefully analyze the outcome while taking this aspect into consideration.

Bi-allelic loss-of-function variants in BCAS3 cause a syndromic neurodevelopmental disorder.

BCAS3 microtubule-associated cell migration factor (BCAS3) is a large, highly conserved cytoskeletal protein previously proposed to be critical in angiogenesis and implicated in human embryogenesis and tumorigenesis. Here, we established BCAS3 loss-of-function variants as causative for a neurodevelopmental disorder. We report 15 individuals from eight unrelated families with germline bi-allelic loss-of-function variants in BCAS3. All probands share a global developmental delay accompanied by pyramidal tract involvement, microcephaly, short stature, strabismus, dysmorphic facial features, and seizures. The human phenotype is less severe compared with the Bcas3 knockout mouse model and cannot be explained by angiogenic defects alone. Consistent with being loss-of-function alleles, we observed absence of BCAS3 in probands' primary fibroblasts. By comparing the transcriptomic and proteomic data based on probands' fibroblasts with those of the knockout mouse model, we identified similar dysregulated pathways resulting from over-representation analysis, while the dysregulation of some proposed key interactors could not be confirmed. Together with the results from a tissue-specific Drosophila loss-of-function model, we demonstrate a vital role for BCAS3 in neural tissue development.

Factors affecting the intraoperative calculi excretion during flexible ureteroscopy lithotripsy: an in vitro analysis.

OBJECTIVE: To explore the parameters influencing intraoperative calculi excretion (ICE) during flexible ureteroscopy lithotripsy (fURL) using in vitro simulation experiments. METHODS: 3D-printed human kidney models were used to simulate the elimination of gravel during fURL. The factors influencing the ICE during fURL were analyzed by comparing the effects of different degrees of hydronephrosis (mild, moderate, and severe), surgical positions (supine and lateral position), ratios of endoscope-sheath diameter (RESD) (0.625, 0.725, and 0.825), gravel sizes (0.50-1.00 mm, 0.25-0.50 mm, and 0.10-0.25 mm), and ureteral access sheaths (UASs) (traditional UAS and negative-pressure UAS) on ICE. RESULTS: The impacts of various UAS, RESD, degree of hydronephrosis, surgical positions, and gravel sizes on ICE were all significant (p < 0.05). We found no evidence of multicollinearity for all the independent variables, and the linear regression equation fitted as ICE ( g / min ) = 0.102 + 0.083 ∗ UAS grade - 0.050 ∗ RESD grade - 0.048 ∗ hydronephrosis grade + 0.065 ∗ position grade - 0.027 ∗ gravel size grade (R2 = 0.569). CONCLUSION: Employing negative-pressure UAS, smaller RESD, milder hydronephrosis, lateral position, and smaller gravel size contribute to improved ICE during fURL. Among them, the adoption of negative-pressure UAS had the most substantial effects.

Variant functional assessment in Drosophila by overexpression: what can we learn?

The last decade has been highlighted by the increased use of next-generation DNA sequencing technology to identify novel human disease genes. A critical downstream part of this process is assigning function to a candidate gene variant. Functional studies in Drosophila melanogaster, the common fruit fly, have made a prominent contribution in annotating variant impact in an in vivo system. The use of patient-derived knock-in flies or rescue-based, "humanization", approaches are novel and valuable strategies in variant testing but have been recently widely reviewed. An often-overlooked strategy for determining variant impact has been GAL4/upstream activation sequence-mediated tissue-defined overexpression in Drosophila. This mini-review will summarize the recent contribution of ectopic overexpression of human reference and variant cDNA in Drosophila to assess variant function, interpret the consequence of the variant, and in some cases infer biological mechanisms.

Wind turbine icing characteristics and icing-induced power losses to utility-scale wind turbines.

A field campaign was carried out to investigate ice accretion features on large turbine blades (50 m in length) and to assess power output losses of utility-scale wind turbines induced by ice accretion. After a 30-h icing incident, a high-resolution digital camera carried by an unmanned aircraft system was used to capture photographs of iced turbine blades. Based on the obtained pictures of the frozen blades, the ice layer thickness accreted along the blades' leading edges was determined quantitatively. While ice was found to accumulate over whole blade spans, outboard blades had more ice structures, with ice layers reaching up to 0.3 m thick toward the blade tips. With the turbine operating data provided by the turbines' supervisory control and data acquisition systems, icing-induced power output losses were investigated systematically. Despite the high wind, frozen turbines were discovered to rotate substantially slower and even shut down from time to time, resulting in up to 80% of icing-induced turbine power losses during the icing event. The research presented here is a comprehensive field campaign to characterize ice accretion features on full-scaled turbine blades and systematically analyze detrimental impacts of ice accumulation on the power generation of utility-scale wind turbines. The research findings are very useful in bridging the gaps between fundamental icing physics research carried out in highly idealized laboratory settings and the realistic icing phenomena observed on utility-scale wind turbines operating in harsh natural icing conditions.

Comparative analysis of pain outcomes in hypoglossal nerve stimulation: Avoiding the digastric tendon.

OBJECTIVE: Upper airway stimulation effectively treats patients with obstructive sleep apnea, especially among those with low long-term compliance with continuous positive airway pressure. Traditional methods to implant the hypoglossal nerve stimulator involve retraction of the digastric tendon to identify the nerve and improve exposure for stimulator implantation. Transient submental pain and discomfort are known side effects of the procedure. Placement without retraction provides an alternative approach to minimize postoperative pain. This study compares post-operative pain outcomes of patients in whom the digastric tendon was and was not retracted. METHODS: Retrospective chart review of patients who received the hypoglossal nerve stimulation implant at a single institution between 2017 and 2021. A combination of descriptive and qualitative data, including age, gender, comorbidities, and postoperative symptoms are analyzed to characterize patient outcomes resulting from this intraoperative technique. The categorical and continuous variables were analyzed using chi-squared tests and independent t-tests, respectively. RESULTS: Patients report overall satisfaction after implantation and titration. A total of 108 patients underwent HGNS implantation between September 2017 and January 2021 using the aforementioned techniques. 1.69 % of patients experienced postoperative submental pain as compared to 18.37 % prior to the change in technique (p < 0.01). CONCLUSION: Avoidance of digastric tendon retraction in the implantation of the stimulating lead is a safe and effective technique that reduces postoperative pain and discomfort. Our institution has demonstrated an alternative technique for hypoglossal stimulator implantation which improves perioperative outcomes. LAY SUMMARY: Upper airway stimulation is an effective treatment for obstructive sleep apnea. During surgery, the digastric tendon is often moved to identify the nerve and improve access. This study shows that avoiding digastric tendon movement safely reduces postoperative pain and discomfort. LEVEL OF EVIDENCE: III.

Integrating Automated Labeling Framework for Enhancing Deep Learning Models to Count Corn Plants Using UAS Imagery.

Plant counting is a critical aspect of crop management, providing farmers with valuable insights into seed germination success and within-field variation in crop population density, both of which are key indicators of crop yield and quality. Recent advancements in Unmanned Aerial System (UAS) technology, coupled with deep learning techniques, have facilitated the development of automated plant counting methods. Various computer vision models based on UAS images are available for detecting and classifying crop plants. However, their accuracy relies largely on the availability of substantial manually labeled training datasets. The objective of this study was to develop a robust corn counting model by developing and integrating an automatic image annotation framework. This study used high-spatial-resolution images collected with a DJI Mavic Pro 2 at the V2-V4 growth stage of corn plants from a field in Wooster, Ohio. The automated image annotation process involved extracting corn rows and applying image enhancement techniques to automatically annotate images as either corn or non-corn, resulting in 80% accuracy in identifying corn plants. The accuracy of corn stand identification was further improved by training four deep learning (DL) models, including InceptionV3, VGG16, VGG19, and Vision Transformer (ViT), with annotated images across various datasets. Notably, VGG16 outperformed the other three models, achieving an F1 score of 0.955. When the corn counts were compared to ground truth data across five test regions, VGG achieved an R2 of 0.94 and an RMSE of 9.95. The integration of an automated image annotation process into the training of the DL models provided notable benefits in terms of model scaling and consistency. The developed framework can efficiently manage large-scale data generation, streamlining the process for the rapid development and deployment of corn counting DL models.

Development and Testing of a Rocket-Based Sensor for Atmospheric Sensing Using an Unmanned Aerial System.

Measurements of the vertical structure of the lower atmosphere are important to the understanding of air quality. Unmanned Aerial Systems (UASs, drones) can provide low cost, repeatable measurements of the temperature, pressure, and relative humidity. A set of inexpensive sensors controlled with an Arduino microprocessor board were tested on a UAS against a meteorology grade sensor. Two modes of operation for sampling were tested: a forward moving sampler and a vertical ascent sampler. A small particle sensor (Sensiron SPS30) was integrated and was capable of retrieving vertical aerosol distributions during an inversion event. The thermocouple-based temperature probe and the relative humidity measurement on the Bosch BME280 sensor correlated well with the meteorological sensor. The temperature and relative humidity sensors were then deployed on a rocket sounding platform. The rocket sounding system performed well up to a height of 400 m. The inexpensive sensors were found to perform adequately for low-cost development and uses in education and research.

Filling the Gaps: Using Synthetic Low-Altitude Aerial Images to Increase Operational Design Domain Coverage.

A key necessity for the safe and autonomous flight of Unmanned Aircraft Systems (UAS) is their reliable perception of the environment, for example, to assess the safety of a landing site. For visual perception, Machine Learning (ML) provides state-of-the-art results in terms of performance, but the path to aviation certification has yet to be determined as current regulation and standard documents are not applicable to ML-based components due to their data-defined properties. However, the European Union Aviation Safety Agency (EASA) published the first usable guidance documents that take ML-specific challenges, such as data management and learning assurance, into account. In this paper, an important concept in this context is addressed, namely the Operational Design Domain (ODD) that defines the limitations under which a given ML-based system is designed to operate and function correctly. We investigated whether synthetic data can be used to complement a real-world training dataset which does not cover the whole ODD of an ML-based system component for visual object detection. The use-case in focus is the detection of humans on the ground to assess the safety of landing sites. Synthetic data are generated using the methods proposed in the EASA documents, namely augmentations, stitching and simulation environments. These data are used to augment a real-world dataset to increase ODD coverage during the training of Faster R-CNN object detection models. Our results give insights into the generation techniques and usefulness of synthetic data in the context of increasing ODD coverage. They indicate that the different types of synthetic images vary in their suitability but that augmentations seem to be particularly promising when there is not enough real-world data to cover the whole ODD. By doing so, our results contribute towards the adoption of ML technology in aviation and the reduction of data requirements for ML perception systems.

The Alarmin Triad-IL-25, IL-33, and TSLP-Serum Levels and Their Clinical Implications in Chronic Spontaneous Urticaria.

This study delves into the critical role of alarmins in chronic spontaneous urticaria (CSU), focusing on their impact on disease severity and the quality of life (QoL) of patients. We investigated the alterations in alarmin levels in CSU patients and their correlations with the Urticaria Activity Score (UAS7) and the Dermatology Life Quality Index (DLQI). We analyzed serum levels of interleukin-25 (IL-25), interleukin-33 (IL-33), and thymic stromal lymphopoietin (TSLP) in 50 CSU patients, comparing these to 38 healthy controls. The study examined the relationship between alarmin levels and clinical outcomes, including disease severity and QoL. Elevated levels of IL-33 and TSLP in CSU patients (p < 0.0001) highlight their potential role in CSU pathogenesis. Although IL-25 showed higher levels in CSU patients, this did not reach statistical significance (p = 0.0823). Crucially, IL-33's correlation with both UAS7 and DLQI scores underscores its potential as a biomarker for CSU diagnosis and severity assessment. Of the alarmins analyzed, IL-33 emerges as particularly significant for further exploration as a diagnostic and prognostic biomarker in CSU. Its substantial correlation with disease severity and impact on QoL makes it a compelling candidate for future research, potentially serving as a target for therapeutic interventions. Given these findings, IL-33 deserves additional investigation to confirm its role and effectiveness as a biomarker and therapeutic target in CSU.

Serum Concentration of IL-5 Receptor (IL-5R) and Associations with Disease Severity in Patients with Chronic Spontaneous Urticaria (CSU) and Atopic Dermatitis (AD).

The immunological pathogenesis of atopic dermatitis (AD) and chronic spontaneous urticaria (CSU) has not been fully elucidated yet. The aim of our research was to assess the serum concentration of interleukin-5 receptor (IL-5R) in relation to the disease activity and pruritus intensity in adult patients with AD and CSU. This pilot study included 45 participants (15 patients with AD, 15 patients with CSU, and 15 healthy controls). Blood samples were taken to examine the serum levels of IL-5R using the enzyme-linked immunosorbent assay (ELISA) test. The Scoring Atopic Dermatitis (SCORAD) index, the Urticaria Activity Score (UAS7), and the Visual Analogue Scale (VAS) were used to assess the disease activity and the pruritus intensity, respectively. Obtained results revealed that the IL-5R concentration was significantly higher in patients with CSU than in patients with AD and in the controls (p = 0.038). There was a positive correlation between the IL-5R level and the SCORAD index in patients with AD (r = -0.9, p = 0.047), which was not found for the CSU activity by UAS7 and with the pruritus severity by VAS in both examined groups of patients. Our findings underscore higher serum levels of IL-5R among CSU and AD patients, which may highlight its functional role in the pathogenesis of these diseases. In contrast, IL-5R might not be fully useful in reflecting the severity of symptoms. Although our results are promising, this study should be conducted on a larger cohort of patients.

Enhancement of Vivid-based photo-activatable Gal4 transcription factor in mammalian cells.

The Gal4/UAS system is a versatile tool to manipulate exogenous gene expression of cells spatially and temporally in many model organisms. Many variations of light-controllable Gal4/UAS system are now available, following the development of photo-activatable (PA) molecular switches and integration of these tools. However, many PA-Gal4 transcription factors have undesired background transcription activities even in dark conditions, and this severely attenuates reliable light-controlled gene expression. Therefore, it is important to develop reliable PA-Gal4 transcription factors with robust light-induced gene expression and limited background activity. By optimization of synthetic PA-Gal4 transcription factors, we have validated configurations of Gal4 DNA biding domain, transcription activation domain and blue light-dependent dimer formation molecule Vivid (VVD), and applied types of transcription activation domains to develop a new PA-Gal4 transcription factor we have named eGAV (enhanced Gal4-VVD transcription factor). Background activity of eGAV in dark conditions was significantly lower than that of hGAVPO, a commonly used PA-Gal4 transcription factor, and maximum light-induced gene expression levels were also improved. Light-controlled gene expression was verified in cultured HEK293T cells with plasmid-transient transfections, and in mouse EpH4 cells with lentivirus vector-mediated transduction. Furthermore, light-controlled eGAV-mediated transcription was confirmed in transfected neural stem cells and progenitors in developing and adult mouse brain and chick spinal cord, and in adult mouse hepatocytes, demonstrating that eGAV can be applied to a wide range of experimental systems and model organisms.Key words: optogenetics, Gal4/UAS system, transcription, gene expression, Vivid.

Consecutive injections of low-dose interleukin-2 improve symptoms and disease control in patients with chronic spontaneous urticaria.

PURPOSE: To describe the effectiveness and tolerability of low-dose interleukin (IL)-2 in treating patients with chronic spontaneous urticaria (CSU) refractory to H1-antihistamines. METHODS: This retrospective study included CSU patients who received treatment with at least one cycle of IL-2, injected intramuscularly at a dose of 1.0 million international units daily for 7 consecutive days, after failing treatment with H1-antihistamines. Patients were followed up for ≥12 weeks. RESULTS: Of the 15 patients, 7 (46.7%) and 11 (73.3%) achieved complete response at Week 2 and Week 12, respectively. The mean change of urticaria control test (UCT) and weekly urticaria activity score (UAS7) from baseline was 6.6 (95% CI, 4.2 to 8.9) and - 16.9 (95% CI, -24.0 to -9.8), respectively, at Week 12. Local injection-site reactions were the most common adverse events. No serious adverse events were reported. CONCLUSION: Low-dose IL-2 treatment improves symptoms and disease control for CSU patients refractory to H1-antihistamines.

Effect of ureteric access sheath on outcomes of retrograde intrarenal surgery for renal stone disease: a randomized controlled trial.

BACKGROUND: The need of ureteric access sheath (UAS) in retrograde intrarenal surgery (RIRS) has been controversial for gaining high success in terms of stone free rate (SFR), reducing operative times and complications. There has been lack of high level of evidence in the literature on this topic. MATERIALS AND METHODS: This prospective randomized controlled trial (RCT) was conducted in the Department of Urology, PGIMER, Chandigarh from July 2019 to Dec 2021. The effect of UAS on the outcome of RIRS (SFR, operative time and complications) for renal stone disease was assessed. Ninety patients were randomized into two groups: 41 patients in Group 1 (RIRS with UAS) and 40 patients in Group 2(RIRS without UAS) were finally analyzed after exclusion. All the patients underwent preoperative double J stent placement at least 10 days prior to the definitive procedure. Operative time was recorded and postoperative pain was assessed by visual analogue scale(VAS) at 6 and 24 h postoperatively. Complications and emergency visits were recorded up to one month post procedure. SFR was assessed at 1 month using noncontrast CT KUB. Success was defined as absence of any residual fragment more than 3 mm in maximum diameter. RESULTS: Demographic parameters (age, body mass index, and comorbidities) and preoperative parameters (stone burden, proportion of recurrent stone formers and proportion of patients with inferior calyceal stones) were comparable between the two groups. Operative times (45.49 vs 48.38 min; p - 0.484) and VAS scores at 6 and 24 h post-op (p - 0.577) were also comparable between Group 1 and Group 2. SFR was comparable in Group 1 and Group 2 (78.05% vs 80%, p - 0.829). Postoperative complications were higher in the UAS group, but not statistically significant (4.88% vs 0%; p - 0.157). CONCLUSION: The use of UAS during RIRS is not associated with improved SFR. RIRS can be performed safely without the use of UAS and without increasing postoperative complications.

Unmanned aerial vehicles for surveillance and control of vectors of malaria and other vector-borne diseases.

The use of Unmanned Aerial Vehicles (UAVs) has expanded rapidly in ecological conservation and agriculture, with a growing literature describing their potential applications in global health efforts including vector control. Vector-borne diseases carry severe public health and economic impacts to over half of the global population yet conventional approaches to the surveillance and treatment of vector habitats is typically laborious and slow. The high mobility of UAVs allows them to reach remote areas that might otherwise be inaccessible to ground-based teams. Given the rapidly expanding examples of these tools in vector control programmes, there is a need to establish the current knowledge base of applications for UAVs in this context and assess the strengths and challenges compared to conventional methodologies. This review aims to summarize the currently available knowledge on the capabilities of UAVs in both malaria control and in vector control more broadly in cases where the technology could be readily adapted to malaria vectors. This review will cover the current use of UAVs in vector habitat surveillance and deployment of control payloads, in comparison with their existing conventional approaches. Finally, this review will highlight the logistical and regulatory challenges in scaling up the use of UAVs in malaria control programmes and highlight potential future developments.

Sidelobe Suppression Techniques for Near-Field Multistatic SAR.

Multirotor Unmanned Air Systems (UAS) represent a significant improvement in capability for Synthetic Aperture Radar (SAR) imaging when compared to traditional, fixed-wing, platforms. In particular, a swarm of UAS can generate significant measurement diversity through variation of spatial and frequency collections across an array of sensors. In such imaging schemes, the image formation step is challenging due to strong extended sidelobe; however, were this to be effectively managed, a dramatic increase in image quality is theoretically possible. Since 2015, QinetiQ have developed the RIBI system, which uses multiple UAS to perform short-range multistatic collections, and this requires novel near-field processing to mitigate the high sidelobes observed and form actionable imagery. This paper applies a number of algorithms to assess image reconstruction of simulated near-field multistatic SAR with an aim to suppress sidelobes observed in the RIBI system, investigating techniques including traditional SAR processing, regularised linear regression, compressive sensing. In these simulations presented, Elastic net, Orthogonal Matched Pursuit, and Iterative Hard Thresholding all show the ability to suppress sidelobes while preserving accuracy of scatterer RCS. This has also lead to a novel processing approach for reconstructing SAR images based on the observed Elastic net and Iterative Hard Thresholding performance, mitigating weaknesses to generate an improved combined approach. The relative strengths and weaknesses of the algorithms are discussed, as well as their application to more complex real-world imagery.

Reflectance Measurements from Aerial and Proximal Sensors Provide Similar Precision in Predicting the Rice Yield Response to Mid-Season N Applications.

Accurately detecting nitrogen (N) deficiency and determining the need for additional N fertilizer is a key challenge to achieving precise N management in many crops, including rice (Oryza sativa L.). Many remotely sensed vegetation indices (VIs) have shown promise in this regard; however, it is not well-known if VIs measured from different sensors can be used interchangeably. The objective of this study was to quantitatively test and compare the ability of VIs measured from an aerial and proximal sensor to predict the crop yield response to top-dress N fertilizer in rice. Nitrogen fertilizer response trials were established across two years (six site-years) throughout the Sacramento Valley rice-growing region of California. At panicle initiation (PI), unmanned aircraft system (UAS) Normalized Difference Red-Edge Index (NDREUAS) and GreenSeeker (GS) Normalized Difference Vegetation Index (NDVIGS) were measured and expressed as a sufficiency index (SI) (VI of N treatment divided by VI of adjacent N-enriched area). Following reflectance measurements, each plot was split into subplots with and without top-dress N fertilizer. All metrics evaluated in this study indicated that both NDREUAS and NDVIGS performed similarly with respect to predicting the rice yield response to top-dress N at PI. Utilizing SI measurements prior to top-dress N fertilizer application resulted in a 113% and 69% increase (for NDREUAS and NDVIGS, respectively) in the precision of the rice yield response differentiation compared to the effect of applying top-dress N without SI information considered. When the SI measured via NDREUAS and NDVIGS at PI was ≤0.97 and 0.96, top-dress N applications resulted in a significant (p < 0.05) increase in crop yield of 0.19 and 0.21 Mg ha-1, respectively. These results indicate that both aerial NDREUAS and proximal NDVIGS have the potential to accurately predict the rice yield response to PI top-dress N fertilizer in this system and could serve as the basis for developing a decision support tool for farmers that could potentially inform better N management and improve N use efficiency.

Non-Destructive Measurements for 3D Modeling and Monitoring of Large Buildings Using Terrestrial Laser Scanning and Unmanned Aerial Systems.

Along with the development and improvement of measuring technologies and techniques in recent times, new methods have appeared to model and monitor the behavior of land and constructions over time. The main purpose of this research was to develop a new methodology to model and monitor large buildings in a non-invasive way. The methods proposed in this research are non-destructive and can be used to monitor the behavior of buildings over time. A method of comparing point clouds obtained using terrestrial laser scanning combined with aerial photogrammetric methods was used in this study. The advantages and disadvantages of using non-destructive measurement techniques over the classic methods were also analyzed. With a building located in the University of Agricultural Sciences and Veterinary Medicine Cluj-Napoca campus as a case study and with the help of the proposed methods, the deformations over time of the facades of that building were determined. As one of the main conclusions of this case study, it can be stated that the proposed methods are adequate to model and monitor the behavior of constructions over time, ensuring a satisfactory degree of precision and accuracy. The methodology can be successfully applied to other similar projects.

Unmanned Aerial Systems and Deep Learning for Safety and Health Activity Monitoring on Construction Sites.

Construction is a highly hazardous industry typified by several complex features in dynamic work environments that have the possibility of causing harm or ill health to construction workers. The constant monitoring of workers' unsafe behaviors and work conditions is considered not only a proactive but also an active method of removing safety and health hazards and preventing potential accidents on construction sites. The integration of sensor technologies and artificial intelligence for computer vision can be used to create a robust management strategy and enhance the analysis of safety and health data needed to generate insights and take action to protect workers on construction sites. This study presents the development and validation of a framework that implements the use of unmanned aerial systems (UASs) and deep learning (DL) for the collection and analysis of safety activity metrics for improving construction safety performance. The developed framework was validated using a pilot case study. Digital images of construction safety activities were collected on active construction sites using a UAS, and the performance of two different object detection deep-learning algorithms/models (Faster R-CNN and YOLOv3) for safety hardhat detection were compared. The dataset included 7041 preprocessed and augmented images with a 75/25 training and testing split. From the case study results, Faster R-CNN showed a higher precision of 93.1% than YOLOv3 (89.8%). The findings of this study show the impact and potential benefits of using UASs and DL in computer vision applications for managing safety and health on construction sites.