Beyond Conventional Monitoring: A Semantic Segmentation Approach to Quantifying Traffic-Induced Dust on Unsealed Roads.

Road dust is a mixture of fine and coarse particles released into the air due to an external force, such as tire-ground friction or wind, which is harmful to human health when inhaled. Continuous dust emission from the road surfaces is detrimental to the road itself and the road users. Due to this, multiple dust monitoring and control techniques are currently adopted in the world. The current dust monitoring methods require expensive equipment and expertise. This study introduces a novel pragmatic and robust approach to quantifying traffic-induced road dust using a deep learning method called semantic segmentation. Based on the authors' previous works, the best-performing semantic segmentation machine learning models were selected and used to identify dust in an image pixel-wise. The total number of dust pixels was then correlated with real-world dust measurements obtained from a research-grade dust monitor. Our method shows that semantic segmentation can be adopted to quantify traffic-induced dust reasonably. Over 90% of the predictions from both correlations fall in true positive quadrant, indicating that when dust concentrations are below the threshold, the segmentation can accurately predict them. The results were validated and extended for real-time application. Our code implementation is publicly available.

Exploiting Big Data for Experiment Reporting: The Hi-Drive Collaborative Research Project Case.

As timely information about a project's state is key for management, we developed a data toolchain to support the monitoring of a project's progress. By extending the Measurify framework, which is dedicated to efficiently building measurement-rich applications on MongoDB, we were able to make the process of setting up the reporting tool just a matter of editing a couple of .json configuration files that specify the names and data format of the project's progress/performance indicators. Since the quantity of data to be provided at each reporting period is potentially overwhelming, some level of automation in the extraction of the indicator values is essential. To this end, it is important to make sure that most, if not all, of the quantities to be reported can be automatically extracted from the experiment data files actually used in the project. The originating use case for the toolchain is a collaborative research project on driving automation. As data representing the project's state, 330+ numerical indicators were identified. According to the project's pre-test experience, the tool is effective in supporting the preparation of periodic progress reports that extensively exploit the actual project data (i.e., obtained from the sensors-real or virtual-deployed for the project). While the presented use case concerns the automotive industry, we have taken care that the design choices (particularly, the definition of the resources exposed by the Application Programming Interfaces, APIs) abstract the requirements, with an aim to guarantee effectiveness in virtually any application context.

A benchmark dataset for binary segmentation and quantification of dust emissions from unsealed roads.

The generation of reference data for machine learning models is challenging for dust emissions due to perpetually dynamic environmental conditions. We generated a new vision dataset with the goal of advancing semantic segmentation to identify and quantify vehicle-induced dust clouds from images. We conducted field experiments on 10 unsealed road segments with different types of road surface materials in varying climatic conditions to capture vehicle-induced road dust. A direct single-lens reflex (DSLR) camera was used to capture the dust clouds generated due to a utility vehicle travelling at different speeds. A research-grade dust monitor was used to measure the dust emissions due to traffic. A total of ~210,000 images were photographed and refined to obtain ~7,000 images. These images were manually annotated to generate masks for dust segmentation. The baseline performance of a truncated sample of ~900 images from the dataset is evaluated for U-Net architecture.

Relationship between donated kidney volume determined by ultrasound adjusted for clinical factors and 1-month and 1-year creatinine clearance: A retrospective study.

BACKGROUND: Graft volume as a surrogate of nephron numbers correlates with allograft function. The primary aim of this study was to correlate renal volume determined by ultrasound, adjusted to recipient clinical parameters in order to determine post-transplant renal function at the end of the first year. MATERIALS AND METHODS: A total of 140 patients were enrolled in this study, including 75 males, with a total mean age of 41.2 ± 13.5 years. Clinical data of all donors and recipients undergoing kidney transplantation at our institution between 2003 and 2019 were reviewed. The volume of transplanted kidney was measured by ultrasonography on the fifth day after the operation and correlated with recipients' clinical parameters and then adjusted with first-month and first-year post-transplantation creatinine clearance. RESULTS: The mean allograft volume measured using ultrasonography was 175.0 ± 37.2 mL. Absolute donor kidney volume had a non-significant correlation with creatinine clearance at 1 month and at 1 year after transplantation. The kidney volume/recipient body weight ratio had a positive, and significant, correlation with creatinine clearance at 1 month and at 1 year after transplantation (r = 0.326, p < 0.001, and r = 0.183, p = 0.038, respectively). CONCLUSION: Our data demonstrated that 12-month creatinine clearance is influenced by ratio of donated kidney volume/recipient body weight.

Does maturity estimation, 2D:4D and training load measures explain physical fitness changes of youth football players?

OBJECTIVES: The purpose of the present study was two-fold: (1) To analyse physical fitness changes of youth football players after a full-season; and (2) to examine whether physical fitness changes are explainable by estimated maturity status, 2digit:4digit ratio (2D:4D) from each hand and training load (TL) measures. METHODS: Twenty-seven youth elite Under-15 football players were daily monitored for training load measures during 38 weeks. At the beginning and at the end of the season, all players were assessed for physical fitness. Also, the maturity status estimation and the length of the second and fourth digits of both hands were collected at the beginning of the season. RESULTS: Significant differences were found for all physical fitness measures after the season. The second and fourth digits of left and right hands had negative moderate correlations with change of direction (COD) changes (r=-.39 to - 0.45 | p = .05 to 0.02). Also, the maturity offset measure had negative moderate correlations with COD changes (r=-.40 | p = .04). From the reported significant correlations, the maturity offset, Left 4D, Right 2D and Right 4D significantly predicted the Mod.505 COD test changes (ß = 0.41, p = .04; ß = -0.41, p = .04; ß = -0.45, p = .02; and ß = -0.44, p = .03, respectively). CONCLUSION: The maturity offset and the 2D:4D measures have the potential to predict COD performance changes over-time in youth football players. Given the lack of associations between the maturity estimation, 2D:4D and training load measures, with the overall physical fitness measures, coaches should rely only at COD changes.

Quantification of training and match load in elite youth soccer players: a full-season study.

BACKGROUND: The present study aimed to quantify training and match load in elite young soccer players over the course of an entire season. METHODS: Using a longitudinal design, session-rate of perceived exertion (s-RPE) and its metrics (weekly acute workload [wAW], acute to chronic workload ratio [wACWR], training monotony and training strain) were examined in twenty-one elite young soccer players (mean±standard deviation; age: 16.1±0.2 years; height: 176.8±5.6 cm; body mass: 67.3±5.7 kg; BMI: 21.5±1.4 kg/m2; V̇O2max: 47.6±3.8 mL.kg-1.min-1) during the whole season containing 4 meso-cycles: preseason (Pre-S), early-season (Ear-S), mid-season (Mid-S), and end-season (End-S). RESULTS: Repeated-measures analysis of variance examined variations in s-RPE load data across the 4 meso-cycles and 1-week of microcycle. Analyzing data revealed the End-S had a significant greater wAW compared to Early-S (P=0.002, g=0.96) and Mid-S (P<0.001, g=1.09). However, no differences between in-season periods were observed in wACWR (P=0.524). The within-week variations revealed significant lower wAW in prematch a day (MD-1) (P<0.001), 1 day after match (MD+1) (P<0.001) and 2 days after match (MD+2) (P<0.001) compared to match day (MD) for overall team analysis. Additionally, analyses by playing position showed that fullbacks have a significant lower AW in MD+2 compared to MD (P<0.029). CONCLUSIONS: The periodization of training load indicated variations across the whole season in young elite players. The weekly microcycle perceived load could be identified as follows; there are higher training loads on MD-3 and MD-2 which was similar to intensities experienced by players throughout the match play and, furthermore, lower overall WL on the MD+1 and MD+2 in order to ensure the optimal recovery of the players.

Association between Training Load and Well-Being Measures in Young Soccer Players during a Season.

This study aimed to analyze the correlations among weekly (w) acute workload (wAW), chronic workload (wCW), acute/chronic workload ratio (wACWR), training monotony (wTM), training strain (wTS), sleep quality (wSleep), delayed onset muscle soreness (wDOMS), fatigue (wFatigue), stress (wStress), and Hooper index (wHI) in pre-, early, mid-, and end-of-season. Twenty-one elite soccer players (age: 16.1 ± 0.2 years) were monitored weekly on training load and well-being for 36 weeks. Higher variability in wAW (39.2%), wFatigue (84.4%), wStress (174.3%), and wHI (76.3%) at the end-of-season were reported. At mid-season, higher variations in wSleep (59.8%), TM (57.6%), and TS (111.1%) were observed. Moderate to very large correlations wAW with wDOMS (r = 0.617, p = 0.007), wFatigue, wStress, and wHI were presented. Similarly, wCW reported a meaningful large association with wDOMS (r = 0.526, p < 0.001); moderate to very large associations with wFatigue (r = 0.649, p = 0.005), wStress, and wHI. Moreover, wTM presented a large correlation with wSleep (r = 0.515, p < 0.001); and a negatively small association with wStress (r = -0.426, p = 0.003). wTS showed a small to large correlation with wSleep (r = 0.400, p = 0.005) and wHI; also, a large correlation with wDOMS (r = 0.556, p = 0.028) and a moderate correlation with wFatigue (r = 0.343, p = 0.017). Wellness status may be considered a useful tool to provide determinant elite players' information to coaches and to identify important variations in training responses.

Automatic Evaluation of Crown Preparation Using Image Processing Techniques: A Substitute to Faculty Scoring in Dental Education.

BACKGROUND: This study presents a new and innovative experimental method, including software and its prerequisite instruments, to use image processing techniques for crown preparation analysis. METHOD: A platform was designed and constructed to take images from artificial teeth in different angles and directions and to process and analyze them by the proposed method to evaluate the quality and quantity of crown preparation. For each tooth, two series of images were taken from the artificial teeth before and after preparation, and image series were registered by two semi-automated and automated methods to transform them into one coordinate system. Region of interest was segmented by user interaction, and tooth region was segmented by substeps such as transformation to hue, saturation, and value color space, edge detection, morphology operations, and contour extraction. Finally, the amount and angle of crown preparation were computed and compared with standard measures to evaluate the quality of crown preparation. The proposed method was applied to a local dataset collected from Isfahan University of Medical Sciences. RESULTS: Difference between the angle of crown preparation computed by the proposed method and that of the experts showed a mean absolute error of 7.17°. The correlation between the segmented regions by the proposed method and those of the experts was also evaluated by the Intersection over Union (IOU) criterion. The best and worst performances achieved in cases by IOU were 0.94 and 0.76, respectively. Finally, the segmentation results of the proposed method indicated an average IOU of 0.89 in all images. CONCLUSION: Students can use this method as an assessment tool in preclinical tooth preparation to compare their crown work with standard parameters.