Hired Research Articles

Geometry measurement of subsurface cracks in concrete from ultrasonic images

Geometry measurement of concrete subsurface damage is as crucial as detection and localization for condition evaluation. Ultrasonic reflection-based imaging can map subsurface reflector geometry, however direct measurements from images are inaccurate. In this study, amplitude of imaged reflectors is used to accurately measure geometry of horizontal and inclined reflectors in concrete subsurface. Four statistical parameters have been tested for suitability of measurement by studying their performances with respect to crack geometry (length and angle) and positions in concrete using simulations. These tests show that the ‘max’ parameter measured reflector geometry with the least error. The technique is frequency independent in the commonly used 50 to 150 kHz range of concrete inspection. For validation of the technique, experimental studies were performed on three concrete specimens with various embedded linear reflectors and one specimen with multilinear reflectors. Isolated horizontal reflectors and isolated inclined reflectors in concrete were measured with minimum 98%, and 94.5% accuracy, respectively. Compared to the prevalent pixel count approach and decibel drop techniques in medical field and metal NDT, the proposed technique performs significantly better. Measurement of multilinear and multiple-originating cracks achieved at least 90% accuracy. The technique was also tested on an arbitrary oriented crack in a three dimensional setup with significant accuracy.

A computer approach to assess age-related changes of the brain white matter in Alzheimer's disease

BackgroundAge is one of the major risk factors for Alzheimer's disease (AD) which is considered the most common adult-onset dementia. There is little information about age-related changes during brain dementia. MethodsThis study observed age-related variations in the brain throughout adulthood in magnetic resonance imaging (MRI) of the AD and healthy brains. The Open Access Series of Imaging Studies (OASIS) is used as a database. The method consists of design and develop a computer approach based on artificial intelligence (AI) to segment white matter (WM) from the MRI. Then, the number of pixels within the segmented white matter (WM) of the brain was calculated. Correlation was used to investigate age relation with WM changes in the normal and AD brain. ResultsThe WM change with aging was more correlated in AD group (rAD = −0.505, p-value = 0.0007) than control group (rControl = −0.357, p-value = 0.0001). ConclusionHigher correlation of WM pixel counts with age in AD group approved that AD is characterized by the relevant involvement of the WM and age. Our approach gained additional information on the quantitative pathological changes associated with the AD as the most common brain disorder of the elderly.

Remote sensing image road network detection based on channel attention mechanism

Extracting and detecting road network consistency from high-resolution remote sensing images has been a hot and difficult problem in the computer vision. Although it has made significant progress, there is still a phenomenon of high training accuracy but unsatisfactory actual extraction and detection results. The attention mechanism is one of the efficient and practical mechanisms in deep learning. It improves the performance of deep learning by selectively focusing on a portion of all information while ignoring other visible information, while effectively utilizing computing resources. Numerous experiments have also confirmed that the attention mechanism is resource-saving and effective. Its plug and play feature brings great convenience to programmers. In order to provide better road network detection results and solve the above problem, this paper combines the channel attention mechanism with ResNet and proposes SE-ResNet and ECA-ResNet for remote sensing image road network detection, making networks extract and learn road network features and ignore some non-road network features. The experimental results show that on the Massachusetts roads (MR) and CHN6-CUG roads datasets, ECA-ResNet and SE-ResNet based on channel attention mechanism perform similar to LeNet7 and ResNet in terms of accuracy, loss, accuracy convergence, and loss convergence, and even increase a certain computational burden. However, their final road network detection results (including road network detection pixel count, precision, recall, accuracy, IOU, F1 score, and actual road network detection result) of the former are significantly better than those of the latter. The channel attention mechanism makes the deep neural network pay more attention to the extraction and learning of road network features, while ignoring the extraction and learning of some non-road network features, which improves the accuracy of containing road network samples and reduces the accuracy of not containing road network samples. Therefore, the performance of ECA-ResNet and SE-ResNet is similar to that of LeNet7 and ResNet in the accuracy, loss, accuracy convergence and loss convergence, but the final road network detection results of ECA-ResNet and SE-ResNet are significantly better than those of LeNet7 and ResNet. Therefore, the proposed ECA-ResNet and SE-ResNet have broad application prospects in road network detection, especially ECA-ResNet.

Semantic Segmentation of Urban Remote Sensing Images Based on Deep Learning

In the realm of urban planning and environmental evaluation, the delineation and categorization of land types are pivotal. This study introduces a convolutional neural network-based image semantic segmentation approach to delineate parcel data in remote sensing imagery. The initial phase involved a comparative analysis of various CNN architectures. ResNet and VGG serve as the foundational networks for training, followed by a comparative assessment of the experimental outcomes. Subsequently, the VGG+U-Net model, which demonstrated superior efficacy, was chosen as the primary network. Enhancements to this model were made by integrating attention mechanisms. Specifically, three distinct attention mechanisms—spatial, SE, and channel—were incorporated into the VGG+U-Net framework, and various loss functions were evaluated and selected. The impact of these attention mechanisms, in conjunction with different loss functions, was scrutinized. This study proposes a novel network model, designated VGG+U-Net+Channel, that leverages the VGG architecture as the backbone network in conjunction with the U-Net structure and augments it with the channel attention mechanism to refine the model’s performance. This refinement resulted in a 1.14% enhancement in the network’s overall precision and marked improvements in MPA and MioU. A comparative analysis of the detection capabilities between the enhanced and original models was conducted, including a pixel count for each category to ascertain the extent of various semantic information. The experimental validation confirms the viability and efficacy of the proposed methodology.

Mitomycin Intravascular Chemoembolization for Corneal Neovascularization.

The purpose of the study was to evaluate the efficacy of mitomycin C intravascular chemoembolization (MICE) for corneal neovascularization (CNV). This is a prospective, nonrandomized, interventional study. Patients with stable CNV irrespective of the underlying etiology were enrolled in the study. 0.1% mitomycin C was injected intravascularly in CNV at the slit lamp under topical anesthesia. To evaluate the regression of vessels, the ImageJ software was used to trace and quantify vasculature by a pixel count in standardized clinical slit-lamp photographs. Eight eyes from 8 patients with corneal neovascularization and lipid keratopathy were studied. The mean age at treatment was 37 ± 12.75 (range 17-64) years. The median follow-up was 419.5 days (74-1166 days). Herpes simplex keratitis was the main underlying etiology (75%). The visual axis was compromised in 75%, and 100% had stromal scarring. The mean pixel count before MICE was 5983.41 ± 5004.96 pixels. After the treatment, the mean pixel count was 2060.38 ± 3142.96 pixels (delta: 3923.03, P = 0.029). No complications were recorded during the follow-up period. No recurrence of the CNV was observed at the last follow-up. Two eyes (25%) underwent a successful keratoplasty 4 months after MICE. MICE effectively reduced neovascularization with no immediate safety concerns, though its impact on vision and long-term safety requires further investigation with larger, longer term studies.

An Image Processing Tool for Automated Quantification of Bacterial Burdens in Zebrafish Larvae.

Zebrafish larvae are used to model the pathogenesis of multiple bacteria. This transparent model offers the unique advantage of allowing quantification of fluorescent bacterial burdens (fluorescent pixel counts: FPC) in vivo by facile microscopical methods, replacing enumeration of bacteria using time-intensive plating of lysates on bacteriological media. Accurate FPC measurements require laborious manual image processing to mark the outside borders of the animals so as to delineate the bacteria inside the animals from those in the culture medium that they are in. Here, we have developed an automated ImageJ/Fiji-based macro that accurately detect the outside borders of Mycobacterium marinum-infected larvae.

Multimodal Fusion for Enhanced Semantic Segmentation in Brain Tumor Imaging: Integrating Deep Learning and Guided Filtering Via Advanced 3D Semantic Segmentation Architectures

ABSTRACTBrain tumor segmentation is paramount in medical diagnostics. This study presents a multistage segmentation model consisting of two main steps. First, the fusion of magnetic resonance imaging (MRI) modalities creates new and more effective tumor imaging modalities. Second, the semantic segmentation of the original and fused modalities, utilizing various modified architectures of the U‐Net model. In the first step, a residual network with multi‐scale backbone architecture (Res2Net) and guided filter are employed for pixel‐by‐pixel image fusion tasks without requiring any training or learning process. This method captures both detailed and base elements from the multimodal images to produce better and more informative fused images that significantly enhance the segmentation process. Many fusion scenarios were performed and analyzed, revealing that the best fusion results are attained when combining T2‐weighted (T2) with fluid‐attenuated inversion recovery (FLAIR) and T1‐weighted contrast‐enhanced (T1CE) with FLAIR modalities. In the second step, several models, including the U‐Net and its many modifications (adding attention layers, residual connections, and depthwise separable connections), are trained using both the original and fused modalities. Further, a “Model Selection‐based” fusion of these individual models is also considered for more enhancement. In the preprocessing step, the images are resized by cropping them to decrease the pixel count and minimize background interference. Experiments utilizing the brain tumor segmentation (BraTS) 2020 dataset were performed to verify the efficiency and accuracy of the proposed methodology. The “Model Selection‐based” fusion model achieved an average Dice score of 88.4%, an individual score of 91.1% for the whole tumor (WT) class, an average sensitivity score of 86.26%, and a specificity score of 91.7%. These results prove the robustness and high performance of the proposed methodology compared to other state‐of‐the‐art methods.

A magnesium alloy with ultrahigh Gd content manufactured by laser directed energy deposition: Heat treatment and microstructure evolution

High RE content is able to improve the age-hardening response of Mg–RE alloys, thus enhancing mechanical properties. Here, we successfully produce a Mg–22Gd–2Zn–0.4Zr (wt%) alloy with ultrahigh Gd content using laser directed energy deposition (LDED) and investigate the microstructure evolution during heat treatment. Results show that for the studied alloy, the yield strength is 333 MPa after solution at 520 °C for 2 hours and aging at 200 °C for 64 hours, superior to most existing Mg–Gd alloys, due to the high number density of the strengthening β' phase resulting from high supersaturation. During solution treatment, increasing the temperature improves the solution efficiency by reducing the holding time, while preventing the overgrowth of grains. The peak hardness is around 139 Hv for both 175 °C and 200 °C aging, indicating that the peak hardness of Mg alloys with high Gd content is insensitive to aging temperature. This research can serve as guidance for the heat treatment and microstructure control of high-Gd-content magnesium alloys.

Calculation of electron-impact ionization of various benzene derivatives

Calculations of the electron-impact ionization cross-section of pyrene, anthracene, benzoyl chloride, benzophenone, and phthalonitrile are reported over a wide energy range. A comparison of theoretical models, viz. spherical complex optical potential (SCOP), pixel counting method (PCM), and the binary encounter Bethe (BEB) model is carried out. SCOP calculations provide the inelastic cross-section, and the ionization cross-section is extracted from it. This result is modified with PCM, a model previously applied to ion collisions which takes geometric screening corrections into account. The BEB model is used as an independent approach to calculate the ionization cross-section. It is demonstrated that all model results are in reasonable agreement with each other. Comparison is also made with other theoretical data where available.

Fully Automatic Quantitative Measurement of Equilibrium Radionuclide Angiocardiography Using a Convolutional Neural Network.

The aim of this study was to generate deep learning-based regions of interest (ROIs) from equilibrium radionuclide angiography datasets for left ventricular ejection fraction (LVEF) measurement. Manually drawn ROIs (mROIs) on end-systolic and end-diastolic images were extracted from reports in a Picture Archiving and Communications System. To reduce observer variability, preprocessed ROIs (pROIs) were delineated using a 41% threshold of the maximal pixel counts of the extracted mROIs and were labeled as ground-truth. Background ROIs were automatically created using an algorithm to identify areas with minimum counts within specified probability areas around the end-systolic ROI. A 2-dimensional U-Net convolutional neural network architecture was trained to generate deep learning-based ROIs (dlROIs) from pROIs. The model's performance was evaluated using Lin's concordance correlation coefficient (CCC). Bland-Altman plots were used to assess bias and 95% limits of agreement. A total of 41,462 scans (19,309 patients) were included. Strong concordance was found between LVEF measurements from dlROIs and pROIs (CCC = 85.6%; 95% confidence interval, 85.4%-85.9%), and between LVEF measurements from dlROIs and mROIs (CCC = 86.1%; 95% confidence interval, 85.8%-86.3%). In the Bland-Altman analysis, the mean differences and 95% limits of agreement of the LVEF measurements were -0.6% and -6.6% to 5.3%, respectively, for dlROIs and pROIs, and -0.4% and -6.3% to 5.4% for dlROIs and mROIs, respectively. In 37,537 scans (91%), the absolute LVEF difference between dlROIs and mROIs was <5%. Our 2-dimensional U-Net convolutional neural network architecture showed excellent performance in generating LV ROIs from equilibrium radionuclide angiography scans. It may enhance the convenience and reproducibility of LVEF measurements.

Ultrasonographic features of female urethral caruncle: a retrospective study of 20 patients

Female urethral caruncle is the most common urethral mass in postmenopausal women, yet there is a lack of studies on its imaging. The aim of this study was to provide a summary of the clinical and ultrasound features as well as the precise location of female urethral caruncle. This study reviewed the clinical and ultrasonographic records of 20 consecutive women with pathologically confirmed urethral caruncle. Data on patient demographics, symptoms, and transperineal and transrectal ultrasound imaging features, including location, shape, margin, size, blood flow, and inner echo of the caruncle, were extracted. Each patient presented with only one mass at the urethral meatus. Most caruncles were located on the posterior lip (75%) of the urethra, presenting as oval (80%), mixed-echoic (50%), or hypo-echoic (40%) nodules with abundant linear (40%) or dendritic (60%) blood flow. The average distance between the bladder neck and the cranial end of the masses was 28 mm. Hyper-echogenic spots, cystic echo areas, and macrocalcifications were detected in thirteen caruncles (70%). This study shows that transperineal combined with transrectal ultrasound can be used to assess female urethral caruncle, and its relative location to the urethra can be accurately described, which is helpful for surgeons making preoperative localization and conversations.

Enhanced feature extraction YOLO industrial small object detection algorithm based on receptive-field attention and multi-scale features

Abstract To guarantee the stability and safety of industrial production, it is necessary to regulate the behavior of employees. However, the high background complexity, low pixel count, occlusion and fuzzy appearance can result in a high leakage rate and poor detection accuracy of small objects. Considering the above problems, this paper proposes the EFE-YOLO (Enhanced feature extraction-You Only Look Once) algorithm to improve the detection of industrial small objects. To enhance the detection of fuzzy and occluded objects, the PSRFA (PixelShuffle and Receptive-Field Attention) upsampling module is designed to preserve and reconstruct more detailed information and extract the receptive-field attention weights. Furthermore, the MSE (multi-scale and efficient) downsampling module is designed to merge global and local semantic features to alleviate the problem of false and missed detection. Subsequently, the AFAF (Adaptive Feature Adjustment and Fusion) module is designed to highlight the important features and suppress background information that is not beneficial for detection. Finally, the EIoU loss function is used to improve the convergence speed and localization accuracy. All experiments are conducted on homemade dataset. The improved YOLOv5 algorithm proposed in this paper improves mAP@0.50 (mean average precision at a threshold of 0.50) by 2.8\% compared to the YOLOv5 algorithm. The average precision and recall of small objects show an improvement of 8.1\% and 7.5\%, respectively. The detection performance is still leading in comparison with other advanced algorithms.

An Application of the Scaled–Pixel–Counting Protocol to Quantify the Radiological Features of Anatomical Structures of the Normal Tarsal Joint in Horses

Abstract Background: As high-performance human and equine athletes train and compete at the highest level of effort, the prevention of high-performance-cased diseases, such as osteoarthritis (OA), requires knowledge of the anatomy and physiology of the subjected bones. Objective: Implementation of the scaled–pixel–counting protocol to quantify the radiological features of anatomical structures of the normal equine tarsal joint as the first step in the prevention of the tarsal joints OA in high-performance sport horses. Methods: A radiographic examination was performed in six cadaverous equine pelvic limbs. The dorso–plantar projection of the tarsal joint was performed using density standard (DS) attached to the radiographic cassette, standard X-ray equipment and standard diagnostic imaging protocol. On each of the radiographs, pixel brightness (PB) was extracted for each of the 10 steps (S1–S10) of DS. On each of the radiographs, seven regions of interest (ROIs) were annotated representing four bones (II tarsal bone [II TB], III tarsal bone [III TB], IV tarsal bone [IV TB] and central tarsal bone [CTB]) and three joints (proximal intertarsal joint [PIJ], distal intertarsal joint [DIJ] and tarsometatarsal joint [TMJ]), respectively. For each ROI, the percentage (%) of number of pixels (NP) from each range was calculated. Results: The % of NP was lower in bones than in joint spaces for S1–S6 and was higher in bones than in joint spaces for S8–S10. The % of NP was higher in PIJ than TMJ for S1 and higher in PIJ than DIJ for S4. No differences were found between consecutive bones for all examined steps of DS. Conclusions: An application of the scaled–pixel–counting protocol provides the quantitative radiological features of normal bone and joint structures of the tarsal joint in horses, making possible differentiation of the lucency of joint space and opacity of bone structure.

Phase identification and micromechanical properties of non-traditional and natural pozzolan based alkali-activated materials

Four groups of non-traditional and natural pozzolan (NNP) based (aluminosilicate-based) materials, calcined clays, ground bottom ashes, volcanic ashes, and fluidized bed combustion ashes, were alkali activated using a hybrid solution of sodium silicate and sodium hydroxide. The microhardness and reduced modulus of the phases present in eleven alkali-activated pastes were measured using nanoindentation. At least 800 data points were collected from 28-day old ambiently cured paste samples. Unsupervised machine learning techniques i.e., k-means clustering and Gaussian mixture modeling (GMM) were used for the classification of the micromechanical properties supplemented by scanning electron microscopy (SEM) and energy dispersive X-ray spectroscopy (EDS). The clustering of micromechanical and EDS data revealed five distinct phases in these hardened pastes. The alkali-activated gels identified had reduced modulus values ranging from 12 to 34 GPa. The remnant phases were partly reacted grains and unreacted minerals exhibiting reduced modulus values ranging from 35 to 105 GPa. Micromechanical property contour plots and SEM image pixel count plots were used to validate the phase assemblage. Additionally, the identification capabilities and advantages of the method are assessed by direct comparison with experimental results for different alkali-activated gels.

Synthetic temporal bone CT generation from UTE-MRI using a cycleGAN-based deep learning model: advancing beyond CT-MR imaging fusion.

The aim of this study is to develop a deep-learning model to create synthetic temporal bone computed tomography (CT) images from ultrashort echo-time magnetic resonance imaging (MRI) scans, thereby addressing the intrinsic limitations of MRI in localizing anatomic landmarks in temporal bone CT. This retrospective study included patients who underwent temporal MRI and temporal bone CT within one month between April 2020 and March 2023. These patients were randomly divided into training and validation datasets. A CycleGAN model for generating synthetic temporal bone CT images was developed using temporal bone CT and pointwise encoding-time reduction with radial acquisition (PETRA). To assess the model's performance, the pixel count in mastoid air cells was measured. Two neuroradiologists evaluated the successful generation rates of 11 anatomical landmarks. A total of 102 patients were included in this study (training dataset, n = 54, mean age 58 ± 14, 34 females (63%); validation dataset, n = 48, mean age 61 ± 13, 29 females (60%)). In the pixel count of mastoid air cells, no difference was observed between synthetic and real images (679 ± 342 vs 738 ± 342, p = 0.13). For the six major anatomical sites, the positive generation rates were 97-100%, whereas those of the five major anatomical structures ranged from 24% to 83%. We developed a model to generate synthetic temporal bone CT images using PETRA MRI. This model can provide information regarding the major anatomic sites of the temporal bone using MRI. The proposed algorithm addresses the primary limitations of MRI in localizing anatomic sites within the temporal bone. CT is preferred for imaging the temporal bone, but has limitations in differentiating pathology there. The model achieved a high success rate in generating synthetic images of six anatomic sites. This can overcome the limitations of MRI in visualizing key anatomic sites in the temporal skull.

A study on the occurrence modes and distribution characteristics of sulfur and mercury in coal gasification slag

Although coal gasification is recognized as a core technology for clean coal utilization, S and Hg can migrate to gas, wastewater, and slag during the gasification process, causing environmental pollution. It is well known that S and Hg have a strong affinity. Therefore, the interaction between S and Hg during the gasification process warrants further investigation. In this study, the occurrence modes and distribution characteristics of S and Hg in gasification slag were systematically investigated using multiple treatments and various characterization techniques. The results showed that sulfur in the gasification slag exists predominantly as organic sulfur, while mercury mainly exists as HgS/silicate-bound Hg. Although the relative enrichment index of Hg (RE < 0.7) indicates its high volatility, a more pronounced enrichment effect for mercury of fine slag was indicated by its much higher RE than coarse slag. When exploring the relationship among the contents of C, S, and Hg and specific surface area in gasification slag, it was found that the correlation between S and Hg content in fine slag was the strongest, with a correlation coefficient (R2) of 0.96, indicating a significant influence of sulfur content in fine slag on mercury content. Additionally, it was observed that the S and Hg contents in gasification slag increased with the decrease of particle size and density. These results provide an important understanding of the distribution, migration, and transformation behavior of S and Hg during coal gasification, as well as a certain theoretical support and technical basis for the resource utilization of gasification slag.

Towards the establishment of a green and sustainable analytical methodology for hyperspectral imaging-based authentication of wholemeal bread

The increased interest in whole-grain products, along non unified European regulations on the composition of wholemeal bread could lead to its misleading labelling. Therefore, to ensure the safety of consumers, both health-wise and from possible fraud, a novel hyperspectral imaging-based authentication method is being proposed, given that no previous study has combined imaging techniques with authentication of wholemeal flour content. Quantification based on pixel counting by classification (QPC) utilizes multivariate analysis methods such as PLS-DA and SVM to classify pixels within a bread sample (as Wholemeal and White flour), based on their visible-near-infrared spectra, to later estimate its proportion of wholemeal flour. This is in accordance with the heterogeneous nature of bread samples, in which individual pixels belonging to both wholemeal and white flour can be accounted for, which was proved by implementing unsupervised training techniques such as hierarchical cluster analysis (HCA). Results show that the quantification model was able to successfully predict wholemeal flour content with a maximum deviation of 8 g wholemeal flour/100 g flour from the estimated value.

Role of Piezo2 in Schwann Cell Volume Regulation and Its Impact on Neurotrophic Release Regulation.

Tactile perception relies on mechanoreceptors and nerve fibers, including c-fibers, Aβ-fibers and Aδ-fibers. Schwann cells (SCs) play a crucial role in supporting nerve fibers, with non-myelinating SCs enwrapping c-fibers and myelinating SCs ensheathing Aβ and Aδ fibers. Recent research has unveiled new functions for cutaneous sensory SCs, highlighting the involvement of nociceptive SCs in pain perception and Meissner corpuscle SCs in tactile sensation. Furthermore, Piezo2, previously associated with Merkel cell tactile sensitivity, has been identified in SCs. The goal of this study was to investigate the channels implicated in SC mechanosensitivity and the release process of neurotrophic factor secretion. Immortalized IFRS1 SCs and human primary SCs generated two distinct subtypes of SCs: undifferentiated and differentiated SCs. Quantitative PCR was employed to evaluate the expression of differentiation markers and mechanosensitive channels, including TRP channels (TRPV4, TRPM7 and TRPA1) and Piezo channels (Piezo1 and Piezo2). To validate the functionality of specific mechanosensitive channels, Ca2+ imaging and electronic cell sizing experiments were conducted under hypotonic conditions, and inhibitors and siRNAs were used. Protein expression was assessed by Western blotting and immunostaining. Additionally, secretome analysis was performed to evaluate the release of neurotrophic factors in response to hypotonic stimulation, with BDNF, a representative trophic factor, quantified using ELISA. Induction of differentiation increased Piezo2 mRNA expression levels both in IFRS1 and in human primary SCs. Both cell types were responsive to hypotonic solutions, with differentiated SCs displaying a more pronounced response. Gd3+ and FM1-43 effectively inhibited hypotonicity-induced Ca2+ transients in differentiated SCs, implicating Piezo2 channels. Conversely, inhibitors of Piezo1 and TRPM7 (Dooku1 and NS8593, respectively) had no discernible impact. Moreover, Piezo2 in differentiated SCs appeared to participate in regulatory volume decreases (RVD) after cell swelling induced by hypotonic stimulation. A Piezo2 deficiency correlated with reduced RVD and prolonged cell swelling, leading to heightened release of the neurotrophic factor BDNF by upregulating the function of endogenously expressed Ca2+-permeable TRPV4. Our study unveils the mechanosensitivity of SCs and implicates Piezo2 channels in the release of neurotrophic factors from SCs. These results suggest that Piezo2 may contribute to RVD, thereby maintaining cellular homeostasis, and may also serve as a negative regulator of neurotrophic factor release. These findings underscore the need for further investigation into the role of Piezo2 in SC function and neurotrophic regulation.

The Effect of Priority Assignment the Role of Evaluator and Executive in Collaborative Training on the Acquisition of Kinematic and Accuracy of Dart Throwing Skill

Background: Collaborative training can enhance individual learning, but the effect of role assignment on skill acquisition is unclear. Objectives: Therefore, this study aims to explore the influence of the evaluator and executor roles on the accuracy and kinematic indicators of dart throwing skill. Methods: Forty-eight female university students (mean age = 21.71 ± 1.14 years) participated in the study. Following dart throwing familiarization, participants were randomly assigned to individual group (IG), first-performer (FPG), and first-evaluator groups (FEG) (as a dyad condition) with alternating role orders. All groups completed a pre-test of 10 dart throws while kinematics was recorded via video camera. Practice consisted of 20 blocks of 6 trials (n = 120 physical trials for IG; n = 60 evaluation and n = 60 physical trials for FPG and FEG). Post-tests 1 and 2 directly followed after role reversals for dyads after each 60 trials in the acquisition phase. Accuracy was assessed via mean radial and variable errors. Kinematics (elbow release angle, average angular velocity, elbow range of motion) were analyzed using Kinovea software. Results: A two-way ANOVA revealed the FPG exhibited a significantly smaller release angle compared to IG. However, no significantly differences observed between FEG and IG for kinematic variables. Accuracy improved significantly from pre-to post-test at the three groups. Individual group led to higher accuracy than FPG, and frist-performer group had higher RE than the first-evaluator. Conclusions: The findings of this study support the benefits of observational learning in the early stages of learning. Also, priority assignment the role of evaluator and executive can influences motor performance in a dyadic approach.

Distributional loss for convolutional neural network regression and application to parameter estimation in satellite navigation signals

Convolutional Neural Network (CNN) have been widely used in image classification. Over the years, they have also benefited from various enhancements and they are now considered state-of-the-art techniques for image-like data. However, when they are used for regression to estimate some function value from images, few recommendations are available to construct robust CNN regressor models. In this study, a robustness enforcing mechanism is proposed for CNN regression models. It combines convolutional neural layers to extract high level features representations from images with a soft labelling technique that helps generalization performance. More specifically, as the deep regression task is challenging, the idea is to account for some uncertainty in the targets that are seen as distributions around their mean. Building from earlier work (Imani and White, 2018), a specific histogram loss function based on the Kullback-Leibler (KL) divergence is applied during training. The prior distributions are selected according to the physical characteristics of the parameters to estimate. To assess and illustrate the technique, the model is applied to Global Navigation Satellite System (GNSS) multipath estimation where multipath signal parameters have to be estimated from correlator output images from the I and Q channels. The multipath signal delay, magnitude, Doppler shift frequency and phase parameters are estimated from synthetically generated datasets of satellite signals. Experiments are conducted under various receiving conditions and various input images resolutions to test the estimation performances quality and robustness. The results show that the proposed soft labelling CNN technique using distributional loss outperforms classical CNN regression under all conditions. Furthermore, the extra learning performance achieved by the model allows the reduction of input image resolution from 80x80 down to 40x40 or sometimes 20x20.