Sr Model Research Articles

Rice yield prediction using Bayesian analysis on rainfed lands in the Sumbing-Sindoro Toposequence, Indonesia

Since rainfed rice fields typically lack nutrients, frequently experience drought, and require more fund to support farming operations, the production results become erratic and unpredictable. This research aims to construct location-specific rice yield predictions in the rainfed rice fields among the Sumbing-Sindoro Toposequence, Central Java, using a Bayesian method. This study is a survey with an exploratory descriptive methodology based on data from both field and laboratory research. Prediction model analysis using the Bayesian Neural Network (BNN) method on 12geographical units, sampling spots were selected with intention. The following variables were measured: soil (pH level, Organic-C, Total-N, Available-P, Available-K, soil types, elevation, slope) and climate (rainfall, evapotranspiration). According to the statistical analysis used, the BNN model’s performance has the highest accuracy, with an RMSE value of 0.448 t/ha, which compares to the MLR and SR models, indicating the lowest error deviation. To obtain the ideal parameter sampling design, parameter distribution is directly and simultaneously optimised using an optimisation technique based on Pareto optimality. The top 7 data sets (slope, available-P, evapotranspiration, soil type, rainfall, organic-C, and pH) yielded the highest accuracy based on the test results for the three-parameter groups. The coefficient of determination has the highest value, 0.855, while the RMSE test for the model using the top 7 data set has the lowest error value at 0.354 t/ha and 18.71%, respectively. By developing location-specific rice yield predictions using a Bayesian method, farmers and agricultural practitioners can benefit from more accurate and reliable estimates of crop productivity

Multimodal-Boost: Multimodal Medical Image Super-Resolution Using Multi-Attention Network With Wavelet Transform.

Multimodal medical images are widely used by clinicians and physicians to analyze and retrieve complementary information from high-resolution images in a non-invasive manner. Loss of corresponding image resolution adversely affects the overall performance of medical image interpretation. Deep learning-based single image super resolution (SISR) algorithms have revolutionized the overall diagnosis framework by continually improving the architectural components and training strategies associated with convolutional neural networks (CNN) on low-resolution images. However, existing work lacks in two ways: i) the SR output produced exhibits poor texture details, and often produce blurred edges, ii) most of the models have been developed for a single modality, hence, require modification to adapt to a new one. This work addresses (i) by proposing generative adversarial network (GAN) with deep multi-attention modules to learn high-frequency information from low-frequency data. Existing approaches based on the GAN have yielded good SR results; however, the texture details of their SR output have been experimentally confirmed to be deficient for medical images particularly. The integration of wavelet transform (WT) and GANs in our proposed SR model addresses the aforementioned limitation concerning textons. While the WT divides the LR image into multiple frequency bands, the transferred GAN uses multi-attention and upsample blocks to predict high-frequency components. Additionally, we present a learning method for training domain-specific classifiers as perceptual loss functions. Using a combination of multi-attention GAN loss and a perceptual loss function results in an efficient and reliable performance. Applying the same model for medical images from diverse modalities is challenging, our work addresses (ii) by training and performing on several modalities via transfer learning. Using two medical datasets, we validate our proposed SR network against existing state-of-the-art approaches and achieve promising results in terms of structural similarity index (SSIM) and peak signal-to-noise ratio (PSNR).

Effects of crustal assimilation on 238U-230Th disequilibria in continental arc settings

Compositions of arc magmas depend on several factors and are often thought to reflect conditions in the mantle wedge and at the slab-mantle interface. However, in continental arc settings, magmas are also influenced by assimilation of continental crust. Here, we present measurements and modeling of 238U-230Th activity ratios, Sr, Nd, Hf, and Pb isotopic compositions, and major and trace element concentrations in young, historic lavas erupted from Reventador, an active stratovolcano in the Ecuadorian Andes. In arc lavas, 238U-230Th disequilibria are often assumed to reflect processes occurring in the mantle wedge, as U and Th behave differently in this relatively oxidized and fluid-rich environment. Enhanced mobility of hexavalent U in aqueous fluids results in (230Th/238U) < 1 and elevated (238U/232Th), which are common in arc lavas. However, the majority of Reventador lavas have (230Th/238U) = 1.0–1.1 and (238U/232Th) = 0.94–1.12, the latter of which is considerably lower than the depleted mantle ((238U/232Th) ∼ 1.5, Sims and Hart, 2006). While this Th enrichment could be due to melting of subducted oceanic crust, approximately linear trends between (230Th/232Th), wt. % SiO2, and radiogenic isotope ratios indicate otherwise. We argue that crustal assimilation lowers long-term, or time-integrated, (238U/232Th) in Reventador magmas. To quantify the effects of assimilation we modeled stepwise assimilation and fractional crystallization. Observed trends between (230Th/232Th), 87Sr/86Sr, εNd, εHf, and 208Pb/206Pb can be reproduced by up to 10% assimilation, which is consistent with previous regional studies. However, reproducing the full spectrum of isotopic diversity among Reventador lavas requires heterogeneous basalt compositions. In a broader context, this study emphasizes the need to consider crustal processes when examining continental arcs. While 238U-230Th disequilibria develop in the mantle wedge, they can be overwritten by subsequent interaction with continental crust.

Adding a simple production term to Reynolds-averaged Navier–Stokes turbulence models for flows over two-dimensional hills

We consider an additional production term for the k,ε turbulence model that is activated by curvature, for turbulent flow over two-dimensional hills of varying steepness. The new term depends on the difference between the strain rate, S, and the rotation, R, which we refer to as the “SR” modification. It is compared to the standard k,ε turbulence model, the Kato–Launder model, and the re-normalization group and realizable versions of the k,ε model. The Kato–Launder model showed the best overall predictions for mean velocity, turbulent kinetic energy, and Reynolds shear stress at most locations before, on, and after the crest of the hills. The SR model was slightly less accurate but uniquely predicted the flow separation in the lee of the steeper hill and was also correctly predicted the flow re-attachment point. This study demonstrates the importance of including a curvature production term in k–ε-based models for flows over hills.

Design of a safety round model for intensive care units

IntroductionSafety Rounds (SR) are an operational tool that allow knowing adherence to good practices, help identify risks and incidents in patient safety (PS), allowing improvement actions to be implemented. The objective of this work was the design of a procedure to perform SR in an Intensive Care Unit (ICU). MethodsPreparation of a checklist for the development of SR in the ICU through the nominal group technique, with the participation of managers, middle managers and professionals from different disciplines and categories. In the first place, a group of experts agreed, based on the recommendations on good practices in PS, the definition of items, their coding, the criteria for compliance and the impact of non-compliance. Subsequently, its viability was determined through a cross-sectional study through the piloting of two SRs to adjust the items in real clinical practice conditions. ResultsA specific SR model for ICUs has been obtained through a checklist. The group of experts prepared a first list made up of 39 items of 6 essential dimensions and defined the method of implementation. Mean time to complete the two SRs was 85 min, including the briefing and subsequent debriefing. After the validation pilot, the dimensions were reduced to 5, 3 items were deleted, 2 items were transferred to another dimension and 3 items related to nosocomial infections and informed consent were modified. In addition, the data sources, the compliance criteria and their relative weight were redefined. The final list was considered useful and relevant to improve practice. ConclusionsThrough a consensus methodology, a checklist has been built to be used in the RS of an ICU. This model can serve as a basis for its use in healthcare services with similar characteristics.

WLSAN: Wavelet-Layer-Spatial Attention Network for Single Image Super Resolution

Single Image Super Resolution has been a hot topic in recent years, which has wide application prospects. Some recent works use attention in SR to capture the inter-channel and inter-spatial relationships of feature maps. How- ever, these works cannot focus on the image features at different frequency do- mains. At the same time, the loss function of some SR models will make the model more inclined to reconstruct the smooth part and cannot consider the de- tails in multiple directions of the image. To address these problems, we propose a Wavelet-Layer-Spatial Attention Network (WLSAN), which makes use of both essential global context and local information to improve accuracy and visual quality. Specifically, the proposed WLSAN consists of wavelet attention to model inter-dependencies by decomposing the image signals and non-local attention, including channel-spatial-layers. Meanwhile, we combine L1 with improved Sobel Loss, which enhances the stability during training and constrains different aspects of the HR image generation. Extensive experiments demonstrate that the proposed WLSAN exceeds many classical methods and states of the arts.

A Mother’s Intentional Use of Serve and Return Interactions: A Start to Child Participation, Decolonized Parenting, and Child-led Play

Amidst the large corpus of international research on the relevance and deficiency of quality adult-child interactions in the first years of a child’s life there seems to be limited knowledge on how adults can build their capacity to offer high-quality interactions in homes and early years settings. Recent neuroscientific evidence presents the “Serve and Return” (SR) model to promote the “practice” of successful interactions that help build a child’s brain on a larger societal scale. To this, the SR model takes center stage in the presented work to showcase the aftermath of its intentional use by one mother to promote quality interactions with her infant in Malta. This paper aims to explore: (1) the attitudes, knowledge, and understanding the mother adopts to initiate and develop successful SR style of interactions with her daughter (age: 10 to 24 months); and (2) the type of interactions that were facilitated through the mother’s intentional use of the SR model over time. The work is framed within Bowlby’s attachment theory, postcolonial theory, and a child’s rights lens. It draws on data from a fourteen-month study: the mother’s reflective journal, transcriptions of recordings interactions, and monthly video-recorded analytic discussions between the researcher and the mother. Findings locate a transformation point that led the mother to explore a more sensitive and responsive attitude, strengthen her understanding, and overcome challenges faced with SR interactions. A key result is how a bi-directional ‘loop’ developed and generated affordances of child-led playful interactions that maximized learning, promoted child participation, and decolonized parenting. Implications are discussed to address the need for counseling, support, and training for parents and educators and activism on quality interactions. Keywords: Serve and return, adult-child interactions, child-led play, decolonized parenting, child participation DOI: 10.7176/JEP/14-12-05 Publication date: April 30 th 2023

Diseño de un modelo de ronda de seguridad para unidades de cuidados intensivos

IntroductionSafety Rounds (SR) are an operational tool that allow knowing adherence to good practices, help identify risks and incidents in patient safety (PS), allowing improvement actions to be implemented. The objective of this work was the design of a procedure to perform SR in an Intensive Care Unit (ICU). MethodsPreparation of a checklist for the development of SR in the ICU through the nominal group technique, with the participation of managers, middle managers and professionals from different disciplines and categories. In the first place, a group of experts agreed, based on the recommendations on good practices in PS, the definition of items, their coding, the criteria for compliance and the impact of non-compliance. Subsequently, its viability was determined through a cross-sectional study through the piloting of two SRs to adjust the items in real clinical practice conditions. ResultsA specific SR model for ICUs has been obtained through a checklist. The group of experts prepared a first list made up of 39 items of 6 essential dimensions and defined the method of implementation. Mean time to complete the two SRs was 85minutes, including the briefing and subsequent debriefing. After the validation pilot, the dimensions were reduced to 5, 3 items were deleted, 2 items were transferred to another dimension and 3 items related to nosocomial infections and informed consent were modified. In addition, the data sources, the compliance criteria and their relative weight were redefined. The final list was considered useful and relevant to improve practice. ConclusionsThrough a consensus methodology, a checklist has been built to be used in the RS of an ICU. This model can serve as a basis for its use in healthcare services with similar characteristics.

Comparison of Ultrasound Scores in Differentiating between Benign and Malignant Adnexal Masses

Subjective ultrasound assessment by an expert examiner is meant to be the best option for the differentiation between benign and malignant adnexal masses. Different ultrasound scores can help in the classification, but whether one of them is significantly better than others is still a matter of debate. The main aim of this work is to compare the diagnostic performance of some of these scores in the evaluation of adnexal masses in the same set of patients. This is a retrospective study of a consecutive series of women diagnosed as having a persistent adnexal mass and managed surgically. Ultrasound characteristics were analyzed according to IOTA criteria. Masses were classified according to the subjective impression of the sonographer and other ultrasound scores (IOTA simple rules -SR-, IOTA simple rules risk assessment -SRRA-, O-RADS classification, and ADNEX model -with and without CA125 value-). A total of 122 women were included. Sixty-two women were postmenopausal (50.8%). Eighty-one women had a benign mass (66.4%), and 41 (33.6%) had a malignant tumor. The sensitivity of subjective assessment, IOTA SR, IOTA SRRA, and ADNEX model with or without CA125 and O-RADS was 87.8%, 66.7%, 78.1%, 95.1%, 87.8%, and 90.2%, respectively. The specificity for these approaches was 69.1%, 89.2%, 72.8%, 74.1%, 67.9%, and 60.5%, respectively. All methods with similar AUC (0.81, 0.78, 0.80, 0.88, 0.84, and 0.75, respectively). We concluded that IOTA SR, IOTA SRRA, and ADNEX models with or without CA125 and O-RADS can help in the differentiation of benign and malignant masses, and their performance is similar to the subjective assessment of an experienced sonographer.

Zero-Shot Blind Learning for Single-Image Super-Resolution

Deep convolutional neural networks (DCNNs) have manifested significant performance gains for single-image super-resolution (SISR) in the past few years. Most of the existing methods are generally implemented in a fully supervised way using large-scale training samples and only learn the SR models restricted to specific data. Thus, the adaptation of these models to real low-resolution (LR) images captured under uncontrolled imaging conditions usually leads to poor SR results. This study proposes a zero-shot blind SR framework via leveraging the power of deep learning, but without the requirement of the prior training using predefined imaged samples. It is well known that there are two unknown data: the underlying target high-resolution (HR) images and the degradation operations in the imaging procedure hidden in the observed LR images. Taking these in mind, we specifically employed two deep networks for respectively modeling the priors of both the target HR image and its corresponding degradation kernel and designed a degradation block to realize the observation procedure of the LR image. Via formulating the loss function as the approximation error of the observed LR image, we established a completely blind end-to-end zero-shot learning framework for simultaneously predicting the target HR image and the degradation kernel without any external data. In particular, we adopted a multi-scale encoder–decoder subnet to serve as the image prior learning network, a simple fully connected subnet to serve as the kernel prior learning network, and a specific depthwise convolutional block to implement the degradation procedure. We conducted extensive experiments on several benchmark datasets and manifested the great superiority and high generalization of our method over both SOTA supervised and unsupervised SR methods.

Meta-Learning based Degradation Representation for Blind Super-Resolution.

Blind image super-resolution (blind SR) aims to generate high-resolution (HR) images from low-resolution (LR) input images with unknown degradations. To enhance the performance of SR, the majority of blind SR methods introduce an explicit degradation estimator, which helps the SR model adjust to unknown degradation scenarios. Unfortunately, it is impractical to provide concrete labels for the multiple combinations of degradations (e.g., blurring, noise, or JPEG compression) to guide the training of the degradation estimator. Moreover, the special designs for certain degradations hinder the models from being generalized for dealing with other degradations. Thus, it is imperative to devise an implicit degradation estimator that can extract discriminative degradation representations for all types of degradations without requiring the supervision of degradation ground-truth. To this end, we propose a Meta-Learning based Region Degradation Aware SR Network (MRDA), including Meta-Learning Network (MLN), Degradation Extraction Network (DEN), and Region Degradation Aware SR Network (RDAN). To handle the lack of ground-truth degradation, we use the MLN to rapidly adapt to the specific complex degradation after several iterations and extract implicit degradation information. Subsequently, a teacher network MRDAT is designed to further utilize the degradation information extracted by MLN for SR. However, MLN requires iterating on paired LR and HR images, which is unavailable in the inference phase. Therefore, we adopt knowledge distillation (KD) to make the student network learn to directly extract the same implicit degradation representation (IDR) as the teacher from LR images. Furthermore, we introduce an RDAN module that is capable of discerning regional degradations, allowing IDR to adaptively influence various texture patterns. Extensive experiments under classic and real-world degradation settings show that MRDA achieves SOTA performance and can generalize to various degradation processes.

A Data Enhancement Method toward Real-World Single Image Super-Resolution

Introducing convolutional neural networks (CNNs) into single image super-resolution (SISR) has achieved remarkable performance in experimental scenarios over the past decades. However, maintaining constant mapping complexity, most existing CNN-based SISR approaches make it challenging to reconstruct high-quality images in real scenarios because of considerable variation between authentic degradation and simulated degradation. In this paper, to improve SISR models’ capabilities in the real world, we propose a data enhancement method, consisting of frequency domain data augmentation (FDA) and dynamical frequency loss (DFL). By introducing high-resolution images’ frequency information, the FDA enhances the quality and quantity of data, regularizing the model to learn “how” to appropriately apply super-resolution on different frequency components of a given image. In addition, to further strengthen the regularization effect, we design DFL to dynamically assign the loss trade-off hyperparameters of distinct frequency components, guiding the model to allocate computational overhead reasonably. Considering quantitative analysis and visual quality in combination, extensive experiments prove that the proposed enhancement method significantly improves SR models’ capabilities in real scenarios without adding any computational cost to the evaluation procedure.

Online Video Super-Resolution With Convolutional Kernel Bypass Grafts

Deep learning-based models have achieved remarkable performance in video super-resolution (VSR) in recent years, but most of these models are less applicable to online video applications. These methods solely consider the distortion quality and ignore crucial requirements for online applications, e.g., low latency and low model complexity. In this paper, we focus on online video transmission in which VSR algorithms are required to generate high-resolution video sequences frame by frame in real time. To address such challenges, we propose an extremely low-latency VSR algorithm based on a novel kernel knowledge transfer method, named the convolutional kernel bypass graft (CKBG). First, we design a lightweight network structure that does not require future frames as inputs and saves extra time for caching these frames. Then, our proposed CKBG method enhances this lightweight base model by bypassing the original network with “kernel grafts”, which are extra convolutional kernels containing the prior knowledge of the external pretrained image SR models. During the testing phase, we further accelerate the grafted multibranch network by converting it into a simple single-path structure. The experimental results show that our proposed method can process online video sequences up to 110 FPS with very low model complexity and competitive SR performance.

Variable-density topology optimization and bending test of quasi-honeycomb sandwich structures

The topology optimization is considered to enhance the strength, stiffness, and specific energy absorption of a quasi-honeycomb sandwich structure since it can achieve the optimal distribution of materials. However, the existing material interpolation models do not make the topology structure have good clarity and stability. In the present study, a novel variable-density topology optimization based on an improved interpolation model is developed for the design of a quasi-honeycomb core. The combined cells are circularly spreading outward from the geometric center of the design domain, and the wall thickness function of the equivalent cell (i.e. a simplified model of the combined cell) is established on the basis of relative density. The SR material interpolation model is modified by adding the minimum elastic modulus term, fitting the weighting and penalty factors, and adopting the volume constraint of Bi-directional Evolutionary Structural Optimization (BESO). The optimization is conducted to minimize the compliance of the quasi-honeycomb core, in which the relative densities of equivalent cells are chosen as the design variables due to the mapping between topology elements and equivalent cells. The three-dimensional (3D) geometric models of original and optimized quasi-honeycomb cores, upper face sheets, and lower face sheets are built using SolidWorks and printed on a 3D printer. The deflection, strain, bending stiffness, and energy absorption under different material retention rates, restraint positions, and face sheet thicknesses are investigated by three-point bending tests. It is found that the improved SR material interpolation model is efficient for suppressing the grid dependence and checkerboard, and the mechanical properties of optimized quasi-honeycomb sandwich structures are significantly enhanced in comparison with original structures, confirming that the developed method provides important guidance for designing and optimizing the quasi-honeycomb sandwich structure.

DGRN: Image super-resolution with dual gradient regression guidance

In single image super-resolution (SISR), deep neural networks learn mainly nonlinear functions to obtain promising high-resolution (HR) images. However, there are usually two undesired limitations to recovered images of existing SR methods. First, since this task is typically an ill-posed problem, recovering the structural information for the SR process is usually sharp edges but distorted. Second, since this task generally has an extremely large space for the mapping function, learning this mapping from low-resolution (LR) to HR images is typically difficult. For the most part, SR models usually suffer from the lack of structural information for the objects in images and poor performance. To address the above issues, we propose a dual gradient regression scheme in the first stage of the network to recover the structure information of objects in images and the corresponding loss function to learn the difference between structural maps. In the second stage of the network, we restore HR gradient maps by the first stage to provide additional structural information for the second stage, further constraining the structure of the SR image and reducing the space of the possible functions. Extensive experiments demonstrate our results outperform the state-of-the-art SR methods in the SSIM, and achieve better visual effects than the state-of-the-art SR methods.

Remote Sensing Image Super-Resolution via Residual-Dense Hybrid Attention Network

Nowadays, remote sensing datasets with long temporal coverage generally have a limited spatial resolution, most of the existing research uses the single image super-resolution (SISR) method to reconstruct high-resolution (HR) images. However, due to the lack of information in low-resolution (LR) images and the ill-posed nature of SISR, it is difficult to reconstruct the fine texture of HR images under large-scale magnification factors (e.g., four times). To address this problem, we propose a new reference-based super-resolution method called a Residual-Dense Hybrid Attention Network (R-DHAN), which uses the rich texture information in the reference image to make up for the deficiency of the original LR image. The proposed SR model employs Super-Resolution by Neural Texture Transfer (SRNTT) as a backbone. Based on this structure, we propose a dense hybrid attention block (DHAB) as a building block of R-DHAN. The DHAB fuses the input and its internal features of current block. While making full use of the feature information, it uses the interdependence between different channels and different spatial dimensions to model and obtains a strong representation ability. In addition, a hybrid channel-spatial attention mechanism is introduced to focus on important and useful regions to better reconstruct the final image. Experiments show that compared with SRNTT and some classical SR techniques, the proposed R-DHAN method performs well in quantitative evaluation and visual quality.

LENS: Bandwidth-efficient video analytics with adaptive super resolution

Video streaming analytic pipelines are deployed widely nowadays, where in many cases videos are transmitted continuously from cameras to servers. However, video analytic accuracy highly depends on video resolution, and when bandwidth suffers only low-resolution videos can be transmitted which leads to low accuracy. The rapid development of super resolution DNNs sparks the possibility of reconstructing high-resolution videos reliably from low resolution videos, and thus boosts video analytic accuracy. However, pretrained SR models may fail to cope with dynamic video content, while introducing online learning can be efficient under this condition. In this paper, we propose a practical system, LENS, which integrates an online learning period into analytic pipelines. The experimental results show that LENS is capable of responding to video dynamics and retraining SR models for changes quickly. In summary, LENS can save bandwidth consumption by up to 87%, or achieve a higher accuracy by up to 9.6% compared with state-of-the-art methods with slight additional bandwidth.

Advances on Self-Regulation Models: A New Research Agenda Through the SR vs ER Behavior Theory in Different Psychology Contexts.

The aim of this paper is to demonstrate how Bandura's Social Cognitive Theory (1986) influenced the development of several complementary models of the construct of Self-Regulation. Building on the foundation of Self-Determination Theory, SDT (2000), and Zimmerman's Self-Regulation Theory, SR (2001), with their assumptions, contributions, goddesses, and limitations, we come to the Self- vs. External Regulatory Theory, SR-ER (2021). Finally, we integrate recent evidence demonstrating the explanatory adequacy of the SR vs. ER model for different psychological constructions in different settings related to education, health, clinical practice and social work. Complementary, a new theoretical and empirical research agenda is presented, to continue testing the adequacy of SR vs. ER assumptions, and to better understand the behavioral variability of the different constructs studied.

Silico antimonate nanocomposite material: I- preparation, characterization and its application for separation of strontium and rubidium from aqueous solutions

ABSTRACT Sorption of Sr(II) and/or Rb(I) onto synthesised silico antimonate (SiSb) nanocomposite was investigated in this work, using batch equilibrium and column techniques. SiSb was fabricated by precipitation technique and characterised by various analytical tools. The adsorption of Sr(II) and/or Rb(I) includes the influence of shaking time, distribution coefficient, kinetics, capacity, and column separation. The data prove that SiSb has a quick equilibrium time (40 min), the distribution coefficients (Kd) as a function of pH have maximum separation factors ( α R b S r ) equal to 162.1 at pH 6, reaction kinetics follow a pseudo-second-order model, sorption capacity for Sr(II) and Rb(I) is 48.5 and 13.8 mg/g, respectively. Column data reveal that Sr(II) can be loaded and separated from Sr(II)-Rb(I) as a simulation model for Sr(II) recovery from its Sr(II)-Rb(I) system using different concentrations of HNO3 as eluent.

Simulation analysis of SR motor speed regulation system based on PI control

The switching reluctance motor speed regulation system (SRD) will produce more serious nonlinear problems when running, and the current conventional solution is analyzed and discussed as a PI control method(HE 2008). Based on the SR motor model included in Matlab/Simuliunk simulation system, the simulation results are obtained by using the comparison method with or without PI control, and the advantages and disadvantages of the PI control method are analyzed to achieve the requirements for the switched reluctance motor control system.