Training Process Research Articles

Anatomical prior-based vertebral landmark detection for spinal disorder diagnosis

As one of fundamental ways to interpret spine images, detection of vertebral landmarks is an informative prerequisite for further diagnosis and management of spine disorders such as scoliosis and fractures. Most existing machine learning-based methods for automatic vertebral landmark detection suffer from overlapping landmarks or abnormally long distances between nearby landmarks against anatomical priors, and thus lack sufficient reliability and interpretability. To tackle the problem, this paper systematically utilizes anatomical prior knowledge in vertebral landmark detection. We explicitly formulate anatomical priors of the spine, related to distances among vertebrae and spatial order within the spine, and integrate these geometrical constraints within training loss, inference procedure, and evaluation metrics. First, we introduce an anatomy-constraint loss to regularize the training process with the aforementioned contextual priors explicitly. Second, we propose a simple-yet-effective anatomy-aided inference procedure by employing sequential prediction rather than a parallel counterpart. Third, we provide novel anatomy-related metrics to quantitatively evaluate to which extent landmark predictions follow the anatomical priors, as is not reflected within the widely-used landmark localization error metric. We employ the localization framework on 1410 anterior-posterior radiographic images. Compared with competitive baseline models, we achieve superior landmark localization accuracy and comparable Cobb angle estimation for scoliosis assessment. Ablation studies demonstrate the effectiveness of designed components on the decrease of localization error and improvement of anatomical plausibility. Additionally, we exhibit effective generalization performance by transferring our detection method onto sagittal 2-D slices of CT scans and boost the performance of downstream compression fracture classification at vertebra-level.

SDR2Tr‐GAN: A Novel Medical Image Fusion Pipeline Based on GAN With SDR2 Module and Transformer Optimization Strategy

ABSTRACTIn clinical practice, radiologists diagnose brain tumors with the help of different magnetic resonance imaging (MRI) sequences and judge the type and grade of brain tumors. It is hard to realize the brain tumor computer‐aided diagnosis system only with a single MRI sequence. However, the existing multiple MRI sequence fusion methods have limitations in the enhancement of tumor details. To improve fusion details of multi‐modality MRI images, a novel conditional generative adversarial fusion network based on three discriminators and a Staggered Dense Residual2 (SDR2) module, named SDR2Tr‐GAN, was proposed in this paper. In the SDR2Tr‐GAN network pipeline, the generator consists of an encoder, decoder, and fusion strategy that can enhance the feature representation. SDR2 module is developed with Res2Net into the encoder to extract multi‐scale features. In addition, a Multi‐Head Spatial/Channel Attention Transformer, as a fusion strategy to strengthen the long‐range dependencies of global context information, is integrated into our pipeline. A Mask‐based constraint as a novel fusion optimization mechanism was designed, focusing on enhancing salient feature details. The Mask‐based constraint utilizes the segmentation mask obtained by the pre‐trained Unet and Ground Truth to optimize the training process. Meanwhile, MI and SSIM loss jointly improve the visual perception of images. Extensive experiments were conducted on the public BraTS2021 dataset. The visual and quantitative results demonstrate that the proposed method can simultaneously enhance both global image quality and local texture details in multi‐modality MRI images. Besides, our SDR2Tr‐GAN outperforms the other state‐of‐the‐art fusion methods regarding subjective and objective evaluation.

DeepPipe: A Multi-Stage Knowledge-Enhanced Physics-Informed Neural Network for Hydraulic Transient Simulation of Multi-Product Pipeline

In the chemical pipelining industry, owing to the high-pressure transportation process, an accurate hydraulic transient simulation tool plays a central role in preventing the slack line flow and overpressure from causing pipeline operation treacherous. Nevertheless, the current model-driven method often faces challenges in balancing computational efficiency with accuracy, and the existing data-driven models struggle to produce explainable results from the physics perspectives since insufficient theoretical principles are incorporated into the model training. Additionally, the existing physics-informed learning architecture fails to achieve a gradient-balanced training, resulting from the significant magnitude difference in outputs and multiple loss terms. Consequently, a Multi-Stage Knowledge-Enhanced Physics-Informed Neural Network (MS-KE-PINN) is proposed for the hydraulic transient simulation of multi-product pipelines. To enforce the neural network producing simulation results with high consistency to physical laws, the governing equations, boundary, and initial condition are incorporated into the training process for an efficient mesh-free simulation. Then, considering that the significant magnitude difference between outputs can easily lead to deficient performance in the gradient descent, the magnitude conversion on the outputs and the equivalent conversion of the governing equations are implemented to enhance the training effect of the neural network. Subsequently, to tackle the imbalanced gradient of multiple loss terms with fixed weights, a multi-stage hierarchical training strategy is designed to improve the approximation capacity of the neural network. Numerical simulation cases demonstrate a better approximation function of the proposed model than the state-of-art models, while the mean absolute percentage errors yielded by MS-KE-PINN are reduced by 77.4 %, 88.7 %, and 87.8 % in three simulation operation conditions for pressure prediction. Furthermore, experimental investigations from a real-world multi-product pipeline suggest that the proposed model can still draw accurate simulation results even under complex and dynamic hydraulic transient scenarios in practice, with root mean squared errors reduced by 94.8 % and 80 % than that of the physics-informed neural network. To this end, the proposed model can conduct accurate and effective hydraulic transient analysis, thus ensuring the safe operation of the pipeline.

Habilidades no técnicas en la educación en cirugía. Una revisión panorámica de la literatura

IntroductionThere is a growing recognition of incorporating non-technical skills during the training process of a surgeon, as a strategy to increase their future professional performance. There is a gap in the educational methodology used. A panoramic review of the literature is carried out to identify the status, gaps and research opportunities. MethodsPanoramic review of the literature with the Joanna Briggs Institute methodology. Studies that addressed instruction, measurement, outcome evaluation, and the educational impact of non-technical skills on residents were analyzed. ResultsThe studies analyzed were carried out between 2012 and 2021. The skills studied were situational awareness, decision making, communication, teamwork, and leadership. There are studies on validation of instruments and implementation of education models. The knowledge gaps identified were the lack of standardization of the methods used for the training and evaluation of these competencies, as well as the lack of studies in Latin America. DiscussionThe teaching of non-technical skills is a pending issue in the training of a surgeon. The relevance of the topic requires its study and incorporation into study curricula.

Enhancing high-resolution reconstruction of flow fields using physics-informed diffusion model with probability flow sampling

The application of artificial intelligence (AI) technology in fluid dynamics is becoming increasingly prevalent, particularly in accelerating the solution of partial differential equations and predicting complex flow fields. Researchers have extensively explored deep learning algorithms for flow field super-resolution reconstruction. However, purely data-driven deep learning models in this domain face numerous challenges. These include susceptibility to variations in data distribution during model training and a lack of physical and mathematical interpretability in the predictions. These issues significantly impact the effectiveness of the models in practical applications, especially when input data exhibit irregular distributions and noise. In recent years, the rapid development of generative artificial intelligence and physics-informed deep learning algorithms has created significant opportunities for complex physical simulations. This paper proposes a novel approach that combines diffusion models with physical constraint information. By integrating physical equation constraints into the training process of diffusion models, this method achieves high-fidelity flow field reconstruction from low-resolution inputs. Thus, it not only leverages the advantages of diffusion models but also enhances the interpretability of the models. Experimental results demonstrate that, compared to traditional methods, our approach excels in generating high-resolution flow fields with enhanced detail and physical consistency. This advancement provides new insights into developing more accurate and generalized flow field reconstruction models.

Partially multi-view clustering via re-alignment

Multi-view clustering learns consistent information from multi-view data, aiming to achieve more significant clustering characteristics. However, data in real-world scenarios often exhibit temporal or spatial asynchrony, leading to views with unaligned instances. Existing methods primarily address this issue by learning transformation matrices to align unaligned instances, but this process of learning differentiable transformation matrices is cumbersome. To address the challenge of partially unaligned instances, we propose Partially Multi-view Clustering via Re-alignment (PMVCR). Our approach integrates representation learning and data alignment through a two-stage training and a re-alignment process. Specifically, our training process consists of three stages: (i) In the coarse-grained alignment stage, we construct negative instance pairs for unaligned instances and utilize contrastive learning to preliminarily learn the view representations of the instances. (ii) In the re-alignment stage, we match unaligned instances based on the similarity of their view representations, aligning them with the primary view. (iii) In the fine-grained alignment stage, we further enhance the discriminative power of the view representations and the model’s ability to differentiate between clusters. Compared to existing models, our method effectively leverages information between unaligned samples and enhances model generalization by constructing negative instance pairs. Clustering experiments on several popular multi-view datasets demonstrate the effectiveness and superiority of our method. Our code is publicly available at https://github.com/WenB777/PMVCR.git.

Research on trajectory planning based on deep reinforcement learning

Abstract For trajectory planning in a three-dimensional continuous space with multiple complex constraints, traditional optimal control methods face significant challenges, such as long computation times and poor dynamic performance. Using deep reinforcement learning algorithms for training agents in flight trajectory planning can effectively improve the dynamic performance of the planning algorithms. This paper focuses on training agents for UAV emergency landing and obstacle avoidance trajectory planning based on deep reinforcement learning algorithms. Within the reinforcement learning framework, we design the training environment, state space, action space, reward function, and neural network structure. To address common issues in reinforcement learning, such as poor generalization and slow training speed, we improve the training process using the concept of curriculum learning. Comparisons with pseudospectral methods demonstrate that deep reinforcement learning can effectively handle trajectory planning tasks in real flight environments, achieving trajectory quality close to that of pseudospectral methods while offering superior real-time performance.

Surrogate modeling of multi-dimensional premixed and non-premixed combustion using pseudo-time stepping physics-informed neural networks

Physics-informed neural networks (PINNs) have emerged as a promising alternative to conventional computational fluid dynamics (CFD) approaches for solving and modeling multi-dimensional flow fields. They offer instant inference speed and cost-effectiveness without the need for training datasets. However, compared to common data-driven methods, purely learning the physical constraints of partial differential equations and boundary conditions is much more challenging and prone to convergence issues leading to incorrect local optima. This training robustness issue significantly increases the difficulty of fine-tuning PINNs and limits their widespread adoption. In this work, we present improvements to the prior field-resolving surrogate modeling framework for combustion systems based on PINNs. First, inspired by the time-stepping schemes used in CFD numerical methods, we introduce a pseudo-time stepping loss aggregation algorithm to enhance the convergence robustness of the PINNs training process. This new pseudo-time stepping PINNs (PTS-PINNs) method is then tested in non-reactive convection–diffusion problem, and the results demonstrated its good convergence capability for multi-species transport problems. Second, the effectiveness of the PTS-PINNs method was verified in the case of methane–air premixed combustion, and the results show that the L2 norm relative error of all variables can be reduced within 5%. Finally, we also extend the capability of the PTS-PINNs method to address a more complex methane–air non-premixed combustion problem. The results indicate that the PTS-PINNs method can still achieve commendable accuracy by reducing the relative error to within 10%. Overall, the PTS-PINNs method demonstrates the ability to rapidly and accurately identify the convergence direction of the model, surpassing traditional PINNs methods in this regard.

Engaging endometrial cancer survivors as peer supporters for equitable cancer care: The SISTER Study training process

Engaging endometrial cancer survivors as peer supporters for equitable cancer care: The SISTER Study training process

Forging a green future: Synergizing industry 4.0 technologies and circular economy tactics to achieve net-zero in sustainable supply chains

Industry 4.0 (I4.0) and Circular Economy (CE) are emerging in academic, managerial, and policy debates, leading to integrating sustainable supply chain and net zero paradigms as an important phenomenon for maintaining competitive advantages in business. Although CE and I4.0 have significant benefits, their integration is largely untapped, representing a significant opportunity to integrate technological advancements with sustainable practices. Hence, this study investigates how CE and I4.0 can be integrated to achieve net zero in a knowledge-based sustainable supply chain. As part of this objective, the paper conducts an exploratory systematic review of selected articles published in peer-reviewed journals. Three main categories are identified from the selected articles: (i) CE principles and I4.0 technologies integration, (ii) the role of CE-I4.0 nexus in a sustainable supply chain (iii) leveraging CE-4.0 integration for net zero sustainable supply chains. We propose a multi-perspective framework to analyze the net zero sustainable supply chain implementation level using I4.0, CE, and stakeholders’ perspectives. A recommendation from this study suggests increased attention from sustainable supply chain stakeholders on developing infrastructure, including knowledge-building development and training processes focused on net zero. By utilizing our improved knowledge of I4.0 and CE, the results of the study will help researchers, businesses, and policymakers to develop an effective and integrated strategic approach to foster a net zero sustainable supply chain.

Schools and industries producing educational-labor paths in secondary TVET in Chile: Who sets the skills agenda?

This research studies the relations and articulations between two schools from the Antofagasta Region, located in the mining north of Chile, and three of mining companies in the country, which have part of their main operations in the surrounding territories of these schools. This study interrogates the forms of articulation between these schools and the companies, analyzing the main actions, agendas and institutional purposes that both the schools and the companies seek regarding each institutional needs and perspectives. We critically examine these articulations and relationships because, as a result of Chilean public policy in the area of TVET, which is intended to be an industry demand-oriented training policy, the mining industry is actively influencing the school training processes and curriculum, which does not necessarily result in the acquisition of relevant and significant skills for students. This study was designed from a qualitative approach, through the application of two-rounds of situated in-depth interviews to schools’ managers and professionals from mining companies from the north region of Chile. The findings illustrate the ways in which different efforts, contributions and formative actions provided by the companies are reshaping the educational processes inside the schools, establishing educational agendas that expect to provide more efficient alignments between the schools and the companies’ labor needs. Specifically, the paper argues that mining industry companies promote a reduced technical skills approach. This does not include long-term educational planning within the schools, and alternative technical, relational and transformational approaches to skills are absent. The former conventional notions of vocational education and training are being challenged by theoretical and empirical literature. A critical discussion on the skills agenda setting in VET systems is also presented. This study offers an original analytical review and an in-depth study on the dynamics and discourses that articulate and motivate the collaboration between VET schools and mining companies in the Chilean North.

Дослідження впливу фаз менструального циклу на функціональний стан кваліфікованої ветеранки спорту з дзюдо

Purpose: to investigate the influence of menstrual cycle phases on the functional status of a qualified female veteran judo athlete. Material and methods. The following methods were used in the study: analysis of scientific and methodological information and Internet sources; generalization of advanced practical experience; measurement of sensorimotor reactions and determination of heart rate variability indices; methods of mathematical statistics. A qualified veteran female judo athlete (Master of Sports of Ukraine) in the age category F2 (1983-1979) took part in the study. We performed 84 measurements of heart rate variability (n=42, HRV in the supine position; n=42, heart rate variability during the test task dedicated to measuring the choice reaction). The measurement was performed using two computer programs for mobile devices running iPadOS «Research HRV» and «HRV SR+CR» during morning hours (7-8 hours) and afternoon hours (17-18 hours). Results: analysis of the dynamics of changes in heart rate variability parameters obtained in the supine position indicates an increase in sympathetic activity in the follicular phase of the menstrual cycle. Analysis of comparisons of heart rate variability parameters in different phases of the menstrual cycle indicates that the greatest number of statistically significant (p<0,05) differences is observed in the first half of the day. These changes indicate the dynamics of the decrease in the tone of the sympathetic part of the autonomic nervous system in the follicular phase when performing test tasks provided by the computer program «HRV SR+CR». Analysis of the study results indicates that the indicators of heart rate variability are also influenced by the measurement conditions. The test tasks of the computer program «HRV SR+CR» provide cognitive load and concentration of attention, especially in the second stage, where it is necessary to choose the sought-after figure. During cognitive tasks there is an increase in the activity of the parasympathetic nervous system, which leads to an increase in heart rate variability. High level of heart rate variability is associated with better cognitive functions and adaptive response to stress. Consequently, these differences in heart rate variability obtained using the «Research HRV» and «HRV SR+CR» programs may be the result of interactions between physiological changes during the menstrual cycle as well as the influence of measurement conditions. Understanding the changes in heart rate variability indices during test tasks related to the manifestation of the choice reaction provides information about the influence of cognitive load and attention concentration on the functional state of the female athlete. This will allow to plan the training process of wrestling taking into account the phases of the menstrual cycle and functional capabilities that are inherent in high-skilled female athletes. Conclusions. The parameters of heart rate variability and sensorimotor reaction time provide information about the functional state of martial artists. Understanding of metabolic and hormonal processes in different phases of the menstrual cycle of qualified wrestlers will allow to optimize their training loads and recovery measures.

Аналіз результатів анкетування волейболістів-аматорів та здобувачів освіти ЗВО фізичної культури і спорту щодо теоретичної підготовки в навчально-тренувальному процесі волейболістів

The aim of the study is to determine the opinions of amateur volleyball players and students of higher education institutions in the field of physical culture regarding theoretical preparation. Materials and Methods. During the research, the following methods were used: methods of theoretical level of research, methods of empirical level of research and mathematical statistical methods. Our survey aimed to identify the attitudes of amateur volleyball players and students of higher education institutions in physical culture regarding distance teaching of volleyball and theoretical preparation during both online and offline training processes. We proposed 8 specific questions in the survey about the respondents' awareness of theoretical preparation in volleyball, its significance, and the availability of modern forms and methods, as well as their self-assessment of theoretical preparedness, etc. A total of 70 respondents participated in the survey, including: 1 Master of Sports of International Class (1.4%); 1 Master of Sports (1.4%); 6 Candidates for Master of Sports (8.6%); 8 First-Class players (11.4%); 3 Second-Class players (4.3%); and 51 unclassified players (72.9%). Among all respondents, 49 were female (70%) and 21 were male (30%). By age: under 20 years – 17 individuals (24.2%); 20 to 25 years - 24 (34.3%); 25 to 30 years – 18 (25.8%); 30 to 35 years – 7 (10,0%); 35 to 40 years – 3 (4.3%); over 40 years – 1 (1.4%). Additionally, 65 volleyball players live in the city (92.85%), 1 in an urban-type settlement (1.43%), and 4 (5.72%) in rural areas. Among the respondents there were 24 students (34.3%), 40 (57.1%) working volleyball players, and 6 (8.6%) temporarily unemployed. The experience of volleyball training among the respondents varied from 1 to over 20 years: from 0 to 5 years – 19 (27.1%), from 5 to 10 years – 22 individuals (31.4%); from 10 to 15 years – 14 (20%); from 15 to 20 years – 9 (12.85%); over 20 years – 6 (8.6%). The survey was conducted during the "Fit-Mix" park volleyball tournament among amateur teams in Dnipro from March 9 to March 10, 2024, which involved 10 teams. Results. The analysis of the responses from amateur athletes and students of higher education institutions in physical culture to the question "Do you feel the need to acquire theoretical knowledge in volleyball?" indicates that 15 of them (21.4%) do not need theoretical knowledge at all, 14.3% rely on the coach's knowledge, only 8 (11.4%) have a constant need for knowledge about volleyball, and 37 (52.8%) feel the need for theoretical knowledge "from time to time." Conclusions. The research established that our assumption as to the necessity of scientific substantiating the structure and content of theoretical preparation in volleyball is confirmed by the majority of respondents expressing a need for theoretical knowledge. This is a relevant issue which solution will enhance the quality of training for higher education students in the field of physical culture and sports.

Multi‐Deep Learning Approach With Transfer Learning for 7‐Stages Diabetic Retinopathy Classification

ABSTRACTProposed novel investigation focused on leveraging an innovative diabetic retinopathy (DR) dataset comprising seven severity stages, an approach not previously examined. By capitalizing on this unique resource, this study′s findings set a new benchmark for DR classification, highlighting the transformative potential of incorporating advanced data into AI models. This study developed a Vgg16 transfer learning model and gauged its performance against established algorithms including Vgg‐19, AlexNet, and SqueezeNet. Remarkably, our results achieved accuracy rates of 96.95, 96.75, 96.09, and 92.96, respectively, emphasizing the contribution of our work. We strongly emphasized comprehensive severity rating, yielding perfect and impressive F1‐scores of 1.00 for “mild NPDR” and 97.00 for “no DR signs.” The Vgg16‐TL model consistently outperformed other models across all severity levels, reinforcing the value of our discoveries. Our deep learning training process, carefully selecting a learning rate of 1e‐05, allowed continuous refinements in training and validation accuracy. Beyond metrics, our investigation underscores the vital clinical importance of precise DR classification for preventing vision loss. This study conclusively establishes deep learning as a powerful transformative tool for developing effective DR algorithms with the potential to improve patient outcomes and advance ophthalmology standards.

Adversarial contrastive representation training with external knowledge injection for zero-shot stance detection

Zero-shot stance detection (ZSSD) is a task that involves identifying the author’s perspective on specific issues in text, particularly when the target topic has not been encountered during the model training process, to address rapidly evolving topics on social media. This paper introduces a ZSSD framework named KEL-CA. To enable the model to more effectively utilize transferable stance features for representing unseen targets, the framework incorporates a multi-layer contrastive learning and adversarial domain transfer module. Unlike traditional contrastive or adversarial learning, our framework captures both correlations and distinctions between invariant and specific features, as well as between different stance labels, and enhances the generalisation ability and robustness of the features. Subsequently, to address the problem of insufficient information about the target context, we designed a dual external knowledge injection module that uses a large language model (LLM) to extract external knowledge from a Wikipedia-based local knowledge base and a Chain-of-Thought (COT) process to ensure the timeliness and relevance of the knowledge to infer the stances of unseen targets. Experimental results demonstrate that our approach outperforms existing models on two benchmark datasets, thereby validating its efficacy in ZSSD tasks.

FEFA: Frequency Enhanced Multi-Modal MRI Reconstruction With Deep Feature Alignment.

Integrating complementary information from multiple magnetic resonance imaging (MRI) modalities is often necessary to make accurate and reliable diagnostic decisions. However, the different acquisition speeds of these modalities mean that obtaining information can be time consuming and require significant effort. Reference-based MRI reconstruction aims to accelerate slower, under-sampled imaging modalities, such as T2-modality, by utilizing redundant information from faster, fully sampled modalities, such as T1-modality. Unfortunately, spatial misalignment between different modalities often negatively impacts the final results. To address this issue, we propose FEFA, which consists of cascading FEFA blocks. The FEFA block first aligns and fuses the two modalities at the feature level. The combined features are then filtered in the frequency domain to enhance the important features while simultaneously suppressing the less essential ones, thereby ensuring accurate reconstruction. Furthermore, we emphasize the advantages of combining the reconstruction results from multiple cascaded blocks, which also contributes to stabilizing the training process. Compared to existing registration-then-reconstruction and cross-attention-based approaches, our method is end-to-end trainable without requiring additional supervision, extensive parameters, or heavy computation. Experiments on the public fastMRI, IXI and in-house datasets demonstrate that our approach is effective across various under-sampling patterns and ratios.

Зміни у показниках периферійного зору баскетболісток 11–12 років під впливом спеціально підібраних вправ

In team game sports, peripheral vision can be useful for simultaneously tracking the movements of opponents and teammates. The purpose of the study: to experimentally test the effectiveness of specially selected exercises aimed at changes in the peripheral vision of basketball players aged 11-12 years. Research methods: theoretical analysis of scientific and methodological literature, pyrometry method, pedagogical experiment, methods of mathematical statistics. The device ‘Forster's Perimeter’ was used to determine the index of peripheral visual field. The field of vision was determined for the left and right eyes separately for the white and green colours of the two main meridians - horizontal outward (to the temple) and to the middle (to the nose) and vertical - upward and downward. The study was conducted at the research laboratory of the Kharkiv State Academy of Physical Culture. The study involved 30 female basketball players from Kharkiv aged 11-12 years. In order to establish the effectiveness of using specially selected exercises during training, young basketball players were divided into control and experimental groups, each of which consisted of 15 girls. For 4 months, the training process of the experimental group was based on the standard training programme for basketball for children and youth sports schools and was supplemented by specially selected sets of exercises aimed at developing peripheral vision and improving the condition of the eye muscles. Special sets of exercises aimed at developing peripheral vision. Results of the study. The ‘Forster Perimeter’ device does not allow to set the field of vision in the selected direction by more than 90º. It should be noted that the index of peripheral vision horizontally outward, both with the right and left eyes, for both colours in all basketball players exceeded this index. Thus, it was not possible to establish the indicators of peripheral vision in the horizontal outward direction and to study the influence of specially selected exercises on these indicators. The analysis of indicators in the direction up, down and inwards revealed the highest indicators along the vertical meridian with the right and left eyes downwards, both in the CG and EG. Comparing the indicators of peripheral vision of the right and left eyes to white, it was found that in the EG there were significant differences in the indicators upwards (t=2.54, p<0.05) and in the middle (t=4.47, p<0.05), in the CG - in all three directions (t=2.43, p<0.05; t=2.27, p<0.05, t=3.56, p<0.05. In indicators of peripheral vision of the right and left eyes for green colour significant differences are observed only in EG in the upward direction (t=2.19; p<0.05) After the pedagogical experiment the repeated testing was conducted, the results of which indicated a significant improvement of indicators of peripheral vision of basketball players of EC of the right eye both for white and green colour in all three directions (p<0.005). Significant changes in the indicators of peripheral vision of the left eye occurred only for white colour along the vertical meridian downwards (t=2.06; p<0.05) and upwards (t=2.04; p<0.05). For other indicators, the changes were positive, but not significant. Conclusions. The use of specially selected exercises positively influenced on indicators of peripheral vision of sportswomen of 11-12 years old of EG. Thus, the improvement in the right eye was 5.08% upwards, 6.08% downwards, 9.58% in the middle of white colour; in green colour - 11.82%, 5.86%, 5.91%, respectively. In the left eye, the improvement was 6.58% for white, 7.57% for blue, and 1.08% for green; 7.38%, 7.81%, 5.70% for green, respectively.

Design player robot badminton-based microcontroller

Robots are one of the technologies that is currently advancing quickly. Generally speaking, a robot's movement is similar to that of an automobile; it can only move forward, backward, left, and right. Because the movement is controlled by these movements, it is thought that the robot's movement is extremely restricted to the left and right directions. solely with the front wheels. As a result, a robot was developed in this study that can control sliding motions to the left and right utilizing omniwheels on its front and back wheels. Badminton is a sport involving rackets that is played by two people or two opposing pairs. Robotic badminton players are employed as a substitute for human trainers in the training process, particularly for service and drive motions. With the use of a wireless joystick, the robot's ATMega 8535 microprocessor controls both the robot's direction of motion and the movement of its racket. Using a double acting pneumatic cylinder that requires 7 bar of air pressure, the robot service arm uses the compressor's air pressure. The average time it takes for the racket to strike the ball at 7 bar of wind pressure is 00:5.2 seconds. The time it takes for the ball to fall onto the racket in the absence of wind pressure is 00:28 seconds on average. A difference value of 00:22.7 seconds is acquired, and this value will be utilized as the programming reference delay. The robot encounters a slope with an average angle change of 7º when moving forward, an average angle change of 10º when moving backward, an average angle change of 5.2º when moving right, and an average angle change of 3º when moving left. The uneven field surface causes the robot to move at a slope, which modifies the speed of the motor on the wheels

Eco-education: an intervention in the curriculum and in the training process of teachers in the Feira Nova-PE School System

Eco-education: an intervention in the curriculum and in the training process of teachers in the Feira Nova-PE School System

Development of chipping and passing skill test instruments for U-23 futsal players in Central Java Province

Introduction. One of the sports that is currently developing is futsal. This sport has also been competed at beginner, semi-professional and even professional levels. Futsal is a sport that is similar to football in terms of technique, but have differences in terms of game rules. For this reason, several development efforts need to be made to achieve optimal results. One thing that needs to be considered is the test and measurement aspect. This research designed a basic futsal test measuring tool for players aged 18-23 years old with the aim of producing a basic futsal skills test by measuring the chipping test and passing test. Objective. The objective of this research is to produce a tool for measuring basic futsal skills that has high validity and reliability in chipping and passing tests so that it can be used in the learning and training process for U-23 futsal sports. Method. The research design used is developmental research with procedures for planning product development and developing initial product types/models for futsal players aged 18-23 years. The study involved 15 PORPROV futsal players for small groups and 90 PORPROV futsal players for large group trials, consisting of 6 districts: Banyumas, Klaten, Kebumen, Kendal, and Kudus Regencies. Next, validity, reliability and norm tests are carried out on the product skills test. Results. The validation and reliability tests for small-scale instruments consisted of basic skills. The validity test for the chipping test was 0.972, and the retest was 0.994 with a reliability of 0.978. The validity of the passing test was obtained at 0.910, the retest was 0.981 and the reliability was 0.947. Large-scale validity results for basic skills in the chipping test were 0.887, with a retest value of 0.975 and a reliability of 0.935. The validity of the passing test was 0.954, with a retest value of 0.989 and a reliability of 0.977. This indicates that the measuring instrument is reliable and will produce consistent results, even when tested at different times. There is no significant difference in the norms for the chipping and passing tests (p > 0.05), indicating that the product instrument used is objective. Conclusion. From this research, a reliable measuring tool for assessing futsal skills in players aged 18-23 years has been constructed.