Test Data Research Articles

STORYTELLING METHOD USING HAND PUPPET MEDIA: COGNITIVE DEVELOPMENT OF CHILDREN AGED 4-6 YEARS

The main purpose of the study on storytelling methods with hand puppet media in relation to the cognitive development of children aged 4-6 years is to understand and analyze the impact of using hand puppets as an aid in storytelling activities on various aspects of cognitive abilities in preschool children and to explore how children's interactions with hand puppets in the context of stories can improve language skills, conceptual understanding, information processing, logical thinking skills, problem-solving skills, emotional intelligence, and literacy basics. This study uses a quantitative quasi-experimental design approach. The subjects of the study were 19 students aged 4-6 years at Labscool Kindergarten in the form of one group pretest-posttest design analyzed using the Paired Samples Test. The results of the Paired Samples Test data analysis, it can be concluded that there is a significant difference between the pre-test and post-test scores. showing an average decrease of 8,474 points in the cognitive development of children aged 4-6 years. Because the p value is very small (0.000), this difference is very statistically significant. This means that there is a clear impact of using this method in improving children's cognitive development. cognitive enhancement in children through storytelling methods with hand puppet media in accordance with existing theories regarding cognitive stimulation at an early age. This method is very effective in improving various aspects of child development, especially in terms of thinking skills, speaking skills, and their understanding of the social world around them

A Multi Parameter Synchronous Identification Method for Stiffness and Damping of Single Fixed Clamp Based on Pareto Algorithm

As a composite structure, the single fixed clamp (SFC) is an important supporting component of the aeroengine piping system. The dynamic parameters (stiffness and damping) of SFC have significant differences in bolt direction and opening direction. Accurately identifying the dynamic parameters of an SFC in both directions is of great significance for the study of pipeline system dynamics. At present, there is very little research on the identification of dynamic parameters for such SFC. Therefore, an SFC-straight pipe structure for identifying the dynamic parameters of an SFC is proposed in this paper. In this structure, one end of the straight pipe is completely fixed, and the other end is supported by an SFC. This structure can better reflect the working state of the SFC. A dynamic model of this structure is established based on the finite element method for parameter identification of SFC. In the finite element model (FEM), the constraint effect of the SFC is simplified into two identical spring-damping groups. Considering the structural asymmetry, spring and damping parameters for bolt direction and opening direction are separately set in each spring damping group. Next, based on the Pareto multi-objective genetic algorithm, an identification algorithm and procedure for the stiffness and damping of the SFC using modal test data as input parameters are proposed. Through experimental testing, parameter identification is carried out for DK8 type SFC, and a straight pipe experimental structure completely supported by two SFCs is constructed to verify the correctness of the identification results.

Pengaruh Model Cooperative Script Terhadap Pemahaman Siswa Materi Pecahan Biasa Kelas IV SD Negeri 10 Sungailiat

The students’ struggle to understand and use common fractions correctly, especially when dealing with fractions with different denominators, was the driving force behind this study. Researchers at SD Negeri 10 Sungailiat set out to test fourth graders’ understanding of common fractions using the Cooperative Script model. A quantitative study using a pre-experimental design based on a one-group pretest-posttest was used. In this study, saturated sampling was used for the sample. 27 fourth graders from SD Negeri 10 Sungailiat participated in the study. Ten questions covering common fractions served as the test data collection tool. A paired sample t-test was used to test the hypothesis and ensure the normality of the data. There was a statistically significant relationship between the use of common fractions material in the pretest and posttest. The value found 0.00<0.05 in the calculation of the paired sample t-test using SPSS 26 shows this. This proves that Ha is true and H0 is false. Fourth graders of SD Negeri 10 Sungailiat benefited from the approach through the Cooperative Script model in learning fractions.

Change in transverse relaxation rates (R2) and change in cognition for older African Americans

AbstractDespite transverse relaxation rate (R2) being one of the fundamental contrasts in MRI, most investigations of brain R2 and cognition have been cross‐sectional and conducted in predominantly non‐Latino White adults. We investigated the profile of R2 as related to cognition in 212 older African Americans (~75 years of age) with longitudinal 3T MRI scans and cognitive test data to determine how changes in R2 are associated with changes in cognition. For each participant, the slopes of global cognitive and five cognitive domain scores were each separately combined with voxel‐specific slopes of R2 in whole brain voxelwise analyses. Participants with less negative rates of R2 change within left basal ganglia and centrum semiovale, bilateral hippocampal complex and temporal gyri, parietooccipital white matter, as well as posterior cingulate displayed less negative slopes in global cognition. Similar associations were seen for regional R2 change and episodic memory (most robustly within bilateral hippocampi) as well as semantic memory (left greater than right hemisphere involvement). Results suggest a relatively wide distribution of regional associations between rates of changes in R2 and changes in global cognition for older African Americans; a profile that became more regionally specific when considering individual cognitive domains. Relative preservation of tissue integrity across grey and white matter, and in key regions associated with specific cognitive domains, is associated with slower cognitive decline for older African Americans. These results may lay the foundation for more directed work to support healthy brain aging in older African Americans.

DETERMINATION OF STANDARD TIME FOR BISCUIT PACKAGING PROCESSING

A firm named PT. XYZ specializes in the production of biscuits, wafers, and chocolate chips. The biscuit production process encompasses several stages, beginning with the collection of raw materials in the warehouse, followed by weighing them according to the recipe, and culminating in packaging and storage in the finished product warehouse. A problem arose during the packaging stage in the first work shift, where production fell short of the target only 200 cartons of biscuits were produced compared to the goal of 250 cartons per shift. To address this issue, standard time calculations will be conducted. The research process involves observing cycle times in the packaging process, testing data adequacy, ensuring data uniformity, identifying rating factors, calculating normal time, identifying allowances, determining standard time, and calculating labor requirements, utilizing a stopwatch to measure the necessary work time accurately. The calculated standard time for secondary packaging is 75.683 seconds, while for tertiary packaging it is 53.409 seconds. Based on these results, it is determined that an additional eighteen workers are needed for secondary packaging, and two more workers are required for tertiary packaging.

Expert System for Diagnosing Dengue Fever with Comparison of Naïve Bayes and Dempster Shafer Methods

An expert system for diagnosing dengue fever (DF) using a comparison of the Naive Bayes and Dempster Shafer methods aims to provide a solution to assist medical personnel in diagnosing this disease. Dengue fever is a disease caused by the dengue virus infection through the bite of Aedes mosquitoes. It has symptoms similar to other diseases and requires rapid and accurate diagnosis. The Naive Bayes and Dempster Shafer methods were chosen because both have different approaches to handling uncertainty and imprecise information. The Naive Bayes method is a probability-based classification that assumes independence between features. Meanwhile, Dempster Shafer is an approach to handling uncertainty. Therefore, comparing Naive Bayes and Dempster Shafer allows for classification with structured and fairly straightforward data, offering accuracy and flexibility in dealing with uncertainty. Applying this expert system with these methods can help in the faster and more accurate diagnosis of DF and provide better recommendations in situations where the available data is incomplete or ambiguous. From the test data calculations, the two methods show that the Naive Bayes method has a higher percentage value of 93%, while Dempster Shafer has 86%.

A proficient approach for the classification of Alzheimer’s disease using a hybridization of machine learning and deep learning

Alzheimer’s disease (AD) is a neurodegenerative disorder. It causes progressive degeneration of the nervous system, affecting the cognitive ability of the human brain. Over the past two decades, neuroimaging data from Magnetic Resonance Imaging (MRI) scans has been increasingly used in the study of brain pathology related to the birth and growth of AD. Recent studies have employed machine learning to detect and classify AD. Deep learning models have also been increasingly utilized with varying degrees of success. This paper presents a novel hybrid approach for early detection and classification of AD using structural MRI (sMRI). The proposed model employs a unique combination of machine learning and deep learning approaches to optimize the precision and accuracy of the detection and classification of AD. The proposed approach surpassed multi-modal machine learning algorithms in accuracy, precision, and F-measure performance measures. Results confirm an outperformance compared to the state-of-the-art in AD versus CN and sMCI versus pMCI paradigms. Within the CN versus AD paradigm, the designed model achieves 91.84% accuracy on test data.

Correction method of Mohr-Coulomb strength criterion for rock based on freeze-thaw and residual effects

Under confining pressure, rocks transition from brittle failure to plastic failure, and residual strength exists after complete failure. However, in the process of establishing rock damage constitutive models, the strength criteria used usually do not consider residual stress. In cold region engineering, the freeze-thaw effect caused by temperature changes should be considered in the constitutive model, and strength criteria should also be introduced. Considering the failure characteristics of micro element when rock is subjected to freeze-thaw and load, and based on the impact of reducing the effective bearing area on each damage, the total damage variable and constitutive model of rock under freeze-thaw and load are established. Starting from the characteristics of the entire process of rock deformation, the revised Mohr-Coulomb (M-C) strength criterion of rock is established by considering freeze-thaw cycles and residual effects. The results show that: The theoretical curve and test curve of the constitutive model are not completely consistent, but the variance R2 between the two does not exceed 0.6, indicating that the theoretical curve is in good agreement with the test curve and can reflect the entire process of rock deformation and failure, verifying the rationality of the constitutive model and damage variable description. With the increasing of freeze-thaw cycles, the strength decreases and the deformation increases of rock. As the number of freeze-thaw cycles increases, the strength decreases and deformation increases. When the freeze-thaw cycle reaches 40 cycles, the strength decreases by more than 60%. With the increasing of confining pressure, the strength and deformation also increase. When the confining pressure increases from 0 to 6 MPa, the strength of red sandstone increases by more than 80% under the same freeze-thaw cycles, which is consistent with the actual situation. The revised M-C strength criterion data does not exceed the test data and is relatively close to the test data. The difference between the two is less than 25%, indicating that the established strength criteria can be safely used as a basis for rock elemental failure, verifying the rationality of the strength standard considering freeze-thaw and residual effects. This Revised M-C strength criterion introduces the influence of freeze-thaw cycles and residual stress factors, which not only characterizes the relationship between internal stress parameters in rock limit states under different freeze-thaw cycles, but also addresses the disadvantage of Drucker-Prager (D-P) criterion being more conservative. This method is based on the measured results of rock triaxial test, which makes it more flexible and the calculation results closer to reality.

Dynamic Prediction of Physical Exertion: Leveraging AI Models and Wearable Sensor Data During Cycling Exercise.

Background/Objectives: This study aimed to explore machine learning approaches for predicting physical exertion using physiological signals collected from wearable devices. Methods: Both traditional machine learning and deep learning methods for classification and regression were assessed. The research involved 27 healthy participants engaged in controlled cycling exercises. Physiological data, including ECG, heart rate, oxygen saturation, and pedal speed (RPM), were collected during these sessions, which were divided into eight two-minute segments. Heart rate variability (HRV) was also calculated to serve as a predictive indicator. We employed two feature selection algorithms to identify the most relevant features for model training: Minimum Redundancy Maximum Relevance (MRMR) for both classification and regression, and Univariate Feature Ranking for Classification. A total of 34 traditional models were developed using MATLAB's Classification Learner App, utilizing 20% of the data for testing. In addition, Long Short-Term Memory (LSTM) networks were trained on the top features selected by the MRMR and Univariate Feature Ranking algorithms to enhance model performance. Finally, the MRMR-selected features were used for regression to train the LSTM model for predicting continuous outcomes. Results: The LSTM model for regression demonstrated robust predictive capabilities, achieving a mean squared error (MSE) of 0.8493 and an R-squared value of 0.7757. The classification models also showed promising results, with the highest testing accuracy reaching 89.2% and an F1 score of 91.7%. Conclusions: These results underscore the effectiveness of combining feature selection algorithms with advanced machine learning (ML) and deep learning techniques for predicting physical exertion levels using wearable sensor data.

Spatial and temporal analysis of West Nile virus infection in mosquito and human populations based on arboviral detection testing data

West Nile virus (WNV) is a mosquito-borne zoonotic flavivirus which often causes asymptomatic infection in humans but may develop into a deadly neuroinvasive disease. In this study, we aimed to investigate variables potentially associated with human WNV infection using human and mosquito WNV surveillance and monitoring datasets, established over 20 years, from 2003 to 2022, across the province of Ontario, Canada. We combined climatic and geographic data, mosquito surveillance data (n = 3010 sites), blood donation arboviral detection testing data in the human population, and demographic and socio-economic data from Canadian population censuses. We hypothesized that spatio-temporal indices related to mosquito vector habitat and phenology, in addition to human demographic and socio-economic factors, were associated with WNV infection in the human population. Our results show that high habitat suitability of the main WNV vector in southerly locations of this region, Cx. pipiens/restuans (IRR = 2.0), and variables related to lower income (IRR = 2.8), and shelter infrastructure spending (IRR = 0.7), were key risk factors associated with WNV infection among blood donors from 2003 to 2022 across Ontario (R2 = 0.67). These results may inform points of entry for practical intervention aimed at reducing risk of mosquito-borne pathogens in Canada.

Limitations of panoramic radiographs in predicting mandibular wisdom tooth extraction and the potential of deep learning models to overcome them

Surgeons routinely interpret preoperative radiographic images for estimating the shape and position of the tooth prior to performing tooth extraction. In this study, we aimed to predict the difficulty of lower wisdom tooth extraction using only panoramic radiographs. Difficulty was evaluated using the modified Parant score. Two oral surgeons (a specialist and a clinical resident) predicted the difficulty level of the test data. This study also aimed to evaluate the performance of a deep learning model in predicting the necessity for tooth separation or bone removal during wisdom tooth extraction. Two convolutional neural networks (AlexNet and VGG-16) were created and trained using panoramic X-ray images. Both surgeons interpreted the same images and classified them into three groups. The accuracies for humans were 54.4% for both surgeons, 57.7% for AlexNet, and 54.4% for VGG-16. These results indicate that accurately predict the difficulty of wisdom teeth extraction using panoramic radiographs alone is challenging. However, AlexNet and VGG-16 had sensitivities of more than 90% for crown and root separation. The predictive ability of our proposed model is equivalent to that of an oral surgery specialist, and a recall value > 90% makes it suitable for screening in clinical settings.

Study on interfacial mechanical properties and structural detail damage of CRTS II slab ballastless track

The CRTS (China Railway Track System) II slab ballastless track is widely utilized in high-speed railway construction owing to its excellent structural integrity. However, its interfacial performance deteriorates under high-temperature conditions, leading to significant damage in structural details. Furthermore, the evolution of its performance under these conditions has not been comprehensively studied. In this study, a bilinear cohesive damage model was developed using positive tensile and push-out model tests to describe the interfacial mechanical behavior of the track structure. A three-dimensional refined numerical simulation model of the CRTS II slab ballastless track was developed and validated using existing test data to analyze the distribution of structural damage and its evolution under varying temperature conditions. The results demonstrate that the proposed bilinear cohesive damage model effectively characterizes the interlayer damage evolution in the track structure. As the overall temperature increases, interlayer separation initiates at the wide-narrow joints and propagates from the slab ends toward the center. At a temperature rise of 60 °C, the interface becomes fully separated, and the vertical displacement of the wide-narrow joints and the track slab reaches 1.09 cm. The middle and end sections of the wide joints are particularly susceptible to compressive damage, with the top section being more sensitive to temperature changes. These results provide critical insights into the damage mechanisms and performance evolution of ballastless tracks under thermal loading, offering a foundation for improved design and maintenance strategies.

Decision Tree for Determining Hospital Treatment for Covid-19 Patients Based on Hematology Parameters Using the C5.0 Algorithm

The rapid spread of the COVID-19 disease which occurred globally throughout the world some time ago, requires early detection of COVID-19 which is very important for patients and also the people around them to be able to fight the COVID-19 pandemic. Therefore, a classification analysis will be carried out to make decisions regarding determining COVID-19 patients who do not require hospitalization or who require Regular Ward, Semi-Intensive Care Unit, or Intensive Care Unit (ICU) in hospitals based on hematology parameters from the Machine Learning Repository. Kaggle Dataset uses the C5.0 algorithm assisted by Rstudio software. It is also known that because the data contains missing data, it is also necessary to handle missing data using the Mean Method assisted by SPSS software. Performance evaluated using the Confusion Matrix method produces an accuracy value of 78% which is considered quite good, where testing with the C5.0 Algorithm uses a training and testing data ratio of 40:60. This research was carried out with the aim of simplifying and speeding up the performance of medical personnel so that COVID-19 patients receive fast and appropriate treatment to help reduce COVID-19 cases in a population.

Pengaruh Pengendalian Akuntansi, Sistem Pelaporan, Dan Kejelasan Sasaran Anggaran Terhadap Akuntabilitas Kinerja Instansi Pemerintah Kabupaten Pekalongan

The change in regional budget standards is to create regional budgets accurately and economically, efficiently, and effectively that represent the interests and aspirations of local communities in relation to regional financial management. Accountability must be fulfilled by the government by looking at the budget, accounting control, and reporting system. The purpose of this study is to determine the effect of accounting control, reporting system, and clarity of budget targets on the accountability of the performance of government agencies of Pekalongan Regency. This research belongs to the type of quantitative research. The data collection method in this study was a questionnaire method using a sample of 51 respondents. Sampling technique by purposive sampling method. This study used a multiple linear regression test data analysis method with the help of SPSS 26. The results showed that accounting control affects the accountability of the performance of government agencies in Pekalongan District. The reporting system and clarity of budget targets do not affect the accountability of the performance of government agencies in Pekalongan District.

Artificial Intelligence-Aided Diagnosis System for the Detection and Classification of Private-Part Skin Diseases: Decision Analytical Modeling Study.

Private-part skin diseases (PPSDs) can cause a patient's stigma, which may hinder the early diagnosis of these diseases. Artificial intelligence (AI) is an effective tool to improve the early diagnosis of PPSDs, especially in preventing the deterioration of skin tumors in private parts such as Paget disease. However, to our knowledge, there is currently no research on using AI to identify PPSDs due to the complex backgrounds of the lesion areas and the challenges in data collection. This study aimed to develop and evaluate an AI-aided diagnosis system for the detection and classification of PPSDs: aiding patients in self-screening and supporting dermatologists' diagnostic enhancement. In this decision analytical modeling study, a 2-stage AI-aided diagnosis system was developed to classify PPSDs. In the first stage, a multitask detection network was trained to automatically detect and classify skin lesions (type, color, and shape). In the second stage, we proposed a knowledge graph based on dermatology expertise and constructed a decision network to classify seven PPSDs (condyloma acuminatum, Paget disease, eczema, pearly penile papules, genital herpes, syphilis, and Bowen disease). A reader study with 13 dermatologists of different experience levels was conducted. Dermatologists were asked to classify the testing cohort under reading room conditions, first without and then with system support. This AI-aided diagnostic study used the data of 635 patients from two institutes between July 2019 and April 2022. The data of Institute 1 contained 2701 skin lesion samples from 520 patients, which were used for the training of the multitask detection network in the first stage. In addition, the data of Institute 2 consisted of 115 clinical images and the corresponding medical records, which were used for the test of the whole 2-stage AI-aided diagnosis system. On the test data of Institute 2, the proposed system achieved the average precision, recall, and F1-score of 0.81, 0.86, and 0.83, respectively, better than existing advanced algorithms. For the reader performance test, our system improved the average F1-score of the junior, intermediate, and senior dermatologists by 16%, 7%, and 4%, respectively. In this study, we constructed the first skin-lesion-based dataset and developed the first AI-aided diagnosis system for PPSDs. This system provides the final diagnosis result by simulating the diagnostic process of dermatologists. Compared with existing advanced algorithms, this system is more accurate in identifying PPSDs. Overall, our system can not only help patients achieve self-screening and alleviate their stigma but also assist dermatologists in diagnosing PPSDs.

IMPLEMENTATION OF PROPHET IN AMERICAN ELECTRICITY FORECASTING WITH AND WITHOUT PARAMETER TUNING

Prophet is one of the machine learning approximation methods that accommodate trends, seasonality, and holiday impacts in time series data. Generally, the performance of machine learning models can be improved by implementing hyperparameter tuning. This study investigates whether hyperparameter tuning can improve the model's performance. To show its effectiveness, the Prophet model constructed by parameter tuning is compared to the one with fixed parameter values (namely the default model) for both the original series and the Box-Cox transformed series in terms of mean absolute percentage error (MAPE). Based on the experimental results of the twenty-four daily electricity load time series in American Electric Power (AEP). This shows that parameter tuning successfully reduces the MAPE of the default model in the range of about 3-8% for training data. However, there is no guarantee for testing data. Although, in some cases, parameter tuning can reduce the MAPE value of the default model by up to 38%, in other cases, it actually increases the MAPE of the default model by almost 15%. The experiments on testing data also show that models built from transformed data do not necessarily produce more accurate forecast values than those built from the original data.

Transfer learning with inception V4 for behavioral anomaly detection in CCTV surveillance

Heightened security concerns and better affordability have driven the proliferation of video surveillance systems. Developing advanced CCTV cameras capable of real-time analysis of behavioral patterns to find abnormal patterns is highly anticipated and will help avert hazardous incidents. Deep Learning approaches, specifically Convolutional Neural Network (CNN) architecture-based approaches, have been extensively used for anomaly detection tasks in video analytics. The study results from research applying diversified Inception V4 transfer learning methodologies to accurately and efficiently identify abnormal activities in video surveillance systems. This study utilized the Inception V4 framework to classify video keyframes that are representative of normal or abnormal behavior. This paper will elaborate on applying transfer learning techniques of pre-training and fine-tuning, which will employ the required attributes from the input information to build a specialized predictor. The effectiveness of the presented models was evaluated through experimental studies that utilized UCF-Crime data for training and testing. Metrics, such as accuracy, recall, precision, and F1 scores, were employed as evaluation criteria to assess the performance of each model. The Fine-Tuned (F-T) model demonstrated performance metrics of 930%, 91.74%, 88.33%, and 90.01%, whereas the Pre-trained (P-T) model showed 88.70%, 88.93%, 87.12%, and 88.02%, respectively. These findings suggest that Transfer Learning (TL), employing the Inception V4 architecture, can effectively distinguish between normal and abnormal video behaviors. Moreover, adjusting the weights of particular layers through fine-tuning can improve the performance.

Acute subdural hematomas in nonagenarians and centenarians.

There is minimal literature on the outcomes of acute traumatic subdural hematoma (SDH) in patients 90years of age or older. This study aims to characterize the presentation and acute outcomes of patients in this population, particularly for surgical candidates. Patients 90years of age or older with acute SDH between 2013-2023 were analyzed (n=117). Multivariable binomial logistic regression assessed associations with favorable outcome, defined as a discharge to a non-hospice facility with a Glasgow Coma Scale (GCS) of 14 or greater. Nominal data was analyzed via Wilcoxon rank-sum test and categorical data was analyzed via Chi-squared test. For this patient population mortality was 7.7%. 86.3% of all patients had favorable outcome.Eight patients underwent surgery, with two resulting in mortality.. However, 62.5% of patients who underwent surgery had a favorable outcome. Patients undergoing surgery had longer average length of stay (P=0.002), greater in-hospital mortality (P=0.013), and younger age (P=0.008) compared to non-surgical patients. Prior independence (OR 7.07, 95% CI 1.33-37.45, P=0.022) and higher GCS at arrival (OR 1.67, 95% CI 1.11-2.49, P=0.013) were associated with favorable outcomes. 86.3% of patients 90years of age or older with acute subdural hematomas had a favorable outcome in our series. Prior independence and higher GCS at arrival were associated with favorable discharge. Several patients had good outcomes after craniotomy for acute SDH, indicating there are some patients in this age group who should be considered for surgery.

Configurational paths to promoting children’s agility and balance quality: based on fuzzy-set qualitative comparative analysis

BackgroundEarly childhood is a sensitive period for the development of agility and balance quality. Currently, children’s agility and balance quality are gradually declining, and the pathways for enhancing these qualities are limited. In light of this, the study adopts a set theory perspective to explore the configurational pathways through which subsystems of gross motor skills can promote children’s agility and balance quality.MethodsThis study incorporates test data from 84 children aged 3 to 6 years, employing fuzzy-set Qualitative Comparative Analysis (fsQCA) to examine how configurations of six subsystems within gross motor skills (running, jumping, throwing, catching, kicking, and striking) influence the promotion of children’s agility and balance quality.ResultsNecessary condition analysis reveals that individual subsystems of gross motor skills alone cannot determine the promotion of agility and balance quality in children. Further configuration analyses identify two paths for promoting agility quality ( Overall Consistency = 0.889, Overall Coverage = 0.337 ) and two paths for promoting balance quality ( Overall Consistency = 0.875, Overall Coverage = 0.346 ).ConclusionSubsystems of gross motor skills can promote children’s balance and agility quality through configurational effects. Specifically, promoting agility quality should primarily involve combined exercises of jumping, running, and catching actions, while promoting balance quality should focus on combined exercises of kicking, jumping, and running actions. Furthermore, prioritizing children’s balance quality can support the children’s agility quality. These findings offer important practical guidance for promoting children’s agility and balance quality.

Ensemble Model Approach for Predicting the Yield of Dehydrogenation Products during the Oxidative Dehydrogenation of n-Butane.

Efficient and selective oxidative dehydrogenation (ODH) catalysts are crucial to advance the production of valuable petrochemicals. In this study, we leverage the power of machine learning to predict dehydrogenation (DH) product yield and unravel the factors influencing the product distribution. A comprehensive data set obtained from experiments conducted in a fixed-bed reactor under varying temperatures, feed ratios (O2/n-butane), and metal oxide loadings (Ni, Fe, Co, Bi, Mo, W, Zn, and Mn) on an aluminum oxide support served as the basis for model development. Three supervised machine learning models, Boosted Tree (BT), Extreme Gradient Boosting Linear (XGBL), and Support Vector Machine Radial (SVMR), were evaluated. The ensemble technique of the three models showed remarkable accuracy, with an RMSE of 1.65 and MAE of 1.14 on the test data set, and it demonstrated robust generalization capabilities by capturing 87% of the variation in DH yield. In the feature importance analysis of the selected models, Mo, Co, Ni, and W emerged as critical factors influencing the DH yield. The practical significance of these findings lies in their potential to revolutionize catalysis research and industrial applications. The ability of the ensemble model to predict DH yields opens new avenues for optimizing DH products and designing more advanced catalysts. By providing essential insights into the influential variables governing the ODH reactions, researchers can make informed decisions to achieve higher yields and efficiencies.